JP2021043955A5 - Invention document analysis system, invention document analysis method, and invention document analysis processing program - Google Patents

Description

The present disclosure relates to an invention document analysis system and related technology.

Conventionally, a machine translation device is known (see Patent Document 1, for example).

JP 2018-190287 A

A conventional machine translation device can output an appropriate translation result only when the Japanese document to be translated is described in a certain format. It is not necessarily useful when a translator or the like translates an invention document. For example, it is not always the case that an invention document is properly translated by a conventional machine translation device, and the translator needs to check the result translated by the machine translation device and correct it as appropriate.

The present disclosure provides an invention document system capable of analyzing invention documents expressing technical ideas in Japanese and outputting useful information to those who use the invention documents. The present disclosure, for example, allows a translator to efficiently translate a translation result document based on an invention document that expresses a technical idea in Japanese (that is, a document that is the result of translating the invention document into a foreign language such as English or Chinese). To provide an invention document analysis system capable of outputting information useful for purposeful or proper preparation. The present disclosure also provides a method (invention document analysis method) and an invention document analysis processing program related to the invention document analysis system. The present disclosure also provides a document for display including a document written in a markup language, the data generated by the inventive document analysis method and which may include a script as a computer program.

The invention document analysis system in the present disclosure is an invention document analysis system that analyzes an invention document, which is a document describing claims and specifications for a patent application in which technical ideas are expressed in Japanese. A setting information acquiring unit for acquiring setting information including condition information indicating extraction conditions, a document acquiring unit for acquiring an invention document, and an invention document acquired by the document acquiring unit is analyzed based on the setting information. and an output unit configured to output information generated based on an analysis result of the invention document acquired by the document acquisition unit, wherein the analysis unit outputs information acquired by the document acquisition unit. an important phrase extraction unit for extracting important phrases from the invention document based on the setting information, and the output unit extracts a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit Outputs information generated based on each phrase.

In addition, the invention document analysis method according to the present disclosure analyzes an invention document, which is a document describing claims and specifications for a patent application in which a technical idea is expressed in Japanese, in a device equipped with a microprocessor, and analyzes the invention document as a document for display. wherein the invention document analysis process includes a document acquisition step of acquiring an invention document, and a predetermined invention document acquired by the document acquisition step. A patent generated based on the analysis result of the analysis step for the invention document acquired by the document acquisition step by extracting the key phrase based on the extracted key phrase extraction condition and an output step of generating and outputting the display document for displaying the application-related information, the display document including a document written in a markup language and interpreted by a browser in a device equipped with a microprocessor. Patent application-related information including claim information that represents the content of claims in an invention document for a patent application that expresses the technical idea in Japanese, and specification information that represents the content of the specification in the invention document. is included as content to be displayed, and the complaint information representing the content of the complaint is extracted based on the conditions for extracting predetermined key phrases from among the phrases of the complaint. For each key phrase, display control information for controlling the display mode of the display element of the key phrase is included, and among the key phrases represented in the claim information, a plurality of character strings constituting the key phrase are different from each other. Each of the display control information related to each of the key phrases includes information for controlling display elements of the plurality of key phrases to be displayed in a display mode in which different display colors are added, and the claim information includes: The display control information related to the important phrase composed of the same character string as any one of the plurality of important phrases having different character strings constituting the important phrase among the important phrases to be expressed. contains information for controlling the display element of the key phrase to be displayed in a display mode in which the same display color as the display mode of the display element of the one key phrase is added, The specification information representing the content of the specification includes, for each key phrase extracted based on the conditions for extraction of key phrases among the terms in the specification, the display mode of the display element of the key phrase. any one of the plurality of important phrases in which the character strings constituting the important phrases in the claim information are different from each other among the important phrases represented in the specification information The display control information related to the same important phrase as the two important phrases has the same display color as the display color added as the display mode of the display element of the one important phrase in the claim information. Contains information for controlling to display in a display mode with the addition of
In addition, the invention document analysis processing program in the present disclosure analyzes and displays invention documents, which are documents describing claims and specifications for patent applications expressing technical ideas in Japanese, in a device equipped with a microprocessor. It is a program for realizing the invention document analysis method described above by executing invention document analysis processing for generating a document .

According to the invention document analysis system , the invention document analysis method , and the invention document analysis processing program according to the present disclosure, useful information can be output. Useful information may be displayed according to the display document in the present disclosure. In addition, the invention document analysis system, invention document analysis method, display document, and invention document analysis processing program in the present disclosure are, for example, for the translator to efficiently or properly create a translation result document based on the invention document. can be useful for

FIG. 1 is a diagram showing an example of a work flow related to translation of an invention document. FIG. 2 is a diagram showing an example of the flow of translation work by a translator. FIG. 3 is a diagram listing an example of factors that hinder the efficiency or appropriateness of translation for obtaining useful rights. FIG. 4 is a diagram showing an example of the configuration of the invention document analysis system according to the first embodiment. FIG. 5 is a diagram showing an example of contents of setting information according to the first embodiment. FIG. 6 is a diagram showing an example of contents of patent application related information according to the first embodiment. FIG. 7 is a flowchart showing an example of invention document analysis processing according to the first embodiment. FIG. 8 is a diagram showing an example of the hardware configuration of the invention document analysis system according to the first and second embodiments. FIG. 9 is a diagram showing an example of the hardware configuration and network configuration of the invention document analysis system according to the first and second embodiments. FIG. 10 is a diagram showing another example of the hardware configuration and network configuration of the invention document analysis system according to the first and second embodiments. FIG. 11 is a diagram showing an example of the configuration of an invention document analysis system according to the second embodiment. FIG. 12 is a diagram showing an example of main data handled by the invention document analysis system according to the second embodiment. FIG. 13 is a diagram showing an example of contents of setting information according to the second embodiment. FIG. 14 is a diagram showing an example of invention document standard specifications for translation. FIG. 15 is a diagram showing an example of contents of patent application related information according to the second embodiment. FIG. 16 is a diagram showing a configuration example of an HTML document, which is an example of a display document related to patent application related information. FIG. 17 is a diagram showing an example of a display screen displayed by a browser or the like based on a display document related to patent application related information. FIG. 18 is a diagram showing an example of key phrase management information. FIG. 19 is a diagram showing an example of items of attribute information of important phrases in the important phrase management information. FIG. 20 is a diagram showing a display example of the inclusion relation information portion in the important word relation information of the patent application related information as a display document. FIG. 21 is a diagram showing an example of warning information items and description items of patent application related information. FIG. 22 is a diagram showing an example of claim information in patent application related information as a display document displayed on the browser. FIG. 23 is a diagram showing an example of information displayed in response to an operation on important terms in complaint information displayed on the browser. FIG. 24 is a diagram showing an example of a screen displayed in response to an operation on important terms in complaint information displayed on the browser. FIG. 25 is a diagram showing an example of claim-based specification information in patent application related information as a display document displayed on the browser. FIG. 26 is a diagram showing an example of specification information in patent application related information as a display document displayed on the browser. FIG. 27 is a diagram showing an example of a screen displayed in response to an operation on a code added to an important phrase in specification information displayed on the browser. FIG. 28 is a diagram showing an example of a specification heading list in patent application related information as a document for display displayed on the browser. FIG. 29 is a diagram showing another example of a specification heading list in patent application related information as a display document displayed on the browser. FIG. 30 is a diagram showing an example of a code list and a drawing code list in patent application related information as a display document displayed on the browser. FIG. 31 is a diagram showing an example of a screen displayed in response to an operation on a code in the code list displayed on the browser. FIG. 32 is a diagram showing an example of a configuration claim tree in patent application related information as a display document displayed on a browser. FIG. 33 is a diagram showing an example in which citation relationships are cut in accordance with an operation on symbols for expressing citation relationships in the constituent claim tree displayed on the browser. FIG. 34 is a diagram showing an example of claim translation information in patent application related information as a display document displayed on the browser. FIG. 35 is a diagram showing an example of a selection menu of elements of a translation word candidate set displayed in response to an operation on a translation word of an important word in the complaint translation information displayed on the browser. FIG. 36 is a diagram showing an example of an important phrase list in patent application related information as a display document displayed on the browser. FIG. 37 is a diagram showing an example in which a translation word candidate set in an important phrase list displayed on a browser is changed to a corresponding translation word according to an operation of selecting the element. FIG. 38 is a diagram showing another example of an important phrase list in patent application related information as a display document displayed on the browser. FIG. 39 is a diagram showing an example of a display screen displayed by the display unit of the invention document analysis system according to the second embodiment. FIG. 40 is a flowchart showing an example of invention document analysis processing according to the second embodiment. FIG. 41 is a flow chart showing an example of the citation relationship analysis process. FIG. 42 is a flow chart showing an example of the complaint key phrase extraction processing. FIG. 43 is a flow chart showing an example of a specification key phrase extraction process. FIG. 44 is a flow chart showing an example of inter-element relationship determination processing. FIG. 45 is a flow chart showing an example of processing for determining the degree of importance of each key phrase. FIG. 46 is a flowchart showing an example of warning information generation processing. FIG. 47 is a flow chart showing an example of processing for generating complaint information. FIG. 48 is a flow chart showing an example of complaint information generation processing. FIG. 49 is a flowchart showing an example of code determination processing. FIG. 50 is a flow chart showing an example of claim-based drawing information generation processing. FIG. 51 is a flow chart showing an example of claim-based specification information generation processing. FIG. 52 is a flow chart showing an example of claim-based abstract information generation processing. FIG. 53 is a flow chart showing an example of modified complaint information generation processing. FIG. 54 is a flow chart showing an example of claim tree generation processing. FIG. 55 is a flow chart showing an example of the detailed information generation process. FIG. 56 is a flow chart showing an example of processing for generating various translation information. FIG. 57 is a flowchart showing an example of processing for generating an important phrase list, etc. FIG. FIG. 58 is a flow chart showing an example of processing for generating a learning model for translation of important phrases. FIG. 59 is a flow chart showing an example of a learning model generation process for translation.

The invention document analysis system in the present disclosure is an invention document analysis system that analyzes an invention document, which is a document describing claims and specifications for a patent application in which technical ideas are expressed in Japanese. A setting information acquiring unit for acquiring setting information including condition information indicating extraction conditions, a document acquiring unit for acquiring an invention document, and an invention document acquired by the document acquiring unit is analyzed based on the setting information. and an output unit configured to output information generated based on an analysis result of the invention document acquired by the document acquisition unit, wherein the analysis unit outputs information acquired by the document acquisition unit. an important phrase extraction unit for extracting important phrases from the invention document based on the setting information, and the output unit extracts a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit It is an invention document analysis system that outputs information generated based on each word.

As a result, the invention document analysis system outputs information based on the results of analysis of invention documents describing claims and specifications prepared by, for example, inventors (for example, inventors or their related parties) or patent attorneys. For example, for translators who translate the invention document (for example, translators or other people who use the invention document), referring to the output information may facilitate understanding of the invention document. . Facilitating the understanding of the invention document is useful for translators to translate the invention document appropriately or efficiently. Information generated based on key words in an invention document can be useful in cases where a translator determines corresponding translation words corresponding to key words in the invention document before translating the entire invention document.

Here, the condition information includes key word candidate character string pattern information indicating a key word candidate character string pattern representing a character string pattern that is a key word candidate, and a reference used for referring to the previously described character string. Reference character string pattern information that indicates the reference character string pattern that indicates the pattern of the character string, and code character that indicates the code character string pattern that indicates the character string pattern of the code appended after the character string that indicates the element name It includes string pattern information and specific particle character string pattern information indicating a specific particle character string pattern representing a pattern of a character string that is a predetermined particle, and the important phrase candidate character string pattern information has at least the first character in Chinese characters. and a predetermined character string whose first character is katakana are determined to correspond to the important phrase candidate character string pattern, and the reference character string pattern information is at least "the above '' corresponds to the reference character string pattern, and the code character string pattern information includes at least a predetermined character string whose first character is a number corresponds to the code character string pattern. and the specific particle character string pattern information includes at least one of "wo", "ni", "ga", "to", "from", "he" and "ha" A character is determined to correspond to the specific particle character string pattern, and the important phrase extraction unit adds a first character string corresponding to the reference character string pattern to the invention document acquired by the document acquisition unit. a first extracting unit for extracting a character string identical to the second character string as an important phrase when a second character string corresponding to the important phrase candidate character string pattern exists following the above; In the claim of the invention document obtained by, when there is a full stop character following the third character string corresponding to the above-mentioned key phrase candidate character string pattern, the same character string as the third character string is used as the key phrase. a second extracting unit for extracting, from the invention document acquired by the document acquiring unit, a fourth character string corresponding to the key phrase candidate character string pattern followed by a fifth character string corresponding to the code character string pattern; a third extracting unit for extracting a character string identical to the fourth character string as an important phrase if there is, and the invention document acquired by the document acquisition unit corresponds to the important phrase candidate character string pattern a fourth extraction unit for extracting a character string identical to the sixth character string as an important phrase when a seventh character string corresponding to the specific particle character string pattern exists subsequent to the sixth character string. In the extraction of the key words, the key word extracting unit is configured such that, when a plurality of character strings correspond to the key word candidate character string pattern, one character string among the plurality of character strings is replaced by another character. When the string is included in the description of the invention document, the remaining character string excluding the one character string from among the plurality of character strings is selected and extracted as an important phrase, and the output unit outputting patent application related information generated based on the analysis result of the analysis unit for the invention document acquired by the document acquisition unit, wherein the patent application related information is obtained from the invention document acquired by the document acquisition unit; Each of the plurality of key phrases extracted by the key phrase extracting unit is output as a display document containing content to be displayed, and the patent application related information is to be displayed in the display document. including claim information representing the content of the claim of the invention document acquired by the document acquisition unit, wherein the claim information representing the content of the claim of the invention document acquired by the document acquisition unit is obtained from the invention document by the key phrase For each of the plurality of key words in the claim extracted by the extracting unit, display control information for controlling the display mode of the key word is included, and the patent application related information should be displayed in the display document. , including specification information representing the content of the specification of the invention document acquired by the document acquisition unit, wherein the specification information representing the content of the specification of the invention document acquired by the document acquisition unit is the invention For each of a plurality of key phrases in the specification extracted from the document by the key phrase extraction unit, display control information for controlling a display mode of the key phrase is included, and in the claim information and the specification information, For each of the plurality of key phrases extracted by the key phrase extracting unit, the display control information for controlling the display mode of the key phrase corresponds to the display mode of the key phrase corresponding to the display control information. It includes highlighting information for differentiating the display mode of words other than the plurality of important words in the claim information and the description information, and among the important words expressed in the claim information, the character string that constitutes the important words is Each of the display control information for controlling a display mode corresponding to each of a plurality of key phrases different from each other is a mutually different display control information for controlling each of the plurality of key phrases to be displayed in a mutually different display mode. includes identification information that is the same as any one of the plurality of key phrases in which the character strings constituting the key phrase in the claim information are different from each other, among the key phrases represented in the specification information The display control information for controlling the display mode of the key phrase is to display the display element of the key phrase in a display mode that is at least partially the same as the display mode of the display element of the one key phrase in the claim information. It includes information for controlling display, and among the key words and phrases represented in the specification information, the character strings constituting the key words and phrases in the claim information are different from any of the plurality of key words and phrases. The display control information for controlling the display mode of the key phrase controls the display element of the key phrase to be displayed in a display mode different from any of the display elements of the plurality of key phrases in the claim information. It may include information for

As a result, for example, translators (translators, inventors, patent attorneys, or others) can use the claim information and specification information of the patent application-related information related to the display document displayed by the browser, etc. It may be possible to identify key phrases whose presentation is controlled. In addition, translators, etc., who have browsed the patent application-related information can identify whether each key phrase described in the specification information in the patent application-related information is the key phrase described in the claim. , it may be possible to quickly grasp whether a plurality of key words are the same or different, depending on the display mode of each key word. In addition, in the invention document analysis system, if, for example, highlighting (for example, displaying in bold) is performed as a control of the display mode of the important words, the translator, etc. can quickly grasp the important words in the claim information. can be. The display document generated by this invention document analysis system (that is, the display document including patent application-related information to be displayed) can be interpreted by a browser or the like installed in a device equipped with a microprocessor. As a result, the patent application related information is displayed. A translator or the like can efficiently understand the invention document by browsing the patent application related information in the display document generated based on the invention document.

Also, for example, for each of a plurality of key words in the claim extracted by the key word extracting unit, the key word is included in the claim information representing the content of the claim of the invention document acquired by the document acquiring unit. includes information indicating a display color to be added to the key phrase, and the description information representing the content of the specification of the invention document acquired by the document acquisition unit includes the key phrase For each of the plurality of key words in the specification extracted by the extraction unit, the display control information related to the key word includes information indicating a display color to be added to the key word, and is displayed in the claim information. The display control information related to each of a plurality of key phrases having different character strings constituting the key phrase among the key phrases to be displayed is such that the display element of each of the plurality of key phrases is the identification information for each of the key phrases. Correspondingly, a character string that includes information for controlling display in a display mode to which a different display color is added, and that constitutes important phrases in the claim information among the important phrases represented in the specification information. The display control information related to the same important phrase as any one of the plurality of important phrases different from each other controls the display element of the important phrase to display the one important phrase in the claim information. It may include information for controlling to display in a display mode in which the same display color as the display color added as the display mode of the element is added.

As a result, the translator or the like can view the patent application-related information as a display document using, for example, a PC equipped with a browser, a smartphone, or other computer. Translators, etc., who have viewed the patent application-related information as a display document displayed by a browser, etc., can identify the display color added to the key words in the patent application-related information, and recognize that a certain key word is a claim. It is possible to identify whether or not it is an important phrase described in , and it is possible to quickly grasp whether a plurality of important phrases are the same or different.

Further, for example, the display document is an HTML document including an HTML file written in HTML (Hypertext Markup Language), which includes the patent application-related information as content to be displayed. The display control information related to the important phrase in the claim information, which is composed of the same character string as any one of the plurality of important phrases in which the character string constituting the , for controlling to display in a display mode in which the same display color as that added as the display mode of the one key phrase is added, and the character string constituting the key phrase in the complaint information The display control information related to each of a plurality of key phrases different from each other displays each of the plurality of key phrases in a display mode in which a left border line having a predetermined width is added in a display color that differs for each key phrase. For each of the plurality of key phrases in the specification information, if the key phrase is the same as any one of the plurality of key phrases in the claim information For example, the display control information related to the key phrase in the specification information displays the key phrase in the same display color as the display color of the left boundary line according to the display mode of the one key phrase in the claim information. It is for controlling to display in a display mode with a left border line having a predetermined width added, and if the key phrase in the description information is different from any of the plurality of key phrases in the claim information For example, the display control information related to the key phrase in the specification information is for controlling the key phrase to be displayed in a display mode in which the left border line having the predetermined width is not added. You can do it.

As a result, a translator or the like can browse the patent application-related information as a display document, which is an HTML document, using a PC, smartphone, or other computer equipped with an HTML-compatible browser. Translators, etc., who have viewed the patent application-related information as a display document displayed by a browser, etc., can identify different key phrases included in the claim information in the patent application-related information, By distinguishing the display color of the boundary line, the distinction can be made quickly. It should be noted that the method of expressing different key phrases by using different display colors for the left boundary line added to the key phrases is more important than the method of expressing key phrases by using different character colors or character background colors. There is an advantage that the readability of the important phrase itself is not degraded regardless of whether the background color of the region is dark (eg black) or bright (eg white). In addition, the left border line that can be added to some display elements in HTML documents is not a character, so it is ignored when copying and pasting the text of the display content that includes important phrases. It does not get in the way when copying and pasting into a text editor etc. and editing descriptions including important phrases.

Further, for example, the identification information of the key words and phrases with respect to a plurality of key words and phrases having different character strings constituting the key words and phrases in the claim information representing the content of the claim of the invention document acquired by the document acquisition unit. includes information indicating a serial number determined in ascending order of the earliest position in which a key phrase composed of the same character string as the key phrase was stated in the claim, and the plurality of key phrases in the claim information The display control information relating to each of the plurality of important phrases is, for each of the plurality of important phrases, two of the plurality of important phrases of the first group in which the serial number related to the identification information for each of the important phrases is equal to or less than a predetermined number. The minimum value of the difference in the display color added to each key phrase in each group in all the groups is the plurality of key phrases in the second group and the plurality of key phrases in the first group whose serial number is larger than a predetermined number. Among the plurality of important phrases in the mixed group in which the phrase is mixed, the difference in the display color added to each important phrase in each of the two important phrase pairs is greater than the minimum value in all of the pairs, It may be for controlling the display color added to each important phrase.

As a result, when each key word in the claim information in the patent application-related information as a display document is displayed by a browser, etc., it is possible for translators, etc. who browsed the claim information to quickly identify each key word in the claim information. identification may be possible. Adjustment of the display color based on the serial number (for example, the number of the first appearance of the important word in the claim of the invention document) related to the identification information of the important word by the display control information of the important word is the description part of the claim information with a relatively small item number. Since the difference in display color between a plurality of important words and phrases arranged in (that is, a relatively important part) can be made relatively large, the distinguishability between important words and phrases in that part can be improved.

Further, for example, the predetermined width is a width of one character, and for the plurality of key words having different character strings constituting the key words in the complaint information, the display control information related to the key words is , to control the important words and phrases to be displayed in a display mode in which a right boundary line, an upper boundary line and a lower boundary line are not added, and the difference in the display color is the hue component of the display color The difference may be the difference, or the difference in each component of the RGB values representing the display color.

As a result, the boundary line added to the key phrase is a simple left boundary line, so that the visibility of the key phrase is improved. In addition, since the left boundary line has a width of one character (for example, a width expressed in 1 em), a rectangle painted in a display color of one character is displayed immediately before each of the plurality of important phrases in the claim information. Therefore, even if a rectangle for one character is included in the character string, it is difficult to disturb the arrangement of each character in the complaint information, so there is an effect that the visibility of each character is less likely to be disturbed. For example, if a monospaced font is used as the font for displaying each character in the complaint information in the document for display, if a rectangle for one character is mixed in the character string, the arrangement of each character will be changed. It may be possible to keep them aligned, and even if a proportional font is used as the font for displaying each character in the claim information, the width of the rectangle for one character is enough for a relatively large number of characters. Due to the fact that there is not much difference in width (especially the width of Japanese full-width characters such as relatively many kanji, hiragana, katakana, etc.), when viewing the complaint information, the arrangement of each character is disturbed and visibility is greatly hindered. There is no such thing.

Further, for example, the patent application related information includes each line of the claim information, and for each line or item of the included claim information, immediately after the content of the line or item, the line or It includes claim translation information in which a translation line containing the result of replacing key words included in the item with corresponding translated words corresponding to the key words is inserted, and the patent application related information includes each line of the specification information. Then, for each line of the included specification information, immediately after the content of the line, a translation line containing the result of replacing the key phrase contained in the line with the corresponding translated word corresponding to the key phrase was inserted. Description translation information is included, and the claim translation information and the description translation information are corresponding translations corresponding to the same important phrases as each of the plurality of important phrases in which the character strings constituting the important phrases in the claim information are different from each other. for the word, including display control information for controlling the display mode of the corresponding translated word corresponding to the relevant important word, and relating to the corresponding translated word corresponding to the important word in the claim translation information and the specification translation information; The display control information is for controlling the corresponding translated word to be displayed in a display mode in which a left boundary line having the predetermined width is added in the same color as the display color added to the key phrase. may be

As a result, for example, a translator or the like who browses the claim translation information and the specification translation information of the patent application-related information related to the display document displayed by a browser or the like can By identifying the display color of the left boundary line, it is possible to quickly grasp which important phrase described in the claim corresponds to a corresponding translated word.

Further, for example, the patent application-related information includes claim translation information representing a result of replacing a key phrase included in the content of the claim information with a corresponding translated word corresponding to the key phrase, and the patent application-related information includes: Includes specification translation information representing the result of replacing key phrases contained in the content of the specification information with corresponding translated words corresponding to the key phrases, and the claim translation information and the specification translation information are in the claim information display control information for controlling the display mode of the corresponding translated word corresponding to the same important phrase as each of the plurality of important phrases having different character strings constituting the important phrase; and the display control information related to the corresponding translated word corresponding to the key phrase in the claim translation information and the specification translation information displays the corresponding translated word in the same color as the display color added to the key phrase It may be for controlling to display in a display mode in which the left boundary line having the predetermined width is added.

As a result, for example, a translator who browses the claim information, the claim translation information, and the description translation information of the display document related to the display document displayed by a browser, etc., will be able to understand the important words and phrases of the claim information and the corresponding translation. By identifying the display color of the left boundary line added to the word, it is possible to quickly grasp which important word in the claim information corresponds to a corresponding translated word in the claim translation information and the specification translation information. It becomes possible to

Further, for example, the setting information includes information for specifying an important phrase setting dictionary that lists important phrases to be extracted, and in the important phrase setting dictionary, for at least some of the listed important phrases, Corresponding translation words are associated, the invention document analysis system includes an important phrase setting dictionary acquisition unit that acquires the important phrase setting dictionary based on the setting information, and the important phrase extraction unit extracts the important phrase When the key words listed in the setting dictionary are included in the invention document acquired by the document acquisition unit, the key words are extracted from the invention document, and the key words in the claim information or the specification information are extracted. If the phrase is an important phrase associated with a corresponding translated word in the important phrase setting dictionary, the important phrase setting is used as the corresponding translated word for the relevant important phrase in the complaint translation information or the specification translation information. A corresponding translated word associated with the key phrase in the dictionary may be used.

As a result, for example, when an inventor, etc. or a patent attorney who created an invention document wants to define specific words as important words, or when he wants to define corresponding translations for at least some of the important words, , by generating an important phrase setting dictionary in advance, the invention document analysis system can output appropriate patent application related information. Therefore, the translator may be able to translate the invention document efficiently or properly by referring to the patent application-related information. In addition, by creating a key phrase setting dictionary in cases such as when the translator has defined corresponding translation words for key phrases, invention documents provided by inventors or patent attorneys can be processed by the invention document analysis system. Appropriate patent application-related information can be output when analyzed.

Further, for example, in the display document related to the patent application-related information generated for the invention document acquired by the document acquisition unit, the display related to the key phrase extracted from the invention document by the key phrase extraction unit The control information is to display the display elements of the relevant important phrases on a search site on the network according to the operation, such as a web page containing the relevant important phrases, a definition of the relevant important phrases, a synonym of the relevant important phrases, or a synonym of the relevant important phrases. It may function as a graphical user interface (GUI) that executes a process of searching for related images or a process of translating the relevant key words on a translation site on the network.

As a result, translators, etc., who have browsed the patent application-related information related to the display document displayed by a browser, etc., can operate the key phrases in the displayed patent application-related information (i.e., operate the display elements of the key phrases) to , the search results of the key words (e.g. web pages containing key words, definitions of key words, synonyms, related images), translation results of key words, etc. can be obtained. It may be possible to efficiently or properly understand about This may allow the translator to efficiently or properly determine translation terms for key terms.

Further, for example, in the display document related to the patent application-related information generated for the invention document acquired by the document acquisition unit, the display related to the key phrase extracted from the invention document by the key phrase extraction unit The control information displays at least a part of the attribute information of the key phrase, or the importance of the key phrase determined based on the attribute information of the key phrase, depending on the operation of the display element of the key phrase. , and the attribute information of the key words extracted from the invention document, if there is a claim section defining the key words in the claim of the invention document Information indicating the paragraph number of the relevant paragraph, information indicating the paragraph number of the relevant paragraph if there is a claim paragraph that refers to the relevant important phrase in the claim of the invention document, and information indicating the relevant paragraph number in the invention document If there is a description with a code added to the words, information indicating the code, and information identifying whether or not there is a description in which the key word is used as a subject in the invention document. good too.

As a result, a translator or the like who browses the patent application-related information related to the document for display displayed by a browser or the like can obtain information on the importance or attribute information of the key phrase by operating the displayed key phrase. to some extent, it may be possible to recognize which key words in an invention document are important, and to efficiently or properly understand the key words. For this reason, the translator can perform efficient translation by preferentially determining translation terms for important key terms.

Further, for example, in the display document related to the patent application-related information generated for the invention document acquired by the document acquisition unit, the display related to the key phrase extracted from the invention document by the key phrase extraction unit The control information is a GUI for executing an important phrase inclusion description listing process for listing and displaying lines containing the relevant important phrase from the claim information and the specification information in accordance with the operation of the display element of the relevant important phrase. In the above-mentioned key phrase inclusion description listing process, the lines containing the key phrases to be operated are listed from the claim information and the specification information and displayed, and in each line that is listed and displayed The important phrase is highlighted, and the displayed line is displayed as a GUI for displaying links to multiple lines including the line in the claim information or the description information according to the operation on the line. may be a process of adding display control information for functioning.

As a result, translators, etc., who have viewed the patent application-related information related to the display document displayed by a browser, etc., can operate the key phrases in the displayed patent application-related information, and as a result of listing the key phrase inclusion description processing, You can see the lines containing that key phrase in the claim information and specification information that are listed. Therefore, it may be possible for translators, etc., to efficiently or properly understand the important terms in the invention document. This may also allow the translator to efficiently or properly determine translation terms for key terms. In addition, by including the manipulated important phrase, the important phrase in the line listed by the important phrase inclusion description enumeration process is highlighted, so that the translator can accurately identify the important phrase. In addition, the translator or the like further operates one of the lines listed by the key phrase inclusion description enumeration process by including the operated key phrase, so that it is further displayed. Multiple lines of claim information, specification information, or other invention documents that precede or follow a single line can be readily identified.

Further, for example, the patent application-related information includes an important phrase list in which important phrases are listed on a new line for each important phrase extracted from the invention document by the important phrase extraction unit, and each line of the important phrase list has a predetermined Arranged in order, the order is the order of importance determined for the important phrases for each line, the order according to the sort result of the character code order for the important phrases for each line, and the invention about the important phrases for each line It may be in order of frequency of use in the document, or in order of frequency of use in the claim of the invention document for each line of key words.

By checking the list of important words in the patent application-related information, the translator can quickly grasp the important words contained in the invention document. Efficient translation can be achieved by starting the translation of the entire invention document after In addition, for translators who browsed a list of important words and phrases arranged in order of importance, number of uses in invention documents, or number of uses in claims, the important words were arranged. Efficient translation may be possible by determining translation terms for each key term in turn. In addition, for translators who view the list of important words and phrases arranged in the order according to the character code order, multiple important words and phrases ( For example, by comparing "temporary recording folder" and "temporary recording folder", or "external storage device" and "external storage transmission"), it is possible to quickly detect typos related to the ending of important phrases. obtain. In addition, the inventor, etc., patent attorney, or translator can edit the list of important words in the patent application-related information that is output as a result of having the invention document analysis system once analyze the invention document. It may be possible to efficiently generate, update, etc. an important phrase setting dictionary that can be used to appropriately extract important phrases.

Further, for example, the display control information related to each of a plurality of key phrases having different character strings constituting the key phrase in the complaint information may display each of the plurality of key phrases in a different display color for each key phrase. It is for controlling to display in a display mode in which a left border line having a predetermined width is added, and for each important phrase in the important phrase list, the relevant important phrase is the plurality of important phrases in the claim information. If it is the same as any one of the key phrases, the key phrase in the key phrase list is displayed with a left border line according to the display mode of the one key phrase in the claim information. Display control information may be added for controlling display in a display mode in which the left boundary line having the predetermined width is added in the same display color as the color.

As a result, translators, etc., who have browsed the patent application-related information as a display document can distinguish the key words and phrases described in the claim information among the key words and phrases in the key word list. It may be possible to quickly identify key phrases in the key phrase list that correspond to each key phrase being viewed.

Further, for example, the analysis unit obtains a set of corresponding translation word candidates for one or more key phrases extracted by the key phrase extraction unit from the invention document acquired by the document acquisition unit. A translation word candidate set specifying unit for specifying a certain translation word candidate set, wherein each line of the important word list includes one important word and a corresponding translation word or a translation word candidate set corresponding to the important word/phrase You can do it.

As a result, by referring to a translation word candidate set or a corresponding translation word corresponding to the key words included in the key word list of the patent application related information output by the invention document analysis system, the translator can, for example, correspond to the key words. It may be possible to efficiently or properly determine a translation word corresponding to an important word by selecting one translation word from a set of candidate translation words.

Further, for example, in a row containing an important phrase and a translation word candidate set corresponding to the important phrase in the important phrase list, if the number of elements of the translation word candidate set is plural, the translation word A plurality of elements of the candidate set are listed in descending order of relevance indicating the evaluation value of the degree of relevance as a translation of the key phrase, and are included in the key phrase list, and are included in the translation word candidate set including the plurality of elements. In the corresponding display element, each element of the candidate translation set is displayed in a selectable manner, the selected element is determined as the corresponding translation word, and the content of the display element of the candidate translation word set is displayed as the determined correspondence To have a function as a GUI for executing a process of replacing with a translated word and displaying it, and a process of generating and outputting translation assistance information, which is information in which the important word and the corresponding translated word are associated with each other. Display control information is added, and the analysis unit extracts the translation word by predetermined arithmetic processing based on data generated by collecting and integrating a plurality of translation assistance information output in the past by the invention document analysis system. It may have a function of calculating the validity of the elements of the candidate set.

As a result, by referring to the translation word candidate set containing the elements in descending order of relevance corresponding to the important words included in the important word list, the translator can efficiently or properly translate the translation words corresponding to the important words. It may be possible to determine Also, in the past, a translator viewing the important word list, a person related to the translator (for example, other translators belonging to the same department or group as the translator), etc. selected from the translation word candidate set Since it is relatively easy to operate the invention document analysis system so as to calculate the validity of the elements of the translation word candidate set corresponding to the key phrase based on the results obtained, it is possible to maintain the validity at a high level. It can be realized relatively easily.

Further, for example, the analysis unit includes a warning information generation unit that generates warning information based on the invention document acquired by the document acquisition unit, the patent application related information includes the warning information, and the warning information When the generation unit detects that the invention document acquired by the document acquisition unit includes a description that does not satisfy the condition that the same element name is described immediately before the same code, In the description of the invention document acquired by the document acquisition unit, the warning information includes indication information indicating the same code and the element names of a plurality of different expressions to which the code is added. , where there is a parenthesized statement sandwiched between the opening and closing parentheses, the relationship between the parenthesized statement and the character string statement immediately preceding the parenthesized statement is clear. When it is detected that a bracketed statement that is not included is included, indication information indicating that the meaning of the bracketed statement is not clear and the position of the parenthetical statement in the specification of the invention document is added to the warning information. , and if a word or phrase is described after the reference character string in any of the claims of the invention document acquired by the document acquisition unit, the referenced word or phrase that is the same as that word or phrase is to the reference string that does not meet the requirement that it must appear in the part preceding the reference string in the If it is detected that such a description is included, the fact that there is no description of the preceding referenced phrase, the section number of the section containing the description related to the detected reference character string, and the reference character By including in the warning information indication information indicating the content of the description related to the column and using a predetermined narrower concept phrase list, other items among the claims of the invention document acquired by the document acquisition unit are identified. If it is detected that an independent claim, which is a clause that is not cited, contains a statement that does not satisfy the condition of not using a word or phrase indicating a more specific concept, the number of the independent claim and the word or phrase and that a word indicating a subordinate concept is used is included in the warning information, and the important word extracted by the important word extraction unit from the claim of the invention document acquired by the document acquisition unit If it is detected that the description of the description of the invention document does not satisfy the condition that the words and phrases are described in the specification, the relevant key words and phrases and the fact that the key words and phrases are not described in the description is included in the warning information, and the two important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit are one of the important phrases When a predetermined number of characters are deleted from any of the Then, the two key phrases and indication information indicating that one of the two key phrases may be erroneously written are included in the warning information, and the invention document acquired by the document acquisition unit is extracted from the invention document. When two key phrases extracted by the key phrase extraction unit are converted from half-width characters constituting one of the key phrases to full-width characters, the one key phrase after the conversion; Pointing out that the notation of the two key words and the two key words is formally inconsistent when there is a relationship in which the other key words and phrases of the two key words and phrases are the same. Information may be included in the warning information.

As a result, by referring to the warning information in the patent application-related information output by the invention document analysis system (for example, information pointed out in the warning information, etc.), the inventor, etc. or patent attorney who created the invention document can Modifications to the invention document, if any, can be made. In addition, the translator, for example, receives invention documents to be translated and patent application-related information from the inventors, etc. or patent attorneys, so that even if the warning information in the patent application-related information remains pointed out, Since it can be presumed that the inventor, etc. or the patent attorney determined that there is no particular need to deal with the indication, it is possible to obtain an appropriate invention document to be translated, and as a result, the translation of the invention document can be performed efficiently or properly.

Further, for example, the warning information generation unit may add the claim corresponding to the indication of the indication information to at least one display element of the indication information in the warning information included in the patent application related information as the display document. It is also possible to add display control information for causing the display element to function as a GUI for displaying links to the information or description locations in the specification information.

As a result, the inventor, etc. or the patent attorney who browses the warning information of the patent application-related information related to the display document displayed by a browser or the like can operate the indicated information in the displayed warning information to point out the indicated information. It will be possible to confirm the description in the claim information or specification information that corresponds to the above, so that the invention document can be appropriately corrected as necessary.

Further, for example, the patent application-related information includes a description heading list in which lines containing heading descriptions in the description of the invention document acquired by the document acquisition unit are listed in the order of description in the description, and the invention The document analysis system inserts one or more types of predetermined brackets (for example, corner Parentheses, angle brackets, round brackets, etc.), unconditionally, or on the condition that there is no period character "." at the end of the line , may be treated as a line including the description of the heading.
As a result, a translator or the like who browses the specification heading list in the patent application-related information can get an overview of what is described in the specification of the invention document. In addition, the inventors, etc. or the patent attorney can quickly confirm whether or not the description of each heading in the specification of the invention document is appropriate by browsing the description heading list. For example, in the specification heading list in the patent application related information output to the invention document analysis system, the descriptions "(first embodiment)" and "(third embodiment)" are included as two consecutive lines. , it can be understood that the heading "(Second Embodiment)" is missing in the specification of the invention document analyzed by the invention document analysis system.

Further, for example, the invention document analysis system treats a line containing a description sandwiched between an opening square bracket and an closing square bracket as a line containing the description of the heading, and the invention document analysis system in the specification heading list. For the line containing the description of the heading representing the paragraph number in the specification of the document, the important words extracted by the important phrase extraction unit from the claims of the invention document within the paragraph range related to the paragraph number in the specification If there is an important phrase that is the same as the phrase, the important phrase may be added to the line of the description heading list.
As a result, a translator or the like who browses the specification heading list in the patent application-related information may be able to quickly guess or confirm the outline of what is described in the specification of the invention document. If the translator can quickly infer the outline of the specification, it is more likely that the translator will be able to translate the sentences described in the specification efficiently or properly. In addition, for each important phrase (that is, the important phrase extracted from the claim) added to the line containing the description of the heading representing the paragraph number in this specification heading list, the same display color is used for the important phrase of the same character string. (For example, the display color of the left boundary line of key phrases) may be attached, and different key phrases may be assigned different display colors. Adding a display color to an important phrase is realized, for example, by display control information for a display element for the important phrase. This can increase the possibility that a translator or the like who browses the specification heading list related to the document for display displayed by a browser or the like can quickly recognize whether or not the key words are the same. In addition, in addition to adding important phrases extracted from the claims to the line containing the description of the heading representing the paragraph number in the specification heading list, If the important phrase is present in the paragraph of that paragraph number, the important phrase may be added by displaying it in a display mode different from that of the important phrase extracted from the claim.

Further, for example, the analysis unit discriminates the relationship between the elements represented by each of the key phrases extracted by the key phrase extraction unit from the invention document acquired by the document acquisition unit, and the key phrases indicating the result of the discrimination. an inter-element relationship determination unit that generates relationship information, wherein the patent application related information includes the important phrase relationship information; Inclusion relationship information expressing structural inclusion relationships between elements represented by each of the multiple key phrases extracted by the unit, and between elements represented by each of the multiple key phrases extracted from the invention document by the key phrase extraction unit Recording relationship information that expresses the relationship between a recording medium and the content of the recording medium when the relationship exists, and the relationship between elements represented by each of a plurality of important phrases extracted from the invention document by the above-mentioned important phrase extraction unit. Program implementation relationship information expressing the relationship when there is a relationship with the content implemented by the program, and when there is an equivalence relationship between the elements represented by each of the multiple key phrases extracted from the invention document by the key phrase extraction unit Equivalence relationship information expressing the relationship, and hierarchical conceptual relationship information expressing the relationship when there is a conceptual hierarchical relationship between elements represented by each of the plurality of key phrases extracted from the invention document by the key phrase extraction unit. and may be included.
As a result, a translator who browses the key phrase-related information in the patent application-related information output by the invention document analysis system can efficiently understand the relationships between multiple key phrases in the invention documents analyzed by the invention document analysis system. Therefore, it may be possible to efficiently or properly determine translation terms corresponding to each of the plurality of important terms.

Further, for example, the setting information acquired by the setting information acquisition unit includes comment specifying information that is information specifying a comment line or a comment, and the analysis unit acquires the claim information in the patent application related information a claim tree generation unit that generates a claim tree that expresses the citation relationship of each item of the claim represented in the tree structure format, the patent application related information includes the claim tree, and the claim tree generation unit For each clause of the claim in the above claim information, write the information indicating the clause number of the clause cited by the clause on a new line in ascending order of the clause number, using the symbol for expressing the citation relationship and the clause number. generated a claim tree, and for each item related to each line of the claim tree, if the line immediately preceding that item in the claim information is a comment line in a predetermined format specified based on the comment specifying information , the content of the comment line is added to the line that describes the item number of the item in the claim tree, and if the line immediately preceding the item in the claim information is not the comment line, the same line as the heading of the item , when comments are written in a predetermined format specified based on the information for specifying comments, the content of the comments shall be added to the line in which the item number of the item in the claim tree is described, and the claim If the line immediately preceding the relevant paragraph in the information is not the comment line and the comment is not stated in the same line as the heading of the relevant paragraph, the extraction of the key words stated in the relevant paragraph of the claim of the invention document When there are one or more key phrases extracted by the Department, at least one of the one or more key phrases shall be added to the line describing the item number of the relevant paragraph in the claim tree. good too.
As a result, the translator can confirm the comments included in the claims of the invention document by the inventors or the patent attorney by looking at the claim tree in the patent application-related information output by the invention document analysis system based on the invention document. , it may be possible to efficiently or accurately understand the significance of each item through comments based on the citation relationships of each item in the claims. In addition, for clauses that do not contain any comments on the claim clauses of the invention document, the key phrases of that clause are shown in the claim tree in the patent application-related information output by the invention document analysis system based on the invention document. Therefore, it is possible that a translator, or an inventor or patent attorney who has somewhat forgotten the contents of the invention document after the passage of time can understand the meaning of that clause of the claim. Translators can translate claim terms efficiently or properly if they have a good understanding of the meaning of each claim term.

Further, for example, the claim tree generation unit generates a configuration claim tree that expresses the citation relationship of each item of the claim represented in the claim information in the patent application related information in a tree structure format, The application-related information includes the constituent claim tree, and the claim tree generation unit replaces the lines in ascending order of the item number for each item of the claim in the claim information, and adds the item number of the item cited by the item. A constituent claim tree is generated in which the information indicating the When there are one or more key phrases extracted by the department, each key phrase is added to the line that describes the item number of the paragraph, and if there are multiple key phrases to be added to the paragraph, If the elements represented by each of the important terms have a compositional inclusion relationship, a description representing the relationship between the important terms may be appended to the line.
By viewing the configuration claim tree in the patent application-related information output by the invention document analysis system based on the invention document, the translator or the content of the invention document can be forgotten somewhat after the passage of time. The inventors, etc. or patent attorneys who have done so can grasp the citation relationship of each claim section in the invention document, and also grasp the relationship between multiple important terms described in the claim section. It may be possible to efficiently understand the significance of the term.

Further, for example, the invention document analysis system, based on the correction information associated with the predetermined inappropriate character string pattern information, character string corresponding to the inappropriate character string pattern indicated by the inappropriate character string pattern information If the column exists in the claim in the invention document acquired by the document acquisition unit, the content of the claim after amendment is added to the patent application related information by correcting the claim based on the correction information. The claim tree generation unit includes the modified claim information generated so as to represent the claim tree, and the claim tree generation unit causes the display element for the item number of the claim tree or the constituent claim tree of the patent application related information as the display document to be: Add display control information to have a function as a GUI for displaying the description part of the item number of the claim information in the display document according to the operation of the display element, and add the display control information to the claim tree or In the constituent claim tree, a display element for the symbol for expressing the citation relationship is provided with, in accordance with the operation of the display element, a citation relationship disconnection process for severing the citation relationship represented by the symbol. Display control information for providing a GUI function is added, and the citation relation disconnection processing updates the content of the modified claim information in the display document to reflect the disconnection of the citation relation. , changing the sign for expressing the citation relation as the display element to a predetermined sign to express that the citation relation has been severed, and re-displaying the display element. You can do it.
As a result, inventors, etc. or patent attorneys, for example, after creating invention documents for filing in Japan, can file foreign applications, etc., based on the application strategies for each country, the differences in the legal systems related to patents in each country, etc. If you want to use the invention document as a Japanese text for translation for the purpose of changing the composition of claims, the claim tree or claim tree of the patent application-related information as a display document output by the invention document analysis system based on the invention document Through some GUI manipulation of the constituent claim tree, one can effectively de-quote another term in one claim section and generate or modify modified claim information reflecting that de-citation. can update. After that, by acquiring and perusing the patent application-related information as a display document, the translator can translate for foreign applications, etc., based on the modified version of the claim information. In addition, the inventors or the patent attorney may, for example, copy and paste the display contents of the corrected claim information after the operation of the GUI, and pass the document generated to the translator to request translation of the document.

Further, for example, the invention document analysis system expresses, of the key words and phrases extracted from the invention document by the key word extraction unit, key words and phrases corresponding to codes, by associating the codes and the key words and phrases. A code list, which is a list, is generated and included in the patent application related information, and the invention document analysis system enumerates the codes described after the key words and phrases extracted from the invention documents by the key word extraction unit. Then, when the description in which the key phrase extracted by the key phrase extracting unit and the key phrase followed by the code does not exist in the invention document, the key phrase When an element represented by a phrase structurally includes an element represented by another key phrase or is structurally included in an element represented by another key phrase, the structural inclusion of the key phrase and the other key phrase The code list may be generated by determining a code based on the relationship and representing the determined code and the key phrase in association with each other.
As a result, the invention document analysis system determines that the invention document includes descriptions to which a code is added for each of the key terms in which there is a structural inclusion relationship between the elements represented by each of the plurality of key terms in the invention document. If there is no key word, the code for the key word is automatically determined based on the inclusion relationship, and a code list in which the code and the key word are associated is generated. Etc. or a patent attorney may be able to efficiently or properly complete the invention document. For example, inventors or patent attorneys prepare invention documents without describing codes, and insert necessary codes into the invention documents based on the code list generated by the invention document analysis system. It may be possible to complete the document.

Further, for example, the document acquisition unit further acquires the drawing document corresponding to the invention document acquired by the document acquisition unit, and the drawing document generated based on the analysis result of the invention document acquired by the document acquisition unit An element name described with a code added in the invention document, among a plurality of key phrases extracted from the invention document by the key phrase extraction unit, in the claim information or the specification information of the patent application related information , the display control information related to the key phrase is such that the code related to the key phrase in the drawing document corresponding to the invention document is It may include information for display as a GUI element for displaying the described portion.
As a result, the translator can use the GUI related to the same key words as the key words in the claim information or the specification information of the patent application-related information as the display document and the descriptions to which the code is added in the invention document. By operating on, it is possible to quickly check the part of the drawing where the code corresponding to the key phrase is described, so it is possible to efficiently understand the key phrase. may increase the likelihood that a patentee will be able to translate the invention document efficiently or correctly.

Further, for example, the document acquisition unit acquires a plurality of invention documents and a plurality of translation result documents that are translation results of each of the plurality of invention documents, and the invention document analysis system acquires the invention to be translated. An acquisition unit for acquiring invention document standard specifications for translation that defines a plurality of conditions to be satisfied by a document; A judgment is made as to whether or not at least some of the conditions among the plurality of conditions stipulated in the Standard Provisions for Invention Documents for Translation are satisfied, and among the plurality of invention documents, the conditions for which the judgment is made are selected. A document evaluation unit that selects invention documents whose degree of satisfaction exceeds a predetermined degree, and a set of invention documents selected by the document evaluation unit and translation result documents corresponding to the invention documents are used as training data. a machine learning unit that generates a learning model for translation, which is a learning model for machine translation, by machine learning, and the output unit outputs the learning model for translation generated by the machine learning unit. It may also include a model output unit.
As a result, an invention document having a relatively high conformity to the invention document standards for translation is selected, and a pair with the corresponding translation result document is used as training data. A combination of an inappropriate invention document and a translation result document whose content is inconsistent due to a translation error or the like generated based on the inappropriate invention document is less likely to be used as teacher data, and an invention document analysis system can generate an appropriate learning model for translation. In addition, according to a system (for example, the invention document analysis system 20, etc.) that machine-translates invention documents by arithmetic processing using this generated learning model for translation, appropriate translation results can be obtained to some extent, so the translator can , it may be possible to translate the invention document efficiently or properly by referring to the translation result and correcting it as appropriate.

Document for display according to the present disclosure, which is output by the invention document analysis system described above (for example, a system that can be realized by causing an invention document analysis process to be performed by causing a device equipped with a microprocessor to execute an invention document analysis process program) (that is, a display document that includes patent application-related information to be displayed) is data that can include a script as a computer program, is data that includes a document written in a markup language, and is data that includes a document written in a markup language. The generated patent application related information is included as content to be displayed. The display document in the present disclosure may be recorded in a non-temporary recording medium such as a computer-readable ROM, optical disk, hard disk, etc., and distributed or distributed. When the display document in the present disclosure is distributed, the display document is subject to interpretation by a browser or the like installed in a device equipped with a microprocessor, and as a result, it is generated by the invention document analysis system described above. This will display the patent application related information. A translator or the like can efficiently understand the invention document by browsing the patent application related information in the display document generated based on the invention document. In addition, by browsing the displayed patent application-related information, the translator can efficiently or properly translate the claims and the specification of the invention document represented by the claim information and the specification information included in the patent application-related information, for example. can be translated into By viewing and referring to the displayed patent application-related information, the inventors, etc. or patent attorneys can, for example, view the claims and specification information of the invention document represented by the claim information and specification information included in the patent application-related information, respectively. The specification may be updated with appropriate content, for example to make it easier to translate.

The display document in the present disclosure includes, for example, a document written in a markup language, is subject to interpretation by a browser or the like in a device equipped with a microprocessor, and is an invention for a patent application in which technical ideas are expressed in Japanese. A display document containing patent application-related information including claim information representing the content of the claims in the document and specification information representing the content of the specification in the invention document as content to be displayed, wherein the claim controls the display mode of display elements for key phrases extracted based on predetermined key phrase extraction conditions among the terms of the complaint. each of the display control information relating to each of a plurality of key phrases having different character strings constituting the key phrase among the key phrases represented in the complaint information, each of the plurality of key phrases It is for controlling each display element to be displayed in a display mode in which a display color different from each other is added. The display control information relating to an important phrase composed of the same character string as any one of the plurality of different important phrases causes the display element of the important phrase to display the one important phrase. It is for controlling to display in a display mode with the same display color added as the display mode of the element, and the description information representing the content of the specification is includes display control information for controlling the display mode of the display element of the key phrase for each key phrase extracted based on the conditions for extracting the key phrase, and is displayed in the specification information The display control information related to the same important phrase as any one of the plurality of important phrases in which the character strings constituting the important phrase in the claim information are different from each other It is for controlling the display elements of important phrases to be displayed in a display mode to which the same display color as the display mode of the display element of the one important phrase in the claim information is added. , the display control information related to important words and phrases different from any of the plurality of important words and phrases in which the character strings constituting the important words and phrases in the claim information are different from each other among the important words and phrases represented in the specification information, This display document is for controlling display elements of key phrases to be displayed in a display mode different from any of the display elements of the plurality of key phrases in the claim information.
As a result, when the patent application-related information is displayed by a browser or the like, a plurality of important phrases composed of mutually different character strings extracted from the claims of the invention document can be displayed in the claim information or specification in the patent application-related information. Important phrases in claim information or specification information displayed in a display mode to which display colors different from each other are added in the document information, and composed of the same character string as any one of the plurality of important phrases is displayed in a display mode in which the same display color as that one important phrase is added. Therefore, a translator or the like viewing the patent application-related information displayed by the browser can quickly identify key words that are the same as and different from each of the multiple key words by the added display colors. , the content of claim information or specification information can be efficiently understood. For translators, efficient understanding of the content of claim information or specification information is useful for efficient translation of claims and specification. Therefore, a translator who obtains a display document containing patent application-related information from an inventor, etc. or a patent attorney who created an invention document causes a browser to interpret the display document, displays the patent application-related information, and displays the contents of the document. By browsing, there is a possibility that the invention document can be translated efficiently. In addition, a translator who obtains the invention document from the inventor or patent attorney who created the invention document can use the invention document analysis system (for example, the invention document analysis system 20, etc.) in this disclosure to apply the patent based on the invention document. By generating a display document that includes application-related information and having the browser interpret the display document to display the patent application-related information and view the contents, there is a possibility that the invention document can be translated efficiently. .

Further, for example, the display document is an HTML document including an HTML file written in HTML (Hypertext Markup Language) as the content of the patent application-related information to be displayed, and the conditions for extracting key words are: A character that is a candidate for an important phrase following the first character string corresponding to the reference character string pattern representing the pattern of the reference character string used for referencing the character string previously described in the claim or the specification A first extraction condition for extracting a character string identical to the second character string as an important phrase when there is a second character string corresponding to the key phrase candidate character string pattern representing the pattern of the sequence; a second extraction condition for extracting a character string identical to the third character string as an important phrase when a period character exists following the third character string corresponding to the important phrase candidate character string pattern; Or, in the specification, a coded character string representing the pattern of the coded character string appended after the character string representing the element name following the fourth character string corresponding to the key phrase candidate character string pattern a third extraction condition for extracting a character string identical to the fourth character string as a key phrase when a fifth character string corresponding to the pattern exists; If the 6th character string corresponding to the pattern is followed by the 7th character string corresponding to the specific particle character string pattern representing the pattern of the character string that is a predetermined particle, it is the same as the 6th character string a fourth extraction condition for extracting a character string of as an important phrase; In the case where multiple character strings apply to the string pattern, if one character string among the multiple character strings is included in the other character strings in the description of the claim or the specification, the multiple character strings and a selection extraction condition for selecting and extracting key words from the remaining character strings after excluding the one character string, wherein the key word candidate character string pattern includes at least the first character. A predetermined character string of kanji characters and a predetermined character string whose first character is katakana, the reference character string pattern corresponds to at least the character string "above", and the code character string pattern corresponds to corresponds to at least a predetermined character string whose first character is a number, and the specific particle character string pattern includes at least "wo", "ni", "ga", "to", "kara", " The display control information related to each of the plurality of important phrases that correspond to any of the characters "he" and "wa" and that have different character strings constituting the important phrases in the claim information is the plurality of important phrases It is for controlling each display element to be displayed in a display mode in which a left border line having a predetermined width is added in a different display color for each key phrase, and for each key phrase in the specification information , if the key phrase is the same as any one of the plurality of key phrases in the claim information, the display control information related to the key phrase in the specification information is the key phrase of the key phrase The display elements are displayed in a display mode to which a left boundary line having the predetermined width is added in the same display color as the display color of the left boundary line according to the display mode of the display element of the one important phrase in the claim information. If the key phrase in the description information is different from any of the plurality of key phrases in the claim information, the display control information related to the key phrase in the description information is the key phrase may be controlled to display the display element in a display mode in which the left boundary line having the predetermined width is not added.
As a result, translators, etc., who view the patent application-related information as a display document displayed by a browser, etc., can add different key phrases included in the claim information in the patent application-related information to each of the key phrases. can be quickly distinguished by identifying the display color of the left border line. It should be noted that the method of expressing different key phrases by using different display colors for the left boundary line added to the key phrases is more important than the method of expressing key phrases by using different character colors or character background colors. There is an advantage that the readability of the key phrase itself is not degraded regardless of whether the background color of the area is a dark color (e.g. black) or a bright color (e.g. white). This is useful when the color can be changed to black or the like, or when the display document implements a GUI that allows selection of the background color. In addition, the left border line that can be added to some display elements in HTML documents is not a character, so it is ignored when copying and pasting the text of the display content that includes important phrases. It does not get in the way when copying and pasting to a text editor etc. and editing descriptions including important phrases.

Further, for example, the predetermined width is a width of one character, and the patent application-related information includes, in the claim information, each of a plurality of important phrases in which the character strings constituting the important phrases are different from each other. In the next line, the list of important phrases listed is included, and for each important phrase in the list of important phrases, display control information for controlling the display mode of the display element of the important phrase is added, and in the list of important phrases The display control information related to the important phrase is the same as any one of the plurality of important phrases having different character strings constituting the important phrase in the claim information. For example, a left boundary line having the predetermined width is added to the display element of the key phrase in the same display color as the display color of the left boundary line according to the display mode of the display element of the one key phrase in the claim information. It may be for controlling to display in a different display mode.
As a result, translators, etc., who have browsed the patent application-related information as a display document can distinguish the key words and phrases described in the claim information among the key words and phrases in the key word list. It may be possible to quickly identify key phrases in the key phrase list that correspond to each key phrase being viewed. In addition, since the left boundary line has a width of one character (for example, a width expressed in 1 em), a rectangle painted in a display color of one character is displayed immediately before each of the plurality of important phrases in the claim information. Therefore, even if a rectangle for one character is included in the character string, it is difficult to disturb the arrangement of each character in the complaint information, so there is an effect that the visibility of each character is less likely to be disturbed. In addition, for example, if a monospaced font is used as the font for displaying each character in the complaint information in the display document, when a rectangle for one character is mixed in the character string, the arrangement of each character can be kept in alignment, and even if a non-monospaced font is used as the font for displaying each character in the claim information, the width of a rectangle for one character is sufficient for a relatively large number of characters. Since there is not much difference with respect to the width, when the claim information is visually observed, the arrangement of each character is not disturbed and visibility is not greatly hindered. In addition, it is possible to efficiently understand the contents of claim information and specification information by having good visibility of characters in patent application-related information or being able to quickly identify each important word with different character strings. obtain. For translators, efficient understanding of claim and specification information is useful for efficient translation of claims and specification of invention documents.

Further, for example, each row of the important phrase list includes one important phrase and a corresponding translated word corresponding to the relevant important phrase, or a translation word candidate set that is a set of candidates for the corresponding translated word for the relevant important phrase. and the display control information relating to the important phrase in the important phrase list is configured to display elements of the set of candidate translation words for the important phrase in response to an operation to display any element of the set of candidate translation words. selected according to the operation on the display element of the set of candidate translation words in the state of functioning as the GUI. determined element of the translation word candidate set is determined as the corresponding translated word corresponding to the important phrase, and the content of the display element of the translation word candidate set is replaced with the determined corresponding translated word and displayed. It is good also as including the script for performing the process to carry out.
As a result, translators, etc. who have browsed the patent application-related information as a display document can operate the GUI of the translation word candidate set corresponding to the key words in the key word list in the patent application-related information displayed by the browser etc. By selecting any element from the set of candidate translation words, the corresponding translation words corresponding to the important words in the list of important words can be easily determined and displayed. In addition, the translator etc. can, for example, copy and paste the important phrase list displayed by the browser etc. By pasting it into a text editor or the like and editing it as necessary, the invention document analysis system (for example, the invention document analysis system 20, etc.) in the present disclosure can extract important information from the invention document that is the basis for generating patent application related information. It is possible to relatively easily generate an important phrase setting dictionary that can be used to extract words (for example, an important phrase setting dictionary that can be obtained and used by the important phrase setting dictionary acquisition unit 203).

In addition, for example, the display control information related to the key phrase in the patent application related information is such that the display element of the key phrase is displayed on a search site on the network in response to an operation, a web page including the key phrase, It functions as a GUI that executes the definition of important phrases, the synonyms of the relevant important phrases, the processing of searching for related images of the relevant important phrases, or the processing of translating the relevant important phrases on a translation site on the network. You can do it.
As a result, translators, etc., who have browsed the patent application-related information related to the display document displayed by a browser, etc., can operate the key phrases in the displayed patent application-related information (i.e., operate the display elements of the key phrases) to , the search results of the key words (for example, web pages containing key words, definitions of key words, synonyms, related images), or translation results of the key words, so that the patent application related It may be possible to efficiently or properly understand the key words in the invention document on which the information was generated. This may allow the translator to efficiently or properly determine translation terms for key terms.

Further, for example, the display control information related to the key phrase in the patent application related information may display at least a part of the attribute information of the key phrase, or display the display element of the key phrase according to the operation. It functions as a GUI for displaying the degree of importance of the key phrase determined based on the attribute information of the key phrase, and the attribute information of the key phrase is the key phrase in the claim represented by the claim information. If there is a claim section that defines Information indicating an item number, and information indicating the code when there is a description with a code added to the key phrase in the specification represented by the description information may be included.
As a result, translators, etc., who view the patent application-related information related to the document for display displayed by a browser, etc., can obtain information on the degree of importance or attribute information of the key phrases by operating the displayed key phrases. Therefore, it becomes possible to recognize, to some extent, which key phrases in the invention document on which the patent application-related information was generated is important, and to understand the key phrases efficiently or properly. can be possible. For this reason, the translator can perform efficient translation by preferentially determining translation terms for important key terms.

Further, for example, the display control information related to the key phrase in the patent application related information may change the display element of the key phrase to a line containing the key phrase from the claim information and the specification information according to the operation. It functions as a GUI for executing an important phrase inclusion description enumeration process, wherein the important phrase inclusion description enumeration process selects lines containing important phrases to be operated from the claim information and the specification information. Enumerate and display, highlight the relevant important phrases in each of the enumerated and displayed lines, and in the displayed lines, according to the operation on the lines, the lines in the claim information or the description information are displayed. It may be a process of adding display control information for causing the line to function as a GUI for displaying links to multiple lines.
As a result, translators, etc., who have viewed the patent application-related information related to the display document displayed by a browser, etc., can operate the key phrases in the displayed patent application-related information, and as a result of listing the key phrase inclusion description processing, You can see the lines containing that key phrase in the claim information and specification information that are listed. Therefore, the translator or the like may be able to efficiently or properly understand the key terms in the invention document on which the patent application-related information was generated. This may also allow the translator to efficiently or properly determine translation terms for key terms. In addition, by including the manipulated important phrase, the important phrase in the line listed by the important phrase inclusion description enumeration process is highlighted, so that the translator can accurately identify the important phrase. In addition, the translator or the like further operates one of the lines listed by the key phrase inclusion description enumeration process by including the operated key phrase, so that it is further displayed. Multiple lines of claim information, specification information, or other invention documents that precede or follow a single line can be readily identified.

Further, for example, the patent application related information includes claim translation information representing the results of machine translation of the claims represented in the claim information, and machine translation results of the specification represented in the specification information. Including specification translation information, one line or one item representing the result of machine translation for one line or one item of the claim information in the claim translation information is the entire line or item of the claim information Replace the complete translation line expressed in the target language, or the key phrase contained in the line or paragraph of the claim information with the corresponding translated word corresponding to the key phrase, or a set of candidate translation words for the key phrase. is a partial translation line that is the result of the translation, and one line representing the result of machine translation for one line of the description information in the description translation information is the entire line of the description information in the translation target language This is the result of replacing the complete translation line represented by or the key phrase contained in the line of the specification information with the corresponding translation word corresponding to the key phrase, or the translation word candidate set for the key phrase The claim translation information and the specification translation information are partial translation lines, and the claim translation information and the specification translation information are the same as any one of the plurality of key phrases in which the character strings constituting the key phrases in the claim information are different from each other. For key phrases, including display control information for controlling the display mode of the display element of the result of machine translation with the key phrase as the object of machine translation, the display control information related to the display element of the result of the machine translation is display of the display element in such a manner that at least part of the display mode of the display element has the same display color as the display color added to the display element of the important phrase in the claim information and the specification information; It may be for controlling the aspect.
As a result, for example, a translator who browses the patent application-related information related to the display document displayed by a browser etc. can add By identifying the displayed display color, it is possible to quickly grasp which key words in the claim information or specification information correspond to the results of the machine translation of the key words in the claim translation information or the description translation information. It becomes possible.

Further, for example, the claim translation information includes each line of the claim information, and for each line or item of the included claim information, immediately after the content of the line or item, the content of the line or item The complete translation line or the partial translation line representing the result of machine translation corresponding to the machine translation target is inserted, and the description translation information includes and includes each line of the description information For each line of the specification information, immediately after the line, the complete translation line or the partial translation line representing the machine translation result corresponding to the machine translation target of the line is inserted, and the claim translation information And the description translation information includes a display mode of at least a part of the machine translation target in the claim translation information and the description translation information, and a display of at least a part of the machine translation result corresponding to the machine translation target display control for each display element in order to control the display mode of the element to be different in at least one of character background color, character color, character decoration, font size, font style, and font weight Information may be added.
As a result, translators, etc., who view patent application-related information as a display document displayed by a browser, etc., will be able to specify the lines to be machine-translated and the machine-translated Lines of translation results can be quickly identified by differences in at least one of character background color, character color, character decoration, font size, font style, and font weight. In addition, while visually confirming the lines to be machine-translated in the claim translation information and the description translation information, the translator appropriately adjusts the contents of the lines of the machine translation results that are placed after the lines to be machine-translated. It may be possible to modify and efficiently produce a better translation.

Further, for example, the patent application-related information includes warning information, and the warning information indicates that the claim or the specification of the invention document satisfies a plurality of conditions stipulated in a predefined invention document standard specification for translation. Information indicating whether or not the conditions are satisfied and if the conditions are not satisfied, and information indicating that the claim or the specification of the invention document satisfies the multiple conditions specified in the standard provisions of the invention document for translation An invention indicating the evaluation value of conformity of the invention document to the Standard Provisions for Invention Documents for Translation, which is calculated by a predetermined calculation based on the results of inspections to determine whether or not at least some of the conditions are satisfied. It may include document evaluation information, specification access information for accessing the invention document standard specification for translation, and version information indicating a version of the invention document standard specification for translation.
As a result, by referring to the warning information (for example, information pointed out in the warning information) in the patent application-related information as a display document displayed by a browser, etc., it became the basis for generating the patent application-related information. The inventor, etc. or the patent attorney who created the invention document can amend the invention document if necessary. In addition, the translator, for example, receives a display document related to the patent application-related information from the inventor, etc. or the patent attorney, so that even if the warning information in the patent application-related information remains pointed out, the translator can Since it can be presumed that the inventor, etc. or patent attorney determined that there is no particular need to deal with the above, it is possible to grasp the appropriate content of the translation target, and as a result, the translation of the invention document can be efficiently performed Or it may be possible to do it properly. In addition, the translator or the like can access the standard specification of the invention document for translation and browse its contents by referring to the specified access information in the warning information. Also, the translator or the like can check which version of the standard specification of invention documents for translation has been used by referring to the version information of the standard specification of invention documents for translation in the warning information.

In addition, the invention document analysis processing program according to the present disclosure analyzes invention documents, which are documents describing claims and specifications for patent applications expressing technical ideas in Japanese, in a device equipped with a microprocessor. An invention document analysis processing program for generating a document for display by performing analysis processing, wherein the invention document analysis processing includes a document acquisition step of acquiring an invention document, and the document acquisition step an analysis step of analyzing an acquired invention document by extracting key phrases based on predetermined key phrase extraction conditions; and an output step of generating and outputting the display document for displaying the patent application related information generated based on the analysis result.
By installing this invention document analysis processing program in a device or the like having a microprocessor, the device or the like can implement the invention document analysis processing. The display document as described above is generated by the invention document analysis processing realized by the invention document analysis processing program. Browsing may facilitate understanding of the invention document for translators and the like. Promoting the understanding of the invention document is useful for translators to translate the invention document appropriately or efficiently.

Here, for example, the invention document analysis process displays a GUI screen that enables a selection operation of one or more of the display documents output by the output step, and displays the selected display document. Processing may include subjecting the document to interpretation by a browser on the device.
As a result, by executing the invention document analysis processing program on a device equipped with a microprocessor and selecting one of the display documents generated in the past as the execution result, the patent application related information related to the display document can be obtained. will be displayed by the browser. Therefore, when there are multiple display documents generated as a result of executing the invention document analysis processing program, translators, etc. can compare and view the patent application related information related to each of the multiple display documents. Thus, there is a possibility that the patent application related information related to the display document generated based on the specific invention document among the plurality of display documents can be efficiently understood.

In addition, the invention document analysis system and related technology described above can be used as a whole or a part of equipment, devices, integrated circuits, systems, methods, programs (that is, computer programs), computer-readable recording media, etc. It can be embodied in any manner.

Hereinafter, in order to facilitate understanding of the technology in the present disclosure, embodiments will be illustrated and described in detail with reference to the drawings as appropriate. However, description of well-known techniques will be omitted as appropriate. The drawings are schematic diagrams and are not strictly illustrated. In addition, the number, arrangement, shape, attribute, state, numerical value, connection mode between elements, execution order, inclusion relationship, etc. of various elements in the description and drawings of this embodiment are only examples, and the scope of claims is not intended to limit the claimed subject matter described in Among the various elements in the description and drawings of this embodiment, elements not described in the independent claims can be arbitrarily added.

(Embodiment 1)
An example of an embodiment of an invention document analysis system will be described below with reference to the drawings.

[1. Information related to the embodiment of the invention document analysis system]
The invention document analysis system shown in the embodiment of the present disclosure is a system that executes invention document analysis processing for analyzing invention documents.

In the present disclosure, an invention document is a document describing claims or a specification for a patent application in which a technical idea is expressed in Japanese. By the way, in order to obtain patent rights (e.g., patent rights) in regions other than Japan (e.g., documents written in a foreign language other than Japanese, to a foreign country other than Japan) , for patent applications, etc.), there are cases where an invention document prepared by an inventor is translated by a translator to create a translation result document. A translation result document is a document containing at least one of the claims and the specification written mainly in a foreign language. The foreign language used to describe the translation result document is English as an example, and Chinese as another example. For the sake of convenience, English will be used as an example of the foreign language used to describe the translation result document, but the language used to describe the translation result document is not limited to English.

One example of the purpose of creating the invention document analysis system shown in the embodiment in this disclosure is to obtain useful rights in regions other than Japan, so that the translator can efficiently or It is to provide a useful system for creating properly.

[1-1. Invention document]
An invention document is a document in which a technical idea is expressed in Japanese and a claim or specification for a patent application is described. Here, a document means document data, and the content of a document may include descriptions of one or more documents. Note that the invention document may be a document that describes both the claims and the specification. An invention document, for example, consists of a plurality of lines. Each line is each part separated by a line feed code in the document data.

The description of the invention document, which is a document expressing the technical idea in Japanese, should be mainly written in Japanese in terms of language, and foreign language words may be used partially. A claim is, for example, the description of a document "claims" in a Japanese patent application, or the description of one or more "claims" in a Japanese patent application. In addition, even if the document is composed in a specific format different from the description format of the Japanese patent application, the description substantially equivalent to the description content of the "claims" or "description" in the Japanese patent application By converting the specified format, the document containing the document can be treated as a document containing the description of the "claims" or "description" of the patent application in Japan, so the document describing the claims or the description for the patent application I assume. For example, the claims may be the contents of the document "Claims" in an international application (that is, an international application under the Patent Cooperation Treaty).

An example of an invention document is a document of a patent application in Japan that expresses a technical idea in Japanese, including claims and specifications, regardless of whether it is before or after the filing of the application. An example of an invention document is an incomplete document in the preparatory stage of a patent application in Japan that expresses a technical idea in Japanese, including at least one of claims and a specification. Also, as an example of an invention document, a foreign patent application (i.e., a patent application filed in a region other than Japan) that expresses the technical idea in Japanese, including at least one of claims and descriptions. documents or documents at the stage prior to being translated into foreign languages as foreign patent applications (for example, Japanese manuscripts for translation, etc.). An example of an invention document is a document such as an invention memo that expresses a technical idea in Japanese and includes descriptions corresponding to at least one of the claims and the specification. Also, examples of invention documents include data substantially equivalent to the contents of patent publications (e.g., patent publication publications, patent publication publications, etc.) published by Japanese or foreign government offices or international bureaus.

[1-2. Work related to translation of invention documents]
An example of the work flow related to the translation of invention documents will be described below.

FIG. 1 shows an example of the work flow associated with translating invention documents. As shown in the figure, the inventor first prepares an invention memo describing the content of the technical idea he has created, organizes the content of the invention memo, and essentially forms a claim or specification for a patent application. Create an invention document stating The inventor, etc. (for example, the inventor, the applicant who has been assigned the right to obtain a patent from the inventor, the collaborators in the organization to which the inventor belongs, etc.) must have a patent attorney prepare the invention document. sometimes left to The inventor, etc. or the patent attorney may also create a drawing document describing the drawing for the patent application.

When the inventor, etc. or the patent attorney requests the translator to translate the invention document, the inventor, etc. or the patent attorney may, as necessary, specify corresponding translation words for important words (that is, so-called keywords) in the invention document, In some cases, special translation instructions may be given in accordance with the region in which the application is to be obtained (for example, in response to a strategy that considers the foreign laws, judicial precedents, etc.). An important phrase in an invention document written mainly in Japanese (that is, a document that expresses a technical idea in Japanese) is one or more words (that is, a character string consisting of one or more characters), and is not written in Japanese. It may be one or more words of a phrase. The translator creates a translation result document by translating according to the invention document, designation of corresponding translation words for key words, special translation instructions, and the like.

FIG. 2 shows an example of the flow of translation work by a translator. As shown in the figure, for example, the translator first understands the outline of the invention document, and if a corresponding translation word has been specified, the translator determines the corresponding translation word for the important words in the invention document by referring to it. . Then, the translator proofreads, modifies, etc. the invention document as necessary to facilitate the translation of the invention document. Then, the translator translates the invention document after proofreading, alterations, etc., and creates a translation result document as a result. When translating, the translator may, for example, cause a machine translation system or the like to perform machine translation, and utilize the translation result of the machine translation to create a translation result document. Finally, the translator reviews the translation result document as the translation result, and corrects the translation result document as necessary.

[1-3. Consideration of Factors Hampering Efficiency or Appropriateness of Translation for Acquisition of Useful Rights]
FIG. 3 is a diagram listing an example of factors that hinder the efficiency or appropriateness of translation for obtaining useful rights.

If the invention document is inappropriate, it may be difficult, for example, for a translator who is not a technical expert to understand the invention document or to decide how to modify and translate the invention document. Become. As a result, it takes time to investigate the invention document for understanding, or to communicate with the creator of the invention document for confirmation, and the translator may not be able to translate efficiently. In addition, there is a possibility that a translator may not be able to perform a proper translation due to an incorrect understanding of an inappropriate invention document.

Inappropriate invention documents for obtaining useful rights include, as shown in Fig. 3, for example, those containing clerical errors, inconsistent descriptions, ambiguous expressions, relative expressions, etc., and phrases without corresponding appropriate translated phrases. content, content whose exact meaning is unclear, content that does not formally conform to foreign laws and judicial precedents, content that may pose problems in enforcing patent rights, etc. An example of a relative expression is the description of “heavy first member”. For example, if a relative expression is included, the translator may be confused as to how to translate the relative expression in order to obtain useful rights. Examples of sentences where the exact meaning is not obvious include sentences that lack a subject and that make it difficult for anyone but a technical expert to determine what the subject is. Examples of statements that do not formally conform to foreign laws, regulations, and judicial precedents include: Claim recitations directed to what is not (eg, programs in the United States) are included. It should be noted that descriptions that may pose problems in exercising patent rights are not necessarily problematic, but they may be problematic. Examples of statements that may be subject to patent enforcement issues include "preferably is", "features of the present invention" using the word "invention" to have the meaning of the claimed subject matter in the United States. is ~.” and the like. Translators may hesitate to modify such statements to obtain useful rights.

Special translation instructions that are inappropriate for obtaining useful rights include special translation instructions that are unclear in specific work content. An example of a special translation instruction in which the specific content of the work is unclear is an instruction to resolve multiple dependent claims in which the content after modification cannot necessarily be determined in a single way. A special translation instruction with unclear specific work content can hinder efficient translation.

In addition, when the translator utilizes the translation results of machine translation by a machine translation system etc., if the translation accuracy of the machine translation is not sufficient, the translator may need a lot of time to review the translation results of the machine translation. .

[1-4. Example of use of embodiment of invention document analysis system]
An embodiment of the invention document analysis system according to the present disclosure can output, for example, information pointing out, evaluating, etc. deficiencies in the invention document. Further, in one embodiment of the invention document analysis system, for example, information that supports determination of corresponding translation words for key words in the invention document can be output. Also, in one embodiment of the invention document analysis system, for example, information useful for improving the accuracy of machine translation of invention documents can be output.

Therefore, for example, an inventor or patent attorney who created an invention document uses an embodiment of the invention document analysis system in the present disclosure, and utilizes the output based on the analysis of the invention document according to the embodiment. Therefore, it may be possible to obtain an opportunity to review the inappropriate invention document and correct it appropriately.

For example, an inventor, etc. or a patent attorney who created an invention document uses an embodiment of the invention document analysis system in the present disclosure, and information on the output result based on the analysis of the invention document (for example, output When providing the translator with the result itself, or information that makes it possible for the translator to know the similar output result, the translator can perform the translation work (see Figure 2) efficiently or properly. there is a possibility. This is because the information on the output result based on the provided analysis result of the invention document enables the translator to easily resolve any hesitation that may occur when translating for the purpose of obtaining useful rights.

For example, a translator who receives an invention document from an inventor or a patent attorney uses an embodiment of the invention document analysis system in the present disclosure, and utilizes the output based on the analysis of the invention document according to the embodiment By doing so, there is a possibility that the translation work (see FIG. 2) for the invention document can be performed efficiently or appropriately. In addition, when using a machine translation system, etc., the translator can improve the accuracy of machine translation by utilizing the information output by one embodiment of the invention document analysis system in the present disclosure, thereby improving the translation work (Fig. 2) can be performed efficiently or appropriately.

[2-1. Configuration Example of Invention Document Analysis System According to Embodiment 1]
FIG. 4 shows an example of the configuration of the invention document analysis system 10. As shown in FIG.

The invention document analysis system 10 is a system that executes invention document analysis processing for analyzing invention documents.

The invention document analysis system 10 is a system for analyzing invention documents and outputting information such as patent application-related information based on the analysis results. be done. Here, as an example, the invention document analysis system 10 is assumed to be realized by a computer equipped with an operating system (OS) including a file system and other programs (for example, application programs, etc.). . Here, the size and aspect of the computer provided with the microprocessor do not matter, and may be, for example, a supercomputer, a general-purpose computer, a minicomputer, a PC (Personal Computer), a tablet, a smart phone, or the like. Also, the microprocessor may be, for example, a quantum processor, and the computer including the microprocessor may be, for example, a quantum computer. A computer, for example, may have an input device and a display device. The computer input device may be a pointing device such as a mouse, keyboard, touch pad, voice input device, or the like. The computer display device may be, for example, a liquid crystal display, an organic EL (OEL: Organic Electro-Luminescence) display, or the like. The input device and the display device of the computer may be integrated. For example, the computer may include a touch panel in which a touch pad is superimposed on the display surface of the display device.

Users of the invention document analysis system 10 include, for example, a creator of the invention document (for example, an inventor or a patent attorney), or a translator who uses the invention document (for example, a person who translates the invention document into a foreign language based on the invention document). A translator who prepares a translation result document for a foreign application, or a user of the invention document other than the translator) is assumed. The user of the invention document analysis system 10 may be a person who does not correspond to any of inventors, patent attorneys, translators, and the like.

As shown in FIG. 4, the invention document analysis system 10 includes a setting information acquisition unit 101, a document acquisition unit 102, an important phrase setting dictionary acquisition unit 103, an invention document standard definition acquisition unit 104 for translation, an analysis unit 105, and a document evaluation unit. 106 , a machine learning unit 107 and an output unit 108 . The functions of the setting information acquisition unit 101, the document acquisition unit 102, the keyword setting dictionary acquisition unit 103, the invention document standard definition acquisition unit 104 for translation, the analysis unit 105, the document evaluation unit 106, the machine learning unit 107, and the output unit 108 are , for example, by one or more computers executing a program.

[2-1-1. Setting information acquisition part]
The setting information acquisition unit 101 acquires setting information used as a basis for the invention document analysis system 10 to analyze the invention document. The setting information includes information to be referred to when analyzing the invention document. Analysis of the invention document includes extraction of key terms from the invention document. FIG. 5 shows an example of the content of setting information.

The setting information is information that the invention document analysis system 10 refers to. The setting information may exist inside or outside the invention document analysis system 10, for example. The configuration information may be any form of information. The setting information, for example, whether it exists as the contents of a file (such as a text file) or as the contents of a database, is one or more user-defined environment variables managed by the OS of the computer. It may exist as content or may exist as data constituting a part of the invention document analysis system 10 (for example, data described in a program for realizing the invention document analysis system 10). When the setting information exists as data constituting part of the invention document analysis system 10, the invention document analysis system 10 uses a graphical user interface (GUI) or the like to process all or all of the setting information. A part of the contents may be displayed so that the user can change the part of the setting information.

For example, if the setting information exists outside the invention document analysis system 10 (for example, it exists as the content of an external file), the setting information acquisition unit 101 reads the setting information into the invention document analysis system 10. , the acquisition of setting information may be realized by converting into a data format that is easy to use within the invention document analysis system 10 . In addition, the setting information acquisition unit 101 reads external setting information (for example, setting information as the contents of a file), and uses the read contents as data constituting a part of the invention document analysis system 10 in advance. Setting information may be obtained by overwriting all or part of the setting information for which is defined.

The setting information includes condition information indicating conditions for extracting key words from invention documents to be analyzed by the invention document analysis system 10 . A character string that satisfies the extraction conditions indicated by the condition information is an important phrase. It is assumed that the condition information is defined and operated so that this important phrase is a phrase that is presumed to be important to some extent, but the accuracy of the estimation that it is important is 100%. No need. Important words and phrases are, for example, keywords and key phrases. A character string is composed of one or more characters that can be represented by character codes, such as kanji, kana characters, alphabetic characters, numbers, symbols, and others. One character code representing a character is determined according to an encoding format such as UTF-8, Shift_JIS, or Unicode.

The condition information includes, for example, important phrase candidate character string pattern information, reference character string pattern information, code character string pattern information, specific particle character string pattern information, and the like. Important phrase candidate character string pattern information, reference character string pattern information, code character string pattern information, and specific particle character string pattern information are, for example, information in which character string patterns indicating sets of character strings to be extracted are represented by regular expressions. is. Note that the condition information may include information related to extraction conditions indicating other character string patterns, information related to extraction exception conditions indicating extraction exceptions, and the like, for extracting important phrases.

The key phrase candidate character string pattern information indicates key phrase candidate character string patterns representing patterns of character strings that are candidates for key phrases. The key phrase candidate character string pattern information includes, for example, a predetermined character string whose first character is Kanji (for example, a character string such as "control device" or "control system"), and another predetermined character string whose first character is Katakana. A character string (for example, a character string such as "sensor" or "sensing method") is defined so as to correspond to the key phrase candidate character string pattern. Note that the key phrase candidate character string pattern information does not necessarily have to be defined so that all character strings whose leading characters are kanji or katakana correspond to the key phrase candidate character string pattern. For example, "receive", which is part of the character string of the verb "to receive" described in the invention document, may not be included in the predetermined character string whose first character is Chinese characters. Since certain conditions can be attached to a character string to be a predetermined character string, for example, a character string that is part of the beginning of a verb is not included in the predetermined character string even if the first character is Kanji or Katakana. Alternatively, a character string immediately followed by "su" may not be included in the predetermined character string even if the first character is kanji or katakana.

The reference character string pattern information indicates a reference character string pattern representing a reference character string pattern used for referencing the previously described character string. The reference character string pattern information is defined so that, for example, character strings such as "above", "above", "this", "above", "that", etc. correspond to the reference character string pattern.

The coded character string pattern information indicates a coded character string pattern representing the pattern of the character string of the code appended after the character string representing the element name. Each reference numeral is added to a part of the drawing in the drawing for the patent application. In addition, in the specifications for patent applications, etc., the same reference numerals as the reference numerals added to the part in the figure are used after the element name indicating the part in the figure in order to refer to the part in the figure. , can be described. A code may also be referred to as a reference code.

Code character string pattern information is, for example, a predetermined character string whose first character is a number (for example, a character string such as “100”, “101a”, “122-1”, “123′”, etc.) It is determined to correspond to the pattern. Note that the coded character string pattern information does not necessarily have to be defined so that all character strings whose first character is a number correspond to the coded character string pattern. Also, the code string pattern information may be defined such that, for example, a string whose first character is not a number (for example, an alphabetic character) further corresponds to the code string pattern.

The specific particle character string pattern information indicates a specific particle character string pattern representing a pattern of character strings that are predetermined particles. The specific particle character string pattern information includes, among particles, any character of, for example, "wo", "ni", "ga", "to", "from", "he" and "wa" It is defined to correspond to a string pattern.

The setting information, for example, further includes information for specifying important phrase setting dictionaries.

The information for specifying the important phrase setting dictionary is information necessary for the important phrase setting dictionary acquisition unit 103 of the invention document analysis system 10 to acquire the important phrase setting dictionary. It is information necessary for accessing the file, such as information on the file path (File Path) indicating the location of the file. It should be noted that, for example, the identification information of the key phrase setting dictionary may be the key phrase setting dictionary itself.

The setting information may include, for example, information for specifying the storage location of the output file. An example of information for specifying the storage destination of the output file is information specifying a predetermined folder (that is, a predetermined directory) in the file system.

[2-1-2. Document Acquisition Unit]
The document acquisition unit 102 acquires invention documents. The document acquisition unit 102 can sequentially acquire each of a plurality of invention documents, but it may be capable of acquiring a plurality of invention documents at the same time, for example. The invention document acquired by the document acquisition unit 102 can be used by the analysis unit 105 and the machine learning unit 107 .

For example, when the invention document exists as a file stored in a recording medium or the like, the document acquisition unit 102 has a function of acquiring the invention document (that is, the document data of the invention document) by reading the file. have. Note that the document acquisition unit 102, for example, extracts the invention document from database data, data stored in the memory of a computer that constitutes the invention document analysis system 10 (for example, an application program when the clipboard is available in the OS). data that has been copied, etc. and stored in a memory area used as a clipboard), the data can be read out from a database, memory, etc. to reproduce the invention document. may have a function to obtain

For example, the document acquisition unit 102 can acquire, in addition to a plurality of invention documents, a plurality of translation result documents that are translation results of each of the plurality of invention documents. The translation result document is used by the machine learning unit 107, for example.

For example, in addition to the invention document, the document acquisition unit 102 may acquire the drawing document corresponding to the invention document. A drawing document corresponding to an invention document is a document representing a drawing referred to in the specification or the like of the invention document. In general, the same reference numerals as those attached to a portion in a drawing for a patent application follow a word or phrase representing an element corresponding to that portion in the specification for a patent application. Drawing documents exist as files such as PDF (Portable Document Format) files, for example. If the drawing document exists as a searchable PDF file that is a PDF file with text information added (that is, a PDF file in which character strings are made searchable), the symbols in each drawing represented in the drawing document, etc. is easily searchable. Also, even if the drawing document exists as a PDF file that is not a searchable PDF file, conventional optical character recognition (OCR) technology or character recognition technology using machine learning is used. Thus, for example, it is possible to search for symbols and other character strings in each drawing represented in the drawing document, and for example, it is also possible to convert the PDF file into a searchable PDF file using existing technology.

[2-1-3. Important phrase setting dictionary acquisition unit]
The important phrase setting dictionary acquisition unit 103 acquires the important phrase setting dictionary based on the information for specifying the important phrase setting dictionary in the setting information acquired by the setting information acquiring unit 101 . The important phrase setting dictionary is information listing a plurality of important phrases to be extracted (that is, information including a plurality of important phrases). The information is configured so that the corresponding translated word obtained by translating the key word into a predetermined language other than Japanese (for example, English) may be associated with the key word. In the important phrase setting dictionary, for example, some important phrases are associated with corresponding translated words.

The important phrase setting dictionary may exist, for example, as a file, as the content of a database, or as data within the invention document analysis system 10 .

The important phrase setting dictionary can be used for extracting important phrases by the important phrase extraction unit 1051 in the analysis unit 105 .

[2-1-4. Acquisition Department for Standard Provisions of Invention Documents for Translation]
An invention document standard specification for translation acquisition unit 104 acquires an invention document standard specification for translation that defines a plurality of conditions to be satisfied by an invention document to be translated.

For example, the Standard Provisions of Invention Documents for Translation are information that defines the conditions that an invention document to be translated should satisfy. Contains bad string pattern information that indicates the string pattern. In addition, the information that defines the conditions to be satisfied by the invention document to be translated is, for example, inappropriate character string pattern information representing the character string pattern of potentially inappropriate description parts that do not satisfy the conditions. Corresponding to all or part of it, it contains correction information on how to correct the part of the description that may be inappropriate.

The invention document standard specification for translation is used by the analysis unit 105 and the machine learning unit 107, for example. In addition, the correction information as an example of the content of the invention document standard specification for translation is used to generate the corrected claim information and the corrected specification information that can be included in the patent application related information that can be output by the output unit 108. obtain.

[2-1-5. Analysis Department]
The analysis unit 105 analyzes the invention document acquired by the document acquisition unit 102 based on the setting information acquired by the setting information acquisition unit 101 . The analysis unit 105 includes an important phrase extraction unit 1051 , a translation word candidate set identification unit 1052 , a classification unit 1053 and a translation unit 1054 . For example, the analysis unit 105 determines whether or not the invention document acquired by the document acquisition unit 102 satisfies at least some of a plurality of conditions defined in the invention document standard specification for translation. , based on the determination result, generates warning information for pointing out potentially inappropriate parts in the invention document. Among the plurality of conditions defined in the standard specification of invention documents for translation, the conditions to be determined by the analysis unit 105 as to whether or not the invention document satisfies the conditions are, for example, information for selection defined in the setting information. etc., or by the user's selection operation of the invention document analysis system 10 (that is, narrowed down).

This warning information can be included in the patent application related information that can be output by the output unit 108 . It should be noted that the analysis unit 105 determines whether or not the invention document satisfies the conditions defined in the standard specification of invention documents for translation, for example, if inappropriate character string pattern information that can be included in the standard specification of invention documents for translation is used. This is done depending on whether or not a character string corresponding to the indicated inappropriate character string pattern exists in the invention document. The warning information generated as a result of the analysis by the analysis unit 105 of the invention document may also include, for example, invention document evaluation information indicating the compatibility of the invention document with the invention document standards for translation. The invention document evaluation information indicates, for example, an evaluation value as a result of evaluating the conformity of the invention document to the invention document standard specification for translation. For example, the evaluation value as a result of the evaluation of the conformity of the invention document to the standard provisions for invention documents for translation is the number of conditions selected as judgment targets from among the multiple conditions specified in the standard provisions for invention documents for translation. It may be a conformance rate, which is the ratio of the number of conditions determined to be satisfied by the invention document. In addition, for example, the level of the precision rate is divided into multiple stages, and the value representing the section to which the judgment result conformity rate corresponds (for example, the serial number determined for each section in order from the lowest ) may be used as the evaluation value.

[2-1-5-1. Key phrase extraction part]
The key phrase extraction unit 1051 extracts key phrases from the invention document acquired by the document acquisition unit 102 based on the condition information included in the setting information. By appropriately defining the condition information, the key phrase extraction unit 1051 can, for example, extract It becomes possible to extract a plurality of key terms from the claims or the specification.

The key phrases extracted by the key phrase extraction unit 1051 are used, for example, to generate information such as patent application related information output by the invention document analysis system 10 . Here, using an example in which an invention document includes a claim and a specification, the key phrase extraction unit 1051 for extracting key phrases from the invention document will be described in detail. The important word/phrase extraction unit 1051 performs extraction according to the first extraction condition, the second extraction condition, the third extraction condition, and the fourth extraction condition for the extraction of important words/phrases. 10512 , a third extractor 10513 and a fourth extractor 10514 .

The first extraction unit 10511 extracts the condition information following the character string corresponding to the reference character string pattern indicated by the reference character string pattern information in the condition information in the claim and specification of the invention document acquired by the document acquisition unit 102 . If there is a character string corresponding to the key phrase candidate character string pattern indicated by the key phrase candidate character string pattern information in , the same character string as the key phrase candidate character string pattern is extracted as an important phrase. have a function.

The second extraction unit 10512 extracts a period character following the character string corresponding to the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information in the claim of the invention document acquired by the document acquisition unit 102. exists, the same character string as the character string corresponding to the key phrase candidate character string pattern is extracted as the key phrase. A punctuation character is, for example, ".".

The third extraction unit 10513 extracts from the invention document acquired by the document acquisition unit 102, following the character string corresponding to the key phrase candidate character string pattern indicated by the key phrase candidate character string pattern information in the condition information, If there is a character string corresponding to the coded character string pattern indicated by the coded character string pattern information, it has a function of extracting the same character string as the character string corresponding to the key phrase candidate character string pattern as an important phrase.

The fourth extraction unit 10514 extracts an important phrase candidate character string, which is a character string corresponding to the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information, from the invention document acquired by the document acquisition unit 102. Subsequently, if there is a specific particle character string that is a character string that corresponds to the specific particle character string pattern indicated by the specific particle character string pattern information in the condition information, the character string that corresponds to the important phrase candidate character string pattern is determined. It has a function to extract the same character string as an important phrase.

Note that the key phrase extraction unit 1051 may extract key phrases from the invention document, for example, based on information related to extraction conditions included in the condition information. In addition, for example, the important phrase extraction unit 1051 uses the first extraction unit 10511, the second extraction unit 10512, the third extraction unit 10513 or the fourth extraction unit 10514 to Some of the key phrases extracted from the invention document may be treated as non-key phrases. Also, the important phrase extraction unit 1051 may be modified so as not to include any one of the first extraction unit 10511, the second extraction unit 10512, the third extraction unit 10513, and the fourth extraction unit 10514. .

Also, the important phrase extraction unit 1051 extracts, for example, the same important phrases as the important phrases included in the important phrase setting dictionary acquired by the important phrase setting dictionary acquisition unit 103 in the invention document acquired by the document acquisition unit 102. If it is included, the same key phrase as that included in the key phrase setting dictionary may be extracted from the invention document.
In addition, the important phrase extraction unit 1051 may use one or a small number of relatively complex important phrase candidate character string patterns for extracting important phrases, or use relatively simple important phrase candidate character string patterns. A plurality of them may be used. For example, in order to extract an important phrase, the important phrase extraction unit 1051 extracts, when a plurality of character strings correspond to an important phrase candidate character string pattern, one of the plurality of character strings When the character string is included in the description of the invention document, the remaining character string excluding one character string from among the plurality of character strings may be selected and extracted as an important phrase. That is, the important phrase extraction unit 1051 extracts important phrases according to the first extraction condition, the second extraction condition, the third extraction condition, and the fourth extraction condition. In the case where one of the multiple character strings is included in the description of the claim or specification of the invention document, that one character string out of the multiple character strings A selection extraction condition for selecting and extracting important phrases from the excluded remaining character strings can be used.

[2-1-5-2. Translation word candidate set identification unit]
The translation word candidate set identifying unit 1052 identifies each of the key words extracted by the key word extraction unit 1051 from the invention document acquired by the document acquisition unit 102, and identifies a translation word that is a set of corresponding translation word candidates for the key words. Identify a candidate set. The translation word candidate information representing the translation word candidate set specified by the translation word candidate set specifying unit 1052 for each key word is included in the patent application related information output by the invention document analysis system 10, for example.

The translation word candidate set includes one or more elements (that is, corresponding translation word candidates). A corresponding translated word is a word/phrase resulting from translating an important word/phrase into a foreign language. Here, as an example, it is assumed that the corresponding translated words are English words and phrases, but the corresponding translated words may be words and phrases of languages other than English (for example, Chinese). For example, when the important phrase is "amount of change", examples of elements of the translation word candidate set include "variation" and "amount of change".

As a specific example, the translation word candidate set identification unit 1052 uses bilingual dictionary information (for example, conventionally known Japanese-English dictionary data) in which Japanese words and phrases are associated with foreign language words, and extracts important words and phrases. By searching the bilingual dictionary information using the key phrase extracted by 1051 as a key, one or more bilingual phrases corresponding to the key phrase are detected, and a set of the detected phrases is defined as the key phrase. is identified as a set of translation word candidates. As a specific example of the bilingual dictionary information, for example, the Japanese-English dictionary "dict2" created by the Japanese dictionary project founded by Mr. James William Breen of Australia, or the Japanese-English dictionary is processed, edited, etc. data obtained from The translation word candidate set identification unit 1052 can hold bilingual dictionary information, for example.

The invention document analysis system 10 can output the patent application related information including each key phrase and the translation word candidate information representing the corresponding translation word candidate set through the output unit 108 . For each key phrase in the invention document, the invention document analysis system 10 selects an element selected by the user of the invention document analysis system 10 from among the set of translation word candidates specified corresponding to the key phrase. It is also possible to output translation assistance information, which is information in which the translated word and the relevant important phrase are associated with each other. In this case, as a result of selection by one or more users, one The translation assistance information described above can be accumulated in a recording medium or the like inside or outside the invention document analysis system 10 . The recording medium or the like may be any medium capable of recording data, such as a memory, hard disk, or optical disk. One or more pieces of translation assistance information stored in a recording medium or the like may be integrated to generate translation assistance information in a format in which each key phrase is associated with a set of corresponding translated words. The translation assistance information can be output in the form of file contents, database contents, or the like, and may be output in the form of being displayed. In the case where already generated translation aid information can be used, the translation word candidate set identification unit 1052 uses the already generated translation aid information as another specific example, and uses the already generated translation aid information to extract the key phrase extraction unit 1051. By searching the already generated translation auxiliary information with key phrases as keys, phrases selected by any user in the past as one or more corresponding translated words corresponding to the key phrases are detected. A set of words and phrases that have been extracted may be specified as a set of translation word candidates for the important words and phrases.

As another specific example, the translation word candidate set identification unit 1052 identifies the group to which the invention document acquired by the document acquisition unit 102 belongs by the classification unit 1053 or the technical field identification unit 10531, or the group corresponding to the invention document. When the technical field to be used is specified, the bilingual dictionary information corresponding to the group or technical field is selected from a plurality of bilingual dictionary information, and the important phrase extracted by the important phrase extraction unit 1051 is used as a key. By searching the selected bilingual dictionary information, one or more bilingual words corresponding to the key words are detected, and a set of the detected words is specified as a translation word candidate set for the key words. You can do it. One specific example of this is, for each of a plurality of groups or technical fields, a group-by-group or technical-field-by-group correspondence in which Japanese words and phrases in invention documents belonging to that group or technical field are associated with words and phrases in the language to be translated. It can be used when multiple bilingual dictionary information exists. In each bilingual dictionary information, for example, the order in which it is estimated that the words corresponding to the important words in the invention document in the group or technical field corresponding to the bilingual dictionary information are highly likely to be selected (that is, the corresponding translated words one or more bilingual words/phrases corresponding to the important words/phrases are ordered in descending order of relevance as the It is also possible to determine the arrangement order of each element of the translation word candidate set when information relating to the translation word candidate set is output from the invention document analysis system 10 .

As another specific example, when the classification unit 1053 identifies a group to which one invention document obtained by the document obtaining unit 102 belongs, the translation word candidate set identification unit 1052 identifies another group belonging to the group. A plurality of sets of key phrases extracted by the key phrase extraction unit 1051 and corresponding translated words corresponding to the key phrases are specified from each of the plurality of invention documents and each of the corresponding translation result documents, and the plurality of sets as teacher data for machine learning for key phrase translation, the one acquired by the document acquisition unit 102 by machine translation using a learning model for key phrase translation, which is a learning model generated by machine learning Identify the elements of the translation word candidate set for each of the key words extracted by the key word extracting unit 1051 from the invention document (for example, one or more words obtained as the machine translation result as elements of the translation word candidate set specified).

[2-1-5-3. Classification Department]
The classification unit 1053 classifies each of the plurality of invention documents acquired by the document acquisition unit 102 into groups of key phrases extracted by the key phrase extraction unit 1051, using key phrase groups that are multiple key phrases extracted by the key phrase extraction unit 1051. Based on the inter-correlation, group classification is performed to specify which of the plurality of groups each of the plurality of invention documents belongs to. In order to evaluate the correlation between the important phrase groups, the classification unit 1053 uses an algorithm for counting the number of identical important phrases common to both important phrase groups and a synonym dictionary to identify the same or similar in both important phrase groups. Algorithm for counting the number of important phrases to be used, with each of predetermined character strings of a certain sufficient number (for example, thousands, tens of thousands, etc.) for each important phrase group as elements, for example, the character strings of the elements are important Defining vector data with an element value of 1 when it exists as a phrase and 0 when it does not exist as an important phrase, and using any algorithm such as various algorithms for calculating the correlation coefficient between the vector data good too. Further, the classification unit 1053 may have a function of specifying a group to which each invention document belongs based on designation by the user of the invention document analysis system 10, for example. The group classification unit, method, etc. are used by each user who mutually communicates the operation unit of the invention document analysis system 10 (for example, invention documents, bilingual dictionary information, or information output by the invention document analysis system 10). It can be useful to be unified in each invention document analysis system 10).

Classification section 1053 includes technical field identification section 10531 .

For each of a plurality of technical fields, the technical field identification unit 10531 extracts key phrases from one or more invention documents known to be related to the technical field that have been acquired by the document acquisition unit 102 in the past and are extracted by the key phrase extraction unit 1051 . By using the result of extracting groups in the past, important phrases extracted by the important phrase extraction unit 1051 from invention documents for which technical fields are not specified and which are acquired by the document acquisition unit 102 among a plurality of technical fields. Any technical field evaluated to have a correlation with the group of words or phrases equal to or greater than a predetermined degree is specified as a technical field corresponding to the invention document whose technical field is not specified. The technical field is an example of a group. The technical field is represented by, for example, the International Patent Classification (IPC). The technical field specifying unit 10531 may use classification up to any level of the IPC as the technical field, and for example, use only sections, or only sections and classes, etc., and treat them as one technical field. Further, the technical field specifying unit 10531 may express the technical field using all of IPC sections, classes, subclasses, main groups and subgroups. For example, if the technical field is to be distinguished only by the IPC section, the technical field identification unit 10531 uses patent gazettes and the like to acquire a plurality of invention documents belonging to each section of the IPC, and The key phrase group corresponding to the section, which is extracted by the key phrase extraction unit 1051 by causing the invention document analysis system 10 to acquire each invention document, can be obtained. For example, by using the group of important words and phrases for each section obtained in the past, the technical field specifying unit 10531 can extract the important words from the invention document, which is acquired by the document acquiring unit 102 and whose section as the technical field is not specified. A section that is evaluated to have a correlation with the group of important words and phrases extracted by the word and phrase extraction unit 1051 that is equal to or greater than a predetermined degree can be specified as the technical field of the invention document.

The technical field information, which is information indicating the technical field (for example, IPC) identified by the technical field identifying unit 10531 corresponding to the invention document obtained by the document obtaining unit 102, is, for example, the patent application output by the invention document analysis system 10. Included in Related Information.

The group identified by the classification unit 1053 to which the invention document belongs, or the technical field identified corresponding to the invention document by the technical field identification unit 10531, for example, the translation word candidate set identification unit 1052 identifies the invention document can be used to select bilingual dictionary information for specifying a translation word candidate set corresponding to each key phrase extracted from the . Also, the group classification by the classification unit 1053 can be used by the machine learning unit 107 to generate a translation learning model for each group.

[2-1-5-4. Translation Department]
The translation unit 1054 receives the invention document acquired by the document acquisition unit 102 as an input and executes machine translation of the invention document by a calculation process predetermined for translation using a learning model for translation. The learning model for translation is a model for machine translation that is generated by machine learning using multiple pairs of invention documents and translation result documents as the result of translation by translators etc. based on the invention documents as training data. Learning model.

Here, as an example, the learning model for translation is explained as a learning model used for machine-translating invention documents, which are mainly written in Japanese, into English documents. It may be a learning model used for machine translation into Chinese or other language documents instead of English. As an example of a method for generating a translation learning model for translating Japanese into English, an international publication of an international application written in Japanese and the international application using English of the United States, United Kingdom, etc. A combination of the invention document and the translation result document that contains the content equivalent to the translation result document translated into English for the transition to the national phase of the designated country and published by the government office of the designated country A method of performing supervised machine learning by treating a set as training data is exemplified.

In addition, when invention documents can be classified into multiple groups, it is better to generate a learning model for translation for each group, which is the accuracy of machine translation when an appropriate learning model for translation is selectively used. There is a good possibility that an improvement in the adequacy of translation can be expected. As an example of group classification, there is a group of invention documents related to electrical technology, a group of invention documents related to mechanical technology, and a group of invention documents related to chemical technology. Another example of group classification is to classify the technical field to which the invention document belongs, in the case of classifying by IPC, IPC sections, or different sections and classes are classified into different groups. In addition, as another example of group classification, the department to which the inventor who created the invention shown in one invention document belongs is grouped by the department to which the inventor pertaining to the invention document belongs so as to distinguish it from other departments. Examples of classifying are given.

When there is a learning model for translation for each of a plurality of groups or technical fields, the translation unit 1054 causes the classification unit 1053 to specify, for example, the group or technical field to which the invention document acquired by the document acquisition unit 102 belongs. By selectively using a learning model for translation corresponding to the group or technical field to which the invention document belongs, all or part of the invention document may be machine-translated.

The result of the machine translation of the invention document by the translation unit 1054 can be included in the patent application related information output by the invention document analysis system 10, for example.

[2-1-6. Document Evaluation Department]
The document evaluation unit 106 determines whether each of the plurality of invention documents acquired by the document acquisition unit 102 satisfies at least some of the conditions defined in the invention document standard specifications for translation. Then, one or more invention documents are selected from among the plurality of invention documents for which the degree of satisfaction of the determined condition exceeds a predetermined degree. Among a plurality of conditions defined in the standard specification of invention documents for translation, the conditions to be determined by the document evaluation unit 106 as to whether or not the invention document satisfies the conditions are, for example, the conditions for selection defined in the setting information. It can be selected based on information or the like, or by a user's selection operation of the invention document analysis system 10 .

Invention documents selected by the document evaluation unit 106 can be used by the machine learning unit 107, for example.

[2-1-7. Machine Learning Department]
The machine learning unit 107 generates a learning model for machine translation of the invention document by machine learning.

For example, for each invention document selected by the document evaluation unit 106, the machine learning unit 107 obtains a set of the invention document and the translation result document acquired by the document acquisition unit 102 corresponding to the invention document. A learning model for translation is generated by executing machine learning using a plurality of sets of teacher data as teacher data.

As another example, for each of the plurality of groups, the machine learning unit 107 classifies each invention document, among the plurality of invention documents acquired by the document acquisition unit 102, into the group by the classification unit 1053, Translation, which is a learning model for machine translation, is performed by machine learning using each pair of the invention document and the translation result document obtained by the document obtaining unit 102 as the training data. Generate a learning model for As a result, it is possible to generate a learning model for translation corresponding to each group for each of a plurality of groups related to invention documents. In this example as well, invention documents used as training data may be limited to invention documents selected by the document evaluation unit 106, for example.

As another example, the machine learning unit 107 may extract inappropriate characters from the invention document acquired by the document acquisition unit 102 indicated by inappropriate character string pattern information related to the conditions defined by the standard rules for invention documents for translation. If there is a character string that corresponds to the string pattern, the invention for translation is determined based on the contents of the invention document and the correction information associated with the inappropriate character string pattern information in the standard provisions for invention documents for translation. A modified version of the invention document generated by modifying the content of the invention document so as to satisfy the conditions stipulated in the document standard provisions (that is, a document having content equivalent to the modified invention document), and the invention A learning model for translation is generated by machine learning using a combination of a document and a translation result document acquired by the document acquisition unit 102 corresponding to the document as teacher data. For example, when a character string in an invention document corresponds to an inappropriate character string pattern indicated by inappropriate character string pattern information associated with correction information in the invention document standard specifications for translation, the modified version of the invention document It can be generated by deleting or replacing a string with another string according to its modification information. The amended version of the invention document includes, for example, amended version claim information representing the content of a character string in the claim of the invention document that has been amended based on correction information corresponding to the corresponding inappropriate character string pattern, and the characters of the specification of the invention document. The column includes at least one of corrected version specification information representing contents corrected based on the correction information corresponding to the corresponding inappropriate character string pattern.

The learning model for translation generated by the machine learning unit 107 can be used in the translation unit 1054, for example. The translation learning model generated by the machine learning unit 107 can be used, for example, in a machine translation system or a machine translation program for translating invention documents, or in a general machine translation system.

[2-1-8. Output part]
The output unit 108 outputs information generated based on the analysis result of the analysis unit 105 for the invention document acquired by the document acquisition unit 102 .

The output unit 108 outputs, for example, information generated based on each of the multiple key phrases extracted by the key phrase extraction unit 1051 from the invention document acquired by the document acquisition unit 102 .

As a specific example, the output unit 108 outputs patent application related information generated based on the analysis result of the analysis unit 105 for the invention document acquired by the document acquisition unit 102 . FIG. 6 shows an example of the content of the patent application related information output by the output unit 108. As shown in FIG.

The patent application related information output by the output unit 108 may include warning information generated by the analysis unit 105 .

The output unit 108 outputs, for example, the patent application-related information, each of which is a plurality of important phrases extracted by the important phrase extraction unit 1051 from the invention document acquired by the document acquisition unit 102, as content to be displayed. It has a function to output as a display document. The patent application related information as a display document includes, for example, an important phrase list listing a plurality of important phrases.

Here, the display document is, for example, a document described in a markup language or the like that can be displayed by an application program such as a browser (Web Browser). The display document is, for example, an HTML document written in HTML (Hypertext Markup Language). An HTML document includes at least an HTML file, and the HTML file is written according to HTML5, for example. The content to be displayed, such as key phrases, in the display document should be described as the content of the <body> tag of the HTML file (i.e., described between the <body> tag and the </body> tag). is displayed by a browser or the like. For example, characters to be displayed in the contents of the <body> tag or in the contents of the tags in the hierarchy below it may be set to be displayed in a monospaced font, for example. Multiple characters can be displayed aligned using a monospaced font. Also, characters to be displayed in the contents of the <body> tag or in the contents of the tags in the hierarchy below it may be set to be displayed in a proportional font instead of a monospaced font. For example, the HTML file may include a description for reading an external file as required, or instead, the content corresponding to the external file may be directly described in the HTML file. The external file is, for example, a CSS file in which the display mode of display elements is described in CSS (Cascading Style Sheets), a script file in which a script is described in a script language such as JavaScript (registered trademark), or the like. Therefore, an HTML document, which is an example of a display document, can be composed of files such as one or more HTML files, one or more CSS files, and one or more script files. The HTML file includes information specifying CSS files and script files, for example. The HTML document may consist of an HTML file only, may consist of an HTML file and a CSS file, or may consist of an HTML file and a script file. Incidentally, according to CSS, for example, it is possible to control the display mode of characters in the patent application-related information.

The patent application-related information is, for example, for each of a plurality of important phrases extracted by the important phrase extraction unit 1051 from the invention document acquired by the document acquisition unit 102, to each of the important phrases, additional information related to the important phrase is added. including information about Note that the additional information in the patent application-related information does not necessarily have to be added to each of the important phrases extracted from the invention document by the important phrase extraction unit 1051. It may be added only to each of a plurality of key phrases.

The additional information related to the key phrase in the patent application related information may be, for example, translation word information as information related to the corresponding translation word, which is the translation word expressing the meaning of the key phrase. Here, a translated phrase is a phrase including words expressed in one language other than Japanese (for example, English, Chinese, etc.). For example, an example of a translated word when the important word is "object" is "object". The translated word information as information about the corresponding translated word is, for example, information representing the corresponding translated word itself (for example, machine translation results of important words and phrases), a set of translated word candidates which is a set of candidates for the corresponding translated word, and the like. When the translation word information is translation word candidate information representing a translation word candidate set for key words, the translation word candidate information further includes information related to the translation word candidate set (for example, translation word candidate Each element of the candidate set may include a value indicating the degree of validity as a corresponding translated word, information indicating a rank, etc.).

Further, the additional information related to the key phrase in the patent application related information is, for example, any element of the translation word candidate set identified by the translation word candidate set identification unit 1052 for the key phrase, according to the operation. It includes display control information for displaying the translation word candidate set as a graphical user interface (GUI) element so as to be selectable. Here, the operation can be performed by the computer user, for example, on the input device of the computer when the patent application-related information is displayed on the display device of the computer, for example, by a browser. Examples of GUI elements are buttons (for example, push buttons, radio buttons, etc.), menus, etc. that can be operated in a displayed state, but display elements such as character strings can also be GUI elements. In an HTML document, which is an example of a document for display, a script (for example, a function written in etc.) can be added as the content of an HTML tag (for example, <span> tag) and other elements can be operation-responsive GUI elements that are operable GUI elements.

As a specific example, the display control information included in the additional information related to key words includes translation word candidate information representing a set of translation word candidates and translation word candidates for the key words displayed as GUI elements. A script for executing a determination process for determining an element selected from the set according to the operation as a corresponding translated word corresponding to the key phrase, and each corresponding translated word determined as a result of the execution of the determination process and a script for executing a process of generating and outputting translation assistance information, which is information in which important words and phrases are associated with corresponding translated words. By executing the script in response to the operation, some processing (such as determination processing for determining the corresponding translated word corresponding to the important phrase) is performed, and for example, the patent application related information displayed on the display device of the computer is displayed. Such display contents may change according to the result of the processing. In the determination process for determining an element selected from the candidate translation word set as the corresponding translation word, for example, the displayed translation word candidate set may be replaced with the corresponding translation word and displayed.

In addition, all or part of the display contents displayed by the browser in the patent application related information as the display document can be selected by the user's operation and can be copied and pasted or cut and pasted. By pasting (that is, pasting), for example, it can be included as the contents of a document or the like (for example, a text file or the like) used by an application program running on a computer. In addition, when the content displayed by the browser changes as a result of the execution of the processing executed in response to the user operation on the GUI element related to the patent application related information, all or part of the display content after the change may also be changed by the user. Depending on the operation, it can be selected and can be the target of copy and paste.

In addition, the important phrase extraction unit 1051 acquires the same important phrase as the important phrase associated with the corresponding translation word in the important phrase setting dictionary acquired by the important phrase setting dictionary acquisition unit 103, which is obtained by the document acquisition unit 102. As an example, the additional information related to the key phrase extracted from the invention document represents the corresponding translated word. Also, when the important phrase extraction unit 1051 extracts important phrases other than the important phrases associated with the corresponding translated words in the important phrase setting dictionary from the invention document acquired by the document acquisition unit 102, the extracted important phrases As an example, the additional information related to is displayed as a GUI element so that any element of the set of candidate translation words for the important phrase can be selected according to the operation. Contains display control information for The display control information in this case is, for example, selected according to the operation from the candidate translation information representing the set of candidate translation words for the key words and the set of candidate translation words for the key words displayed as GUI elements. A script for executing determination processing for determining an element as a corresponding translated word corresponding to the key phrase, and for each key phrase for which a corresponding translated word is determined as a result of the determination processing, the key phrase and the corresponding correspondence and a script for executing update processing for updating the important phrase setting dictionary acquired by the important phrase setting dictionary acquisition unit 103 so as to include information associated with the translated word.

The additional information related to the key phrase in the patent application related information may be, for example, the importance of the key phrase, the attribute information of the key phrase, and the like. Further, the additional information related to the key phrase may be display control information for executing some processing related to the key phrase in accordance with the operation of the GUI element. The display control information in this case describes, for example, information indicating the content displayed as a GUI element, information indicating an operation (for example, mouse click operation) on the GUI element, and processing to be activated corresponding to the operation. It is associated with a script.

Examples of the output of information such as patent application-related information in the output unit 108 include writing the information to a recording medium, writing the information as a file, displaying the information, and printing the information. , transmission of the information, output of sound representing the information, and other physical phenomena representing the information.

The output unit 108 may have, for example, all or part of a function corresponding to a browser, and may output the patent application related information by displaying the patent application related information. The output unit 108 may generate a display document (for example, an HTML document) containing patent application related information, and then display the patent application related information according to the display document.

If a claim is included in the invention document acquired by the document acquisition unit 102, the output unit 108 may include, for example, claim information representing the content of the claim in the patent application related information. In patent application-related information as a display document, claim information is one of the contents to be displayed.

The claim information representing the content of the claim of the invention document in the document for display is display control included in the additional information related to each of the key words in the claim extracted by the key word extracting unit 1051. The information includes information for controlling the display mode of the key phrase, such as information indicating the color added to the key phrase. For example, the display control information for a certain key phrase in the patent application-related information as an HTML document is, for example, a <span> tag that describes the key phrase as content in the HTML file (that is, the <span> tag), as an example of identification information determined to distinguish the important phrase from other important phrases, and the contents of the <span> tag of the class name in the CSS file and information defining a display color as a display mode. In this case, the CSS file may include, for example, information indicating colors as display modes of the contents of <span> tags for each of a plurality of pieces of identification information (for example, a plurality of class names). The information indicating the color to be added to the important phrase is, for example, the character color, the character background color, etc. for the character string of the important phrase. This is color information that expresses the line color of one side when the line width is given, for example, using RGB values. For example, the output unit 108 adds different colors (that is, display colors) to each of a plurality of key phrases having mutually different character strings constituting the key phrase extracted by the key phrase extraction unit 1051 in the complaint information. and display it. For example, for a plurality of key phrases having different character strings constituting key phrases, class names are defined so as to be different from each other, and the display color as a display mode of the content of the <span> tag for each class name is set. This can be achieved by defining the color information to be displayed so that different colors are displayed for each class. In addition, the output unit 108 outputs, for example, any one of the above-described key phrases in which the character strings constituting the key phrase extracted by the key phrase extraction unit 1051 in the complaint information are different from each other. Key phrases in the complaint information, which are composed of the same character string, may be displayed in the same color (that is, the same display color) as the aforementioned one key phrase. Adding the same display color to such important words can be realized by using classes with the same class name related to the display color. In addition, if the number of key phrases that differ from each other exceeds a predetermined number (for example, 500, etc.), a fixed order will be determined based on the importance of the key phrases or attribute information (eg, first appearance number). Up to a certain number, different key phrases may be expressed in colors of different RGB values, and important phrases exceeding the fixed number may be expressed in the same color using one predetermined RGB value.

When the specification is included in the invention document acquired by the document acquisition unit 102, the output unit 108, for example, includes the specification information representing the content of the specification in the patent application related information. good. In patent application-related information as a display document, specification information is one of the contents to be displayed.

The description information representing the content of the specification of the invention document in the display document is included in the additional information related to each of the key words in the specification extracted by the key word extracting unit 1051. The display control information included in the key phrase includes information for controlling the display mode of the key phrase, for example, information indicating the color to be added to the key phrase.

For example, for each of the multiple key phrases extracted by the key phrase extraction unit 1051 in the specification information, the output unit 108 determines which of the multiple key phrases extracted by the key phrase extraction unit 1051 in the claim information. If it is the same as, the key phrase in the description information is displayed in the same display mode as the same key phrase in the claim information (for example, displayed with the same color added), and the key phrase in the description information However, if it differs from any of the multiple key phrases extracted by the key phrase extraction unit 1051 in the claim information, the key phrase in the specification information is displayed in a manner different from any of the multiple key phrases in the claim information. may be displayed. As described above, the output unit 108 can use a browser or the like to display whether or not the key words in the specification information are the same key words in the complaint information so as to be identifiable. , a display document in which the display control information for each key phrase in the specification information is appropriately determined may be configured and output. The display control information for one important phrase in the specification information in the display document is, for example, if the one important phrase is the same as any of the important phrases extracted by the important phrase extraction unit 1051 in the claim information, The one important phrase in the specification information is displayed in the same display mode as the same important phrase in the claim information, and the one important phrase in the specification information is extracted by the important phrase extraction unit 1051 in the claim information. If it differs from any of the important phrases, it includes information for controlling to display the one important phrase in the specification information in a display mode different from any of the extracted important phrases in the claim information.

Based on the analysis result of the invention document by the analysis unit 105, when the output unit 108 includes the claim information and the specification information in the patent application related information generated as the document for display, the important phrase extraction unit 1051 extracts from the invention document Of the multiple extracted key words in the claim information or specification information, the key words that are the same as the key words that represent the element names that are added with a code in the invention document are related to the key words. The display control information as additional information is, for example, the key words in the drawing document (for example, searchable PDF file) acquired by the document acquisition unit 102 corresponding to the invention document according to the operation. Operation-responsive GUI element for displaying the part where the code is described (for example, the page, position, etc. where the code is described, specified by searching for the code in the drawing document) (that is, the operation-based It contains information to display as a display element with GUI function to

The output unit 108 in the example of displaying the patent application related information displays the display mode of the multiple key phrases extracted by the key phrase extraction unit 1051 in the claim information and the specification information in the patent application related information as the multiple key phrases. A display document containing display control information and the like including highlighting information for displaying in a manner different from the display mode of words other than the word may be generated, and display may be performed according to the display document. As an example of realizing this display by a browser or the like that displays based on an HTML document as an example of a document for display, the output unit 108 may output a plurality of important As display control information for controlling the display mode of words other than words, a character color, a character background color, etc., as default values for character strings, are determined. Then, in the display control information for controlling the display mode of each of the plurality of important phrases, a <span> tag having the content of the important phrase of the class name determined so as to be able to identify each of the plurality of important phrases as described above Highlight display information such as color information that sets the character color, character background color, etc. as the display mode of the contents of the above to values other than the default values is included.

The output unit 108 in the example of displaying the patent application related information converts each of the multiple key terms extracted by the key term extraction unit 1051 in the claim information in the patent application related information into the key terms according to the operation. It may be displayed as a GUI element for executing information addition display related to words. As an example for realizing this display by a browser or the like that displays based on the display document, the output unit 108 controls the display of each key phrase in the patent application-related information as the display document. Information, for example, information for displaying information added to the key phrase, and information for displaying the key phrase as a GUI element for executing the information added display related to the key phrase in response to an operation. include.

The information-added display related to the important phrase is a process of adding additional information related to the important phrase to the important phrase and displaying it. (For example, a corresponding translation word, a translation word candidate set), etc., or to display search results related to the important phrase. The importance and attribute information of key words and the search results of key words may be specified by any method, and may be the same as those shown in Embodiment 2 described later, for example.

An example of the claim information to be displayed when the output unit 108 outputs, as a display document, patent application related information including claim information representing the content of the claims of the invention document acquired by the document acquisition unit 102 is In addition to the content, for each of a plurality of key phrases extracted by the key phrase extraction unit 1051 in the content of the claim, the portion of the key phrase in the content of the claim is converted into a corresponding translated word or translated word corresponding to the key phrase. The candidate set may contain the replaced content. In this case, the claim information is, for example, for each part (for example, one line of description, etc.) that represents the claim of the invention document, following that part, the important words in the description that copied that part, Alternatively, it may be a mode in which the replaced word is inserted into the translation word candidate set.

Also, the specification information to be displayed when the output unit 108 outputs the patent application-related information including the specification information representing the content of the specification of the invention document acquired by the document acquisition unit 102 as a document for display. For example, in addition to the content of the specification, for each of a plurality of key phrases extracted by the key phrase extraction unit 1051 in the content of the specification, the key phrase part in the content of the specification is added to the key phrase. The corresponding translation word or translation word candidate set may include the replaced content. In this case, the description information is, for example, for each part that represents the description of the invention document (for example, one line of description, etc.), following that part, key phrases in the description that is a copy of that part A mode in which a replacement word or a translation word candidate set is inserted may also be used.

Inappropriateness indicated by inappropriate character string pattern information pertaining to each of several conditions out of a plurality of conditions defined in the invention document standard specification for translation acquired by the standard specification of invention document for translation acquisition unit 104 If a character string corresponding to the character string pattern exists in a claim in the invention document acquired by the document acquisition unit 102, the patent application related information output by the output unit 108 includes, for example, the claim and the translation Based on the correction information associated with the inappropriate character string pattern information in the standard specification of the invention document, it may include the corrected version claim information generated by correcting the claim so as to satisfy the conditions. Some of the conditions defined in the invention document standard specification for translation are, for example, based on information for selection defined in the setting information, or selected by the user of the invention document analysis system 10. can be selected by In addition, for each of several conditions among the plurality of conditions defined in the invention document standard specification for translation acquired by the standard specification of invention document for translation acquisition unit 104, inappropriate character string pattern information related to the condition is indicated. If a character string corresponding to the inappropriate character string pattern exists in the specification of the invention document acquired by the document acquisition unit 102, the patent application-related information output by the output unit 108 is, for example, the specification and the correction information associated with the inappropriate character string pattern information in the standard specifications for invention documents for translation, and amended specification information generated by correcting the specification to satisfy the conditions. can include

When a claim is included in the invention document acquired by the document acquisition unit 102, a predetermined claim (for example, one claim) of the claim refers to a plurality of claims (for example, a plurality of claims). patent application-related information generated based on the analysis result of the invention document by the analysis unit 105, which is output by the output unit 108, for example, one of the predetermined items, the item number of which is Amended claim information representing the result of amending the claim so as to include content changed to quote only the first paragraph, and the citation relationship between each clause of the claim represented by the amended claim information, It can include a modified claim tree as information represented by an expression in which the section numbers of mutually citation relationships are associated with each other using lines or symbols.

The patent application-related information, which is output by the output unit 108 and generated based on the analysis result of the invention document by the analysis unit 105, is, for example, between each of the key phrases extracted from the invention document by the key phrase extraction unit 1051. It may also include key phrase relationship information indicating the relationship between. This important phrase relationship information includes, for example, inclusion relationship information indicating structural inclusion relationships between elements represented by each of a plurality of important phrases. For example, if an invention document describes an "information processing device" that includes an "input section" and a "display section," "information processing device," "input section," and "display section" are extracted as key phrases. Inclusion indicates the relationship that the element "information processing device" represented by the key phrase includes the "input unit" and "display unit" as the element group represented by the key phrase in terms of structure. The output unit 108 can output patent application related information including related information.

Further, the patent application related information output by the output unit 108 may include the result of machine translation of the invention document by the translation unit 1054, for example.

The output unit 108 includes a learning model output unit 1081 as an example.

A display document (e.g., HTML document) containing display control information for displaying each of a plurality of key words output by the output unit 108 as a GUI element that can be selected from a translation word candidate set can be displayed in a browser or the like. determination processing for determining an element selected according to an operation from a translation word candidate set for a key phrase as a corresponding translation word corresponding to the key phrase by a script included in the display control information when it is displayed; , and a process of generating and outputting translation assistance information for each key phrase for which a corresponding translation word has been determined as a result of the determination process.

As described above, the learning model output unit 1081 outputs each of the plurality of translation assistance information generated as a result of displaying each of the display documents output for each of the plurality of invention documents acquired by the document acquisition unit 102. , using pairs of key phrases and corresponding translated words as training data for machine learning for key phrase translation, and outputting a learning model for key phrase translation, which is a learning model generated by machine learning. do. This machine learning is realized by arithmetic processing using, for example, a general machine learning algorithm and using pairs of important words and phrases having a certain correlation and corresponding translation words as teacher data. Examples of general machine learning algorithms include a neural network consisting of an input layer, an output layer, and a hidden layer, with weights representing the degree of information transmission between layers, and deep learning (Deep Learning) that includes many hidden layers. Learning) and the like. In deep learning, learning is performed by adjusting the weight of each layer of the neural network in order to bring the pair of input and output of the neural network closer to the teacher data (that is, to reduce the error). As a method for adjusting this weight, for example, the error back propagation method or the like can be used.

Also, the learning model output unit 1081 may have a function of outputting the learning model for translation generated by the machine learning unit 107, for example. The output format of the learning model (key phrase translation learning model or translation learning model) by the learning model output unit 1081 is any format that can be referred to, for example, by the translation unit 1054 or other processing systems for machine translation. There may be. As an example, the learning model output unit 1081 outputs the learning model as content such as a file in a recording medium inside or outside the invention document analysis system 10, data in a database, or the like.

[2-2. Invention document analysis processing example according to the first embodiment]
An example of invention document analysis processing executed by the invention document analysis system 10 having the above configuration will be described.

FIG. 7 is a flowchart showing an example of invention document analysis processing.

The invention document analysis process includes, for example, a setting information acquisition step S1, a document acquisition step S2, an analysis step S3, and an output step S4.

In the setting information acquisition step S1, the invention document analysis system 10 acquires setting information (see FIG. 5) including condition information indicating conditions for extracting key words.

The invention document analysis system 10 acquires the invention document in the document acquisition step S2.

In the analysis step S3, the invention document analysis system 10 analyzes the invention document acquired in the document acquisition step S2 based on the setting information acquired in the setting information acquisition step S1. The analysis step S3 is a process including an important phrase extraction step S31.

In the important phrase extraction step S31, the invention document analysis system 10 extracts important phrases from the invention document acquired in the document acquisition step S2 based on the condition information of the setting information acquired in the setting information acquisition step S1.

In the output step S4, the invention document analysis system 10 outputs information generated based on the analysis result in the analysis step S3 of the invention document acquired in the document acquisition step S2. In the output step S4, the invention document analysis system 10 outputs information generated based on each of the multiple key phrases extracted in the key phrase extraction step S31 from the invention document acquired in the document acquisition step S2. An example of the information output in the output step S4 by the invention document analysis system 10 is the patent application related information (see FIG. 6). The invention document analysis system 10 acquires the invention document and the corresponding translation result document in the document acquisition step S2, and performs machine learning using pairs of the invention document and the translation result document satisfying certain conditions as training data in the output step S4. A learning model for translation or a learning model for important phrase translation that is generated as a result may be output.

In the important phrase extraction step S31, for example, important phrase candidate character string pattern information indicating an important phrase candidate character string pattern, reference character string pattern information indicating a reference character string pattern, and code indicating a code character string pattern in the condition information are extracted. By referring to the character string pattern information and the specific particle character string pattern information indicating the specific particle character string pattern, the first character string corresponding to the reference character string pattern is included in the invention document acquired in the document acquisition step S2. If there is a second character string corresponding to the key word candidate character string pattern following , the same character string as the second character string is extracted as a key word, and the claim is included in the invention document In that case, if there is a period character following the third character string corresponding to the keyword candidate character string pattern in the claim, the same character string as the third character string is extracted as the important phrase, and the invention If there is a fifth character string corresponding to the code character string pattern following the fourth character string corresponding to the key word candidate character string pattern in the document, the same character string as the fourth character string is regarded as important. If the invention document contains the sixth character string corresponding to the key word candidate character string pattern followed by the seventh character string corresponding to the specific particle character string pattern, the sixth character Extract the same string as the column as important phrases.

The example of FIG. 7 is merely an example, and the invention document analysis system 10 may execute the invention document analysis process by omitting or changing some of the steps shown in FIG. may be executed by adding some processing steps to the plurality of steps shown in FIG. 7, the execution order of the plurality of steps shown in FIG. may be performed in parallel.

[2-3. Example of hardware configuration or network configuration of invention document analysis system]
As described above, the invention document analysis system 10 is realized by, for example, a computer equipped with a memory, a microprocessor, an input device and a display device. The invention document analysis system 10 may be realized by a device such as a single computer, or may be realized by a plurality of devices such as computers. Also, each of the plurality of invention document analysis systems 10 can be used by one or more users.

8 to 10 show an example of the hardware configuration or network configuration of the invention document analysis system 10. FIG.

In the example of FIG. 8, the invention document analysis system 10 is composed of one terminal device 10a. The terminal device 10a is, for example, a computer having a browser function for realizing display based on a display document. As a specific example, the terminal device 10a is a computer equipped with a touch panel or the like, which executes an OS, and can execute an application program for realizing a browser function under the control of the OS. A computer has a configuration in which, for example, a microprocessor (for example, CPU), memory (for example, ROM, RAM), communication interface, connection interface for input/output devices, etc. are connected by a bus. A computer may include, for example, input/output devices. An OS, an application program, etc., including a group of instructions are stored, for example, in a memory, and the instructions of the group of instructions are read from the memory, interpreted, and executed by a microprocessor. The terminal device 10a may be, for example, a desktop PC, a notebook PC (Laptop PC), a smartphone, or the like. The invention document analysis processing program, which is a program for executing the invention document analysis processing (see FIG. 7), may be, for example, one or a plurality of application programs executed by the terminal device 10a. It may be a program (for example, a plug-in module or the like incorporated into the browser) that constitutes a part of the browser that is executed in the . The invention document analysis processing program executed by the terminal device 10a may be written in any language. All or part of the invention document analysis processing program may be, for example, an executable program written in C language, C++ language, etc. and compiled, or may be written in Python (registered trademark) language, etc. It may be a program executed by, for example. In addition, all or part of the invention document analysis processing program is a macro (for example, VisualBasic (registered trademark)) that can be executed incidentally when executing an application program having a document creation and editing function such as Microsoft (registered trademark) Word. It may be a program written in

When the invention document analysis processing program is implemented as an application program executed on the terminal device 10a, the application program has a function of generating and displaying information (for example, patent application related information) based on the analysis result, for example. may have

When the invention document analysis processing program is implemented as an application program executed on the terminal device 10a, the application program generates, for example, patent application-related information as a document for display (for example, an HTML document) and displays it. The document for display may be displayed by a browser (for example, an application program having a browser function for interpreting and displaying the document for display). The browser may access the document for display as, for example, a group of so-called local files to display patent application related information. An application program as an invention document analysis processing program, for example, executes a function as a web server and further activates a browser, thereby allowing the activated browser to access the generated display document as a resource on a so-called local host. You can also display

The display document as an output form of the patent application related information output by the invention document analysis system 10 is, for example, an HTML document. In the present disclosure, an example in which an HTML document is mainly used as a display document as an output mode of patent application-related information is described. For each display element such as words, it may be a document that can control the display mode (display color, etc.) of the display element by adding some display control information. Specifically, for example, Microsoft (registered trademark) It may be a document in a format (so-called DOC file) normally handled by an application program having a document creation and editing function such as Word, etc. As display control information related to display elements such as important phrases, display of operation-responsive GUI elements, etc. A DOC file or the like accompanied by a macro for control may be used.

Further, the invention document analysis processing program executed by the terminal device 10a may output the patent application-related information and the like as contents of a file of any format (for example, a text file).

In the example of FIG. 9, the invention document analysis system 10 includes, for example, one server device 10b and a plurality of terminal devices 10c to 10e connected to the server device 10b via a LAN (Local Area Network). . The terminal devices 10c to 10e are the same as the terminal device 10a, and different users (for example, the same company, the same company, the same office, the same business department, the same department, etc.) are located in the same local environment. users). In addition, in the example of FIG. 9, it is also possible to operate the LAN as a WAN (Wide Area Network). The server device 10b has, for example, a file server function, and includes, for example, a recording medium (for example, memory, hard disk, etc.) for recording files.

For example, the server device 10b holds, in a recording medium, a file containing setting information to be accessed and acquired by each of the terminal devices 10c to 10e. As an example, the server device 10b holds, in a recording medium, a file containing, as content, invention document standard specifications for translation for each of the terminal devices 10c to 10e to access and obtain. As an example, the server device 10b collects and integrates the translation assistance information generated by each of the terminal devices 10c to 10e, and holds a file containing the translation assistance information resulting from the integration. It may have a function of distributing the translation assistance information of the file to each terminal device connected by LAN.

For example, the server device 10b holds a file containing one piece of bilingual dictionary information or each file containing bilingual dictionary information for each of a plurality of groups (for example, technical fields), and is connected via a LAN. It can have a function of distributing required bilingual dictionary information to any one of the terminal devices 10c to 10e.

As an example, the server device 10b, in each of the terminal devices 10c to 10e, outputs an invention document and information output based on the result of invention document analysis processing based on the invention document (for example, a patent application including invention document evaluation information). Related information) and the translation result document created by the user using that information are associated, collected, and stored (that is, stored). In the case where the server device 10b has this function, each of the terminal devices 10c to 10e uses a combination of some invention documents held by the server device 10b and translation result documents corresponding to the invention documents as teacher data. It is possible to generate a learning model by machine learning, and utilize the learning model for machine translation of an invention document to be analyzed in the invention document analysis process, for example.

In the example of FIG. 10, the invention document analysis system 10 is composed of a plurality of computers distributed in various places. The invention document analysis system 10 in the example of FIG. 10 includes, for example, one server device 10f and a plurality of terminal devices 10g and 10h connected to the server device 10f via a LAN or a WAN such as the Internet. The number of terminal devices may be one. The server device 10f may be able to communicate with the server device 10i via LAN or WAN. For example, data to be communicated is encrypted by an existing cryptographic technique, and the data is communicated between devices connected by a WAN. The server device 10i can, for example, perform part of the invention document analysis process.

The terminal devices 10g and 10h are similar to the terminal device 10a, and are assumed to be used by different users. The server device 10f has, for example, a web server function, and includes, for example, a recording medium (for example, memory, hard disk, etc.) capable of storing display document files. The server device 10f has, for example, a CGI (Common Gateway Interface) function implemented by a program written in Perl or the like for part of the invention document analysis processing.

Either of the terminal devices 10g and 10h transmits the invention document to the server device 10f by using, for example, a browser. Upon receiving the invention document, the server device 10f executes invention document analysis processing by requesting the server device 10f to perform some processing as necessary, and as a result, information based on the analysis result of the invention document ( For example, a document for display (for example, HTML document) is generated for patent application related information). The server device 10f outputs information based on the analysis result of the invention document by transmitting the display document to the terminal device that sent the invention document on which the invention document was generated. Either of the terminal devices 10g and 10h that has received the display document implements display control and the like of information based on the display document using the browser. This realizes the output of information based on the analysis result of the invention document in the browser. For example, when patent application-related information is displayed as a display document by a browser, key words in the claim information and key words in the specification information are displayed in a display mode (e.g., character color, character background color, etc.). Also, the browser can display warning information including indications, evaluations, etc. for the invention document. When the warning information is displayed, the user can check whether the invention document has any problems. As a result of information display control by the browser, when operation-responsive GUI elements are displayed on the display device of the terminal device, etc. Processing may be performed and, for example, the display may change. If necessary, the user can freely edit the content displayed by the browser by importing it into an application program (for example, a text editor) having a document creation and editing function by copying and pasting.

For example, the server device 10f authenticates the access source terminal device (that is, the client terminal) to the user, the user group, the terminal, or the terminal group using the associated identification information (ID), password, etc., and registers it in advance. , it is possible to upload invention documents only to a predetermined managed client terminal, and it is possible to display a list of patent application related information etc. as an analysis result of invention documents uploaded in the past. It may have a function to manage so as to enable browsing (that is, downloading), deletion, etc. of patent application related information. In addition, the server device 10f allows a plurality of client terminals authenticated as being in the same group based on the designation of the ID of the same user group or terminal group to view the patent application related information as the analysis result of the same invention document. It is also possible to Further, a predetermined client terminal authenticated by an ID, a password, etc., and the server device 10f may appropriately divide and execute each processing step constituting the invention document analysis processing.

The server device 10f may have, for example, a function as a search site (so-called search engine) that performs searches in response to requests from client terminals. In this case, the server device 10f may execute the invention document analysis process with the invention document acquired as a result of the patent document search performed as the analysis target.

The server device 10f or the server device 10i, for example, based on patent publications published on the Internet by the government offices and international organizations of each country, the invention document shown in the publication and the translation result document corresponding to the invention document. may have a function of collecting a plurality of sets of

[2-4. Effects of Invention Document Analysis System According to Embodiment 1]
The invention document analysis system 10 extracts key phrases from the invention document created by the inventors or patent attorneys by the key phrase extraction unit 1051 based on the setting information, and based on each of the extracted key phrases, the Since the information is output by the output unit 108, there is a possibility that a translator or the like will be able to facilitate understanding of the invention document by referring to the output information. Promoting the understanding of the invention document is useful for translators to translate the invention document appropriately or efficiently.

For example, when there is an expression that refers to a word in an invention document, the key word extraction unit 1051 treats the referenced word as a key word under certain conditions, and extracts the word or phrase written immediately before the full stop character in the claim of the invention document. Because of the treatment of key phrases under certain conditions, phrases that are noted and phrases that describe the claimed subject matter of a claim can be treated as key phrases. The important phrase extraction unit 1051 treats, for example, phrases (for example, noun phrases) that precede particles in an invention document written in Japanese as important phrases under certain conditions, and treats them as important phrases under certain conditions. Since words are treated as key words under certain conditions, relatively important words such as subjects and objects and words representing elements presumed to be illustrated in drawings related to invention documents can be treated as key words. . As a result, information is output by the output unit 108 based on key phrases that are estimated to be important in the invention document by the invention document analysis system 10, so the output information can be useful.

For example, the output unit 108 extracts each of the key phrases extracted from the invention document by the key phrase extraction unit 1051, and related additional information (for example, the importance of the key phrase, attribute information, translation word candidate set). etc.), so that by obtaining the patent application related information, the translator, etc. can grasp multiple important words of the invention document, and the translator can use it to translate the invention document Based on the additional information, it may be possible to efficiently or properly determine the translated phrase corresponding to the key phrase, which is the target language and has the same meaning as the key phrase. Since the patent application-related information output by the output unit 108 includes translation word information (for example, information representing the corresponding translation word itself, a set of translation word candidates, etc.) as information related to the corresponding translation word corresponding to the key word, By referring to the translated word information, the translator may be able to efficiently or properly determine the translated word/phrase corresponding to the important word/phrase. When the output unit 108 outputs the patent application-related information including a translation word candidate set corresponding to the key words, each element of the translation word candidate set has a value indicating the degree of validity of the corresponding translation word. When annotated, the translator may be able to efficiently or properly determine the translation word corresponding to the key word from the translation word candidate set.

In the invention document analysis system 10, for example, the classification unit 1053 performs group classification based on the key phrase group extracted from the invention document by the key phrase extraction unit 1051, and from bilingual dictionary information by group (for example, technical field) , selectively using the bilingual dictionary information of the group to which the invention document belongs, to specify a translation word candidate set for the key words of the invention document. As a result, a group of bilingual dictionary information suitable for the invention document is used, so that a suitable translation word candidate set can be specified for the key phrase.

The output unit 108 outputs the patent application-related information as a display document such as an HTML document, for example. This GUI element, which includes control information, can execute a process of determining one element of the translation word candidate set selected by the operation as the corresponding translation word, and outputting the important phrase and the corresponding translation word as translation assistance information. . As a result, the translator can easily determine the corresponding translation word corresponding to the important word from the translation word candidate set by selecting the GUI element of the document for display. In addition, the translator can edit the corresponding translation word determined from the display content of the display document by the browser or the like using a text editor or the like by copying and pasting. In addition, the result of the selection by the translator may later improve the validity of identifying a translation word candidate set corresponding to the key words by the invention document analysis system 10 via the translation assistance information.

In the invention document analysis system 10, for example, the learning model output unit 1081 generates pairs of key words and corresponding translated words in the translation assistance information by machine learning using training data for machine learning for key word translation. output the important phrase translation learning model. As a result, the machine translation of the important phrases in the invention document can be realized by the arithmetic processing of inputting the important phrases using the learning model for the translation of the important phrases. By referring to the results of this machine translation, the translator may be able to efficiently or properly determine the translated words and phrases for the key words and phrases in the invention document.

The invention document analysis system 10, for example, extracts key phrases from invention documents according to the key phrase setting dictionary, and outputs patent application related information including key phrases and corresponding translations of the key phrases determined according to the key phrase setting dictionary. . As a result, the inventors, etc. or patent attorneys can create an important phrase setting dictionary when they want to set specific phrases as important phrases, or when they want to set corresponding translated words for important phrases. , the invention document analysis system 10 outputs appropriate patent application related information. Therefore, the translator may be able to translate the invention document efficiently or properly by referring to the patent application-related information.

The invention document analysis system 10 identifies, for example, a translation word candidate set corresponding to an important phrase in an invention document by extracting important words from a plurality of invention documents belonging to the same group as the invention document and the corresponding translation result documents. Machine translation is performed by arithmetic processing using a learning model for important phrase translation generated as a result of machine learning using pairs of phrases and corresponding translated words as training data for machine learning. As a result, the invention document analysis system 10 can appropriately identify a translation word candidate set.

The invention document analysis system 10 outputs, for example, as a display document such as an HTML document, patent application-related information including claim information representing the claims of the invention document, and controls the display mode of important terms in the claims in the claim information. Include display control information to As a result, it may be possible to identify key words whose display mode is controlled in complaint information displayed by a browser or the like. In the invention document analysis system 10, if, for example, highlighting (for example, displaying in bold) is performed as control of the display mode of key words, it is possible to quickly grasp the key words in the claim information. For example, the invention document analysis system 10 uses the display elements of key words and phrases in the claim information of the display document as operation-responsive GUI elements, and analyzes the importance, attribute information, corresponding translation words, or translation The complaint information may include display control information for displaying the word candidate set or the search result of the key phrase. As a result, translators, etc., who have viewed the claim information in the display document can obtain various types of information, such as the level of importance and attribute information, by manipulating the displayed key words and phrases. In addition, the translator may be able to efficiently or properly determine translation terms for key terms.

The invention document analysis system 10 outputs patent application related information including specification information representing the specification of the invention document as a display document such as an HTML document, for example. Display control information for controlling the display mode and including display control information for identifiably displaying whether or not the key phrase is stated in the claim, and display control for controlling the display mode of different key phrases to be different can contain information. As a result, translators, etc., who have browsed the display document displayed by a browser, etc., can identify whether or not each key phrase described in the specification information is the key phrase described in the claim. , it may be possible to quickly grasp whether a plurality of key words are the same or different, depending on the display mode of each key word. The invention document analysis system 10 can, for example, use colors as display modes for key phrases that are different from each other (for example, the character color of the key phrases, the character background color, the entire side of a rectangular frame having a line width surrounding the key phrases, or any one of The document for display may include display control information for displaying each important phrase with different colors, such as the color of the boundary line, which is one side, from each other. As a result, a translator or the like who browses a display document displayed by a browser or the like can quickly understand whether multiple key words are the same or different from the color added to each key word. obtain.

The invention document analysis system 10, for example, for each content of the claim information and specification information in the patent application related information output based on the analysis result of the invention document, translates important words in the content, or a translation word candidate set. contains the replaced contents. As an example, the invention document analysis system 10 can insert, immediately after each line of claim information and specification information, a line of content in which key words in the content of the line are replaced with corresponding translation words or translation word candidate sets. The translator may be able to efficiently translate the invention document by editing the content in which the key words are replaced with the corresponding translation words or translation word candidate set.

The invention document analysis system 10 detects, for example, the important words in the claim information or the specification information of the patent application-related information as a display document output based on the analysis result of the invention document. If the description of the element name appended with the code included in the drawing in the drawing document acquired by 102 is a phrase that expresses the element name contained in the invention document, the display element of the important phrase is displayed in the operation Accordingly, a document for display is generated so as to add display control information for giving a function as a GUI for displaying the part in which the code is described in the drawing document. As a result, a translator or the like who browses the document for display displayed by a browser or the like can display and check the part corresponding to the element represented by the key phrase in the drawing document by manipulating the key phrase. As a result, it becomes possible to understand the important words efficiently or properly.

The invention document analysis system 10, for example, based on the determination result of whether the invention document to be translated satisfies a part of the conditions related to the invention document standard specification for translation, which defines a plurality of conditions to be satisfied by the invention document output patent application related information including warning information pointing out potentially inappropriate parts in By referring to this patent application-related information, the inventor or patent attorney who prepared the invention document can correct the invention document if necessary. In addition, for example, by obtaining invention documents and patent application-related information to be translated from inventors, etc. or patent attorneys, the translator can Since it can be presumed that the inventor, etc. or the patent attorney determined that there is no particular need to deal with the indication, it is possible to obtain an appropriate invention document to be translated, and as a result, the translation of the invention document can be It may be possible to do so efficiently or properly. The invention document analysis system 10 can, for example, narrow down some of the conditions of the invention document standard specification for translation, which are used for judgment for pointing out in the warning information, according to the designation in the setting information etc. You may do so. As a result, the inventors, etc. or the patent attorney can cause the invention document analysis system 10 to output patent application-related information that does not include unnecessary indications in the warning information by setting the setting information. By providing relevant information to the translator, etc., it is possible to prevent the translator from being misled by the warning information.

For example, the invention document analysis system 10 adds invention document evaluation information indicating conformity of the invention document to the invention document standards for translation to the warning information in the patent application related information generated based on the analysis result of the invention document. can be included. Suitability is represented, for example, by an evaluation value as a result of suitability evaluation. By referring to this invention document evaluation information, the inventors or the patent attorney may be able to appropriately correct the invention document. Also, the translator can recognize whether or not the invention document is suitable for translation by checking the invention document evaluation information. An invention document containing inappropriate descriptions, for example, is likely to cause translation errors, and a situation may arise in which the translator corrects the invention document in order to obtain appropriate rights before translating it. Therefore, if the warning information in the patent application-related information generated based on the invention document includes invention document evaluation information indicating relatively low conformity with the standard provisions for invention documents for translation, It can be determined that there may be discrepancies in content between the invention document and the translation result document, which is the result of translation based on the invention document, in addition to the difference in language. Because of its generation, it may be possible to determine that it is not suitable for use as teacher data for machine learning.

The invention document analysis system 10, for example, based on the correction information in the invention document standard specification for translation, amended version claim information in which potentially inappropriate descriptions of the claims of the invention document are corrected, and the specification of the invention document Outputs patent application-related information including revised specification information in which descriptions that may be inappropriate in The inventor, etc. or the patent attorney who created the invention document may be able to efficiently revise the invention document by referring to this revised claim information and revised specification information. A translator can efficiently or properly translate the invention document by being provided with the invention document as amended by reference to the amended claim information and the amended specification information.

The invention document analysis system 10, for example, amended claim information that changes a clause citing multiple clauses in the claims of the invention document to a clause quoting only one clause with the first clause number among the plurality of clauses, and It outputs patent application related information including a modified claim tree representing the citation relationship of each item of the claims represented by the modified claim information. The invention document analysis system 10, for example, in the patent application related information as a document for display, a claim tree representing the citation relationship of each claim of the claim of the invention document, including an operation corresponding GUI element that can change the citation relationship. update the modified claim tree and modified claim information to match the changed citation relationships in response to manipulation of the claim tree displayed based on the display document in a browser, etc. obtain. In this case, the inventors or patent attorney can manipulate the claim tree to provide the translator with patent application-related information, including a modified claim tree and modified claim information that reflects the manipulation. Translators who have received patent application-related information from inventors, etc. or patent attorneys, and have been informed that the claims of the invention document should be translated based on the modified version of the claim information, cite multiple paragraphs in the invention document. It may be possible to translate efficiently without hesitation as to whether or not to correct a term, and if so, how to correct it. In addition, the translator or the like can quickly grasp the citation relationship of each item of the claims represented in the modified claim information from the modified claim tree.

The invention document analysis system 10 outputs, for example, patent application related information including key word relationship information indicating the relationship between each of the key words extracted by the key word extraction unit 1051 from the invention document. This important phrase relationship information includes, for example, inclusion relationship information indicating structural inclusion relationships between elements represented by each of a plurality of important phrases. As a result, translators who have acquired patent application-related information can relatively quickly grasp the relationships between multiple key words in an invention document. Or it may be possible to properly determine, as a result of which it may be possible to translate the invention document efficiently or properly.

For example, the invention document analysis system 10 performs group classification of invention documents by the classification unit 1053 based on the correlation between key phrase groups extracted from each of the plurality of invention documents by the key phrase extraction unit 1051, and the machine learning unit By 107, a learning model for translation is generated for each group by machine learning using a plurality of sets of invention documents and corresponding translation result documents as training data. As a result, for example, in a machine translation system or the like, it is possible to machine-translate an invention document by arithmetic processing using a translation learning model suitable for the group to which the invention document belongs among the translation learning models for each group. In addition, the invention document analysis system 10 machine-translates at least a part of the invention document by arithmetic processing using, for example, a translation learning model suitable for the group to which the invention document belongs among the translation learning models for each group. , the patent application related information including the machine translation result may be output. By referring to such machine translation results of the invention document, the translator may be able to translate the invention document efficiently or properly.

For example, the invention document analysis system 10 selects an invention document that satisfies the conditions related to the standard specification of invention documents for translation by the document evaluation unit 106 to a degree exceeding a predetermined degree, and the machine learning unit 107 selects the selected invention document. A learning model for translation for machine translation is generated by machine learning using multiple sets of invention documents and translation result documents corresponding to the invention documents as training data, and the learning model for translation is generated by a learning model output unit 1081. to output As a result, it is difficult to use a combination of an invention document containing inappropriate descriptions and a translation result document that is inconsistent with the invention document due to a translation error or the like generated based on the invention document as training data. An appropriate learning model for translation can be output from the invention document analysis system 10 . As a result, for example, in a machine translation system or the like, it becomes possible to machine-translate an invention document by arithmetic processing using an appropriate learning model for translation output from the invention document analysis system 10 . By referring to the result of machine translation of the invention document, the translator may be able to translate the invention document efficiently or properly.

For example, the invention document analysis system 10 uses the machine learning unit 107 to generate a modified version of the invention document in which inappropriate descriptions in the invention document are corrected based on the correction information included in the invention document standard specification for translation, and the invention document A translation learning model for machine translation is generated by machine learning using pairs with corresponding translation result documents as teacher data, and the learning model output unit 1081 outputs the translation learning model. Although there are language differences between the invention document and the translation result document generated by correcting inappropriate descriptions in the invention document at the translation stage, the discrepancies between the contents are reduced. Since there is a possibility, the learning model for translation output from this invention document analysis system 10 may be appropriate. As a result, for example, in a machine translation system or the like, it is possible to machine-translate an invention document by arithmetic processing using a potentially appropriate learning model for translation output from the invention document analysis system 10 . By referring to the result of machine translation of the invention document, the translator may be able to translate the invention document efficiently or properly.

The invention document analysis system 10 is configured, for example, by installing an invention document analysis processing program for executing invention document analysis processing as illustrated in FIG. 7 in a device having a microprocessor. When the invention document analysis processing program is started in the invention document analysis system 10, the invention document analysis processing is executed. In the invention document analysis process, for example, based on the setting information acquired in the setting information acquisition step S1, the invention document created by the inventor or the like or the patent attorney acquired in the document acquisition step S2 is analyzed in the analysis step S3. This is a process of analyzing and outputting the information generated as the analysis result in the output step S4. The analysis step S3 includes an important phrase extraction step S31 for extracting important phrases from the invention document. For a translator or the like, referring to the information output by the invention document analysis process may facilitate understanding of the invention document. Promoting the understanding of the invention document is useful for translators to translate the invention document appropriately or efficiently. The invention document analysis system 10 can output a display document for displaying patent application related information, for example, in the output step S4. In the invention document analysis processing performed by the invention document analysis system 10, a GUI screen is displayed that enables the selection operation of one or more display documents that have been output in the past in step S4, and the selected document is displayed. A process of subjecting the displayed document to interpretation and display by a browser in a microprocessor-equipped device may also be included.

(Embodiment 2)
Another example of an embodiment of the invention document analysis system will be described below with reference to the drawings.

The invention document analysis system shown in this embodiment is basically a system that executes invention document analysis processing for analyzing invention documents, like the invention document analysis system 10 shown in the first embodiment. The inventive document analysis system shown in the present embodiment corresponds to a part of the inventive document analysis system 10 shown in the first embodiment. This corresponds to a partially modified process. The invention document analysis system according to this embodiment can include all the constituent elements of the invention document analysis system 10 shown in the first embodiment as long as they do not contradict the items described in this embodiment. Regarding the invention document analysis system according to the present embodiment, the description of the same matters as those related to the invention document analysis system 10 shown in the first embodiment will be omitted as appropriate.

[3-1. Configuration example of an invention document analysis system according to the second embodiment]
FIG. 11 shows an example of the configuration of the invention document analysis system 20. As shown in FIG. FIG. 12 shows an example of main data handled by the invention document analysis system 20. As shown in FIG. The invention document analysis system 20 can acquire, for example, setting information, plug-in modules, invention document standard specifications for translation, key phrase setting dictionaries, bilingual dictionary information, translation assistance information, invention documents, drawing documents, translation result documents, and the like. . The invention document analysis system 20 includes, for example, setting information display documents, patent application related information, important phrase group information, teacher data used in machine learning for generating various learning models, learning models for translation, important phrase translation A learning model, a learning model for technical field identification, etc. can be output.

The invention document analysis system 20 is a system that acquires invention documents and executes invention document analysis processing for analyzing the invention documents.

The invention document analysis system 20 is a system for analyzing invention documents and outputting information such as patent application related information (see FIG. 12) based on the analysis results, and includes, for example, a microprocessor that executes a program. It is realized by a device or the like. The invention document analysis system 20 outputs the patent application related information as a document for display, for example, like the invention document analysis system 10 shown in the first embodiment. The invention document analysis system 20 may also output the patent application related information as files in various formats such as text files.

The invention document analysis system 20 may have, for example, the hardware configuration or network configuration shown in any one of FIGS. 8 to 10, like the invention document analysis system 10 shown in the first embodiment. The invention document analysis system 20 may be realized by a device such as a single computer, or may be realized by a plurality of devices such as computers. Also, each of the plurality of invention document analysis systems 20 can be used by one or more users. Here, the explanation will be continued assuming that the invention document analysis system 20 as an example is realized by a computer equipped with an OS including a file system and other programs.

A user of the invention document analysis system 20 is assumed to be, for example, a creator of the invention document (for example, a patent attorney, an inventor, etc.) or a translator who performs processing using the invention document. Here, translators, etc. are divided into translators who translate invention documents into foreign languages and prepare translation result documents for foreign applications, and translators who research, analyze, correct, evaluate, and state opinions about invention documents. and a person who performs various processes using the invention document.

As shown in FIG. 11, the invention document analysis system 20 includes a setting information acquisition unit 201, a document acquisition unit 202, an important phrase setting dictionary acquisition unit 203, an invention document standard definition acquisition unit 204 for translation, an analysis unit 205, and a machine learning unit. 207 and output 208 . Each function of the setting information acquisition unit 201, the document acquisition unit 202, the keyword setting dictionary acquisition unit 203, the invention document standard definition acquisition unit 204 for translation, the analysis unit 205, the machine learning unit 207, and the output unit 208, for example, It is implemented by one or more computers that execute all or part of the analysis processing program. The analysis unit 205 includes an important phrase extraction unit 2051 that executes an important phrase extraction process for extracting important phrases from the invention document, a warning information generation unit 2059 that can generate warning information based on the invention document, and the like.

[3-1-1. Setting information acquisition part]
The setting information acquisition unit 201 is obtained by partially modifying the setting information acquisition unit 101 shown in the first embodiment. The setting information acquisition unit 201 and the setting information acquisition unit 101 may be the same. The setting information acquisition unit 201 acquires setting information used as a basis for the invention document analysis system 20 to analyze the invention document.

The setting information may exist as any data such as database data, data as environment variables of the OS, and may exist as the contents of a file, for example. For example, the file is provided inside a device (e.g., a computer) as one component of the invention document analysis system 20, or provided in an external device that can communicate with the devices that constitute the invention document analysis system 20. , a memory, a hard disk, various optical disks, a magneto-optical disk, or the like, or a memory card, a USB (Universal Serial Bus) memory, or the like, which is detachable from any of these devices.

The setting information acquisition unit 201 may acquire setting information by, for example, reading a setting information file, which is a file containing setting information as content. The setting information acquisition unit 201 may read a plurality of setting information files and integrate the content of the plurality of files according to a predetermined priority order for discrepancies, thereby realizing acquisition of setting information. The setting information file may define general setting information regardless of the group such as the technical field. In one setting information file, a plurality of types of setting information may be defined for each group, such as for each technical field or each inventor's department. A configuration information file may exist. A specific example of the department to which the inventor belongs in the present disclosure is the division, department, etc. to which the inventor belongs within one company or one company, or the company, company, etc. to which the inventor belongs. .

The setting information acquisition unit 201 identifies the group to which the invention document acquired by the invention document analysis system 20 belongs based on general setting information, and from the setting information including the setting information corresponding to the identified group, Setting information corresponding to the specified group may be obtained. The setting information acquisition unit 201 also acquires setting information in a setting information file specified by the user among a plurality of setting information files for each group, or setting information specified by the user among a plurality of types of setting information in one setting information file. It is also possible to obtain the setting information.

FIG. 13 shows an example of the content of setting information.

The setting information may include, for example, the invention document standard specification for translation itself or information for specifying the invention document standard specification for translation. The identification information of the invention document standard specification for translation is, for example, information necessary for accessing the invention document standard specification for translation. The invention document standard specification for translation may exist as any data such as database data, data as environment variables of the OS, etc. For example, it may exist as the contents of a file. Specific examples of the specification information of the standard provisions for invention documents for translation include information such as file paths required to access files containing the standard provisions for invention documents for translation, or information for translation via a network. It is a URL (Uniform Resource Locator) or the like necessary for accessing data as an invention document standard definition.

The setting information includes condition information indicating conditions for extracting key words from invention documents to be analyzed by the invention document analysis system 20 . The condition information may be the contents shown in the first embodiment, or may be partially modified. The condition information includes, for example, important phrase candidate character string pattern information, reference character string pattern information, code character string pattern information, specific particle character string pattern information, and the like. Various character string patterns related to the condition information (for example, key phrase candidate character string patterns indicated by key phrase candidate character string pattern information) are expressed, for example, in a manner in which one or more corresponding character strings of one or more characters are listed. It may be a character string pattern, or it may be a character string pattern expressed in a manner that limits the character code range in which all or part of the corresponding character string is a character string within a certain range, It may be a character string pattern expressed in a manner involving a so-called wildcard specification in which a part of the applicable character string is a character string of the entire range.

The important word candidate character string pattern information is defined in advance, and includes endings specific to technical terms (for example, "apparatus", "substrate", "system", "means", "unit", "step", "medium"). , “medicine”, “file”, etc.) may be included. The key word candidate character string pattern information is a predetermined word or phrase presumed to be a technical term (for example, "accepting part", "accepting part", "accepting part", "screw", "sieve", etc.) itself or It may also include information representing a character string pattern to which a character string including the word at the end corresponds. The setting information may also include technical term-specific ending information indicating one or more technical term-specific ending strings.

A character string corresponding to an important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information may basically be extracted as an important phrase by the important phrase extraction unit 2051 . However, the condition information is an extraction exception indicating a character string pattern for a character string that should not be extracted as an important phrase even if it corresponds to the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information. May contain information on conditions. A character string corresponding to the character string pattern indicated by the information related to the extraction exception condition is not extracted as an important phrase by the important phrase extraction unit 2051, for example.

The key phrase candidate character string pattern information may be, for example, information indicating a plurality of key phrase candidate character string patterns. The important phrase candidate character string pattern information, for example, is a predetermined character string whose first character is either an alphabetic character, a kanji character, or a katakana character, and whose last character is an alphabetic character, a katakana character, a kanji character, or a predetermined hiragana character, It is determined to correspond to one key phrase candidate character string pattern. The key phrase candidate character string pattern information consists of predetermined hiragana characters (e.g., ``e'', ``ki'', ``ke'', ``shi'', ``mi'', ``ri'', ``re'', etc.) immediately after kanji. A character string that includes one or more sets of one character may be determined to correspond to one key phrase candidate character string pattern.

A character string pattern related to a character string that is a candidate for an important phrase indicated by the important phrase candidate character string pattern information is represented by, for example, a regular expression. For example, when the key phrase extraction process executed by the key phrase extraction unit 2051 is implemented by a computer that executes a program written in Python (registered trademark) language, various A string pattern is, for example, a standard library "re" for regular expression operations (e.g., string search, etc.) of Python (registered trademark), or a library provided by a third party that extends the function of "re" It is a character string pattern that can be expressed by a regular expression, which can be used by "regex", etc.

In the important phrase extraction process, one example of a specific reference character string pattern for extracting a reference character string from an invention document by performing a character string search using the function of the library "re" is roughly "' It is a string pattern that enumerates reference strings such as (above|above|relevant|that|description|... (hereinafter omitted)'”. Also, a string search is performed using the function of the library “regex” One example of a specific key phrase candidate character string pattern for extracting key phrase candidate character strings from invention documents by performing ([//::][A-Za-zA-Za-z]+)+)*[A-Za-zA-Za-z]*[ー・\p{Katakana}\p{Han}]+ )... (hereinafter omitted) '" is a character string pattern. Here, "\p{Katakana}" indicates katakana, and "\p{Han}" indicates kanji. There may be multiple key phrase candidate character string patterns. {Han}]*[A-Za-zA-Za-z]*[---・//]?[A-Za-zA-Za-z]+)', "r'([A-Za -zA-Za-z]*[ー・＼p{Katakana}＼p{Han}]+)', ``r'([A-Za-zA-Za-zー・＼p{Katakana}]* [\p{Han}]+[Iuekikukeshisusechitsutenane Himimumeriruregigejizejibibe][ー・\p{Katakana}\p{Han}]*[A-Za -zA-Za-z]+[---//]?[A-Za-zA-Za-z]+)', ``r'[A-Za-zA-Za-z-\p {Katakana}]*[＼p{Han}]+[Iuekikukeshisusechitsutenane Himimumeriruregigejizejibibe][A-Za-zA-Za-z]*[ー・\p{Katakana}\p{Han}]+)'”, “r'([A-Za-zA-Za-zー・\p{Katakana}]*[\p{Han}]+[i Ueki Kukeshi Suse Chitane Himimumeri Ruregigejizejibibe][＼p{Han}] ][ー・＼p{Katakana}＼p{Han}]*[A-Za-zA-Za-z]+[---・//]?[A-Za-zA-Za-z]+) ', ``r'([A-Za-zA-Za-zー・\p{Katakana}]*[\p{Han}]+[Iuekikukeshisusetetsutane Himimumerirure gigejizejibibe][＼p{Han}][iuekikukeshisusechitsutenane himimumeriruregigejizejibibe][A-Za-zA-Za-z]*[ -\p{Katakana}\p{Han}]+)' and the like can be used to search for key phrase candidate character strings. Also, the code string pattern indicated by the code string pattern information is, for example, a pattern determined so as to correspond to a character string that can be used as a code. It may also be a pattern defined to apply to a string of characters such as one or more characters followed by a closing parenthesis. Characters that can be used as symbols are, for example, Arabic numerals, English letters, Greek letters, Roman numerals, some symbols, and the like. One example of a specific code string pattern for extracting a character string used as a code from an invention document by performing a string search using the function of the library "re" is roughly "'([0 -90-9A-Za-zA-Za-z][---・//0-90-9A-Za-zA-Za-z]*)... (Omitted) Patterns such as '" is. In addition, a specific particle character string pattern indicated by specific specific particle character string pattern information for extracting a character string that is a predetermined particle from an invention document by performing a character string search using the function of the library "re" One example is a pattern such as "'( to | is | and | to | to | is |... (partially omitted)...)'".

The setting information may include, for example, information for specifying important phrase setting dictionaries (for example, information used to access the important phrase setting dictionary file). In addition, the setting information may include information for specifying translation auxiliary information (that is, information in which key words and corresponding translated words are associated with each of one or more key words). It is also possible to acquire translation assistance information based on and use the important phrase group in the translation assistance information as an important phrase setting dictionary. The setting information may also include information for specifying bilingual dictionary information, for example. When the invention document analysis system 20 is composed of the devices shown in FIG. 9, for example, the information for specifying the bilingual dictionary information is a file containing the bilingual dictionary information in the server device 10b on the LAN. can be path information including the host name of the server device 10b, etc., indicating the location of the server device 10b.

The setting information may include, for example, important phrase extraction range information for limiting the range of lines from which important phrases should be extracted in the invention document. Examples of information on the scope of extracting key phrases include the parts of the invention document that substantially correspond to the claims (e.g., claims), and the "Mode for Carrying Out the Invention" and "Examples" in the specification. Examples include a portion that substantially corresponds to the description and a range of lines from which key words should be extracted. In normal operation, it is assumed that the claims should be the range from which key words and phrases should be extracted. It may be assumed that

The setting information may include, for example, a non-code criterion that is a criterion for judging that the character strings of the invention document are not codes. The non-code reference may be included in the code character string pattern indicated by the code character string pattern information, or may exist separately from the code character string pattern information. If there is a non-coded reference other than the coded character string pattern information, the important word/phrase extraction unit 2051 of the analysis unit 205, etc., even if the character string corresponds to the coded character string pattern indicated by the coded character string pattern information, It is possible to consider strings that do not match based on non-sign criteria.

The setting information may include, for example, comment identifying information for identifying comment portions or comment lines in the invention document. For example, when the invention document is a document at the preparatory stage of a patent application, comments are items included in the invention document for purposes of calling attention, memorandums, annotations, etc., and are changed ( For example, deletion) is scheduled. A comment line is a line whose entire content is a comment. Examples of information for specifying comments include information expressing that a line including "■" (that is, a so-called solid block) or "*" (that is, a so-called asterisk) at the beginning of the line is a comment line, and "■{ (that is, a so-called solid block and opening curly brace) to "}" (that is, closing curly brace) is a comment.

The setting information can include, for example, importance criterion information indicating criteria for determining the importance of the important phrase extracted by the important phrase extraction unit 2051 from the invention document to be low under certain conditions. This fixed condition is, for example, the condition that both the use following the reference character string and the use preceding the sign are key phrases that are not in the invention document. An example of this importance level reference information is low-importance ending character string pattern information indicating a low-importance ending character string pattern of a character string at the end of a word with a low importance level. Examples of low-importance ending character strings, which are character strings at the end of words related to the low-importance ending character string pattern, include, for example, “number”, “etc”, and “example”.

For example, if there is a plug-in module externally provided as an executable program module for substituting or extending some of the functions of the invention document analysis system 20, the setting information is accessed and executed by the plug-in module. It may include information for plug-in module specification, which is information necessary for executing the plug-in module. As a plug-in module, for example, a program module responsible for processing for determining whether or not an invention document to be analyzed by the invention document analysis system 20 conforms to each of a plurality of items of the invention document standard specifications for translation. , a program module responsible for character string patterns to be added for extension of extraction of important phrases, and extraction processing of important phrases using the character string patterns; A program module or the like for executing a process of outputting a result of arithmetic processing is exemplified. A specific example of the plug-in module identification information is information such as a file path required to access a file containing the plug-in module, or information required to download the plug-in module via a network. URL or the like. The invention document analysis system 20 executes a plug-in module, for example, when executing a function substituted or extended by the plug-in module. If the plug-in module has version information (for example, a version number) for version management, the invention document analysis system 20 detects a plug-in module with a newer version (for example, a version number) than the already acquired plug-in module. If the in-module is available, delete the already acquired plug-in module and acquire and use the new version of the plug-in module. The invention document analysis system 20 provides an API (Application Programming Interface) for making available, from plug-in modules, information on important terms, symbols, etc., obtained by analyzing the invention document by the analysis unit 205, and other various types of information. etc. may be provided. The invention document analysis system 20 can appropriately execute the acquired plug-in module to achieve the purpose of the plug-in module.

The setting information may include, for example, category grouping reference information indicating criteria for distinguishing to which category the element represented by the key phrase extracted from the invention document by the key phrase extraction unit 2051 belongs. Examples of categories include products, methods, programs and data. For example, when a key phrase includes a character string such as "program" or "subroutine" at the end of a key phrase, the category division criteria information expresses that the element represented by the key phrase belongs to the program category. It is the information The category classification criteria information is, for example, when a character string such as "method", "step", or "procedure" is included at the end of an important phrase, the element represented by the important phrase belongs to the category of method. It is information that expresses For example, when a key phrase includes a character string such as "data" or "information" at the end of a key phrase, the category division criteria information expresses that the element represented by the key phrase belongs to the data category. It is the information The category division criteria information is, for example, information expressing that an element represented by an important phrase that does not belong to any of the categories of method, program, and data belongs to the product category.

The setting information includes, for example, the content of fixed phrases used when the analysis unit 205 generates specification information representing the content of an incomplete specification based on the claims of the invention document, the insertion position, the insertion conditions, and the like. It may include one or more boilerplate information to indicate. As an example of fixed phrase information, for example, in the line next to the heading "Mode for Carrying out the Invention" in the specification, "The drawings used in this disclosure are schematic diagrams and are strictly illustrated It is not." Examples of insertion conditions in each fixed phrase information include a condition that a claim of an invention document includes a claim claiming a program as a claim subject, a claim claiming a product as a claim subject, and a claim claiming a recording medium. conditions such as being included.

The setting information is, for example, information relating to the description of one or more elements used when the analysis unit 205 generates specification information representing the contents of an incomplete specification based on the claims of the invention document. , may include unfinished message information indicating the content of the unfinished message for writing support. The incomplete writing support message may include, for example, a character string listing items that should generally be written. The incomplete message information can be employed, for example, as an explanation of the elements indicated by the key phrases in the claim-based specification information generated by the analysis unit 205 based on the key phrases extracted from the claims of the invention document. It is information that can define an incomplete message with different contents depending on which category the element belongs to, such as an object, a method, a program, or data.

The setting information is used, for example, when the analysis unit 205 generates amended version claim information representing claims amended based on the claims of the invention document for the region (for example, the country where the application is to be filed). may contain modification information that defines how to modify it. For example, if a claim of an invention document includes a term that cites multiple terms, this modification information expresses that the term should be changed so that only one term with the smallest number among the multiple terms is cited. Information, etc. Modification information may be included, for example, in the Standard Specification for Invention Documents for Translation.

The configuration information may include information specifying the format of the claims in the modified claim information.

[3-1-2. Document Acquisition Unit]
A document acquisition unit 202 is obtained by partially modifying the document acquisition unit 102 shown in the first embodiment. The document acquisition unit 202 and the document acquisition unit 102 may be the same. The document acquisition section 202 includes an invention document acquisition section 2021 , a drawing document acquisition section 2022 and a translation result document acquisition section 2023 .

The invention document acquisition unit 2021 acquires an invention document to be analyzed by the invention document analysis system 20 according to, for example, specification of the invention document by the user. The invention document acquisition unit 2021 can acquire a plurality of invention documents. The invention document acquired by the invention document acquisition unit 2021 can be used by the analysis unit 205 and the machine learning unit 207 .

The drawing document acquisition unit 2022 acquires the drawing document corresponding to the invention document acquired by the invention document acquisition unit 2021, for example, according to the designation of the drawing document corresponding to the invention document by the user. The drawing documents acquired by the drawing document acquisition unit 2022 can be used by the analysis unit 205 .

The translation result document acquisition unit 2023 acquires the translation result document that is the translation result of the invention document acquired by the invention document acquisition unit 2021, for example, according to the user's designation of the translation result document that is the translation result of the invention document. The translation result document acquired by the translation result document acquisition unit 2023 can be used by the machine learning unit 207 .

Invention documents, drawing documents, and translation result documents are provided by database data, data as environment variables of the OS, data stored in a memory area used as a clipboard, and web servers on networks such as the Internet. It may exist as any data, such as data in a file, but may exist as the contents of a file, for example.

The invention document acquisition unit 2021, the drawing document acquisition unit 2022, and the translation result document acquisition unit 2023 are, for example, files containing invention documents based on the specification of each file path by the user of the invention document analysis system 20. The invention document, the drawing document, and the translation result document can be obtained by accessing the invention document file, the drawing document file containing the drawing document, and the translation result document file containing the translation result document. . The invention document file, the drawing document file, and the translation result document file follow a predetermined file name assignment rule (for example, a rule that the first character string, extension, etc. of the file name are different for each file type, etc.) It may be named, and in this case, the drawing document file or the translation result document file may exist in the same folder as the invention document file, for example, so that the user does not have to specify the file path. may be reduced. Note that the predetermined file name assignment rule may be defined in the setting information acquired by the setting information acquiring unit 201, for example. For example, the drawing document acquisition unit 2022 selects a file in the same or related folder as the invention document acquired by the invention document acquisition unit 2021 (for example, a file other than the invention document and its extension) that matches a predetermined file naming rule. The drawing document may be obtained from a file with the same name and the extension pdf), or the corresponding drawing document may be obtained from a website, etc. on the Internet based on the publication number of the invention document. good too. Also, for example, the translation result document acquisition unit 2023 acquires the translation result document from a file matching a predetermined file name assignment rule in the same or related folder as the invention document acquired by the invention document acquisition unit 2021. Alternatively, the corresponding translation result document may be obtained from a website or the like on the Internet based on the publication number of the invention document.

The drawing document file is, for example, a PDF file. The invention document file and the translation result document file are, for example, text files. The invention document file and the translation result document file may be, for example, a PDF file, or a file in a format mainly used for various application programs having document creation and editing functions such as Microsoft (registered trademark) Word, etc., and XML. (Extensible Markup Language) file. Also, the invention document file and the translation result document file may consist of one or more files in the same format as the display document (for example, HTML document) output by the invention document analysis system 20, for example. For example, the invention document acquisition unit 2021 obtains the claim information and specification information in the patent application related information as display documents output by the invention document analysis system 20 in the past, or the modified claim information and modified specification information, It may be acquired as an invention document including claims and specifications according to the user's instructions. Note that the PDF file may be a searchable PDF file in which the character strings in the content are included in a searchable state. Also, the drawing document acquisition unit 2022 converts a drawing document file that is not a searchable PDF file into a searchable PDF file by character recognition technology using machine learning (for example, deep learning) or character recognition using OCR technology, for example. It may be converted to and used.

The invention document acquisition unit 2021, the drawing document acquisition unit 2022, and the translation result document acquisition unit 2023 respectively edit the contents of the invention document file, the drawing document file, and the translation result document file (for example, format conversion, partial deletion, etc.). In addition, invention documents, drawing documents, and translation result documents may be obtained. As a specific example, the invention document acquisition unit 2021 reads the invention document, which is the content of the invention document file, in a method according to the encoding format of the invention document file (for example, UTF-8, EUC, Shift_JIS, CP932, etc.). , by converting the format as necessary, for example, obtaining an invention document as data of a character code string in a predetermined encoding format (for example, UTF-8) that can represent a relatively large number of characters. do. For the encoding format of the invention document file, for example, the encoding format may be specified according to whether or not an error occurs when the invention document file is read by trial and error. ) may identify the encoding type by reading it tentatively as a string and inspecting the contents.

It should be noted that the invention document analysis system 20 may be configured to have a document creation and editing function (for example, it may be configured to include an application program related to the document creation and editing function such as a text editor). In this case, the invention document acquisition unit 2021 acquires the invention document, which is data in a state of being generated or edited by the process executed in response to the user's input operation in the document creation and editing function of the invention document analysis system 20. It is also possible to Similarly, in the document creation and editing function of the invention document analysis system 20, the translation result document acquisition unit 2023 acquires the translation result document, which is data in a state of being generated or edited by the process executed according to the user's input operation. It is also possible to Moreover, the invention document analysis system 20 may be configured to have a drawing creation and editing function. In this case, the drawing document acquisition unit 2022 acquires the drawing document, which is the data generated or edited by the process executed according to the user's input operation in the drawing creation editing function of the invention document analysis system 20. It is also possible to

If the invention document, the drawing document, and the translation result document exist as data provided by a server device such as a web server on the Internet, for example, the invention document acquisition unit 2021, the drawing document acquisition unit 2022, and the translation result document acquisition unit 2023 accesses the server device via the WAN based on the URL of the server device specified by the user, the information specifying the invention document (for example, the publication number of the publication issued for the invention document), etc. Then, by downloading each data, the invention document, the drawing document, and the translation result document can be acquired respectively. In addition, the invention document, the drawing document, and the translation result document are files or data that can be output by a device equipped with a file server, database, or scanner function connected to a device as one component of the invention document analysis system 20 via a LAN. , for example, the invention document acquisition unit 2021, the drawing document acquisition unit 2022, and the translation result document acquisition unit 2023 receive the content or data of each file via the LAN, thereby obtaining the invention Documents, drawing documents, and translation result documents can be obtained. Therefore, the invention document acquisition unit 2021 reads the handwritten memo of technical ideas, for example, when the memo has substantial contents that can be converted into the claims or the contents of the specification of the invention document. , the invention document can be obtained by receiving data output from a device equipped with a scanner function.

For example, when the invention document acquisition unit 2021 acquires an invention document that is the content of an international application in Japanese whose international publication is provided on the Internet, the translation result document acquisition unit 2023 publishes it on the Internet. The content of the application written in a foreign language to the Office of the prescribed country, etc., which is presumed to correspond to the translation corresponding to this international application, using the information indicating the related application related to the international application A translation result document may be obtained by accessing published patent publications or the like.

[3-1-3. Important phrase setting dictionary acquisition unit]
The important phrase setting dictionary acquisition unit 203 is obtained by partially modifying the important phrase setting dictionary acquisition unit 103 shown in the first embodiment. The important phrase setting dictionary acquisition unit 203 and the important phrase setting dictionary acquisition unit 103 may be the same.

The important phrase setting dictionary acquisition unit 203 can acquire the important phrase setting dictionary based on the information for specifying the important phrase setting dictionary in the setting information acquired by the setting information acquiring unit 201 . The information for identifying the important phrase setting dictionary in the setting information may be information that specifies a plurality of important phrase setting dictionaries and determines their priority. By acquiring word/phrase setting dictionaries and integrating them in a memory or the like according to their priority, they can be used as one important word/phrase setting dictionary.

The content of the important phrase setting dictionary can be created and edited by the user.

The important phrase setting dictionary may exist as any data such as database data, data provided by a web server or the like on a network such as the Internet, and may exist as the contents of a file, for example.

The important phrase setting dictionary may be included as part of the invention document file. For example, predetermined headings such as <important phrase setting dictionary>, <important phrase list>, etc. may be added to the invention document file, and data corresponding to the important phrase setting dictionary may be described after the heading. In this case, the important phrase setting dictionary acquisition unit 203 can acquire the important phrase setting dictionary based on the information for identifying the important phrase setting dictionary in the setting information, which indicates the predetermined headline.

The important phrase setting dictionary acquired by the important phrase setting dictionary acquisition unit 203 can be used by the important phrase extraction unit 2051 in the analysis unit 205 to extract important phrases. The important phrase setting dictionary is information listing a plurality of important phrases to be extracted. In the important phrase setting dictionary, important phrases may be listed by classifying them by some group, such as by the department to which the inventor who created the invention in the invention document belongs, or by the technical field to which the invention belongs. Of the sets of key phrases for each of the multiple groups in the key phrase setting dictionary, a set of key phrases for one group based on setting information, selection by the user, etc. is used for extraction of key phrases by the key phrase extraction unit 2051. It may be used.

The important phrase setting dictionary acquisition unit 203 refers to the information for specifying the important phrase setting dictionary in the setting information, and by specifying a predetermined folder in the file system, obtains the important phrase setting stored as a file in the predetermined folder. You can get a dictionary. For example, in a case where a predetermined folder stores a plurality of key phrase setting dictionary files that are classified into groups such as technical fields and made identifiable by file names, etc., the key phrase setting dictionary acquisition unit 203 acquires an important phrase setting dictionary from files of important phrase setting dictionaries corresponding to a group (for example, a group designated by a user) related to the invention document acquired by the invention document acquiring unit 2021 among the plurality of files. good too. Also, the key phrase setting dictionary acquisition unit 203 has a higher correlation than a predetermined level with the key phrase group extracted from the invention document by the key phrase extraction unit 2051 based on condition information and the like without using the key phrase setting dictionary. An important phrase setting dictionary may be acquired from a file of an important phrase setting dictionary corresponding to a group such as field.

In the key phrase setting dictionary, a corresponding translated word may be added to the key phrase. It can also be said that the translation assistance information is the addition of the corresponding translated words for each of the key words in the key word setting dictionary. In addition, in the important phrase setting dictionary, information containing a set of pairs of important phrases and corresponding translated words for important phrases associated with corresponding translated words can be used as translation assistance information. For important phrases associated with corresponding translated words in the keyword phrase setting dictionary, for example, the translation unit 2054 of the analysis unit 205 can Corresponding translated words are determined, and claim translation information, specification translation information, or the like can be generated based on the determination result. A user (for example, an inventor or a patent attorney) predefines an important phrase setting dictionary so that corresponding translated words are associated with some specific important phrases. output information reflecting the corresponding translated word corresponding to the key phrase based on For example, a translator who receives the output information can clearly recognize the designation of the translation words for the important words, and can translate the invention document properly or efficiently. As an example of using the important phrase setting dictionary, for example, a claim of an invention document created by a user includes important phrases such as "information display timing control section", "information transmission timing control section", and "equipment control section". In this case, in order to simplify the terms of complaints in the translation target language, the user can set important phrases "information display timing control section", "information transmission timing control section" and "equipment control section" in the important phrase setting dictionary. ", respectively, as corresponding translated words "first controller", "second controller", and "third controller". Note that the user can, for example, edit the key phrase list in the patent application-related information that is output as a result of having the invention document analysis system 20 analyze the invention document, thereby efficiently generating the key phrase setting dictionary. , updates, etc.

In the key phrase setting dictionary, the key phrase may be added with a sentence explaining the key phrase with the key phrase as the subject.

For example, as in the invention document analysis system 10 shown in FIG. 9, when there are a plurality of terminal devices 10c to 10e connected by a LAN to a server device 10b having a file server function, each terminal device analyzes the invention document. It may function as system 20 . In this case, each terminal device functioning as the invention document analysis system 20 records the important phrase setting dictionary in a recording medium (for example, memory, hard disk, etc.) provided in the terminal device, and the important phrase setting dictionary is stored in the server device 10b at any time. may be sent to The important phrase setting dictionary in each terminal device can be created and edited by the user of each terminal device. Then, the server device 10b distributes to each terminal device a new key phrase setting dictionary generated as a result of integrating the key phrase setting dictionaries received from each terminal device, and each terminal device receives the distributed important phrase setting dictionary. An existing keyword setting dictionary may be updated based on the dictionary.

In addition, when the output based on the analysis result of the invention document by the invention document analysis system 20 (for example, the output of patent application related information) is realized as a display on the display device provided in the terminal device, equipment, etc. (for example, computer) , the invention document analysis system 20 may add the word/phrase to the important word/phrase setting dictionary according to the user's operation on the operation-responsive GUI element related to the part of the word/phrase of the display content. When a phrase is added to the key phrase setting dictionary in this way, when the invention document analysis system 20 performs invention document analysis processing after that, the key phrase extraction unit 2051 sets the important phrase after the addition of the phrase. Important words are extracted based on the dictionary. In addition, the invention document analysis system 20 adds words to the important phrase setting dictionary according to the user's operation for displaying information based on the analysis result of the invention document on the display device. Based on this, a GUI element for specifying re-analysis, that is, a GUI element (for example, a button drawn as "re-analysis") for re-analyzing the invention document (for example, extracting key phrases, etc.) It may be displayed when the information based on the result is displayed on the display device. The invention document analysis system 20 may display the GUI elements for specifying re-analysis on the display screen, for example, as appropriate, or may always display them.

The important phrase setting dictionary acquisition unit 203 may also acquire a non-important phrase setting dictionary that is information listing a plurality of phrases that should not be extracted as important phrases (information including a plurality of non-important phrases, so to speak). good. In this case, the setting information acquired by the setting information acquisition unit 201 can define the information for specifying the non-key phrase setting dictionary, and the key phrase setting dictionary acquisition unit 203 acquires the non-key phrase setting dictionary in the setting information. A non-important phrase setting dictionary can be acquired based on the identification information.

[3-1-4. Acquisition Department for Standard Provisions of Invention Documents for Translation]
The invention document standard specification acquisition unit 204 for translation is obtained by partially modifying the invention document standard specification acquisition unit 104 for translation shown in the first embodiment. The invention document standard specification for translation acquisition unit 204 and the invention document standard specification for translation acquisition unit 104 may be the same.

The invention document standard stipulations for translation acquisition unit 204 is based on the content of the setting information acquired by the setting information acquisition unit 201 (for example, specification information of the standard stipulations for invention documents for translation), which the invention document to be translated should satisfy. Acquire invention document standard specifications for translation that define multiple conditions. Each of the conditions in the Standard Rules for Invention Documents for Translation is defined, for example, so that the invention document is a Japanese manuscript for translation that is adequately suitable for translation. The invention document standard specification for translation acquired by the invention document standard specification acquisition unit 204 for translation in the invention document analysis system 20 is used, for example, in the warning information generation unit 2059 in the analysis unit 205 to generate warning information based on the invention document. .

The standard specifications for invention documents for translation are assumed to be the specifications established by an organization aiming at standardization of invention documents for translation, but may be the specifications established by any other person. Also, this organization related to standardization may be a division of a company, company, etc., or may be composed of a plurality of companies, companies, etc., regardless of the scale.

For example, if the specification information for the standard specification of invention documents for translation in the setting information is file path information, the standard specification of invention documents for translation acquisition unit 204 accesses the file according to the file path. read and acquire the invention document standard specification for translation from the file. For example, when the specifying information of the invention document standard specification for translation in the setting information is URL information, the acquisition unit 204 of the invention document standard specification for translation acquires a server device or the like on the network according to the URL. Access Invention Document Standard Specification for Translation as a resource provided to download and obtain Invention Document Standard Specification for Translation.

The invention document standard specification for translation may include version information such as a version number indicating the version of the invention document standard specification for translation, for example. The invention document standard specification for translation may be upgraded whenever the content of the specification is changed under a predetermined version management system. The invention document standard specification for translation acquisition unit 204 acquires information for specifying the standard specification for invention document for translation of the setting information acquired by the setting information acquisition unit 201 (for example, information for accessing the standard specification for invention document for translation via a network). If it is possible to access the standard specifications for invention documents for translation based on the URL) and obtain a newer version of the standard specifications for invention documents for translation than the version (for example, version number) of the standard specifications for invention documents for translation that has already been acquired For example, the existing invention document standard specification for translation is deleted, and the new version of the invention document standard specification for translation is acquired.

The standard specifications for invention documents for translation may include, for example, specifications in association with target languages (that is, specifications for each target language), or may target only a specific language (for example, English). It may be a provision that If the invention document standard specifications for translation include specifications for each language to be translated, the language to be translated may be designated by setting information or by user operation on the invention document analysis system 20, for example.

The invention document standard specification for translation may include, for example, data or an inspection program for processing to determine whether the invention document has the conditions to be satisfied. This inspection program is, for example, a program responsible for determining whether or not an invention document conforms to each of a plurality of items (that is, condition items indicating conditions) of the invention document standard specifications for translation. , for example, may be a plug-in module. For example, the warning information generation unit 2059 in the analysis unit 205 executes the inspection program included in the invention document standard specification for translation (that is, by causing the microprocessor to execute the inspection program). It is also possible to determine whether or not the invention document obtained conforms to each of a plurality of conditions stipulated in the invention document standard specification for translation, and to generate warning information using the result of the determination.

The standard specifications for invention documents for translation include, for example, character string patterns for potentially inappropriate descriptions that do not satisfy the conditions in the invention documents as information that defines the conditions that the invention documents to be translated should meet. Inappropriate character string pattern information indicating an inappropriate character string pattern representing The Standard Provisions of Invention Documents for Translation, for example, correspond to all or part of the inappropriate character string pattern information indicating inappropriate character string patterns related to description parts that may be inappropriate, and indicate the inappropriate characters in the invention document. Contains correction information on how to correct the description that may be appropriate.

The standard provisions for invention documents for translation classify condition items, which are items of conditions to be satisfied by invention documents, for example, by handling character strings that may be included in invention documents or by differences in features, and for each condition item, For example, it includes condition item names and pattern information (for example, inappropriate character string pattern information) for extracting inappropriate descriptions in invention documents. Inappropriate descriptions in the invention documents may be potentially inappropriate descriptions, and patent rights are obtained by submitting translation results documents based on the invention documents to a prescribed region (for example, the United States). It may be a description that may cause some disadvantages to Pattern information for extracting inappropriate descriptions may use information other than patterns for specifying character strings. may also include a program or the like relating to an algorithm for extracting descriptions in which a citation of a plurality of items is cited. All or part of the conditional items of the Standard Provisions for Invention Documents for Translation may further include correction information. The correction information may include a program related to an algorithm for correcting the invention document, such as deletion of character strings in the invention document that correspond to the inappropriate character string pattern indicated by the inappropriate character string pattern information. . In addition, correction corresponding to pattern information for extracting as inappropriate description that there is a clause citing multiple clauses in a claim and the clause to which the claim refers further cites multiple clauses The information may include, for example, a program or the like for performing a process of correcting a multiple citation to a singular citation.

In addition, all or part of the condition items of the Standard Provisions for Invention Documents for Translation further include explanations to the user of the reasons for inappropriate descriptions in the invention documents that correspond to the patterns indicated by the pattern information, A conditional item explanation message may be included that provides an explanation to the user of the disadvantage that the description causes, or an explanation to the user of a method for correcting it appropriately. In the condition item explanation message, the explanation of the reason for the inappropriate description may include information such as the provisions of laws and regulations, judicial precedents, etc., which serve as the basis for the reason for the inappropriate description.

FIG. 14 shows an example in which a condition item name and a pattern indicated by pattern information are defined for each condition item, and correction information is added to a part of the condition item, as an example of standard specifications for invention documents for translation. The example shown in the figure is only a simple example, and condition items may be added. Appropriate correction information may be added.

Conditional item names such as "absence of subject in each sentence of specification" shown in FIG. , for example, in warning information generated by the warning information generator 2059 and included in the patent application related information. It should be noted that "each sentence in the specification" is delimited, for example, immediately after the period character or at the linefeed code portion at the end of the line. A plurality of pattern information (for example, character string pattern information) may be associated with one condition item. For example, regarding the conditional item name shown in FIG. 14, regarding the conditional item name "Character string that may be preferable to be changed to other expressions in US applications, etc.", the specification of the invention document states "(1) in FIG. , and (2) in FIG. 2 is a diagram representing . Character string pattern information indicating a character string pattern to which the character string indicating gender (for example, “(1) in FIG. 2”) may be associated. As an example, this character string pattern has a number following the character "figure" followed by a predetermined character such as "no", "in", etc., followed by the predetermined character Statements where there is a statement that encloses an alphanumeric character between parentheses and a closing parenthesis are defined as applicable.

In the condition item with the condition item name "Among the important phrases in the claim, the importance of which is higher than a predetermined level is not stated in the specification" shown in FIG. As a specific example, the pattern information of "Pattern for detecting absence of important phrases" is the degree of importance in the setting information of the important phrases extracted by the important phrase extraction unit 2051 from the claims of the invention document. This is information indicating a set of character string patterns for detecting key words and phrases from the specification of the invention document, for key words and phrases that were not determined to be of low importance based on the reference information.

Another example of a conditional item in the Standard Provisions for Invention Documents for Translation is, for example, the conditional item name "statement of multiple parentheses" and the inappropriate description of multiple parentheses containing parentheses within parentheses. Condition items include pattern information indicating patterns for extracting descriptions and condition item explanation messages such as desirability of reducing parentheses. By using this conditional item, if the description of multiple brackets is included in the invention document, the warning information generated by the warning information generation unit 2059 and included in the patent application related information is corrected to be clearly described. It may include indications related to the description of multiple parentheses to call attention to

As yet another example of the conditional items in the standard provisions for invention documents for translation, for example, the conditional item name "description of functional means in claims" and the description of functional means as an inappropriate description are extracted. condition items including pattern information indicating the pattern of By using this condition item, if the claim of the invention document includes the description of the functional means, the warning information generated by the warning information generation unit 2059 and included in the patent application related information includes the description of the functional means. Such indications may be included. The pattern indicated by this pattern information is, for example, a pattern corresponding to descriptions of so-called functional blocks such as "...means" and "...unit". It is not necessarily inappropriate to describe functional means in a claim, and there may be cases where functional means are described strategically. Since there is a possibility of occurrence, this pointing out in the warning information may be useful for a prima facie call for attention.

The invention document standard specification for translation is used, for example, in the warning information generation section 2059 of the analysis section 205 . In addition, the correction information as an example of the content of the invention document standard specification for translation may be included in the patent application related information output by the output unit 208, for example, in order to generate the corrected claim information and the corrected specification information. Used in analysis unit 205 .

[3-1-5. Analysis Department]
The analysis unit 205 is a partial modification of the analysis unit 105 shown in the first embodiment, and is the same as the analysis unit 105 except for points not specifically shown here.

The analysis unit 205 analyzes the invention document acquired by the invention document acquisition unit 2021 based on the setting information acquired by the setting information acquisition unit 201 .

The analysis unit 205 includes an important phrase extraction unit 2051, a classification unit 2053, a translation unit 2054, an importance determination unit 2055, an attribute identification unit 2056, a complaint citation relationship detection unit 2057, an inter-element relationship determination unit 2058, a warning information generation unit 2059, It includes a complaint information generator 205a, a statement information generator 205b, and a claim tree generator 205c.

The analysis result of the invention document by the analysis unit 205 is used, for example, in the output unit 208 to generate patent application-related information to be output, and in the machine learning unit 207 to evaluate the invention document. .

FIG. 15 shows an example of the contents of the patent application related information generated by the analysis unit 205 and output by the output unit 208. FIG. FIG. 16 shows a configuration example of an HTML document, which is an example of a display document as one expression format of patent application related information. FIG. 17 shows an example of a display screen displayed by a browser or the like based on a display document (for example, HTML document) representing patent application related information. The display screen illustrated in FIG. 17 includes a menu column for displaying a menu for selecting various information items in the patent application related information, a content display column for items of the patent application related information according to the menu selection, and the like. there is In the display screen illustrated in FIG. 17, for example, the above-described GUI element for specifying reanalysis can be displayed in the operation column for specifying reanalysis of the invention document.

[3-1-5-1. Key phrase extraction part]
The key phrase extraction unit 2051 is a partial modification of the key phrase extraction unit 1051 shown in the first embodiment. The important phrase extraction unit 2051 may be similar to the important phrase extraction unit 1051 . Extraction of key phrases from invention documents by the key phrase extraction unit 2051 is useful if it is accurate to some extent, and does not necessarily have to be completely accurate.

The key phrase extraction unit 2051 may include functional configurations similar to those of the first extraction unit 10511, the second extraction unit 10512, the third extraction unit 10513, and the fourth extraction unit 10514, for example. The key phrase extraction unit 2051 extracts, for example, references indicated by the reference character string pattern information in the condition information in the setting information acquired by the setting information acquisition unit 201 in the claim and specification of the invention document acquired by the document acquisition unit 202. If there is a string corresponding to the keyword candidate character string pattern indicated by the key phrase candidate character string pattern information in the condition information following the character string that corresponds to the character string pattern, the key phrase candidate character string pattern is A first extractor having a function of extracting the same character string as the relevant character string as an important phrase may be provided. The important phrase extraction unit 2051 extracts, for example, key phrases indicated by the important phrase candidate character string pattern information in the condition information in the setting information acquired by the setting information acquisition unit 201 in the claims of the invention document acquired by the document acquisition unit 202. A second extraction unit having a function of extracting, as an important phrase, a character string identical to the character string corresponding to the key phrase candidate character string pattern when a period character exists following the character string corresponding to the candidate character string pattern. may be provided. The key phrase extraction unit 2051 extracts key phrase candidate characters indicated by the key phrase candidate character string pattern information in the condition information in the setting information acquired by the setting information acquisition unit 201, for example, in the invention document acquired by the document acquisition unit 202. If there is a character string corresponding to the coded character string pattern indicated by the coded character string pattern information in the condition information following the character string corresponding to the column pattern, the character string corresponding to the key phrase candidate character string pattern A third extractor having a function of extracting the same character string as an important phrase may be provided. Also, the important phrase extraction unit 2051 extracts key phrases indicated by the important phrase candidate character string pattern information in the condition information in the setting information acquired by the setting information acquisition unit 201, for example, in the invention document acquired by the document acquisition unit 202. If a character string corresponding to the specific particle character string pattern indicated by the specific particle character string pattern information in the condition information exists following the character string corresponding to the candidate character string pattern, it corresponds to the key phrase candidate character string pattern. A fourth extraction unit may be provided that has a function of extracting the same character string as the important phrase as the important phrase.

The key phrase extraction unit 2051 executes key phrase extraction processing for extracting key phrases from the invention documents acquired by the invention document acquisition unit 2021 based on the condition information included in the setting information acquired by the setting information acquisition unit 201. do. By appropriately defining the condition information, the key phrase extraction unit 2051 can, for example, extract It becomes possible to extract a plurality of key terms from the claims or the specification.

The key phrases extracted by the key phrase extraction unit 2051 are used to generate information such as patent application related information output by the invention document analysis system 20, for example. Here, using an example in which an invention document includes a claim and a specification, the key word extracting unit 2051 for extracting key words from each of the claims and the specification of the invention document will be described in detail. The key phrase extraction unit 2051 executes, as key phrase extraction processing, a claim key phrase extraction process for extracting key phrases from the claims of the invention document, and a specification key phrase extraction process for extracting important phrases from the specification of the invention document. do.

In the analysis unit 205, for example, the key phrase extraction unit 2051 distinguishes whether the key phrase is extracted from the claim or the specification, and manages the extracted key phrase. The analysis unit 205 can hold important phrase management information for managing important phrases. The key word management information is information in which identification information, importance, attribute information, corresponding translation words, translation word candidate sets, etc. are associated with each key word extracted from the invention document.

The important phrase extraction unit 2051 extracts important phrases in the range according to the important phrase extraction range information in the setting information in the invention document acquired by the invention document acquisition unit 2021 . Here, in the setting information, the scope of all claims and the scope of the description of "modes for carrying out the invention" and one or more "embodiments" in the specification are extracted as key phrases. Description will be made assuming an example where the range is set. As an example, the scope of each claim is defined by the heading of one claim, "Claim n" (where n is a natural number) sandwiched between the opening and closing square brackets in the line order of the invention document. From the line to the beginning of the heading or the end of the invention document, as indicated by the following string of characters enclosed in square brackets (e.g., the string beginning with "Claim", "Title of Document", etc.) is. In addition, the scope of the description of "Method for Carrying Out the Invention" in the specification is, for example, from the heading line "Method for Carrying Out the Invention" enclosed in square brackets to the following: This is up to whichever of the headings or the end of the invention document, which is represented by a string of characters enclosed in square brackets (e.g., "Example", "Description of Symbols", etc.). In addition, the range in which one "Example" is described in the specification is, for example, from the heading line "Example" or "Example m" (m is a natural number) sandwiched between square brackets , to either the heading indicated by the next bracketed string or the end of the invention document, whichever is first.

The key phrase extraction unit 2051 may extract key phrases from the invention document, for example, using a plug-in module that performs the key phrase extraction process.

[3-1-5-1-1. Extraction of Important Words in Claims]
The key phrase extraction unit 2051 searches for key phrase candidates for each claim line of the invention document, for example, as the claim key phrase extraction process, and extracts the key phrase candidates. ) to determine whether or not it can be an important phrase, and extract a phrase that is determined to be an important phrase as an important phrase. Note that the key phrase extraction unit 2051 searches for key phrase candidates by, for example, excluding comment lines or comment portions from the search target range based on the comment specifying information of the setting information.

For example, the key phrase extraction unit 2051 performs character format conversion on each line of the claim of the invention document for searching before searching for key phrase candidates for each line of the claim, and converts the character format to can be used for searching. Examples of character format conversion include conversion of half-width characters to full-width characters, and conversion of lower-case alphabetic characters (eg, “a”) to upper-case alphabetic characters (eg, “A”). Such character format conversion simplifies the character string pattern (for example, key word candidate character string pattern) required for searching key word candidates, and speeds up the processing related to key word extraction. etc. may be realized.

If a plurality of key phrase candidates determined to be possible key phrases are extracted in one line of a claim, and the description ranges of the character strings of the plurality of key phrase candidates partially overlap, the key phrase extraction unit 2051 selects one of the plurality of key phrase candidates based on a defined selection criterion and extracts it as the key phrase. For example, if one key phrase candidate character string among a plurality of key phrase candidate character strings is included in another key phrase candidate character string, This is a criterion of excluding one key phrase candidate character string and selecting an important phrase from the remaining candidate character strings. For example, the key phrase extraction unit 2051 may use one or a few relatively complex key phrase candidate character string patterns for extracting key phrases, or may use relatively simple key phrase candidate character string patterns. A plurality of them may be used. For example, in order to extract an important phrase, the important phrase extraction unit 2051 extracts one of the plurality of character strings when a plurality of character strings correspond to the important phrase candidate character string pattern. When the character string is included in the description of the invention document, the remaining character string excluding the one character string among the plurality of character strings is selected and extracted as a selection target.

For example, if a claim of an invention document contains the same key phrase as the key phrase included in the key phrase setting dictionary acquired by the key phrase setting dictionary acquisition unit 203, the key phrase extraction unit 2051 extracts , as a candidate for an important phrase. For example, the important phrase extraction unit 2051 does not extract the phrases included in the non-key phrase setting dictionary acquired by the important phrase setting dictionary acquisition unit 203 as candidates for important phrases.

The key phrase extraction unit 2051, for example, refers to each character string pattern information indicated by the condition information of the setting information, and extracts the phrases in the claims of the invention document as candidates for key phrases.

As a specific example, the key word extraction unit 2051 extracts key word candidate character strings in the condition information, following the character string corresponding to the reference character string pattern indicated by the reference character string pattern information in the condition information, in the complaint. If there is a character string corresponding to the key phrase candidate character string pattern indicated by the pattern information, the same character string as the character string corresponding to the key phrase candidate character string pattern is extracted as an important phrase candidate. When the same character string as the character string corresponding to the key phrase candidate character string pattern is to be extracted as an important phrase from the key phrase candidates, the important phrase extraction unit 2051, for example, If there is a character string in the claim that includes the character string extracted as the key phrase at the end of the word and corresponds to the key phrase candidate character string pattern indicated by the key phrase candidate character string pattern information, the key phrase A character string corresponding to the candidate character string pattern may be further extracted as an important phrase candidate. As a result, for example, if the character string corresponding to the reference character string pattern is "said", when "control device" is extracted as an important phrase from the description of "said control device" in the claim, Furthermore, the "equipment control device" in the claims that ends with the word "control device" can be further extracted as a candidate for the important phrase. Note that the key phrase extraction unit 2051 detects that a predetermined prefix character string exists following the character string corresponding to the reference character string pattern indicated by the reference character string pattern information in the condition information in the complaint, and that the predetermined prefix character string exists. If there is a character string following the key phrase candidate character string pattern indicated by the key phrase candidate character string pattern information in the condition information, it is the same as the key phrase candidate character string pattern can be extracted as candidates for important phrases. Here, the predetermined prefix character string is an ordinal character string including one or more ordinal numbers such as "first", "first", "first, third to fifth", etc. , or a quantity string expressing the number such as "plurality", "one", "a set", "one or more", etc., or "predetermined", "predetermined", "one It is a limited character string such as "of", "other", and the like. If the ordinal string contains more than one ordinal number, the ordinal string should use ``~'', ``-'', ``,'', comma characters ``,'' as separators between ordinal numbers, or the part of speech as a conjunction. Including character strings, etc. Conjunctions may be identified using conventional morphological analysis techniques or by matching a string of conjunctions (such as "and", "or", "and") against a list of conjunctions. good too. In the conjunctive list, statements such as "and/or", "and/or" may be included.

For example, the important phrase extraction unit 2051 extracts the specific particle character string pattern information in the condition information after the character string corresponding to the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information in the complaint. If there is a character string corresponding to the specific particle character string pattern indicated by , the same character string as the character string corresponding to the key phrase candidate character string pattern is extracted as an important phrase candidate. Note that, for example, the important phrase extraction unit 2051 extracts a predetermined character string (for example, "Each", "Each of", etc.) exists, and following the predetermined character string, there is a character string corresponding to the specific particle character string pattern indicated by the specific particle character string pattern information in the condition information , the same character string as the character string corresponding to the key phrase candidate character string pattern may be extracted as the key phrase candidate.

The important phrase extraction unit 2051 extracts, for example, a character string corresponding to the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information in the complaint, followed by the code character string pattern information in the condition information. If there is a character string that corresponds to the code string pattern shown (for example, a code between the opening and closing parentheses), the same character string as the key phrase candidate character string pattern is extracted as an important phrase candidate.

The key phrase extraction unit 2051 extracts characters other than Chinese characters or predetermined Chinese characters (for example, “each”) in the complaint, followed by the key phrase candidate character string pattern indicated by the key phrase candidate character string pattern information in the condition information. If there is a character string that matches the key phrase candidate character string pattern, the same character string as the character string corresponding to the key phrase candidate character string pattern may be extracted as an important phrase candidate.

For example, the important phrase extraction unit 2051 extracts the important phrase candidate character string pattern information indicated by the important phrase candidate character string pattern information in the condition information after the beginning of a line, punctuation marks, or after verbs, auxiliary verbs, adjectives, conjunctions, adverbs, or predetermined hiragana in a claim. If there is a character string corresponding to the phrase candidate character string pattern, the same character string as the character string corresponding to the key phrase candidate character string pattern may be extracted as an important phrase candidate. Each line in the invention document can be composed of multiple character strings, and the part of speech of each character string (for example, the type of character string classified into verbs, adjectives, conjunctions, etc.) can be determined using existing morphological analysis techniques. can be used to determine to some extent. For this reason, part of the condition information (for example, important word candidate character string pattern information) may indicate character string patterns that differentiate parts of speech. A character string pattern that distinguishes parts of speech is obtained, for example, by first performing morphological analysis on each word in the invention document using a morphological analysis technology, and as a result, preselected words that are each of the predetermined parts of speech. In the case where candidates for important phrases are extracted on the premise that a specific symbol string is added to at least one of immediately before and after the phrase, or the phrase is replaced with a specific symbol string by part of speech, It is a character string pattern expressed by including a specific symbol string for each part of speech. An example of a program for executing morphological analysis is the open-source morphological analysis engine "Mecab" developed by Taku Kudo in a joint research unit project between Kyoto University Graduate School of Informatics and Nippon Telegraph and Telephone Corporation Communication Science Laboratories. is mentioned. For example, the condition information may be defined such that a noun corresponds to one key phrase candidate character string pattern indicated by the key phrase candidate character string pattern information. When determining whether or not there is a character string corresponding to the specific particle character string pattern indicated by the specific particle character string pattern information in the invention document (for example, in a claim), the morphological analysis of the character string Determining whether the string exists or not where the part of speech is a particle may be added.

For example, when there is a character string extracted as a key phrase based on the condition information in the specification of the invention document, the key phrase extraction unit 2051 detects that the same character string as that character string exists in the claim of the invention document. When doing so, the character string may be extracted as an important phrase candidate unconditionally or under certain conditions. An example of this certain condition is that the importance of the key phrases extracted from the specification of the invention document is above a predetermined level. As a specific example, for example, the key phrase extraction unit 2051 follows the character string corresponding to the key phrase candidate character string pattern indicated by the key phrase candidate character string pattern information in the condition information in the specification of the invention document, If there is a character string corresponding to the coded character string pattern indicated by the coded character string pattern information in the condition information, the same character string as the character string corresponding to the key phrase candidate character string pattern is included in the claim of the invention document. If it exists, the character string may be extracted as an important phrase candidate.

For example, when a patent document is indicated as prior art document information in the specification of an invention document, the key phrase extraction unit 2051 extracts key phrases based on the condition information from the claims and specifications of the patent document. , if the claims of the invention document contain the same key words as the key words in the patent document, they may be extracted as key word candidates.

For example, when an "explanation of the code" is described in the specification of the invention document, the key phrase extraction unit 2051 extracts the words and phrases described in association with the code in the "explanation of the code" from the invention document. exists in the claim, the phrase may be extracted as a candidate for the important phrase. For example, if the word in the claim is followed by a predetermined non-following character string among the words in the claim extracted as the candidates for the important word, the key word extracting unit 2051 regards the word as the key word. It is also possible not to extract. The predetermined non-following character string is, for example, "do", "shi", and the like. For example, if a predetermined unnecessary word is included at the head of a claim extracted as an important word candidate, the important phrase extraction unit 2051 removes the predetermined unnecessary word from the phrase. , may be regarded as extracted as candidates for key phrases. Predetermined unnecessary words are, for example, "so-called", "substantially", and "various".

For example, if a character string in a claim extracted as a candidate for an important phrase is a character string that corresponds to an extraction exception condition, the important phrase extraction unit 2051 may not extract the character string as an important phrase. good. Extraction exception conditions may be defined as part of the condition information, for example. Extraction exception conditions include, for example, character strings that are not important words by themselves (e.g., "plural", "on", etc.), character strings that are not important words even if they are alone or included as endings (e.g., "actual", "hundred"). etc.), character strings that indicate units and are not key phrases (for example, "km", "cm", "MB", "kΩ", etc.).

The important phrase extraction unit 2051 extracts, for example, the important phrase extracted from the claim of the invention document, followed by the opening parenthesis and the characters corresponding to the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information. When a string and a closing parenthesis are consecutively included in this order, a character string corresponding to the important phrase candidate character string pattern may be extracted as an important phrase candidate. If the string corresponding to the key phrase candidate character string pattern is multiple words separated by colons ":" and each of the multiple words corresponds to the key phrase candidate character string pattern, the key phrase The extraction unit 2051 may extract each of the plurality of phrases as an important phrase candidate.

The key phrase extraction unit 2051, for example, extracts, as key phrases, phrases that represent the elements described as the subject of a claim in the claims of the invention document (so to speak, the elements that are the subject of a claim). For example, the important phrase extraction unit 2051 extracts the same phrase as the important phrase included in the important phrase setting dictionary acquired by the important phrase setting dictionary acquisition unit 203 in the claim of the invention document, and if there is a period character following the phrase, extracts the phrase as a key phrase that represents the claimed element. For example, if a claim of an invention document contains a period character following a character string corresponding to an important phrase candidate character string pattern indicated by important phrase candidate character string pattern information in the condition information, the important phrase extraction unit 2051 , the same character string as the character string corresponding to the key word candidate character string pattern is extracted as the key word representing the element to be claimed. Whether or not the key phrase extracted by the key phrase extraction unit 2051 represents an element to be claimed in a claim can be one of the items of attribute information in the key phrase management information managed by the analysis unit 205, for example.

The key word candidate character string pattern used to search for the claimed element in the claim of the invention document is the same as the key word candidate character string pattern used to search for the key word candidate for the non-claimed element. may be different, or some may be different. As an example, the key phrase candidate string pattern used to search for the claimed element includes a predetermined string containing the hiragana character "no", which may be used to express loose combinations of phrases, and Another predetermined character string that does not include hiragana "no" is a character string pattern that is determined to be applicable, and is used to search for candidates for important phrases related to elements other than the subject of the claim The key phrase candidate character string pattern may be a character string pattern that does not include a hiragana character "no".

[3-1-5-1-2. Extraction of key terms in the specification]
As the specification key phrase extraction process, the key phrase extraction unit 2051 extracts, for example, an extraction range of key phrases according to key phrase extraction range information in the setting information in the specification of the invention document (for example, “Implementing the invention For example” and “Example”), important words are extracted. Extraction of important phrases in the specification by the important phrase extraction unit 2051 is generally the same as extraction of important phrases in the claims described above, except for some differences. Hereinafter, the explanation of the same thing will be omitted as appropriate, but as long as it can be used to extract key words in the extraction range of key words in the specification of the invention document, the key words in the above-mentioned claims A method similar to the extraction of words may be used.

For example, the key phrase extraction unit 2051 searches for key phrase candidates for each line in the key phrase extraction range in the specification of the invention document. It is determined whether or not it can be an important phrase, and those determined to be an important phrase are extracted as important phrases.

Note that the key phrase extraction unit 2051 searches for key phrase candidates by, for example, excluding comment lines or comment portions from the search target range based on the comment specifying information of the setting information. In addition, the key phrase extraction unit 2051 may search for key phrase candidates, for example, by excluding the quoted range from the search target range. The range of a quoted statement is, for example, the range of two corresponding separate letter codes for citation, which are surrounded by quotation marks or parentheses; When expressed in points, "...", "...", "..." and the like can be mentioned.

For example, the key phrase extraction unit 2051 may perform character format conversion on each line before searching for key phrase candidates for each line in the key phrase extraction range in the specification of the invention document.

In one line of the key phrase extraction range in the specification of the invention document, a plurality of key phrase candidates determined to be possible key phrases are extracted, and the description range of the character strings of the plurality of key phrase candidates is If there is a partial overlap, the key phrase extraction unit 2051 selects one of the plurality of key phrase candidates based on a defined selection criterion and extracts it as the key phrase. Note that the important phrase extraction unit 2051 extracts all descriptions in parentheses in each line of the extraction range of important phrases in the specification of the invention document (i.e., between the opening and closing parenthesis Extraction of candidates for important phrases is performed by separately targeting the description part outside the parentheses formed by concatenating the remaining character strings after removing the description part) and the description parts inside the parentheses. good too.

The key phrase extraction unit 2051 extracts, for example, the same key phrases as the key phrases included in the key phrase setting dictionary acquired by the key phrase setting dictionary acquisition unit 203 are included in the key phrase extraction range in the specification of the invention document. If it is, the word/phrase in the extraction range of important words/phrases in the specification is extracted as an important word/phrase candidate. The important phrase extraction unit 2051, for example, does not extract the phrases included in the non-key phrase setting dictionary acquired by the important phrase setting dictionary acquisition unit 203 as candidates for important phrases.

For example, if the same words as those extracted as important words in the claims of the invention document are included in the extraction range of the important words in the specification of the invention document, the key word extraction unit 2051 The word/phrase in the extraction range of the important word/phrase in the book is extracted as a candidate of the important word/phrase.

The key phrase extraction unit 2051, for example, refers to each character string pattern information indicated by the condition information of the setting information, and extracts the key phrases in the key phrase extraction range in the specification of the invention document as key phrase candidates.

As a specific example, the key phrase extraction unit 2051 extracts the key phrase candidate string pattern indicated by the key phrase candidate string pattern information in the condition information, for example, in the key phrase extraction range in the specification of the invention document. If there is a coded character string following the relevant character string, the same character string as the character string corresponding to the key phrase candidate character string pattern is extracted as an important phrase candidate. The coded character string is, for example, a character string corresponding to the coded character string pattern indicated by the coded character string pattern information in the condition information. If the coded character string pattern information does not reflect the non-coded criteria in the setting information, the coded character string is a character string that corresponds to the coded character string pattern and is not a code based on the non-coded criteria. It is a character string that is not judged as For example, when the description of the invention document includes an "explanation of the code", the code string may be a character string presumed to be the code in the "explanation of the code".

The code string pattern represented by the code string pattern information in a regular expression, for example, is expressed so that a string composed of characters (for example, alphanumeric characters and predetermined symbols) that can be used as a code is applicable. . The code string pattern may be, for example, a character string pattern in which a plurality of codes are connected by "~", "-", ",", comma characters ",", etc. . When the non-code reference is not included in the code string pattern, the non-code reference is a character string that corresponds to the code string pattern, for example, it is rarely used as a code, and is not a code. This is information that defines character examples that are estimated to have a high probability of being judged not to be codes. Examples of character strings that are determined not to be codes based on non-code standards include character strings in which the first three or more characters are uppercase letters, and a predetermined unit character string (e.g., "km", " cm”, “MB”, “kΩ”, etc.). The non-sign criterion may indicate a string that is determined not to be a sign in combination with the ending of the element name immediately preceding the sign. In some cases, a code consisting of one or more numbers followed by a unit character string such as "V" or "mV", and if the element name immediately before the code ends with "distance", the first character Codes formed by following the above numerals with unit character strings such as "m", "cm", and "km" can be used. A non-sign standard is, for example, a character string composed of characters that can be used as a sign, followed by a predetermined character that rarely follows a sign (for example, "tsu", "year", "seconds"). , "times", etc.) is described, a character string composed of characters that can be used as the code may be determined so as not to be the code.

For example, the key phrase extraction unit 2051 selects, from the key phrase extraction range in the specification of the invention document, among the key phrase candidate words and phrases extracted due to the subsequent existence of the code character string, the same content A plurality of words and phrases extracted due to the subsequent existence of the code character string, and a plurality of words and phrases having a common ending and different parts other than the ending (for example, "equipment control unit" and "first control unit" ) exist, the multiple words may be excluded from the key word candidates, and the common ending part (for example, "control part") may be newly extracted as a key word candidate. It should be noted that the subsequent existence of the code character string with the same content from a different position in the extraction range of the key phrase in the specification of the invention document causes the key phrase extraction unit 2051 to temporarily select the key phrase as a candidate for the key phrase. A plurality of words and phrases extracted and excluded from the candidates (for example, “equipment control unit” and “first control unit”) are, for example, the same in warning information generated by the analysis unit 205 for calling attention. It can be pointed out as a group of coded variant phrases.

The important phrase extraction unit 2051 extracts, for example, an important phrase extracted because a coded character string follows it in the extraction range of the important phrase in the specification of the invention document, followed by opening brackets and conditions A character that corresponds to an important phrase candidate character string pattern when a character string that corresponds to the important phrase candidate character string pattern indicated by key phrase candidate character string pattern information in information and a closing parenthesis are consecutively included in this order. A string may be extracted as an important phrase candidate. If the character string corresponding to the key phrase candidate character string pattern is a plurality of words separated by colons ":", the key phrase extraction unit 2051, for example, extracts each of the plurality of words as an important phrase candidate. can be extracted as

The important phrase extraction unit 2051 extracts, for example, a character string that includes a character string extracted as an important phrase in a claim of an invention document at the end of a word, and extracts it into the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information. If the corresponding character string exists in the key phrase extraction range in the specification of the invention document, the character string corresponding to the key phrase candidate character string pattern can also be extracted as a key phrase candidate. good.

For example, the important phrase extraction unit 2051 extracts a character string that corresponds to the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information in the extraction range of the important phrase in the specification of the invention document. If there is a character string corresponding to the specific particle character string pattern indicated by the specific particle character string pattern information in the condition information, the same character string as the character string corresponding to the key phrase candidate character string pattern is selected as the key phrase. Extract as a candidate. Note that, for example, the important phrase extraction unit 2051 extracts a string following the key phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information in the extraction range of the important phrase in the specification. Then, there is a predetermined character string (for example, “each”, “no each”, etc.), and the predetermined character string is followed by the specific particle character string pattern indicated by the specific particle character string pattern information in the condition information. If a corresponding character string exists, the same character string as the character string corresponding to the key phrase candidate character string pattern may be extracted as an important phrase candidate.

The important phrase extraction unit 2051 detects, for example, that a character string corresponding to the important phrase candidate character string pattern indicated by the important phrase candidate character string pattern information in the condition information exists in the extraction range of the important phrase in the specification of the invention document. In this case, a character string corresponding to the key phrase candidate character string pattern may be extracted as an important phrase candidate. In addition, characters extracted as key phrases simply because they correspond to key phrase candidate character string patterns without satisfying additional conditions such as being preceded by character strings that correspond to coded character strings or specific particle character string patterns As for the string, the analysis unit 205 can determine the importance of the key phrase, which is the character string, to be relatively low under certain conditions related to, for example, the number of descriptions of the key phrase in the invention document.

[3-1-5-1-3. Management of extracted key phrases]
The analysis unit 205 manages each key phrase extracted by the key phrase extraction unit 2051 using key phrase management information.

FIG. 18 shows an example of key phrase management information.

The key phrase management information shown in the example of FIG. 18 is information in which each key phrase extracted by the key phrase extraction unit 2051 is associated with identification information, importance, attribute information, a translation word candidate set, and a corresponding translation word. . Each item of the important phrase management information shown in the example of FIG. 18 will be described below.

The key phrase identification information is, for example, an identification code such as a number determined to be different for each of a plurality of key phrases having different contents (that is, character strings). More specifically, the key phrase identification information includes, for example, an identification sign that distinguishes key phrases extracted from the claims of the invention document and key phrases that are not extracted from the claims of the invention document, and the same identification sign. It is an identification code including a serial number for important phrases. The key phrases extracted from the claims of the invention document can also be extracted from the specification of the invention document, and are hereinafter also referred to as the key phrases of the claims. Further, important words and phrases that are not extracted from the claims of the invention document are extracted from the specification although they are not extracted from the claims of the invention document, and are hereinafter also referred to as key words and phrases of the specification. If the number of key words and phrases of claims whose content differs from each other exceeds a predetermined number (for example, 500), the analysis unit 205 selects important words and phrases of claims that do not exceed a predetermined number based on the priority of the key words and phrases. A different identification code (for example, one of "A1" to "A500") is defined for each key phrase, and each key phrase exceeding a predetermined number is not distinguished from each other, and each key phrase has One predetermined identification code (for example, "A999") is defined. Similarly, when the number of key words in the description whose contents differ from each other exceeds a predetermined number, the analysis unit 205 determines whether the number of key words in the description does not exceed the predetermined number based on the priority of the key words. A different identification code (for example, "B1" to "B500") is assigned to each of the key phrases, and key phrases exceeding a predetermined number are not distinguished from each other, and each key phrase has a predetermined 1 code. A single identification code (for example, “B999”) is defined. The priority of important phrases is determined, for example, based on the degree of importance or attribute information (for example, first appearance number) of the important phrases, and the identification code of the important phrases includes serial numbers in order according to the priority. The analysis unit 205 can employ, for example, a serial number determined in ascending order of the first appearance number of the important phrase as the serial number part in the identification code for the important phrase extracted by the important phrase extraction unit 2051 .

The importance of the key phrase is determined by the importance determination section 2055 of the analysis section 205 .

The attribute information of the key phrase is determined by the attribute identification unit 2056 of the analysis unit 205. FIG.

The translation word candidate set of key words is, for example, a set of words that are candidates for corresponding translation words, which are words in which the key words are translated into a predetermined translation target language, and is determined by the translation unit 2054 of the analysis unit 205 .

The corresponding translated word of the key phrase is, for example, a phrase selected by the user of the invention document analysis system 20 from among the candidate translation word set of the key phrase.

Each key phrase extracted from the invention document by the key phrase extraction unit 2051 is used in various processes in the invention document analysis system 20 by referring to, for example, the key phrase management information. For example, the invention document analysis system 20 outputs patent application related information including information about each key phrase extracted from the invention document. The analysis unit 205 converts various types of information included in the patent application related information to be output by the output unit 208 into a translation unit 2054, an inter-element relationship determination unit 2058, a warning information generation unit 2059, a claim information generation unit 205a, a specification It is generated by the document information generation unit 205b, the claim tree generation unit 205c, and the like.

[3-1-5-2. Attribute identification part]
The attribute identification unit 2056 identifies the attribute of each key phrase extracted from the invention document by the key phrase extraction unit 2051 . The attribute identification unit 2056 updates the attribute information of the key phrase management information held by the analysis unit 205 so as to reflect the attribute specified for each key phrase, for example. The attribute identification unit 2056 updates each item corresponding to the various attributes of the attribute information of the important phrase management information, for example, by identifying various attributes of the important phrase. Each part of the analysis unit 205 can use the attribute information of each key phrase extracted from the invention document, for example, by referring to the attribute information of the key phrase management information.

FIG. 19 shows an example of items of attribute information of important phrases in the important phrase management information. The attribute information of key phrases illustrated in FIG. item of whether or not to express", item of "sign", item of "number of uses in the whole invention document, claim part, specification part and invention embodiment part" item, "whether or not it is used as a subject" item, " Structural inclusive relationship between elements represented by key words and elements represented by other key words" item, item "whether or not there is a technical term-specific ending character string", item "whether the word is included in the key word setting dictionary item "whether or not", item "number of characters in important phrase", and item "whether or not it is a low-key phrase and whether or not it contains a low-key word ending character string".

Each item of the attribute information of the important phrase illustrated in FIG. 19 will be described below. This attribute information is defined for each key phrase extracted from the invention document by the key phrase extraction unit 2051, and each item indicates one of the attributes of the corresponding key phrase. The attribute specifying unit 2056 performs processing such as retrieving description parts related to the key phrase from the invention document for each key phrase, thereby obtaining each attribute of the key phrase, that is, each of the attribute information of the key phrase. Identifies the content of the item.

The item "first appearance line number" as one attribute of the key phrase indicates the number of the first line in which the key phrase is described in the invention document among the serial numbers determined for each line of the invention document in the order of description. As another example, the item "First appearance number" indicates the number of the first line in which the key phrase is stated in the claim of the invention document, and when the key phrase is not stated in the claim, The key phrase may indicate the number of the first line described in the specification of the invention document.

The item of "first appearance claim number" as an attribute of a key phrase indicates the number of the first claim (for example, the claim number) of the claims of the invention document in which the key phrase is described, If the word is not stated in the claims of the invention document, for example, a number other than the claim number (eg, 0) is indicated. Here, the explanation will be continued assuming that the "first appearance claim number" as one attribute of the key phrase is 0 when the key phrase is not described in the claim of the invention document. As a result, it is possible to identify whether or not the key phrase is the key phrase of the claim (that is, whether or not it is described in the claim) based on the contents of the item "first-appearing claim number". A key phrase of a claim (ie, a key phrase in a claim) may be a phrase of relatively higher importance than a key phrase of a specification (ie, a key phrase that is not in a claim). In addition, there is a slight possibility that a relatively small key word with a relatively small item number other than 0 in the first item of a claim in which the key word is described may be a word that indicates a relatively high-level item in terms of concept.

The item of "definition claim number set and reference claim number set" as one attribute of the key phrase indicates a set whose elements are the claim numbers of the claims of the invention document in which the key phrase is described. The reference claim number set consists of the reference character string (for example, a character string corresponding to the reference character string pattern indicated by the reference character string pattern information in the condition information) followed by the claim number of the claim section containing the description of the key phrase. A set of elements. A defined claim number set is a set whose elements are the paragraph numbers of the claim paragraphs that contain the statement of the key phrase that is not followed by the reference string. If the number of elements in the referenced claim number set for a key phrase is 0, then the key phrase may be a phrase that is not listed following the reference string in the claim.

The item "whether or not it represents the claimed element of the claim" as one attribute of the key phrase is information indicating whether the element represented by the key phrase is the claimed element in any one of the claims. is.

The item of "code" as one attribute of the key phrase indicates the code when there is a description with a code added to the key phrase in the invention document. Plural codes may be used. If no description with a sign added to the key phrase in the invention document is found, it means that there is no sign. If the item of "sign" is represented by a character string as an example, the content of the item of "sign" is, for example, if there is a description with a sign added to the important phrase, the description of the sign itself , and if a description with a code attached to the important phrase cannot be detected, the character string is made up of only null characters. Also, for example, if the item "sign" is represented by a set of character strings of the sign as an example, if the description with the sign added to the important phrase cannot be detected, the item "sign" The number of elements in the set of character strings that are the contents of is 0, and if there is a code corresponding to the key phrase, the number of elements in the set of character strings that are the contents of the "Code" item is 1 or more . As a result, it is possible to identify whether or not there is a code corresponding to the key phrase based on the content of the item "Code". An important phrase written with a code added in an invention document may be a phrase of relatively higher importance than an unwritten important phrase with a code added. The item of "sign" as an attribute of the key phrase further indicates the sign if there is a description with a sign added to the key phrase in the specification of the invention document, and furthermore, in the specification of the invention document , when the key words are mixed with a description with a code and a description with no code, the mixture may be indicated. For each key phrase extracted by the key phrase extraction unit 2051, the attribute specifying unit 2056 searches the invention document or the specification of the invention document for a portion where the key phrase is described, and By determining whether or not a sign follows an important phrase in a portion, the content of the item of "sign" as one attribute of the important phrase can be specified.

The item "Number of key words used in the entire invention document, the claim part, the specification part, and the invention embodiment part" as an attribute indicates the number of times the key word is described in the entire invention document, The number of times the word is described, the number of times the key word is described in the specification of the invention document, and the number of times the key word is described in the "Mode for Carrying Out the Invention" of the specification of the invention document are shown. The attribute identification unit 2056 identifies the content of this item by counting the number of times each key phrase is described. An important phrase that is relatively frequently described may be of high importance.

The item "whether or not it is used as a subject" as an attribute of a key phrase includes, for example, a description in which the key phrase is used as a subject in the invention document or in the specification of the invention document. indicates whether or not For example, when the attribute identification unit 2056 detects that an invention document or the like includes a description in which the key word is placed immediately before the character "ha", the key word is used as the subject. It is determined that the description is included. This determination result is shown as the content of the item "whether or not the word is used as a subject". Note that the attribute specifying section 2056 includes, for example, a description in which the key phrase is placed immediately before the character "ha", and the character "ha" is determined to be a particle by morphological analysis. It may be determined that the description using the key phrase as the subject is included only when the key phrase is used as the subject. For example, the attribute specifying unit 2056 may be configured so that, for example, in an invention document or the like, the key words are separated by a predetermined character string (for example, "each", "each of", "each", etc.). Even when it is detected that a description placed before a character is included, it may be determined that a description using that key phrase as a subject is included. In addition, the character "wa" written after the subject shown here may be a predetermined particle (for example, "ga", "mo", etc.) or a predetermined continuous particle (for example, "towa", " A predetermined character string that can follow a phrase corresponding to a subject, such as "wa", "de", etc., may be treated in the same way as the character "wa". In this case, one important phrase indicated by the important phrase candidate character string pattern information of the condition information precedes the predetermined character string that can follow the phrase corresponding to the subject treated in the same way as the character "wa". When a character string corresponding to the candidate character string pattern is described in the invention document, the character string corresponding to the important phrase candidate character string pattern is extracted as an important phrase candidate by the important phrase extraction unit 2051. good. Important words and phrases that have the content attribute indicating that the item "use as subject" is used as a subject are assumed to be words and phrases to which some kind of descriptive description has been added to the words and phrases in the invention document. Therefore, it can mean that the phrase is likely to have relatively high importance.

The item "structural inclusion relationship between an element represented by a key phrase and an element represented by another key phrase" as an attribute of a key phrase is, for example, an invention document in which the element represented by the key phrase is When the elements represented by each of the above key words are structurally included, a set of key words representing the elements on the included side, and the elements represented by the key words in the invention document are one or more other Shows a set of important words and phrases representing the containing element when they are structurally included in the element represented by each of the important words and phrases. If the number of elements in each set is 0, it indicates that the element represented by the key phrase has no structural relationship with the elements represented by one or more other key phrases. This item can be used for outputting information to facilitate the user of the invention document analysis system 20 to grasp the relationship between key words.

Items as one attribute of the attribute information of the key phrase specified by the attribute specifying unit 2056 are not limited to those described above. , ``one or more'', ``one'', etc., to which a character string representing a number is added, a set whose elements are character strings representing numbers from each description An item related to "number", which indicates a set of numbers, may be included as one attribute. In addition, the attribute information is, for example, an item indicating the category of key phrases (for example, indicating which of a plurality of types such as product, method, program, etc. the key phrase belongs to), which is determined in accordance with the category division criteria information in the setting information. item) may be included as an attribute.

The attribute identification unit 2056 causes the inter-element relation determination unit 2058 to execute inclusion relation determination processing, thereby determining the compositional inclusion relation existing between the elements represented by each of the key words and phrases as described in each line of the invention document. Determine based on. Not only can there be structural inclusion relationships between elements represented by multiple important terms classified as products, may have a compositional containment relationship. For example, the "control method" as an element of the method represented by the key phrase may include "first control procedure", "second control procedure", etc. as elements of the method represented by the key phrase. good too.

Then, the attribute specifying unit 2056 determines, for each important phrase, a set of important phrases related to the inclusion side as one attribute of the important phrase, Then, a set of important phrases on the including side is specified.

The item "whether or not it has a technical term-specific ending string" as an attribute of the key phrase includes a technical term-specific ending string that includes a predetermined technical term-specific ending. Indicates whether it is a string or not. The attribute identification unit 2056 identifies the content of this item by searching for a predetermined technical term-specific character string from the important phrase. The technical term-specific ending character string can be indicated by technical term-specific ending information in the setting information acquired by the setting information acquiring unit 201, for example. Assuming that technical term-specific endings are properly defined by technical term-specific endings, key phrases with technical term-specific endings are likely to have technical significance. It means to be a phrase.

The item "whether or not the key phrase is included in the key phrase setting dictionary" as one attribute of the key phrase indicates whether or not the key phrase is included in the key phrase setting dictionary acquired by the key phrase setting dictionary acquisition unit 203. indicate. The attribute identification unit 2056 identifies the content of this item by searching for the key phrase from the key phrase setting dictionary acquired by the key phrase setting dictionary acquisition unit 203, for example. There is a possibility that the accuracy of extraction of important phrases in the invention document analysis system 20 is not necessarily high. When the content of the item "whether included in the key phrase set dictionary" of the key phrase indicates that it is included in the key phrase set dictionary, the key phrase is a phrase that does not need to be newly registered in the key phrase set dictionary. , and it means that the phrase has a good chance of being relatively important.

The item "Number of characters of key phrase" as one attribute of the key phrase indicates the number of characters of the key phrase. For example, if a word or phrase that does not follow the reference character string and is not marked with a sign and has one character is extracted as an important phrase, the important phrase will not follow the reference character string. It may be less important than key phrases with two or more characters that are unsigned and unsigned. Also, for example, if a word or phrase that does not follow the reference character string and is not marked with a sign and has two letters is extracted as an important word or phrase, the important word or phrase is added to the reference character string. It may be less important than key phrases with 3 or more characters that are not followed and have no sign added.

The item "whether or not it is a low-key phrase and whether or not it contains a low-key ending character string" as one attribute of a key phrase indicates that the key phrase is a predetermined low-key phrase (for example, "morphology"). , “strength”, etc.), and whether the word includes a predetermined low-importance ending character string at the end of the word. If the content of this item indicates that the important phrase is the same as a low-important phrase or a phrase that includes a low-important ending character string, the importance of the important phrase is relative. is likely to be low.

[3-1-5-3. Importance determination section]
The importance determining section 2055 determines the importance of each important phrase extracted from the invention document by the important phrase extracting section 2051 . The importance determining unit 2055 determines the importance of each important phrase extracted from the claim part and the specification part of the invention document, for example, based on the attribute information of the important phrase specified by the attribute specifying unit 2056. . The importance determining unit 2055 may, for example, determine a relatively high degree of importance of important words and phrases representing elements of claims, or may set the importance of important words and phrases that are used as subjects in invention documents. may be determined to be relatively high, or the importance of an important phrase that is the same as a predetermined low-important phrase or that includes a predetermined low-important ending character string may be determined to be relatively low. The importance level determination unit 2055 may determine a relatively low level of importance for an important word/phrase that is extracted simply because it corresponds to an important word/phrase candidate character string pattern.

The importance determination unit 2055 updates the important phrase management information held by the analysis unit 205 so as to reflect the importance determined for each important phrase, for example.

Hereinafter, as an example of determining the importance of each key phrase by the importance determining unit 2055, the key phrase of the claim (that is, the important phrase described in the claim) and the important phrase of the specification (that is, not described in the claim) An example of determining the importance of each key phrase by distinguishing it from the key phrase described in the specification will be described. Here, it is assumed that the larger the importance value, the higher the importance.

[3-1-5-3-1. Determining the Importance of Key Phrases in Claims]
For each important phrase extracted by the important phrase extraction unit 2051 from the claim of the invention document, the importance determination unit 2055 first sets a first predetermined value (for example, "3") as an initial value of importance. Then, the importance determining unit 2055 increases or decreases the value of the set importance of each important phrase based on the attribute information of the important phrase. When the importance determining unit 2055 increases or decreases the importance of the important phrase of the claim, an upper limit (eg 5) and a lower limit (eg 0) may be set in advance.

For example, when the content of the item "first-appearance claim number" as one attribute of the important phrase is smaller than a constant value (for example, 5) other than 0, the importance determining unit 2055 Increase the importance value by 1. This constant value may be a variable value, such as, for example, half of the total number of claims. Also, the amount by which the value of importance is increased for each of a plurality of different constant values may be made different, for example, such that the smaller the constant value, the greater the amount.

For example, when the number of elements of the reference claim number set in the content of the item "definition claim number set and reference claim number set" as one attribute of the important phrase is 1 or more, the importance determination unit 2055 Increment the preset importance value for the phrase by one.

For example, when the content of the item "whether used as a subject" as one attribute of an important phrase indicates that it is used as a subject, the importance determining unit 2055 Increase the importance value by 1.

For example, if the content of the item "whether or not there is a technical term-specific ending string" as one attribute of the important phrase indicates that it has a technical term-specific ending string, the importance determining unit 2055 Increase the preset importance value for key phrases by one.

For example, when the content of the item "whether or not the word is included in the important phrase setting dictionary" as one attribute of the important phrase indicates that the phrase is included in the important phrase setting dictionary, the importance determining unit 2055 , increments the preset importance value for that keyword by one.

It should be noted that the amount by which the importance determination unit 2055 increases the value of the set importance of the important phrase corresponding to the item of the attribute information of the important phrase does not need to be unified to 1. Different amounts are possible.

The importance determining unit 2055 may decrease the set importance of the important phrase by a predetermined amount corresponding to the item of the attribute information of the important phrase.

For example, the importance determining unit 2055 determines whether the content of the item "whether it is a low-important phrase and whether it includes a low-importance ending character string" as one attribute of the important phrase is a low-importance phrase or a low-importance phrase. If it indicates that a word ending character string is included, the preset importance value for the important phrase is decreased by one.

The importance as a final result of the importance determination unit 2055 updating (for example, increasing or decreasing) the importance according to several items of the attribute information of the important phrase as described above, for example, is the importance of the important phrase. is determined as the importance of

[3-1-5-3-2. Determining the Importance of Key Terms in the Specification Not in Claims]
Of the important phrases extracted by the important phrase extraction unit 2051 from the specification of the invention document, for the important phrases not described in the claims, the importance determination unit 2055 first determines the second predetermined value as the initial value of the importance. (for example, "1"). The second predetermined value is, for example, a value equal to or less than the first predetermined value as the initial value of the degree of importance of the key words in the claims. Then, the importance determining unit 2055 increases or decreases the value of the set importance of each important phrase based on the attribute information of the important phrase. When the importance determining unit 2055 increases or decreases the value of the importance of the key words in the specification, for example, the upper limit (for example, 4) and the lower limit (for example, 0), which can be different from the key words in the claims, are set. It may be determined in advance.

For example, when the content of the item "code" as one attribute of the important phrase indicates that there is a code corresponding to the important phrase, the importance determination unit 2055 Increase the importance value by 1.

For example, when the content of the item "whether used as a subject" as one attribute of an important phrase indicates that it is used as a subject, the importance determining unit 2055 Increase the importance value by one.

For example, if the content of the item "whether or not there is a technical term-specific ending character string" as one attribute of the important phrase indicates that it has a technical term-specific ending character string, the importance determining unit 2055 Increase the preset importance value for key phrases by one.

For example, when the content of the item "whether or not the word is included in the important phrase setting dictionary" as one attribute of the important phrase indicates that the word is included in the important phrase setting dictionary, the importance determining unit 2055 , increments the preset importance value for that keyword by one.

For example, the importance determination unit 2055 determines, for example, the description of the invention document as the content of the item "the number of uses in the entire invention document, the claim part, the description part, and the invention embodiment part" as one attribute of the important phrase. If the number of mentions of the key phrase in the "Mode for Carrying out the Invention" of the document indicates that it is more than a predetermined value (e.g., "2"), the set importance value for the key phrase is incremented by 1.

For example, when the content of the item "number of characters in key phrase" as one attribute of the key phrase indicates that it is greater than a predetermined value (for example, "2"), the importance determining unit 2055 increases the value of the configured importance of .

For example, the importance determining unit 2055 determines whether the content of the item “whether it is a low-important phrase and whether it includes a low-importance ending character string” as one attribute of the important phrase is a low-importance phrase or a low-importance phrase. If it indicates that a word ending character string is included, the preset importance value for the important phrase is decreased by one. For example, the importance determining unit 2055 determines whether the content of the item "whether it is a low-key phrase and whether it includes a low-key ending character string" as one attribute of the key phrase is a low-key phrase, or In the case of indicating that a low important ending character string is included, the set importance value of the important phrase may be updated to "0".

The importance as a final result of the importance determination unit 2055 updating (for example, increasing or decreasing) the importance according to several items of the attribute information of the important phrase as described above, for example, is the importance of the important phrase. is determined as the importance of

[3-1-5-3-3. Update the importance determined for key words]
For example, the importance determination unit 2055 may make a final determination by further updating the once-determined importance of each important phrase.

An example of further updating of once determined importance by the importance determining unit 2055 will be described below.

After once determining the importance of each key phrase, the importance determining unit 2055 determines the importance of the key phrase related to the inclusive element in relation to the structural inclusion relationship between the elements represented by each key phrase. , is further updated so that it is equal to or greater than the highest importance value among the importance levels for each key phrase related to all included elements contained in the element represented by the key phrase. do. The structural inclusion relationship between elements is determined by the inclusion relationship determination processing of the element relationship determination unit 2058 .

In this example, for example, an element represented by the key word "sensor" whose importance is once determined to be "4" and an element represented by the key word "operation reception unit" whose importance is once determined to be "2" When the importance level of the important phrase "input part" representing an element that structurally includes the two elements of is once determined to be "2", the importance level determination unit 2055 The degree will be updated from "2" to "4". As a result, the importance of the important phrase once determined to have the highest importance among the important phrases related to the included element group between the elements having the structural inclusion relationship is finally transferred to the containing element. It will be propagated to the importance of the important phrase related to.

[3-1-5-4. Inter-element relationship determination unit]
The inter-element relation determination unit 2058 performs inter-element relation determination processing for determining the relation between elements represented by each of the key phrases extracted by the key phrase extraction unit 2051 from the invention document. The inter-element relationship determination unit 2058 generates important phrase relationship information indicating the determination result of the relationship between elements represented by each of the important phrases. Upon receiving the determination result by the inter-element relation determination unit 2058, the attribute identification unit 2056 identifies attribute information for each important phrase related to the determination result.

[3-1-5-4-1. Discrimination of Multiple Elements Having Compositional Inclusion Relationship]
The inter-element relationship determination unit 2058 executes inclusion relationship determination processing for determining whether or not the elements represented by the key phrases extracted from the invention document by the key phrase extraction unit 2051 have structural inclusion relationships. Based on the result of the inclusion relationship determination processing by the inter-element relationship determination unit 2058, the attribute identification unit 2056 determines “structural inclusion of the element represented by the key phrase and the element represented by another key phrase” as one attribute of the key phrase. Identifies the content of the "Relationships" item.

Inclusion relationship determination processing by the inter-element relationship determination unit 2058 includes, for example, a description corresponding to a predetermined inclusion description pattern indicating that an element represented by one key phrase includes an element represented by another key phrase from the invention document. It is realized by searching. The predetermined inclusion description pattern may be included in the setting information acquired by the setting information acquisition unit 201 .

As an example of a description corresponding to a predetermined inclusion description pattern, in a sentence in which one key phrase precedes the case particle "ha" as a subject, another key phrase is a predetermined inclusion description character indicating inclusion A statement such that it immediately precedes a string (e.g., "comprises," "includes," "contains," etc.) or other key terms immediately precedes a given inclusion statement string and is present immediately after the predetermined inclusion description character string. Any string that is assumed to represent inclusion may be defined as the pre-determined inclusion description string. In addition, other key phrases in examples of descriptions corresponding to this predetermined inclusion description pattern are conjunctions in which a plurality of key phrases express parallelism or selection, predetermined particles "to" connecting elements, comma characters "," etc. may be enumerated. The predetermined inclusion description string may be a passive-like expression (e.g., "provided in", "included in", etc., for which a further predetermined inclusion description pattern is defined). may

To give a specific example, the inter-element relationship determination unit 2058 determines that the description "input unit including a sensor and an operation reception unit" in the invention document corresponds to a predetermined inclusion description pattern, so that the important phrase "input unit" is determined to include the element represented by the important phrase "sensor" and the element represented by the important phrase "operation reception unit" in terms of structure. In response to this determination result, the attribute specifying unit 2056 determines whether the item "structural inclusion relationship between elements represented by key words and elements represented by other key words" as one attribute of the key words "input part" is included. The important phrase "sensor" and the important phrase "operation reception unit" are included as elements of the set of important phrases representing the elements on the containing side.

Further, to give another specific example, the inter-element relation determination unit 2058 determines that the description in the invention document that "the information processing apparatus includes an input unit, a storage unit, a display information generation unit, and a display unit" Since it corresponds to the inclusion description pattern, the element represented by the important phrase "information processing device" is structurally composed of the element represented by the important phrase "input section", the element represented by the important phrase "storage section", and the important phrase "display information". It is determined that the element represented by the "generation part" and the element represented by the important phrase "display part" are included. In response to this determination result, the attribute specifying unit 2056, for example, selects an item of "structural inclusive relationship between elements represented by key words and elements represented by other key words" as one attribute of the key words "input part". The important phrase "information processing device" is included as an element of the set of important phrases representing the elements on the including side of . For example, the attribute specifying unit 2056 is included on the item of "structural inclusion relationship between an element represented by a key term and an element represented by another key term" as one attribute of the key term "information processing apparatus". As the elements of the set of important phrases representing the elements of , the important phrase "input section", the important phrase "storage section", the important phrase "display information generating section" and the important phrase "display section" are included.

In the inclusion relationship determination process, the inter-element relationship determination unit 2058 determines the purpose of verbs (e.g., "detect", "accept", etc.) other than the predetermined inclusion description character string representing the inclusion relationship in each line of the invention document. Words may be excluded from the search range for statements that fall within a predetermined inclusion statement pattern. That is, in each line of the invention document, the inter-element relation determination unit 2058 removes the search start portion of the line to the verb portion corresponding to the character string other than the predetermined inclusion description character string, and extracts one key phrase from the remaining portion. Description corresponding to a predetermined inclusion description pattern indicating that the represented element includes the element represented by another key phrase (for example, another key phrase exists immediately before a predetermined inclusion description character string, and one key phrase is By searching for a description that exists immediately after the predetermined inclusion description character string, the inclusion relationship between elements represented by multiple important phrases may be determined. As a result, the inter-element relationship determining unit 2058 can, for example, determine the "speech", " Even if "user", "operation", etc. are key phrases, they are excluded. It can be determined that the element represented by " is included.

For example, the inter-element relationship determination unit 2058, in the inclusion relationship determination processing performed on the description of the claim of the invention document, when the subject is not described prior to the predetermined inclusion description character string in a part of the claim , unless the subject is explicitly stated to be preceded by the case particle "wa" before that portion, the key phrase representing the claimed element in that section of the claim shall be deemed to be the subject, and the It may be determined that the element represented by the subject includes the element represented by the important phrase immediately preceding the predetermined inclusion description character string. Further, the inter-element relationship determination unit 2058 performs, for example, in the inclusion relationship determination processing for the description of the claim of the invention document, if the subject is described in a part of the claim prior to the predetermined inclusion description character string. In the case where there is no such part, if the subject preceding the case particle "wa" is specified before the part, the element represented by the subject includes the element represented by the important phrase immediately before the specified inclusion description string. It can be determined that there is

[3-1-5-4-2. Discrimination of a plurality of elements in relation to the recording medium and the contents of the recording medium]
The inter-element relationship determination unit 2058 performs recording relationship determination for determining whether, for example, the elements represented by the key phrases extracted by the key phrase extraction unit 2051 from the invention document have a relationship between the recording medium and the contents of the recording medium. processing can be performed. Here, the recording medium may include what is called a storage medium. The attribute specifying unit 2056 adds, for example, the item “recorded content of the element represented by the key phrase” to the attribute information of the key phrase, and based on the result of the recording relationship determination processing by the inter-element relationship determination unit 2058, It is also possible to specify the contents of the item.

The record relation discriminating process by the inter-element relation discriminating unit 2058 corresponds to, for example, a predetermined recorded description pattern indicating that an element represented by one key phrase in an invention document has recorded contents of an element represented by another key phrase. It is realized by searching the description. The predetermined record description pattern may be included in the setting information acquired by the setting information acquisition unit 201 .

As an example of a description corresponding to a predetermined record description pattern, in a sentence in which one key phrase precedes the case particle "ha" as a subject, another key phrase is a predetermined record description character string (for example, "record ”, “stores”, “stores”, etc.), or other important words and phrases exist immediately before a predetermined record description character string, Examples include a description in which a key phrase exists immediately after the predetermined record description character string. Any character string that is assumed to indicate that information, data, or the like is recorded or stored may be defined as the predetermined record description character string. In addition, other important words and phrases in examples of descriptions corresponding to this predetermined record description pattern are conjunctions in which a plurality of important words and phrases express parallelism or selection, predetermined particles "to" connecting elements, comma characters "," etc. may be enumerated. The predetermined record entry string may be a passive-like expression (e.g., "recorded in", "stored in", etc.) corresponding to which further predetermined record entry pattern is may be defined.

To give a specific example, the inter-element relation determination unit 2058 determines that the description "recording device for recording a setting file" in the invention document corresponds to a predetermined recording description pattern, so that the element represented by the important phrase "setting file" is the recorded content of the recording medium represented by the important phrase "recording device". In response to this determination result, the attribute specifying unit 2056 includes, for example, the important phrase "setting file" as the content of the item "recorded content of the element represented by the important phrase" as one attribute of the important phrase "recording device". .

Further, to give another specific example, the inter-element relation determination unit 2058 determines that the description "the memory stores the operation image, the operation information, and the device control information" in the invention document is a predetermined Since it corresponds to the record description pattern, the element represented by the key phrase "memory" is divided into the element represented by the key word "operation image", the element represented by the key word "operation information", and the element represented by the key word "device control information". is the recorded content. In response to this determination result, the attribute specifying unit 2056, for example, sets the key word "operation image" as the content of the item "recorded content of the element represented by the key word" as one attribute of the key word "memory". The important phrase "operation information" and the important phrase "equipment control information" are included.

In the record relationship determination process, the inter-element relationship determiner 2058 extracts objects of verbs other than predetermined record description character strings in each line of the invention document from the search target range of descriptions corresponding to the predetermined record description pattern. may be excluded. That is, in each line of the invention document, the inter-element relation determination unit 2058 removes the search start portion of the line to the verb portion corresponding to the character string other than the predetermined record description character string, and extracts one key phrase from the remaining portion. A description corresponding to a predetermined record description pattern indicating that the element represented by another key phrase is the record content (for example, another key phrase exists immediately before a predetermined record description character string, By searching for a description in which a word/phrase exists immediately after the predetermined record description character string, it is determined that the elements represented by each of the plurality of important words/phrases have a relationship between the recording medium and the contents of the recording medium. You may

[3-1-5-4-3. Determination of multiple elements in relationship between program and its implementation]
The inter-element relationship determination unit 2058 performs program realization relationship determination for determining whether, for example, the elements represented by the key phrases extracted from the invention document by the key phrase extraction unit 2051 have a relationship between the program and the implementation content of the program. processing can be performed. The attribute specifying unit 2056 adds, for example, the item "implementation content of the element represented by the key phrase" to the attribute information of the key phrase, and based on the result of the program realization relationship determination processing by the inter-element relationship determination unit 2058, The content of the item may be specified.

The program realization relationship determination processing by the inter-element relationship determination unit 2058 is performed, for example, by extracting from the invention document one important phrase (for example, all or endings such as “program”, “routine”, “software”, etc.) that substantially indicates a program. The elements represented by the elements expressed by other important words (for example, words ending with "method", "process", "means", "function") indicating methods, processes, functions, etc. This is realized by searching for a description corresponding to a predetermined program description pattern indicating that the The predetermined program description pattern may be included in the setting information acquired by the setting information acquisition unit 201 .

As an example of a description corresponding to a predetermined program description pattern, in a sentence in which one key phrase precedes the case particle "ha" as a subject, another key phrase is a predetermined program implementation description character string (for example, " "to realize", "to realize", "function as", etc.), or other important words and phrases that exist immediately before a given program implementation description character string, Examples include a description in which a key phrase exists immediately after the predetermined program implementation description character string. Any character string that is assumed to indicate that a function, process, etc. is to be realized or that the function, process, etc. is to be realized may be defined as the predetermined program implementation description character string. In addition, other key phrases in examples of descriptions corresponding to this predetermined program implementation description pattern are conjunctions in which a plurality of key phrases express parallelism or selection, predetermined particles connecting elements "to", comma characters ", " etc. may be enumerated. The predetermined program implementation description character string may be a passive expression (for example, "implemented by" etc.), and a further predetermined program implementation description pattern may be defined corresponding to this expression. good.

To give a specific example, the inter-element relation determination unit 2058 determines that the description "conversion program for realizing the character code conversion function" in the invention document corresponds to a predetermined program implementation description pattern, so that the important phrase "character It is determined that the element represented by "code conversion function" has a relation of the implementation contents of the program represented by the important phrase "conversion program". In response to this determination result, the attribute specifying unit 2056 specifies, for example, the key word "character code conversion function" as the content of the item "realization content of the element represented by the key word" as one attribute of the key word "conversion program". include.

Further, to give another specific example, the inter-element relation determination unit 2058 determines that the description "The conversion routine causes the computer to function as character code conversion means" in the invention document corresponds to a predetermined program implementation description pattern. Therefore, it is determined that the element represented by the important phrase "conversion routine" has the element represented by the important phrase "character code conversion means" as the actual content. In response to this determination result, the attribute specifying unit 2056 selects, for example, the key word "character code conversion means" as the content of the item "implementation content of the element represented by the key word" as one attribute of the key word "conversion routine". include.

In the program realization relationship judging process, the inter-element relation judging section 2058 finds the object of the verb corresponding to each line of the invention document other than the predetermined program realization description character string representing that the function, process, etc. are realized by the program. , may be excluded from the search target range for descriptions corresponding to a predetermined program implementation description pattern. That is, in each line of the invention document, the inter-element relation determination unit 2058 removes the search start portion of the line up to the verb portion corresponding to the character string other than the predetermined program implementation description character string, and extracts one important phrase from the remaining portion. A description corresponding to a predetermined program implementation description pattern indicating that the element represented by is for realizing the element represented by another key phrase (for example, another key phrase immediately before a predetermined program implementation description character string by searching for a description in which one important phrase exists immediately after the specified program implementation description character string), the elements represented by each of the plurality of important phrases are searched for the relationship between the program and the implementation content by the program. A determination may be made about having a relationship.

[3-1-5-4-4. Discrimination of multiple elements in equivalence relationship]
The inter-element relation determination unit 2058 can execute, for example, an equivalence determination process for determining whether there is an equivalence between elements represented by a plurality of key phrases extracted from the invention document by the key phrase extraction unit 2051 . The attribute specifying unit 2056 adds, for example, an item “an element having an equivalence relationship with the element represented by the key phrase” to the attribute information of the key phrase, and based on the result of the equivalence determination processing by the inter-element relationship determination unit 2058 It is also possible to specify the content of the item.

The equivalence determination process by the inter-element relationship determination unit 2058 is performed, for example, by searching for a predetermined key phrase in which another key phrase that is presumed to have the same meaning as the one key phrase following one key phrase from the invention document is described. is realized by searching for a description corresponding to the equivalent description pattern of . The predetermined equivalent description pattern may be included in the setting information acquired by the setting information acquisition unit 201 .

As an example of a description corresponding to a predetermined equivalent description pattern, for example, a case particle "wa" following one important phrase is followed by another important phrase, and the other important phrase is "is ".", "It is also called.", etc. followed by a character string.

Another example of a description corresponding to a predetermined equivalent description pattern is a description in which an opening parenthesis, another key phrase, and a closing parenthesis are consecutively arranged immediately after one key phrase. In this example, for example, between the opening parenthesis and the closing parenthesis, multiple key phrases separated by colons ":" may be included as other key phrases. To give a specific example, the inter-element relationship determination unit 2058 determines that the description "display device (display)" in the invention document corresponds to a predetermined equivalent description pattern, so that the element represented by the important phrase "display device" is It is determined that it has an equivalence relationship with the element represented by the key word "display". To give another specific example, the inter-element relationship determination unit 2058 determines that the description "Graphical User Interface (GUI)" in the invention document corresponds to a predetermined equivalent description pattern, so that the important phrase " It is determined that the element represented by "graphical user interface" has an equivalence relation with the elements represented by each of the important phrase "GUI" and the important phrase "Graphical User Interface". In response to the determination result in this example, the attribute specifying unit 2056 selects, for example, the important phrase "GUI" and Include the key phrase "Graphical User Interface".

[3-1-5-4-5. Discrimination of Multiple Elements in Conceptual Hierarchical Relationship]
The inter-element relation determining unit 2058 executes, for example, hierarchical concept relation determining processing for determining whether there is a conceptual hierarchical relationship between elements represented by a plurality of key phrases extracted from the invention document by the key phrase extracting unit 2051. obtain. The attribute specifying unit 2056 adds, for example, an item “lower-level conceptual element of the element represented by the key phrase” to the attribute information of the key phrase, and based on the result of the upper-lower conceptual relationship determination processing by the inter-element relationship determination unit 2058 It is also possible to specify the content of the item.

The upper-level concept relationship determination processing by the inter-element relationship determination unit 2058 is performed, for example, from the invention document, after one important phrase, other important terms that are presumed to represent a subordinate concept (for example, a specific example) of that one important phrase. This is achieved by searching for descriptions corresponding to a predetermined subordinate concept description pattern in which words are described. The predetermined lower-level concept description pattern may be included in the setting information acquired by the setting information acquisition unit 201 .

Examples of descriptions corresponding to a predetermined subordinate concept description pattern include, for example, following one important phrase, "a specific example of", "an example of", "for example", "is specifically A character string that leads to an exemplary expression such as ” is arranged, and other important phrases are described after the character string that leads to the exemplary expression, and the other important phrases express affirmation “is”, “is There is a description followed by a character string such as ". Note that the character string leading to this exemplary expression may include comma characters ",". In addition, other key phrases in examples of descriptions corresponding to this predetermined subordinate concept description pattern include conjunctions in which a plurality of key phrases express parallelism or selection, predetermined particles connecting elements "to", comma characters ", " etc. may be enumerated.

As another example of a description corresponding to a predetermined subordinate concept description pattern, an opening parenthesis, a character string representing an example such as "for example", another key phrase, and a closing parenthesis are immediately after one important phrase. Consecutively arranged descriptions are included. A character string representing an example such as "for example" may include comma characters "," at the end of a word.

To give a specific example, the inter-element relation determination unit 2058 determines that the description "an example of a display device is a liquid crystal display" in the invention document corresponds to a predetermined subordinate concept description pattern, so that the important phrase "display device" ” is determined to be the element represented by the important phrase “liquid crystal display”. In response to this determination result, the attribute specifying unit 2056, for example, sets the key phrase "liquid crystal display" as the content of the item "lower conceptual element of the element represented by the key phrase" as one attribute of the key phrase "display device". include.

[3-1-5-4-6. Generating Key Word Related Information]
The inter-element relationship determination unit 2058 is output by the output unit 208 based on the results of the inclusion relationship determination process, the recording relationship determination process, the program realization relationship determination process, the equivalent relationship determination process, or the hierarchical concept relationship determination process. Generate important word relational information included in the patent application related information.

In the invention document analysis system 20, when the output unit 208 outputs the patent application related information including the key word relationship information as a display document (for example, an HTML document), the inter-element relationship determination unit 2058 outputs to generate key word relationship information included in the patent application related information of The key phrase relationship information portion of the patent application related information as a document for display generated by the inter-element relation determining unit 2058 includes, for example, a display element corresponding to each key phrase. For example, a browser may interpret the presentation document to display each presentation element. The inter-element relation determination unit 2058 can add, for example, display control information for differentiating the display mode for each different key phrase to the display element corresponding to each key phrase.

[3-1-5-4-6-1. Generation of containment relationship information]
The inter-element relationship determination unit 2058 determines, for example, the structural relationship between the elements represented by the multiple key phrases extracted from the invention document by the key phrase extraction unit 2051 based on the results of the inclusion relationship determination processing, based on the key phrase relationship information. Contains containment information that expresses the containment relation. Any method may be used to express the compositional inclusion relationship between elements in the inclusion relationship information. FIG. 20 shows a display example of the inclusion relation information portion in the important word relation information of the patent application related information as a display document.

As a specific example, the inter-element relationship determination unit 2058 uses, as the inclusion relationship information, a plurality of terms connected by the citation relationships detected by the claim citation relationship detection unit 2057 among the respective terms of the claims of the invention document. For each configured group, based on the inclusion relationship of each key phrase stated in each clause of the claim in that group, the key phrases on the including side and the included side are connected with a line, ruled line symbol “└”, etc. Generate a description that represents the tree structure (ie, hierarchical structure) formed by . The inter-element relationship determining unit 2058 may simplify the inclusion relationship information by omitting the second and subsequent important terms so that only one important term appears in the hierarchical structure. As an example of this case, the inter-element relation determining unit 2058 may, for example, when one important phrase represented by a hierarchical structure reappears in the same hierarchy or a lower hierarchy in the hierarchical structure, the hierarchy below the reappearing important phrase The expression of is omitted. At this time, the inter-element relation determination unit 2058 may add a symbol "..." or the like to the important phrase to indicate that the re-statement of one important phrase is omitted.

For example, in the inclusion relationship information containing descriptions of a plurality of key words, the inter-element relation determination unit 2058 determines, for example, a key word that represents the claim object in any claim of the invention document, to represent the claim object in that key word. may be expressed in such a way that it can be distinguished from other key phrases by appending a symbol (for example, "*") defined in . Such inclusion relation information makes it easy to grasp the compositional inclusion relation between the elements represented by the key words and phrases claimed in the claims and other key words.

For example, the inter-element relation determination unit 2058 determines whether a certain group is described in the inclusion relation information including description of a hierarchical structure representing a plurality of important terms for each group composed of a plurality of terms linked by a citation relationship. Each key phrase may be appended with a section number indicating which section in the group the key phrase is described.

[3-1-5-4-6-2. Generation of record-related information]
The inter-element relation determination unit 2058 determines, in the key word relationship information, whether the elements represented by each of the multiple key words extracted from the invention document by the key word extraction unit 2051 based on the result of the recording relationship determination process are the recording media. Recording relationship information expressing the relationship, if any, to the content of the recording medium may be included. The expression of the relationship between the elements in the recording-related information is, for example, an expression in which important words and phrases related to the recording medium are associated with important words and phrases related to the content of the recording medium, and an expression in which the important words and phrases related to the recording medium are placed at a higher level. Any expression may be used, such as a hierarchical structure in which one or more important terms related to the content are placed at a lower level.

[3-1-5-4-6-3. Generation of program realization relationship information]
The inter-element relationship determination unit 2058 determines, in the key word relationship information, the relationship between the elements represented by each of the multiple key words extracted from the invention document by the key word extraction unit 2051 based on the results of the program realization relationship determination process. If there is a relationship with the content implemented by the program, program implementation relationship information expressing the relationship can be included. The expression of the relationship between the elements in the program realization relationship information may be any expression, such as an expression in which the program and the realization content are associated with each other.

[3-1-5-4-6-4. Generation of equivalence relationship information]
The inter-element relation determination unit 2058 determines, in the key word relation information, whether there is an equivalent relationship between elements represented by each of the multiple key words extracted from the invention document by the key word extraction unit 2051 based on the results of the equivalent relationship determination process. Equivalence relation information that expresses that relation in some cases may be included. The expression of the relationship between the elements in the equivalence relation information may be an expression made by any method, such as an expression in which key terms relating to the elements having an equivalence relation are associated with each other.

[3-1-5-4-6-5. Generation of hierarchical concept relationship information]
The inter-element relation determining unit 2058 uses the important term relation information to determine, for example, conceptually between the elements represented by the multiple key terms extracted from the invention document by the key term extracting unit 2051 based on the result of the hierarchical concept relation determining process. When there is a hierarchical relationship between the two, hierarchical concept relationship information expressing the relationship can be included. The expression of the relationship between elements in the hierarchical concept relation information is, for example, an expression in which key terms related to a plurality of conceptually hierarchical components are associated with each other, key terms related to generic concepts (for example, "elastic body") ) and one or more important words (e.g., "spring" and "rubber") related to the corresponding subordinate concept are expressed in a hierarchical structure, or any other method may be used. .

[3-1-5-5. Claim Citation Relationship Detection Unit]
The claim citation relationship detection unit 2057 executes a citation relationship analysis process for analyzing the citation relationship of each item of claims in the invention document acquired by the invention document acquisition unit 2021, and generates a citation relationship analysis process as a result of this citation relationship analysis process. Retain claim citation relationship information.

The citation relation analysis processing by the claim citation relation detection unit 2057 is performed for each claim item in the invention document, for example, the headline description of the item (for example, the line of "Claim" sandwiched between the opening square bracket and the closing square bracket. This is realized by searching for a description corresponding to a predetermined reference item number description pattern from the description contents of the part other than the description). The predetermined quoted item number description pattern may be included in the setting information acquired by the setting information acquisition unit 201 .

As an example of a description corresponding to a predetermined pattern for describing a cited claim number, for example, a character string "claim" representing a claim is followed by a cited claim number character string containing a number, and the citation A description in which a character string “description” is arranged following the preceding item number character string can be mentioned. When the claim citation relationship detection unit 2057 detects a description corresponding to a predetermined citation item number description pattern in the citation relationship analysis process, for example, the number in the citation item number character string is used as the citation item number. Extract. The claim citation relationship detection unit 2057 detects, for example, a conjunction (for example, "or") in which a plurality of numbers in the citation destination item number character string in the description corresponding to the detected predetermined citation destination item number description pattern indicates parallel or selection. , or if they are separated by delimiters (for example, ",", comma ",", etc.), each of the multiple numbers is extracted as the reference item number. In addition, the claim citation relationship detection unit 2057 detects, for example, the citation destination item number character string in the description corresponding to the detected predetermined citation destination item number description pattern, followed by the first number followed by a range expression character (for example, " ", etc.) is placed, and the range expression character is followed by a second number, all characters greater than or equal to the first number and less than or equal to the second number Extract each integer as a referenced item number. Specifically, the claim citation relationship detection unit 2057 detects the integers "1", "2", "5", " 11” is extracted as the cited claim number, and the integers “1”, “2”, and “3” are extracted based on the cited statement “described in any one of claims 1 to 3” in a certain claim. is extracted as the reference item number.

The claim citation relationship detection unit 2057 generates claim citation relationship information including information that associates each clause of a claim of an invention document with a set of citation destination clause numbers extracted for that clause in the citation relationship analysis process. , update and hold.

The claim citation relationship detection unit 2057 also performs the citation relationship analysis process for the claims of the amended claim information when the amended version claim information representing the content of the amended claim of the invention document is generated by the claim information generation unit 205a or the like. and retain the resulting modified claim citation information.

[3-1-5-6. Warning information generator]
The warning information generation unit 2059 executes warning information generation processing for generating warning information included in the patent application related information output by the output unit 208 of the invention document analysis system 20 .

The warning information generation unit 2059 performs warning information generation processing by searching for inappropriate statements contained in the invention document acquired by the invention document acquisition unit 2021, and generating one or more indications representing indications related to the detected inappropriate statements. It is realized by generating warning information including information. The inappropriate description searched by the warning information generation unit 2059 may be a potentially inappropriate description. FIG. 21 shows an example of items of warning information generated by the warning information generation unit 2059 and description items corresponding to the items.

The warning information generation unit 2059 generates warning information indicating that there is no warning when there is no indication information as the content of the warning information. Note that the warning information generation unit 2059 may omit generation of warning information when there is no indication information as the content of the warning information.

[3-1-5-6-1. Pointing out based on the Standard Provisions for Invention Documents for Translation]
The warning information generation process by the warning information generation unit 2059 is, for example, an examination of whether or not the invention document satisfies a plurality of conditions defined in the invention document standard specifications for translation acquired by the invention document standard specification acquisition unit 204 for translation. This is realized by, for example, including indication information pointing out that fact in the warning information when the condition is not satisfied.

As a specific example, the warning information generation unit 2059 generates a warning information in the invention document that corresponds to the pattern indicated by the pattern information corresponding to each condition item (see FIG. 14) defined in the invention document standard rules for translation. When an inappropriate description is searched for and the inappropriate description is detected, for example, information indicating the position where the inappropriate description is detected in the invention document, the conditional item name corresponding to the conditional item, and is included in the warning information. The information indicating the position where the inappropriate description in the invention document is detected is, for example, the line number of the line of inappropriate description among the line numbers given to each line of the invention document in line order, and the line number of each claim in the invention document. Among them, the paragraph number of the paragraph containing the inappropriate description, the paragraph number of the paragraph containing the inappropriate description among the paragraphs of the specification in the invention document, etc. may be included. The warning information generation unit 2059, for example, uses a plug-in module for performing processing for determining whether or not an invention document conforms to each of a plurality of items of the invention document standard specifications for translation, A warning information generation process may be performed.

As an example of the warning information generation process, the warning information generation unit 2059 determines that the specification of the invention document acquired by the invention document acquisition unit 2021, for example, satisfies the condition that each sentence of the specification contains a subject. When it is detected that a description that does not exist is included, indication information indicating that there is no subject and the content of the detected description is included in the warning information. As a specific example, the warning information generation unit 2059 extracts from the specification of the invention document acquired by the invention document acquisition unit 2021, the condition item of "absence of subject in each sentence of the specification" shown in FIG. A description of a sentence corresponding to a pattern indicated by pattern information for extracting an appropriate description is searched for, and when a description of a sentence corresponding to the pattern is detected, indication information is included in warning information. Although technical experts and persons other than technical experts may be able to assume an implicit subject even if there is no subject, this indication information can be useful for calling attention.

For example, when the warning information generation unit 2059 detects that the invention document acquired by the invention document acquisition unit 2021 contains descriptions that do not satisfy the condition that inappropriate predetermined descriptions are not included, causes the warning information to include indication information indicating that a potentially inappropriate description is included and the content of the detected description. As a specific example, the warning information generation unit 2059 extracts from the invention document acquired by the invention document acquisition unit 2021 the condition of "a character string presumed to be desirably removed" in the invention document standard specification for translation (see FIG. 14). Search for descriptions of character strings that correspond to the pattern indicated by the pattern information (for example, "only", "preferably", etc.) to extract inappropriate descriptions related to the item, and search for descriptions of character strings that correspond to the pattern When detected, the indication information is included in the warning information. For example, character strings such as "only" and "preferably" are not necessarily things that cannot be written, but they can be written carelessly, so this indication information can be useful for calling attention. .

The warning information generation unit 2059 satisfies, for example, the condition that an inappropriate predetermined phrase is not added to the key phrase extracted by the key phrase extraction unit 2051 to the invention document acquired by the invention document acquisition unit 2021. When it is detected that a description that is not included is included, indication information indicating that a description of an important phrase with an inappropriate predetermined phrase is included and the content of the detected description, Include in warning information. As a specific example, the warning information generation unit 2059 extracts from the claim of the invention document acquired by the invention document acquisition unit 2021, "a character string that may be desirable not to be added to the important phrase in the claim" shown in FIG. Search for descriptions of character strings that correspond to the pattern indicated by the pattern information (e.g., “desired”, “predetermined”, etc.) to extract inappropriate descriptions related to the condition items, and character strings that correspond to the pattern is detected, the indication information is included in the warning information. For example, the character string "predetermined" does not necessarily cause a problem, but it can be written carelessly, so this indication information can be useful for calling attention.

For example, the warning information generation unit 2059 does not include a description that causes a disadvantage in interpretation of rights when the invention document acquired by the invention document acquisition unit 2021 is used for acquiring rights in the United States. If it is detected that a description that does not meet the condition that it does not satisfy the condition is included, indication information that indicates that the description that causes disadvantages in terms of right interpretation is included and the content of the detected description is included in the warning information. As a specific example, the warning information generation unit 2059 extracts from the invention document acquired by the invention document acquisition unit 2021 the "character string that may be desirable to be changed to another expression in the US application" shown in FIG. Search for descriptions of character strings that correspond to the pattern indicated by the pattern information for extracting inappropriate descriptions related to condition items (for example, "the characteristics of the present invention"), and search for descriptions of character strings that correspond to the pattern When detected, the indication information is included in the warning information. For example, the phrase "features of the invention," when included in a U.S. application based on an invention document, refers to features of the claimed subject matter (e.g., features of the invention in each of all claims). This indication information can be useful for calling attention, because it can be interpreted as such as referring to

The warning information generation unit 2059, for example, gives the invention document acquired by the invention document acquisition unit 2021 information that is understood in a foreign country (that is, a country other than Japan) when the invention document is used to acquire rights in a foreign country (that is, a country other than Japan). If it is detected that the description does not meet the condition of not including words that may be translated into difficult words, it includes descriptions that may be difficult to understand in foreign countries. The warning information includes indication information indicating the fact and the content of the detected description. As a specific example, the warning information generation unit 2059 detects inappropriate descriptions related to the condition item “use of Japanese terms that are not well known in foreign countries” shown in FIG. Search for descriptions of character strings that correspond to the pattern indicated by the pattern information for extracting Include in warning information. In the pattern indicated by the pattern information for extracting inappropriate descriptions related to the conditional item of "use of terms unique to Japan that are not well known in foreign countries", the symbol "○" that has a good meaning in Japan and the symbol "○" that has a bad meaning in Japan A symbol having a meaning peculiar to Japan, such as the symbol "x", may be applicable.

For example, the warning information generating unit 2059 adds important words and phrases having a predetermined degree of importance or more (for example, importance value is 1 or more), if it is detected that it contains a description that does not satisfy the condition that it is described in the specification of the invention document, the key word is explained in the specification. The warning information includes indication information indicating that there is a possibility that there is a possibility that there is a possibility that the information is not available and the important phrase. The importance of the important phrase is determined by the importance determining section 2055 . For example, the predetermined degree may be fixed in advance or may be set in the setting information acquired by the setting information acquisition unit 201 . As a specific example, the warning information generation unit 2059 obtains from the invention document acquired by the invention document acquisition unit 2021, "Among the important words in the claim, the When a description corresponding to the pattern indicated by the pattern information for extracting inappropriate descriptions related to the condition item of "not stated in the When it is detected that it is not done), the indication information is included in the warning information.

When an inappropriate description is detected in the invention document, the warning information generation unit 2059 determines that one condition item defined in the invention document standard specification for translation, which is the basis of the detection, is inappropriate. When a condition item explanation message such as an explanation to the user is included, the indication information may include the condition item explanation message. For example, the warning information generation unit 2059 may include in the warning information version information (for example, version number) of the invention document standard specification for translation used as a basis for detecting inappropriate descriptions.

The warning information generation unit 2059 generates, for example, one or more conditions narrowed down by the setting information acquired by the setting information acquisition unit 201 or the selection operation by the user, among a plurality of conditions defined in the standard specification of invention documents for translation. Based on the results of the inspection to determine whether the conditions are met, the evaluation value of the conformity of the invention document to the standard provisions for invention documents for translation (for example, conformance rate, etc.) is determined, and the invention indicating the evaluation value Document evaluation information may be included in the warning information.

The warning information generation process by the warning information generating unit 2059 is performed, for example, instead of inspecting inappropriate descriptions in the invention document based on the standard specifications for invention documents for translation, or based on the standard specifications for invention documents for translation. In addition to doing so, it may be done based on various conditions separately defined from the Standard Provisions for Invention Documents for Translation. In this case, in the warning information generation process, the warning information generation unit 2059 checks whether or not the description in the invention document satisfies various conditions defined separately from the invention document standard specifications for translation. When one or more of the conditions are not satisfied, for example, indication information pointing out that the conditions are not satisfied, and information indicating the position where the description in the invention document where the conditions are not satisfied is detected. and may be included in the warning information.

[3-1-5-6-2. Pointing out based on various conditions stipulated separately from the Standard Provisions for Invention Documents for Translation]
An example in which the warning information generation unit 2059 points out descriptions in the invention document that do not satisfy the conditions based on various conditions defined separately from the standard rules for invention documents for translation in the warning information generation process will be described below. . Information relating to one or more of the various conditions shown here may be included in the condition items of the standard specification of invention documents for translation. An invention document containing descriptions that do not satisfy one or more of the various conditions used in the warning information generation process does not necessarily have to be inappropriate. , may be substantially or formally inappropriate, and may be defined for the purpose of calling attention to the user.

For example, the warning information generation unit 2059 determines whether each heading (for example, a description with an opening square bracket and a closing square bracket added, etc.) is correct in the specification of the invention document acquired by the invention document acquisition unit 2021. When it is detected that a description that does not satisfy the condition that there is a certain condition is included, information indicating the position of the description and indication information indicating that the condition is not satisfied are included in the warning information. . A list of appropriate heading character strings in the specification of the invention document can be defined in advance based on laws and regulations, for example. Descriptions related to inappropriate headings in the book can be detected. The list of appropriate heading character strings is, for example, a list of character strings such as "title of the invention" and "technical field". It should be noted that since serial numbers may be added to the endings of character strings in some headings, the warning information generation unit 2059 further adds characters to which serial numbers may be added to the endings in order to detect descriptions related to inappropriate headings. A list of columns (eg, "Patent Documents", "Examples", etc.) may be used.

For example, when the warning information generation unit 2059 detects that the invention document acquired by the invention document acquisition unit 2021 contains a description that does not satisfy the condition that no blank line is included, the description The warning information includes information indicating the position of and pointing information indicating that the condition is not satisfied. A blank line is, for example, a line containing only a line feed code. For example, a line that does not contain characters other than half-width or full-width blank characters may be regarded as a blank line. By specifying descriptions that are regarded as blank lines in the setting information, and the warning information generation unit 2059 refers to the description regarding descriptions that are regarded as blank lines in the setting information acquired by the setting information acquisition unit 201, Empty lines may be recognized.

For example, when the warning information generation unit 2059 detects that the invention document acquired by the invention document acquisition unit 2021 includes a description that does not satisfy the condition that character strings that are registered trademarks are not included, causes the warning information to include information indicating the position of the description and pointing information indicating that the condition is not satisfied. Since the list of character strings of registered trademarks can be defined, the warning information generation unit 2059 refers to the list of character strings of registered trademarks to identify descriptions that include character strings of registered trademarks in the invention document. detectable. In addition, the warning information generation unit 2059 accesses predetermined websites, databases, etc. that provide information on multiple registered trademarks on the Internet, and collects character strings of multiple registered trademarks via the network. , a list of registered trademark character strings may be generated and used for the warning information generation process. An example of a description that does not satisfy the condition that a character string that is a registered trademark is not included is a description of a character string that is a registered trademark. In addition, the warning information generation unit 2059 includes a character string that clearly indicates a registered trademark such as “(registered trademark)” immediately after the character string that is a registered trademark in the description of the character string that is a registered trademark. Only descriptions of character strings that are registered trademarks that are not included may be treated as descriptions that do not satisfy the condition of not including character strings that are registered trademarks.

The warning information generation unit 2059 determines that, for example, the invention document acquired by the invention document acquisition unit 2021 includes a description that does not satisfy the condition that the same element name is described immediately before the same code. When this is detected, the warning information includes pointing information indicating the same code and the element names of a plurality of different expressions to which the code is added. Note that, for example, when the warning information generation unit 2059 detects a description in which a plurality of element names with different expressions are assigned the same reference numerals in the invention document, one element name The indication information may be expressed so that it is possible to identify whether or not the character string of another element name is included at the end of the character string. As a specific example, the description of the invention document includes the statement "The first device 101 and the second device 102 are...", and furthermore, "The device 102 is... 101 is...", the pointing information includes, for example, information such as "same sign different representation information → 101: first device, third device" and "same sign different representation information → 102: device (second device)”.

For example, the warning information generating unit 2059 generates descriptions that do not satisfy the condition that element names for which codes are defined in the specification of the invention document acquired by the invention document acquisition unit 2021 are written with the codes added. is detected, the element name and its code are included, and it is pointed out that the description with the code added to the element name and the description without the code are mixed. Include information in the warning information. As a specific example, if the description of the invention document includes both the description "liquid crystal display 301" and the description "liquid crystal display" without "301" added, the warning information generation unit 2059 Warning information includes indication information pointing out that the description of the invention document contains a mixture of the description "liquid crystal display 301" with a code added to the element name and the description without a code added to "liquid crystal display". Let

For example, the warning information generation unit 2059 adds the code used in the drawing document acquired by the drawing document acquisition unit 2022 to the element name in the specification of the invention document acquired by the invention document acquisition unit 2021. If it is detected that a description that does not satisfy the condition that it is described is included, indication information indicating the code by pointing out that the code is not used in addition to the element name in the specification is included in the warning information. For example, when the drawing document is the content of the searchable PDF file, or when the PDF file containing the drawing document can be converted into the searchable PDF file, the code in the drawing document is the searchable PDF file. Therefore, it can be specified by searching for a character string that matches the code pattern indicated by the code character string pattern information in the condition information of the setting information.

For example, the warning information generation unit 2059 adds to the element name a code that is not used in the drawing document acquired by the drawing document acquisition unit 2022 and does not describe it in the invention document acquired by the invention document acquisition unit 2021. If it is detected that a description that does not satisfy the condition of " is included in the warning information. For example, when a drawing document is the content of a searchable PDF file, or when a PDF file containing a drawing document as content can be converted into a searchable PDF file, the warning information generation unit 2059 generates each By searching for each code added to the element name from, for example, a searchable PDF file, it is possible to identify codes that are not used in the drawing document.

For example, the warning information generating unit 2059 removes a line other than a heading (eg, “title of the invention”, “technical field”, etc.) from the specification of the invention document acquired by the invention document acquiring unit 2021. If it detects that a description that does not satisfy the condition that a full stop character "." The warning information includes pointing information indicating the position of the line in the . It should be noted that the content of the line starts with various opening brackets (e.g., opening angle brackets, opening round brackets, etc.), or starts with various opening brackets following a space character, and ends with the corresponding type of closing bracket. The line may be treated in the same way as the heading line here. Lines other than heading lines do not necessarily end with a period character ".", but if you forget to add a period character "." This indication information can be useful for calling attention to the case where it is interrupted on the way.

For example, the warning information generation unit 2059 detects claims that do not satisfy the condition that one or more period characters "." When it is detected that a term is included, the warning information includes indication information indicating that there is no period character "." and the item number of the item in the claim of the invention document.

For example, if the description of the invention document acquired by the invention document acquisition unit 2021 contains a parenthesized statement sandwiched between an opening parenthesis and a closing parenthesis, the warning information generation unit 2059 removes the parenthesized statement. and the description of the character string immediately preceding the bracketed description (that is, the meaning of the bracketed description is clear). When detected, the warning information includes pointing information indicating that the meaning of the parenthesized description is not clear and the position of the parenthetical description in the specification of the invention document. Specifically, the warning information generation unit 2059 searches for, for example, a bracketed description following a character string other than blank characters in the specification of the invention document, and the detected bracketed description has a clear significance. If it does not correspond to a predetermined proper bracketed character string pattern representing a description, it is determined that the condition that the meaning of the bracketed description is clear is not satisfied. Predetermined proper parenthesized character string patterns are, for example, English notation descriptions related to technical terms whose parenthetical descriptions are the immediately preceding words, descriptions related to examples of the immediately preceding words, or synonyms or additions of the immediately preceding words. If it is a description, it is determined to correspond to this predetermined proper bracketed character string pattern. Appropriate parenthesized character string pattern information indicating a predetermined proper parenthesized character string pattern is included in the setting information. It is also possible to refer to the inner character string pattern information and identify and use the appropriate parenthesized character string pattern. Examples of descriptions corresponding to the predetermined appropriate parenthesized character string pattern include half-width or full-width English expressions such as English letters, blank characters, slashes "/", hyphens "-", and ":". Listings that contain only the letters that appear are listed. Another example of a description corresponding to a predetermined proper parenthesized character string pattern is a character string such as "for example", "in other words", "namely", "so to speak", or "in other words" in parentheses. Examples include a description that begins with a description, or a description that is a character string "hereinafter referred to as . . . " in parentheses.

The warning information generation unit 2059 detects, for example, the description of the invention document acquired by the invention document acquisition unit 2021 that does not satisfy the condition that words having the same meaning should be consistently described in the same notation. If it is detected, the warning information includes indication information indicating that the notation of words with the same meaning is inconsistent, and the content of descriptions related to the detected inconsistent notation. Let For example, the warning information generating unit 2059 defines a predetermined ununiform spelling list that associates different spellings with various words that may be spelled inconsistently. Based on the uniform notation list, it is possible to search for words having the same meaning mixed with different notations in the specification of the invention document. The setting information includes a predetermined non-uniform notation list, and the warning information generation unit 2059 refers to the predetermined non-uniform notation list in the setting information acquired by the setting information acquisition unit 201, It is also possible to search for words and phrases with the same meaning mixed with different notations in the specification of the document. The predetermined non-uniform spelling list is, for example, a list listing a plurality of spellings with the same meaning and the same pronunciation for various words. Examples of the predetermined inconsistent notation list include: list. Note that it is not necessary to unify the notation of words having the same meaning in the invention document, but this indication information can be useful, for example, as a warning to those who want to organize the invention document in terms of form.

For example, if any of the claims of the invention document acquired by the invention document acquisition unit 2021 includes a description citing a plurality of clauses, the warning information generation unit 2059 selects each clause of the quote destination in the description. If it detects that it contains a description that does not satisfy the condition that it is expressed in a form in which the The warning information includes pointing information indicating the item number of the detected item and the content of the description related to the reference. An example of a statement that does not satisfy this condition is "or", "either", etc., such as "the control device described in claims 1 and 2", "the control device described in claims 1 to 3", etc. It is a description that quotes multiple items without using alternative words. In addition, in each clause of the claim of the invention document, it may not be necessary to express the multiple clauses of the cited destination in a form of alternative citation. can be useful.

For example, the warning information generation unit 2059 adds a reference character string (for example, a reference character string indicated by the reference character string pattern information in the condition information of the setting information) to any item of the claim of the invention document acquired by the invention document acquisition unit 2021. (character string that corresponds to the column pattern), the referenced word that is the same as that word appears in the section preceding the reference string in the section or in the section quoted by the section If it is detected that a description related to a reference character string that does not satisfy the condition that it must be described in The warning information includes indication information indicating the item number of the item and the content of the description related to the reference character string. In addition, "the paragraph quoted by the paragraph" pertaining to the above conditions includes the paragraph further quoted by the paragraph quoted by the paragraph, the paragraph further quoted by the paragraph quoted by the paragraph, etc. This applies to the referenced section, which builds on one or more chains of citations. The warning information generation unit 2059 can refer to the claim citation relationship information held by the claim citation relationship detection unit 2057 in order to determine the clause cited by the claim clause. In addition, for example, in the case where a word or phrase is stated after a reference character string in any of the claims of the invention document, the referenced word or phrase that is the same as that word or phrase precedes the reference character string in that paragraph. If the paragraph is not stated in the cited part, and there are multiple paragraphs cited by that paragraph, one or more chains of citations within or from each of the cited multiple paragraphs If the referenced term is not described in the quoted section based on the above, the warning information generation unit 2059 causes the warning information to include indication information indicating that there is no description of the preceding referenced term. obtain. In addition, the indication information does not include the information of the cited item number as one or more paths that consist of each item related to the chain of citations for which there was no description of the preceding referenced term. may As a specific example, claim 1 describes a "sensor", and claims 2 and 3, which do not cite claim 1, do not describe a "sensor", and claim 3 When claim 2 is cited and claim 4, which selectively cites claims 1 and 3, states "said sensor" but does not precede it with "sensor" , the warning information generating unit 2059 generates, for example, the fact that there is no description of the preceding referenced phrase, "4" indicating the detected term, and "said sensor", which is the content of the description related to the reference character string. , “2-3-4”, which is the information of the cited item number as a chained path in which there was no description of the preceding referenced phrase, is included in the indicated information.

For example, the warning information generation unit 2059 sets a condition that a word or phrase indicating a subordinate concept is not used for an independent claim that does not cite another item among the claims of the invention document acquired by the invention document acquisition unit 2021. is detected (i.e., a description using words and phrases indicating a more specific concept), the item number of the independent claim, the word and phrase, and the words and phrases indicating a more specific concept are used. The warning information includes indication information indicating that the For example, the warning information generation unit 2059 searches for descriptions using words and phrases indicating a more specific concept from the independent claims of the claims of the invention document, using a predetermined list of words and phrases indicating a more specific concept. The setting information contains a predetermined lower-level concept word list, and the warning information generation unit 2059 refers to the predetermined lower-level concept word list in the setting information acquired by the setting information acquisition unit 201 to determine the invention. The independent claims of the document may be searched for statements using words indicating a more specific concept. It should be noted that a predetermined lower-level concept word list may include words and phrases representing higher-level concepts of the words in association with the words and phrases representing lower-level concepts. In this case, when the warning information generating unit 2059 detects that the independent claim of the claim of the invention document contains a description using a word or phrase indicating a more specific concept, the warning information generation unit 2059 adds, for example, the modification of the word or phrase indicating the more specific concept to the indication information. As a candidate or the like, a predetermined lower-level concept word list may be referred to, and words/phrases representing higher-level concepts corresponding to the words/phrases representing the lower-level concepts may be included. As an example of a predetermined lower-level concept word list, the lower-level words "display", "send", "print", etc. are associated with the higher-level words "output", and the lower-level words "keyboard", "mouse", etc. are associated with each other. , ``touch pad'', etc., and the broader term ``input device''.

In addition, when the analysis unit 205 of the invention document analysis system 20 analyzes the invention document as a target, as a result of the hierarchical concept relationship determination processing by the inter-element relationship determination unit 2058, there exists between a plurality of important terms in the invention document. Information indicating conceptual hierarchy is obtained. Therefore, based on the information indicating the conceptual hierarchical relationship between a plurality of important words and phrases obtained by the invention document analysis system 20 for each of one or more invention documents, the words and phrases of the lower concept and the words and phrases of the higher concept are determined. It is possible to generate or update a predetermined lower-level concept phrase list in which . Using the predetermined lower-level concept phrase list generated or updated based on one or more invention documents acquired by the invention document acquisition unit 2021 in this way, the warning information generation unit 2059 causes the invention document acquisition unit 2021 to A search may be performed for the independent claims of the claims of an acquired invention document for inclusion of descriptions using phrases indicating a more specific concept. The warning information generation unit 2059 uses the invention document to be searched for descriptions using words and phrases indicating a narrower concept in the independent claims of the claims of the invention document as a basis for generating a predetermined list of narrower concept words and phrases used for the search. may In addition, a more specific concept is only relative, and it is not necessarily inappropriate to use words and phrases indicating a more specific concept in the independent claims of the invention documents. However, the warning information generation unit 2059 uses an appropriately determined predetermined subordinate concept list so that the pointing information related to the words indicating the subordinate concept in the warning information is limited to an unnecessary description. It may be useful as a reminder to avoid inclusion in an independent claim of an invention document.

For example, the warning information generation unit 2059 determines that the important phrases extracted by the important phrase extraction unit 2051 from the claim of the invention document acquired by the invention document acquisition unit 2021 are described in the specification regardless of their importance. If it is detected that the description of the specification of the invention document does not satisfy the condition, the warning information includes the key phrase and the indication information indicating that the key phrase is not described in the specification. It is also possible to let For example, instead of detecting that the description of the specification of the invention document does not satisfy this condition, the warning information generation unit 2059 detects that the condition is set to the "mode for carrying out the invention" of the specification of the invention document. , and, it may be detected that the description, which is the content of "Example" or "Example n" (n is a natural number), is not satisfied. As a specific example, the warning information generation unit 2059 extracts each key phrase extracted from the claim of the invention document by the key phrase extraction unit 2051, and extracts the description of the invention document or the "form for carrying out the invention" of the specification. "", "Example", etc., and if the important phrase cannot be detected, it is assumed that this condition is not met, and indication information indicating the important phrase is included in the warning information.

For example, the warning information generation unit 2059 determines that the elements represented by each of the multiple important phrases extracted by the important phrase extraction unit 2051 from the invention document acquired by the invention document acquisition unit 2021 have structural inclusion relationships. When determined by the inter-element relationship determining unit 2058, if one of the elements in the inclusion relationship on the structure is an entity element, the other element is also an entity element, and one of the elements is a method element. If it is detected that the elements do not satisfy the condition that the other element is also an element of the method, each key word indicating the elements and the elements are consistent in the classification of products and methods. The warning information includes indication information indicating that it should not be done. The warning information generation unit 2059 determines whether or not an element represented by an important phrase is a method element, for example, by determining whether or not the important phrase has a word or phrase listed in a predetermined method ending list as an ending. The predetermined method ending list is, for example, a list listing "method", "step", "procedure", and the like. In the determination process related to this indication information, the warning information generation unit 2059 can treat the element as an entity element if, for example, it determines that an element represented by a key phrase is not a method element. . The setting information includes a predetermined method ending list, and the warning information generation unit 2059 refers to the predetermined method ending list in the setting information acquired by the setting information acquisition unit 201, It may be determined whether or not the represented element is a method element.

For example, the warning information generation unit 2059 does not satisfy the condition that the invention document acquired by the invention document acquisition unit 2021 does not contain characters with character codes other than those that can be used for patent applications in Japan. is detected, the warning information includes pointing information indicating inappropriate characters in the description and indicating that the characters are not represented by usable character codes. The character code that can be used for Japanese patent applications is the Shift_JIS code conforming to JIS-X0208-1997 "Kanji encoding system for information exchange". Note that if the inappropriate characters in the description that does not satisfy the conditions include a predetermined control code (for example, "0x07" for bell control), the warning information generation unit 2059 Control by the control code may be invalidated by converting the code into a predetermined character (such as "●"), and the inappropriate character after conversion may be included in the indication information. For example, when the character code of an inappropriate character corresponds to a circled number, the warning information generation unit 2059 may explicitly include in the indication information that the circled number cannot be used.

The warning information generation unit 2059, for example, adds a description that does not satisfy the condition that the item number of the item in the claim of the invention document acquired by the invention document acquisition unit 2021 is a consecutive number of natural numbers along the line order. is included in the warning information, the item number of the claim item in the description and indication information indicating that the item number of the item is inappropriate are included in the warning information.

For example, the warning information generation unit 2059 adds a condition to the claim of the invention document acquired by the invention document acquisition unit 2021 that the item number of the item to be quoted in the item of the claim is smaller than the item number of the item to be quoted. When it is detected that a description that does not satisfy The indication information is included in the warning information.

For example, the warning information generation unit 2059 adds a double-byte blank character or an opening parenthesis (for example, an opening square bracket, an opening round bracket, etc.) to the invention document acquired by the invention document acquisition unit 2021, except for comment lines. When it is detected that a line that does not satisfy the condition of being a character is included, the content of the line and the indication information indicating that the character at the beginning of the line may be inappropriate, Include in warning information. The comment line is specified based on the comment specifying information of the setting information acquired by the setting information acquiring unit 201, for example. Although the invention document does not necessarily have to have full-width spaces or opening brackets at the beginning of the line, this indication information can be useful, for example, as a reminder to those who want to organize the invention document in terms of form. In addition, for example, if the invention document acquired by the invention document acquisition unit 2021 has a period character "." When it detects that a line that does not satisfy the condition that the may be included in

For example, the warning information generation unit 2059 detects that the invention document acquired by the invention document acquisition unit 2021 includes descriptions that do not satisfy the condition that comma characters and full stop characters are not described consecutively. In some cases, the warning information includes the content of the description and indication information indicating that the description is inappropriate. As a specific example, the warning information generation unit 2059 searches the invention document acquired by the invention document acquisition unit 2021 for descriptions in which two or more comma characters or period characters are consecutive, and searches for such descriptions. is detected, the indication information is included in the warning information. As a specific example, when the warning information generation unit 2059 detects a description in which one comma character and one period character are consecutive in an invention document, an example of including indication information in the warning information is as follows. mentioned.

For example, when the invention document acquired by the invention document acquisition unit 2021 includes an abstract, the warning information generation unit 2059 satisfies the condition that the number of characters in the abstract does not exceed a predetermined maximum number of characters. When it is detected that the description in the abstract is included, the warning information includes indication information indicating that the number of characters in the abstract exceeds a predetermined upper limit number of characters. This predetermined upper limit number of characters is, for example, 400 characters. As a specific example, the warning information generation unit 2059 counts the number of characters described after the headline “summary” and before the headline “selection drawing” in the invention document acquired by the invention document acquisition unit 2021, for example. Then, if the counted number of characters exceeds a predetermined upper limit number of characters, the indication information is included in the warning information.

For example, when the specification of the invention document acquired by the invention document acquisition unit 2021 includes a plurality of paragraph numbers, the warning information generation unit 2059 expresses each of the plurality of paragraph numbers with four-digit Arabic numerals. When it detects that it contains a description of a paragraph number that does not satisfy the condition that it is a serial number starting from "0001", the detected paragraph number and the description of the paragraph number are The warning information includes indication information indicating that it is inappropriate. As a specific example, the warning information generation unit 2059 may, for example, determine that the specification of the invention document acquired by the invention document acquisition unit 2021 has a number written between the opening square bracket and the closing square bracket in order from the beginning. If the detected paragraph number is not represented by 4-digit Arabic numerals, or if multiple paragraph numbers are not listed in sequence starting with "0001" In , the indication information is included in the warning information. Note that, for example, when the number of paragraph numbers detected from the specification of the invention document acquired by the invention document acquisition unit 2021 exceeds 9999, the warning information generation unit 2059 converts each of the multiple paragraph numbers into four-digit numbers. Instead of the condition that the number be represented by Arabic numerals and be a sequential number starting from "0001", each of the paragraph numbers is a number represented by five digits of Arabic numerals, starting with "00001". Using the condition that the number should be a starting sequential number, when a description including a description of a paragraph number that does not satisfy the condition is detected, indication information is included in the warning information.

For example, in the invention document acquired by the invention document acquisition unit 2021, the warning information generation unit 2059 is configured such that each of the headings of formulas, chemical formulas, and tables is continuously generated for each document such as a claim, a specification, and the like. When it is detected that the description of a heading that does not satisfy the condition that it is a description with a number added, the description of the detected heading and the corresponding heading among formulas, chemical formulas and tables is inappropriate. The warning information includes pointing information indicating that the Here, the formula heading is a description in the form of a number written between the letter "number" following the opening square bracket and the closing square bracket. A chemical formula heading is a description in the form of numbers placed between the letter "v" following the opening square bracket and the closing square bracket. Also, table headings are written in the form of numbers between the letters "table" following the opening square bracket and the closing square bracket. Numbers included in each heading of mathematical formulas, chemical formulas, and tables may be numbers composed of one or more Arabic numerals, and such numbers may include alphanumeric characters, the minus sign "-", and the period character. It may be a number to which a branch number expressed by single or a combination of ``.'', opening parenthesis, and closing parenthesis is added. As an example where the headings of multiple formulas are written with consecutive numbers, the formulas are listed in the order of "number 1", "number 2", "number 3-1", "number 3-2", etc. for each document. Examples include headings. As a specific example, the warning information generation unit 2059, for example, for each document such as the specification of the invention document acquired by the invention document acquisition unit 2021, such as a claim, sequentially from the beginning, the "number" following the square bracket at the beginning. A description in a format that includes a number between the closing square bracket is searched as a heading of mathematical formulas, and if multiple headings of mathematical formulas detected in each document are not sequentially numbered, Include indication information in warning information.

The warning information generation unit 2059 does not satisfy the condition that, for example, in the invention document acquired by the invention document acquisition unit 2021, appropriate drawing numbers are added to descriptions of headings of drawings and descriptions related to drawings. When it is detected that the description of the heading of the drawing or the description relating to the drawing is included, the detected description and indication information indicating that the description is inappropriate are included in the warning information. Here, the drawing headings are in the form of a description in which the drawing number is present between the word "Figure" following the opening square bracket and the closing square bracket. Descriptions relating to drawings are described in a format in which a drawing number is present between the character "figure" and a predetermined character string (for example, a character string "reference", a particle character string, etc.). This predetermined character string may be fixed in advance, or may be set in the setting information acquired by the setting information acquiring unit 201, for example. The appropriate drawing number following the word "figure" is a number consisting of one or more Arabic numerals or such number plus alphanumeric characters, a minus sign "-", a period character "." It is the number of the parenthesis and the closing parenthesis added with the branch number expressed singly or in combination. Drawing numbers other than proper drawing numbers are treated as improper drawing numbers. As a specific example, the warning information generation unit 2059 searches the invention document acquired by the invention document acquisition unit 2021 for the description of the heading of the drawing and the description related to the drawing, and If the description includes an inappropriate drawing number, the warning information includes the indication information.

For example, the warning information generation unit 2059 generates a headline “patent document n”, “non-patent document n”, or “example n” with the number “n” added to the invention document acquired by the invention document acquisition unit 2021. ” exists, and when it is detected that it contains the description of these headings that do not satisfy the condition that these headings are appropriately numbered, the detected headings The warning information includes the description and indication information indicating that the number in the description of the heading is inappropriate. Appropriate numbers are written in Arabic numerals representing natural numbers, and are consecutive numbers without secondary numbers in the order of description in each of the headings "Patent document n", "Non-patent document n" and "Example n" is. As a specific example, the warning information generation unit 2059 extracts, for example, from the invention document acquired by the invention document acquisition unit 2021, "patent document n" or "non-patent document n" to which the number "n" is added, or The description of "Example n" is searched, and if the detected description includes an inappropriate number, the indication information is included in the warning information.

For example, the warning information generation unit 2059 may not satisfy the condition that the invention document acquired by the invention document acquisition unit 2021 does not contain any typographical errors in the key phrases extracted from the invention document by the key phrase extraction unit 2051. When it is detected that a description of a certain key word is included, the warning information includes the description of the detected key word and indication information indicating that there is a possibility that the key word is erroneously written. As a specific example, the warning information generation unit 2059 detects two important phrases extracted by the important phrase extraction unit 2051 from the invention document acquired by the invention document acquisition unit 2021. In addition, since there is a possibility that one of the two important phrases has a typographical error, for the purpose of calling attention, etc., provide indication information indicating the two important phrases and the possibility of a typographical error in one of them. Include in warning information. An example of two key phrases that differ from each other by one letter is that if one of the two key phrases is deleted, one of the two key phrases and the other of the two key phrases are deleted. are two key phrases where the key phrases of are identical. Another example of two key phrases that differ from each other by one letter is to delete one n-th (n is a natural number) letter from the beginning that constitutes one of the two key phrases, and Two important phrases in which, when the n-th character from the beginning of the other important phrase is deleted, the one important phrase after deletion and the other important phrase after deletion are the same. is. The warning information generating unit 2059 may include the number of descriptions of each of the two important terms in the invention document, the number of descriptions in the specification of the invention document, and the like in the indication information. As a specific example, if an invention document contains two key phrases “infrared sensor” and “infrared sensor”, the warning information generation unit 2059 may include any of the two key phrases in the indication information. Here are some examples of possible typos. As another specific example, if the invention document contains two important phrases, "lighting control program recording medium" and "lighting control program storage medium", or if the invention document contains "lighting control device" An example is an example in which, when two important phrases “certification control device” are included, the warning information generation unit 2059 indicates that there is a possibility that one of the two important phrases may be erroneously written in the indication information. , are mentioned. Here, the warning information generation unit 2059 generates indication information indicating the possibility of a typographical error when two important phrases extracted from the invention document are two important phrases that differ from each other by only one character. An example of what is included in the warning information is shown. By modifying this example, the warning information generation unit 2059 determines that when two key words extracted from an invention document are words with a number of characters greater than a predetermined first number of characters (for example, 5 characters), When the important phrases are two important phrases that differ from each other by a predetermined second number of characters (for example, two characters), the warning information may include indication information indicating the possibility of a spelling error.

The warning information generation unit 2059, for example, forms the description of key phrases representing the same concept extracted from the invention document by the key phrase extraction unit 2051 into the invention document acquired by the invention document acquisition unit 2021. When it is detected that multiple important phrases that do not satisfy the condition that the The warning information includes indication information indicating that the information is formally inconsistent. In this case, the warning information generation unit 2059 includes, in the indication information, the number of descriptions in the invention document of each of the plurality of important terms whose descriptions are formally inconsistent, the number of descriptions in the specification of the invention document, and the like. It is also possible to let As a specific example, the warning information generation unit 2059 extracts two important phrases extracted by the important phrase extraction unit 2051 from the invention document acquired by the invention document acquisition unit 2021. When one or more characters representing the same meaning are included in the warning information, the indication information is included in the warning information for the purpose of drawing attention, etc., because the notation of the two key words is formally inconsistent. As a specific example, if the invention document contains two important phrases, "first sensor" containing a full-width character "1" and "first sensor" containing a half-width character "1", , the warning information generation unit 2059 indicates that the notation of the two key words is formally inconsistent in the indication information.

The warning information generation unit 2059, for example, in the specification of the invention document acquired by the invention document acquisition unit 2021, so as to be consistent with the relationship between the code and the element name described in the "Description of code" column, If it is detected that a description that does not satisfy the condition that the code attached to the element name is described is included, the detected element name and code, and the "description of code" column The warning information includes the code corresponding to the element name of and indication information indicating that the code does not match. As a specific example, the description of the invention document includes the description "the first device 102", and furthermore, in the column of "description of symbols", "101 first device" and "102 second device" , etc., the warning information generation unit 2059 generates a message indicating that the code of "first device 102" in the specification does not match "101" in the "description of code". The information of is included, for example.

For example, the warning information generation unit 2059, when including in the warning information, indication information indicating an indication based on a predetermined condition with respect to the invention document acquired by the invention document acquisition unit 2021, indicates the reason for the indication. An explanation to the user, an explanation to the user about the disadvantage caused by the description that is the target of the indication, or an explanation to the user of a method for appropriately correcting the description that is the target of the indication May contain messages. The explanation of the reason in this explanation message may include, for example, information such as legal provisions and judicial precedents that serve as the basis for the indication, or information on reference materials related to the indication. For example, the explanation message may be fixedly defined for each condition that is the basis of pointing out the pointing information, or may be defined in the setting information acquired by the setting information acquisition unit 201. However, it may be generated by the warning information generator 2059 according to a predetermined algorithm according to the conditions.

[3-1-5-6-3. Pointing out fees, etc.]
For example, when the claim number of the invention document acquired by the invention document acquisition unit 2021 is a patent application based on the invention document in a prescribed region such as the United States or Europe, the warning information generation unit 2059 When the fees required for patent applications, etc., in Japan exceed a predetermined number that serves as a boundary for a relatively rapid increase, the warning information includes indication information to that effect. This predetermined number may be defined by setting information acquired by the setting information acquiring unit 201, for example. The warning information generation unit 2059 may include information indicating a predetermined area where the application may be made in the indication information. In addition, the warning information generation unit 2059 may include the indication information in the warning information for each of a plurality of predetermined areas.

In addition, the warning information generation unit 2059 determines whether or not to include various indication information related to each predetermined area in the warning information in accordance with the designation in the setting information or the designation by the user of the invention document analysis system 20. , the indication information may be generated according to the determination. As a specific example, the warning information generation unit 2059 generates various indication information related to the United States only when "United States" is specified in the setting information, etc., and sends the generated indication information. It may be included in the warning information.

[3-1-5-6-4. Information related to the indication information included in the warning information]
The warning information generation unit 2059, based on the above-described conditions and the like, includes one or more pieces of indication information in the warning information as a part of the patent application related information output by the output unit 208. Based on the level criteria, the indication level may be determined for each piece of indication information according to the content pointed out by the indication information, the conditions on which the indication information is based, and the like. Examples of criteria for the predetermined indication level include, for example, criteria for determining that the more important the content pointed out by the corresponding indication information, the higher the indication level. Another example of a predetermined indication level criterion is that the invention document that is the subject of the indication information and the translation result document that is assumed to be generated when the invention document is properly translated are included in the indication information. Criteria for determining such that the higher the possibility of disagreement in units of corresponding words and phrases, the higher the pointing level. An example of a relatively high possibility of a discrepancy in word units between the invention document and the translation result document is, for example, pointing information pointing out that there is a clerical error in the invention document. A low example is, for example, indication information pointing out the omission of a code to be added to an element in an invention document. As yet another example of a predetermined indication level criterion, the more likely the description of the invention document that was the subject of the indication information to materially degrade the quality of the document to allow for proper translation, the more likely the indication will be. Criteria for judging levels to be high include: As an example where the description of the invention document that is the subject of the indicated information is highly likely to significantly degrade the quality of the document to enable appropriate translation, for example, the referenced word in one of the claims of the invention document (i.e., the term following the reference string) is not described in the preceding part of the section, the section to which the section is cited, or the section to which the citation is linked.

The warning information generation unit 2059 may indicate the corresponding indication level in the indication information according to the indication level determination result, or include the indication information in the warning information in descending order of the indication level. good. The warning information generating unit 2059, for example, when the pointed out item is pointed out based on the condition corresponding to each condition item of the invention document standard specification for translation acquired by the acquisition unit 204 of the standard specification for invention document for translation, The indication level can be determined in one or both of cases in which the invention is pointed out based on conditions other than the standard provisions for invention documents.

The warning information generation unit 2059 generates, for example, based on the number of indication information pointed out for the invention document acquired by the invention document acquisition unit 2021, or the number of indication information and the indication level for each indication information. Based on this, an evaluation value may be calculated by a predetermined arithmetic expression, and the invention document evaluation information including the calculated evaluation value may be included in the warning information. The predetermined arithmetic expression is, for example, an expression in which the sum of the indication level values of each item of indication information in the warning information is used as an evaluation value. In this case, the warning information generation unit 2059, for example, based on the number of indication information pointed out in the claim description of the invention document acquired by the invention document acquisition unit 2021, or the number of indication information and the indication level for each indication information, the evaluation value is calculated by a predetermined arithmetic expression, and the invention document evaluation information including the calculated evaluation value related to the statement of the claim is included in the warning information. good too. In addition, the warning information generation unit 2059, for example, for the description of the specification of the invention document acquired by the invention document acquisition unit 2021, based on the number of indication information pointed out, or the number of indication information An evaluation value is calculated by a predetermined arithmetic expression based on the indication level for each indication information, and the invention document evaluation information including the calculated evaluation value related to the description of the specification is included in the warning information. good too. The warning information generation unit 2059, for example, for the invention document acquired by the invention document acquisition unit 2021, based on the number of indication information pointed out based on the conditions corresponding to each condition item of the invention document standard specification for translation Alternatively, based on the number of indication information and the indication level for each indication information, for example, the index is calculated by a predetermined arithmetic expression so as to indicate the degree of conformity to the standard provisions of invention documents for translation. It is also possible to calculate the evaluation value to be the value, and include the invention document evaluation information including the calculated evaluation value in the warning information.

The warning information generation unit 2059 uses one of the plurality of setting information acquired by the setting information acquisition unit 201, which is defined for each group such as by technical field or by department to which the inventor belongs. When the warning information includes indication information pointed out to the invention document acquired by the invention document acquisition unit 2021 based on the conditions determined and determined, the group to which the used setting information belongs is identified. The information may be included in the corresponding indication information.

For example, the warning information generation unit 2059, for all or part of the indication information, includes line information (for example, line number) of the description part of the invention document that is the target of the corresponding indication, the claim number of that part, and , may include at least one of the paragraph numbers in that part of the specification. When the warning information generation unit 2059 includes the line number of the description part of the invention document that is the target of the warning information in each piece of indication information in the warning information, the output unit 208 outputs the patent application related information including the warning information. It is useful to output patent application related information by including a description in which the line number is added to each line of the invention document.

[3-1-5-6-5. Generation of Warning Information Part in Document for Display]
When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the warning information as a display document (for example, an HTML document conforming to HTML5), the warning information generation unit 2059 outputs the display document Generate warning information included in the patent application related information as.

The warning information portion of the patent application-related information as a display document generated by the warning information generation unit 2059 includes, for example, one or more display elements. For example, a browser may interpret the presentation document to display each presentation element.

One or more display elements included in the warning information portion enable display of all or part of any indication information, for example. Display elements included in the warning information portion may include those having a link attribute. The warning information generation unit 2059 generates a display element included in the warning information part, for example, for a link to the relevant description part of the description (for example, a potentially inappropriate description) indicated by the indication information (that is, a browser display control information for causing the display element to function as a GUI element for transitioning the display to the description location indicated by the pointing information according to the operation to . For example, the relevant description part to be the link destination is the relevant part (for example, the relevant line) of the invention document included in the patent application related information as the display document, or the claim information included in the patent application related information as the display document. The corresponding part (for example, the relevant section), or the relevant part (for example, the relevant paragraph) in the specification information included in the patent application related information as the display document. For example, the display control information is associated with an operation type (for example, a mouse click operation) in a tag added to a display element (for example, an HTML tag conforming to HTML5), and a script for transitioning the display to the corresponding description location. It is information configured by describing the functions of In warning information as a display document, as a specific example of a display element that displays a piece of indication information pointing out inappropriate descriptions in a claim, warning information and complaint information are each <article> in an HTML document. In the case where it is described sandwiched between the tag and the </article> tag, the content of the indication information is described under the <article> tag of the warning information sandwiched between, for example, the <span> tag and the </span> tag, In the <span> tag, there is an example of describing a function name of a function in JavaScript (registered trademark) to be activated in response to a mouse click operation or the like. For example, this function is written in a script file specified in an HTML file of an HTML document that is read by a browser. This is a function to search for and display a description that is The indicated information that can be displayed in the display element in the warning information is the line number of the description part of the invention document that is the subject of the corresponding indication, the claim number of that part, or the paragraph number of that part of the specification , the warning information generation unit 2059 activates the line number, claim item number, or paragraph number in response to the operation in generating the display control information added to the display element. It may be used as an argument to a script function. By using this argument, the function displays inappropriate lines in the invention document, inappropriate claim sections in the claim information, and inappropriate paragraphs in the specification information. can be realized relatively easily. The invention document, claim information, or specification information in the patent application-related information as the display document may be corrected inappropriate descriptions corresponding to the pointed out information in the warning information.

A display element having a link attribute with indication information as the display content is, for example, an <a> tag (that is, an anchor tag) for a link that specifies the appropriate description part of the inappropriate description pointed out in the indication information as display control information. may be included as

In the warning information part of the patent application-related information as a display document, the relevant description part that is the link destination of the display element related to the indication information is, for example, in the modified claim information included in the patent application-related information as a display document , or the relevant part (for example, the relevant paragraph) in the modified specification information included in the patent application-related information as the display document. The corrected claim information in the patent application-related information as a display document is the content corresponding to the claim in the invention document, and may include the corrected content of the inappropriate description corresponding to the indication in the indication information in the warning information. . In addition, the revised specification information in the patent application-related information as a display document has contents equivalent to the specification of the invention document, and the inappropriate description corresponding to the indication in the indication information in the warning information has been corrected. can contain content.

When generating warning information in a display document, the warning information generation unit 2059 determines a warning level corresponding to one or more pieces of warning information to be included in the warning information, and displays the warning information. Display control information for displaying the indication information in a display mode corresponding to the determined indication level may be added to the display element for displaying the indication information. As an example, when one or more pieces of indication information of warning information are displayed by a browser, the warning information generation unit 2059 adds to each piece of indication information whether or not the indication level of the indication information exceeds a predetermined threshold value. The display control information may be generated so as to selectively add and display the characters "Error" or "Warning" accordingly. As another example, the warning information generation unit 2059 displays each piece of indication information in a color corresponding to the indication level of the indication information when one or more pieces of indication information of the warning information are displayed by the browser. The display control information may be generated as follows. As a specific example of using different colors, the warning information generation unit 2059 adds a class name corresponding to the level of indication to the <span> tag added before indication information to be included in the HTML document, and adds a class name corresponding to the indication level to the HTML document. For example, a CSS file that is read by a browser defines a character color, character background color, etc. as display attributes of a class so that it differs for each class name corresponding to each indication level.

When generating warning information in a document for display, the warning information generation unit 2059 adds one or more pieces of indication information to be included in the warning information to a display element for displaying the indication information in accordance with an operation. Display control information may be added to provide a GUI function for correcting the description indicated by the indicated information and making the correction result part of the corrected claim information or corrected specification information. . As a specific example, the warning information generation unit 2059 may generate warning information in the display document in the case where two key phrases extracted from the invention document are two key phrases that differ from each other by only one character. include a display element of indication information indicating that there is a possibility of Display control information may be added to have a function as a GUI to be reflected in the . As another specific example, the warning information generation unit 2059 may include two important words extracted from the invention document that include one or more characters that express the same meaning but are different only in half-width or full-width. In this case, the warning information in the display document includes a display element of indication information indicating that the notation is inconsistent, etc., and the display element is made to select one of the two important phrases, Display control information may be added to provide a GUI function for reflecting the selection result in the modified claim information or modified specification information.

[3-1-5-7. Complaint information generator]
The claim information generation unit 205a executes a claim information generation process for generating claim information included in the patent application related information output by the output unit 208 of the invention document analysis system 20. FIG. The claim information is information representing the claims in the invention document.

The claim information generating unit 205a generates a Japanese Patent In order to support the efficient preparation of application documents, Japanese manuscripts for translation for patent applications outside Japan, etc., in addition to claim information, various information contained in patent application related information ( for example, claim-based specification information, etc.).

The claim information generation unit 205a can execute a claim-based drawing information generation process for generating claim-based drawing information included in the patent application related information output by the output unit 208 of the invention document analysis system 20, for example. Claim-based drawing information is information about drawings that is generated based on claims in an invention document and that can be used as a basis for generating drawings for patent applications.

The claim information generation unit 205a can execute a claim-based specification information generation process for generating claim-based specification information included in the patent application related information output by the output unit 208 of the invention document analysis system 20, for example. Claim-based specification information is information about a specification that is generated based on claims in an invention document and that can be used as a basis for creating a specification for a patent application.

The claim information generation unit 205a can execute claim-based abstract information generation processing for generating claim-based abstract information included in the patent application related information output by the output unit 208 of the invention document analysis system 20, for example. Claim-based abstract information is information about abstracts that is generated based on claims in an invention document and that can be used as a basis for generating abstracts for patent applications.

The claim information generation unit 205a performs a modified claim information generation process for generating, for example, modified claim information in which the claims of the invention document are included in the patent application related information output by the output unit 208 of the invention document analysis system 20. can be executed.

If the invention document acquired by the invention document acquisition unit 2021 does not contain a claim, the complaint information generation unit 205a performs the following processes: complaint information generation processing, claim-based drawing information generation processing, claim-based specification information generation processing, Execution of abstract information generation processing and modified complaint information generation processing is omitted.

[3-1-5-7-1. Complaint information generation]
The complaint information generation unit 205a realizes the complaint information generation processing by generating complaint information representing the complaint contained in the invention document acquired by the invention document acquisition unit 2021. FIG. The claim information may be a partial correction of the claim included in the invention document acquired by the invention document acquisition section 2021 . As an example of this modification, if the claim includes a predetermined control code such as "0x07" for bell control (for example, a code within the range of "0x00" to "0x1f"), the predetermined control code is For example, conversion to a predetermined character such as “●” is possible.

When the output unit 208 in the invention document analysis system 20 outputs patent application related information including claim information as a document for display (for example, an HTML document), the claim information generation unit 205a outputs the patent application as a document for display. Generate claim information included in related information. FIG. 22 shows an example of claim information in patent application related information as a display document displayed on the browser. In FIG. 22, the content of the complaint information is partly omitted for the sake of convenience.

The claim information portion of the patent application-related information as a display document generated by the claim information generation unit 205a includes, for example, one or more display elements corresponding to the content of each line of each claim item. If there are one or more important phrases extracted by the important phrase extraction unit 2051 in each line of , one or more display elements corresponding to each of the important phrases are included, and each line of each item includes square brackets When a headline such as "Claim n" (n is a natural number) or a comment sandwiched between two is included, one or more display elements corresponding to the headline or comment are included. As a specific example, the complaint information generating unit 205a, when writing complaint information sandwiched between <article> and </article> tags in an HTML document, creates each line of each item of the complaint under the <article> tag. , the display element corresponding to the line is described by sandwiching the content of the line between the <span> tag and the </span> tag, and the display element corresponding to the one line <span> tag , for each key phrase in the line, the display element corresponding to the key phrase is described by sandwiching the key phrase between the <span> tag and the </span> tag. For example, a browser may interpret the presentation document to display each presentation element. A display element corresponding to each line of each item included in the claim information portion, for example, makes the content of the corresponding line displayable by a browser.

The complaint information generating unit 205a controls the display mode of the headline, comment, or important phrase in display elements corresponding to the heading, comment, or important phrase included in the complaint information portion of the display document. Display control information for (for example, highlight display, color display, display transition, etc.) is added.

An example of highlighting an important phrase is, for example, displaying the important phrase in bold. An example of highlighting an important phrase with a relatively high degree of importance is, for example, displaying an important phrase with a relatively high degree of importance in a larger font size than an important phrase with a lower degree of importance. .

A specific example of generating display control information to be added to each of a plurality of important phrases in order to display different important phrases in different display modes (for example, display with different colors) is as follows: If the HTML file of the HTML document contains a <span> tag and a </span> tag and the important phrase is described as a display element, the complaint information generation unit 205a generates a <span> tag related to the display element. 2, an example of assigning identification information (for example, an identification code including an identification symbol and a serial number) defined in the important phrase management information so as to distinguish the important phrase from other important phrases as a class name. In this example, in the CSS file of the HTML document, information defining the color as the display mode of the content of the <span> tag for each class name, which is the identification information of the important phrase (that is, information indicating the color added to the important phrase ) are included, different important words and phrases are displayed in different colors. To give a specific example, different key phrases in the claim information are separated by a certain width (for example, the width of one character represented by "1 em" using the unit "em") by the border-left property, for example. ) and painted in different colors (see FIG. 22). For example, it is preferable to express the left border line with a solid line. To do so, the style of the border line is set to solid. As a specific example, the class names corresponding to the display elements of a plurality of key phrases having different character strings in a claim are defined as kwd1, kwd2, kwd3, . . . , the border-left property is set to "solid 1em #f00;", the color property is set to "#666;", and the font-weight property is set to "bold;". 1em #f0c;”, “#666;” for the color property, “bold;” for the font-weight property, and in the class with the class name kwd3, “solid 1em #f66;” for the border-left property, "#666;" and "bold;" are set in the font-weight property. In FIG. 22, the color (that is, the display color) of the left boundary line with the width of one character is represented by pattern patterns, and a plurality of different pattern patterns represent a plurality of different colors. It should be noted that the method of expressing different key phrases by using different colors for the left boundary line attached to each key phrase is more effective than the method of expressing key phrases by using different character colors or character background colors. There is an advantage that the readability of the important phrase itself is not degraded regardless of whether the background color of is dark (eg, black) or bright (eg, white). Also, since the left border line is not a character, it will be ignored when you copy and paste the displayed content that includes important phrases. It does not get in the way when editing the description etc. Note that, as illustrated in FIG. 22, important words displayed in a display mode with a left boundary line with a width of one character painted in a display color are, for example, (that is, at least one of the right border, upper border, and lower border) may be added, but it is also useful to make it simple to improve the visibility of important words and phrases. There may be no right, top and bottom borders added to key phrases. Note that adding any zero-width boundary line to a key phrase is the same as not adding that boundary line. In addition, a monospaced font may be preferentially used as a font for displaying some or all characters of patent application-related information (for example, claim information and specification information) as a display document. , the width of the left boundary line of the important phrase may be set to one character (for example, 1 em). As a result, if a monospaced font is available, the width of each character is aligned with the rectangle painted with the display color added as the left border line of the key words, so the visibility of each character, each key word, etc. is improved. can improve.

The claim information generation unit 205a, for each key phrase, assigns the class name to be added to the tag that constitutes the display element of the key phrase in ascending order of the first appearance number of the key phrase (for example, the first appearance number in the claim of the invention document). Information that defines the display color (for example, the color of the left border line of the display element) for each class name related to the display element of important phrases in the CSS file, etc. when using identification information that is an identification code that includes a defined serial number So, for example, between multiple classes with the same identification symbol in the identification code as the class name and consecutive serial number parts, the difference in display color is relatively higher than between multiple classes with discontinuous serial number parts. The display color may be specified so that the size is sufficiently large. In this example, the serial numbers corresponding to the important phrases may be determined in any order among the important phrases having the same first appearance number. Another example of the information that determines the display color for each class name (for example, the color of the left border line of the display element) related to the display element of the important phrase is, for example, the identification symbol in the identification code as the class name. All of the differences in the display colors added to each of the important phrases in each of the sets of two of the plurality of important phrases in the first group that are the same and have a serial number part equal to or less than a first predetermined number (for example, 100). Two important phrases out of a plurality of important phrases of a mixed group in which a plurality of important phrases of a second group having a sequence number larger than a predetermined number and a plurality of important phrases of the first group are mixed. The display color may be specified so that the difference in the display color added to each important phrase in each set is greater than the minimum value for all the sets. Since the minimum value of the difference in the display color of each important phrase with a relatively small first line number (for example, 100 kinds of important phrases in the first group) is relatively large, each of the important phrases can be displayed as It can be identified relatively quickly and correctly. The difference in display color is, for example, a difference in hue component (for example, a difference in position when represented on a hue circle such as the Munsell ring), and each component of RGB values (that is, each of red component, green component, and blue component). differences, etc. As a result, for example, when the claim information in the document for display is displayed by a browser, the display element of each important phrase in each section near the beginning of the claim has a different display color from the different important phrases described nearby. They will appear sufficiently different to facilitate identification. In addition, when the claim information in the display document is displayed by the browser, the same key phrases in each section of the claim are displayed in the same display color, so that it is possible to quickly recognize that they are the same key phrases. can be possible. As a simple example showing the relationship between the serial numbers determined in ascending order of the first appearance number of the important phrases and the display colors of the important phrases, the display colors of the four important phrases with the serial numbers 1 to 4 are shown in the hue circle. are defined as colors with hues of 0°, 90°, 180°, and 270° on the color wheel, and the display colors of the following four important phrases with serial numbers from 5 to 8 are respectively determined by hues of 10°, 100°, and 10° on the color wheel. The colors of 190° and 280° are defined, and the display colors of the following four key phrases with serial numbers from 9 to 12 are defined as hues of 20°, 110°, 200°, and 290° on the color wheel, respectively. The display colors of the four important phrases with serial numbers from 13 to 16 are defined as hues 30°, 120°, 210°, and 300° on the color wheel, respectively. An example is to define In this example, among the four types of key phrases in the first group whose sequence number is 4 or less, the minimum value of the difference in the display color added to each key phrase in each of the sets of two key phrases in all sets (that is, a hue difference of 90°) is a mixture of 4 key phrases of the second group with serial numbers greater than 4 and 8 or less, and 4 key phrases of the first group. display color for each key phrase so that the difference in the display color added to each key phrase in each pair of two key phrases is larger than the minimum value (i.e., hue difference 10°) in all pairs is specified. In this example, the hue increment is set to 10° for each group of four types of important phrases, but if the increment is set to 5° or the like, more types of important phrases can be expressed by adding different display colors. . Display control information for each key phrase (for example, information such as properties related to the color of the class for each class name corresponding to the key phrase) adds different display colors to key phrases with serial numbers up to a certain range. , and it is possible to uniformly express important words and phrases whose serial number exceeds a certain range by adding the same display color.

The complaint information generating unit 205a adds, for example, an identification code, etc., as a class name, to identify key phrases having different contents (that is, character strings) to <span> tags associated with display elements of key phrases in the complaint information. In addition to adding an id attribute. This id attribute includes, for example, an identification symbol that identifies the claim information part among the parts in the patent application-related information, an identification code that identifies the important phrase, and a serial number in the important phrase that has the same content ( For example, an identifier (that is, an identifier determined to identify one display element in an HTML document) combined with a number determined in order of description for each of multiple important words and phrases with the same content described in the claim information be.

As another example, if there is a structural inclusion relationship between elements represented by a plurality of key words, the complaint information generation unit 205a may determine that the display elements of the plurality of key words are similar in hue to each other. It is also possible to add display control information that defines the display color (for example, the color of the left boundary line of the display element) to be displayed. As a result, when the complaint information in the display document is displayed by the browser, the important words and phrases representing each of the plurality of elements having structural inclusion relationships are displayed in similar display colors to some extent. Rapid recognition of related key phrases may be possible.

The complaint information generation unit 205a provides a display element corresponding to an important phrase, for example, as a GUI for performing display transitions related to the important phrase (for example, information addition display related to the important phrase) in response to an operation on the browser. Display control information is added in order to add a function (that is, to make the display element an operation-responsive GUI element).

As a specific example of generating display control information for adding GUI functions corresponding to operations to key phrases, the complaint information generating unit 205a generates <span> tags and </span> tags in an HTML file of an HTML document. A function in JavaScript (registered trademark) that is associated with various operations (for example, onmouseover attribute, onclick attribute, etc.) in the <span> tag when an important phrase is described in between, and that is activated according to the operation An example of describing the function name of This function can be written, for example, in a script file specified in an HTML file that is loaded by the browser.

A specific example of the display element of one key phrase in the complaint information in the display document generated by the complaint information generation unit 205a is when multiple key phrases “equipment control unit” are described in the complaint information. The display element corresponding to the fifth “equipment control unit” is, for example, “<span class="c003" id="claiminfo-c003-005" onclick='wordProc ("claiminfo-c003-005")' title= "... (display content with additional information)...">equipment control section</span>" and the like. In this example, the identification code of the important phrase "equipment control unit" is "c003", and the value of the id attribute of the <span> tag of the display element is the identification symbol "claiminfo" of the complaint information and the identification of the important phrase. A character string including a code "c003" and a number "005" in order of description is defined. Also, in this example, when a mouse click operation is performed on a display element, the wordProc function is called with the value of the id attribute as an argument. As a result, in the wordProc function, for example, it is possible to specify the display element from the argument and refer to the character string of the important phrase related to the display element. By extracting the identification code "c003" of the phrase and the number "005" in the order of description, for example, the id attribute of the top display element of the same important phrase is specified as "claiminfo-c003-001", and that It is possible to realize the process of displaying the first display element, for example, the process of replacing the display contents of the display elements of all the important phrases "equipment control section" of the complaint information with the character string etc. input by the user. It is possible to realize

For example, the complaint information generation unit 205a performs processing (that is, important (Additional display of information related to phrases) may be determined to be performed. The information related to the important phrase is, for example, the important phrase management information (see FIG. 18) held in the analysis unit 205 and all or Some information. FIG. 23 shows an example of information related to key words and phrases displayed in response to a mouse-over operation on display elements of key words and phrases in claim information of patent application-related information displayed on the browser. In the example of FIG. 23, the importance of the important phrase and the important phrase are defined as information related to the important phrase "B section" pointed by the mouse pointer by the mouse over operation to the important phrase "B section". The claim number, the claim number referring to the key word, the code associated with the key word in the invention document, etc. are added near the key word "Part B". is displayed in

The complaint information generation unit 205a performs, for example, a script function that is activated when a mouse click operation is performed on a display element of an important phrase displayed on the browser, and performs an important phrase update process that changes the important phrase. A code insertion process that inserts the code after the key word when there is a code corresponding to the key word without the code being described after it, the key word from claim information, specification information or other related invention documents Listing processing of inclusion description of important phrases for enumerating lines containing , processing for searching for lines containing such important phrases from claim information, specification information, etc., search sites on networks such as the Internet (i.e., searches accessible via networks) site), etc., the definition of the important phrase, the synonym of the important phrase, the related image of the important phrase, etc., or the important on the translation site on the network such as the Internet. It may be determined to perform processing such as translating words. Search sites on the Internet such as Google (registered trademark) search sites, for example, provide URL parameters to search for a definition of a term to be searched, to search for related images related to the term, and to search for the term. In some cases, it is possible to search for such translated phrases. A search site for searching for character strings, images, and other information from accessible web pages may be realized by a server on the LAN.

The complaint information generation unit 205a generates a script function that is activated when, for example, a mouse click operation is performed on a display element of an important phrase displayed on the browser, for example, a menu of options is displayed, and an important phrase is displayed according to the selection operation. Word update processing, code insertion processing, key phrase inclusion description listing processing, claim information, specification information, etc., processing to search for lines containing the key phrase, web search sites on networks such as the Internet that include the key phrase A process of searching for a page or the like, or a process of translating the key phrase on a translation site or the like on a network such as the Internet, or the like may be determined to be selectively executed. In order to display a menu that includes options for executing a process of searching for a web page or the like containing the key phrase on a search site or the like on a network such as the Internet, the complaint information generation unit 205a may, for example, display the menu to be generated. An <a> tag (that is, an anchor tag) for linking is included in the element, and the href attribute of the <a> tag is the important phrase that can be acquired by the innerHTML property of the object of the display element of the important phrase clicked with the mouse. The function includes a process of setting a description that follows the URL of a search site on a network such as the Internet by using a character string that is the content of as a URL parameter. In the function, the complaint information generation unit 205a sets the URL parameter corresponding to the function to the href attribute following the URL of the search site that provides various functions such as image search and translation for the menu to be displayed. By describing each <a> tag, it is possible to include options for various functions such as image search and translation in the menu.

The complaint information generation unit 205a is arranged so that the results of processing by this function (for example, search results, translation results, etc.) are displayed in a browser so that the display elements of the important phrase clicked with the mouse are not hidden. , this function may be defined. As an example of a process of searching for a line containing one important phrase α from the specification information within a function of JavaScript (registered trademark), In the display element of each key phrase (for example, <span> tag), an identification symbol that identifies the specification information part in the patent application related information, an identification code that identifies each key phrase, and a serial number within the same key phrase (that is, an identifier determined to identify one display element in the HTML document) is added as an id attribute, and the important phrase α is added, for example, the top number of the serial number is added, and the formed identifier is passed as an argument to document. An example of specifying the display element of the important phrase α by executing the getElementById method and, for example, executing the scrollIntoView method of the specified display element to display the line containing the specified display element in the display area of the browser. is mentioned. As an example of a specific method for realizing the key phrase inclusion description enumeration process, the content of each line in which the key phrase is described in the claim information is combined with the above-described identification symbol, identification code, and serial number. Similarly, collect the contents of each line in which the key phrase is described in the specification information by changing the serial number of the identifier that was created, and list each line that is each collection result and An example of emphasizing and displaying an important phrase is given. As another example of a specific method for realizing the important phrase inclusion description listing process, based on other invention documents related to the invention document from which important phrases are extracted by the important phrase extraction unit 2051, The content of each line in which the key phrase is described in other invention documents is collected by searching for the key phrase, and each line that is the collection result is listed and the key phrase in each line is highlighted. Examples include: The claim information generation unit 205a adds information for identifying other related invention documents (for example, the file name of the invention document, the application number of the patent application, the publication number, the patent number, the title of the invention, etc.) to the display content in this case. ) may be included. Other invention documents related to the invention document from which key phrases are to be extracted by the key phrase extraction unit 2051 are, for example, one or more invention documents specified by user designation (for example, designation in setting information). Alternatively, the headline "Patent document n" (n is a natural number) in the specification of the invention document from which the key phrase is to be extracted is followed by information for identifying the patent document as prior art document information. (eg publication number), it may be the patent document. The invention document analysis system 20 can acquire the content of the patent document from the website via the Internet based on the publication number. In addition, for important phrases related to the GUI element to be operated, which is a display element that has received an operation such as a mouse click operation, the important phrase inclusion description enumeration process of searching for and listing and displaying each line in which the important phrase is described is , may be partially modified, for example, a sentence in which the key phrase is described as the subject (for example, following the key phrase or the sign immediately after it, the case particle "ha" or the case particle compound ”), and list and display each sentence collected as a search result. In addition, for example, in the key phrase inclusion description enumeration process of listing the descriptions related to the key phrases to be operated, the lines containing the key phrases are generated as claim information, specification information, or another invention document (that is, claim information, etc.). Inventive documents other than the original invention document) are listed and displayed, and the important words in each listed and displayed line are highlighted. Accordingly, it is also a process of adding display control information for making that line function as a GUI for link display to multiple lines including that line in claim information, specification information, or another invention document. good. With this, the user further operates on one of the rows listed by including the operated important phrase, so that the complaint information before and after the one row to be further displayed, Multiple lines in specification information or another invention document can be easily identified. Note that the key phrase inclusion description enumeration process for listing the descriptions of the key phrases to be operated is, for example, listing and displaying the lines containing the key phrases from the claim information and the specification information, and listing and displaying them. The key phrase in each displayed line is highlighted, and the displayed line is displayed as a GUI for displaying links to multiple lines including that line in the claim information or specification information according to the operation on that line. It may be a process of adding display control information for making the line function. Link display can transition display content to a link destination (for example, other information that is not currently displayed) according to the operation of a display element (for example, a mouse click operation while the mouse pointer is positioned on the display element). display. In addition, for each of the multiple key words in the claim information in the display document, since the description line of the key word in the claim information and the specification information can be specified in advance, it is possible to include the key word in accordance with the operation on the key word. When the description enumeration process is executed, all or part of the information corresponding to the search result is generated in advance, instead of searching for the description line of the important phrase in the claim information and specification information. By utilizing the generated information, the execution speed of the important phrase inclusion description enumeration process may be increased.

FIG. 24 shows an example of a pop-up screen (for example, a window displayed by pop-up) displayed in response to a mouse click operation on a display element of key phrases in claim information of patent application-related information displayed on the browser. The pop-up screen illustrated in FIG. 24 is displayed in response to a mouse click operation on the key phrase "B section", and includes a plurality of push buttons which are GUI elements for executing various searches for the key phrase "B section", and the execution result of the important phrase inclusion description enumeration process for the important phrase “B part”. The push button can be generated by, for example, the <button> tag, and the href property of the location object is set to "https://..." and the URL of the search site, URL parameters, etc. as the onclick attribute of the <button> tag. By doing so, it may be possible to execute a search in response to a button pressing operation. As a result of executing the key phrase inclusion description enumeration process illustrated in FIG. , is emphasized by adding a character background color, which is expressed by enclosing it in a rectangular frame in the figure, without adding a left boundary line. As an example of an operation method of the invention document analysis system 20, for example, a user (for example, an inventor or a patent attorney) refers to the execution result of the key phrase inclusion description listing process corresponding to the key phrase, and operates the invention document analysis system 20. The important phrase setting dictionary may be edited so as to include the important phrase and sentences appropriately explaining the important phrase according to the need for future utilization in the future.

For example, the complaint information generation unit 205a temporarily or constantly divides the display screen of the browser into a plurality of display areas, and divides the display area of the complaint information and the display area of the processing result by the function activated according to the operation. They may be displayed in parallel (see FIG. 17).

The claim information generation unit 205a searches each line of each claim item of the invention document for a character string having the same content as one of the key phrases extracted by the key phrase extraction unit 2051 from the content of the line. may identify one or more key phrase display elements in the row. For example, if one line of a claim contains only the statement "when input data is processed," the claim information generation unit 205a causes the important phrase extraction unit 2051 to To search the line for the important word "processing" already extracted by the method of excluding verbs from extraction, and treat the "processing" as a display element of the important word as the content of the line in the claim information. may be Conversely, since "processing" cannot be extracted from that line by excluding verbs from extraction targets, the complaint information generation unit 205a treats "processing" as a display element of the important phrase as the content of that line. It is also possible not to do so.

The claim information generation unit 205a adds, for example, a Alternatively, display control information may be added in order to add a function as a GUI for performing display transition to display elements corresponding to, for example, immediately preceding or succeeding headlines in response to operations on the browser. As a specific example of generating display control information for adding a function as a GUI for display transition to the next headline to a headline "Claim n" (n is a natural number), the claim information generation unit 205a generates an HTML document. In the HTML file of <span> and </span>, when the heading "claim n" (where n is a natural number) is described between <span> and </span> tags, an operation (for example, onclick attribute, etc.) and describes the function name of a function in JavaScript (registered trademark) to be activated according to the operation. This function can be written, for example, in a script file specified in the HTML file. For example, the complaint information generation unit 205a searches for and displays a display element with a headline "Claim m" (m is a number one greater than a natural number n) enclosed in square brackets from the content of the complaint information. You can define this function to run.

The complaint information generation unit 205a converts the reference character strings (eg, "said", "above", "that", "that", etc.) included in the complaint information part into <span> tags and </span> tags, for example. As a display element sandwiched between tags, a display for highlighting the reference character string (for example, displaying in bold, underlining, displaying in a predetermined color such as red, etc.) Control information may be added. The highlighting of a display element related to a character string to which a <span> tag is added includes, for example, a text-decoration property, a font-weight property, a border-left property, a color property, a background-color property, etc. as display attributes in CSS. It can be realized by display control information that adjusts the value. For example, in the complaint information in the HTML file, different class names are defined for various display elements such as reference strings, comments, headings, etc. In the CSS file specified in the HTML file, reference strings, comments, By differentiating the value of the property for highlighting for each class of each class name corresponding to various display elements such as headings, for each display element such as reference strings, comments, headings, etc. It is possible to vary the display mode.

If, for example, the complaint information portion contains inappropriate description indicated by the indication information in the warning information generated by the warning information generation unit 2059, the complaint information generation unit 205a converts the inappropriate description into For example, as a display element sandwiched between the <span> tag and the </span> tag, display control information for highlighting the inappropriate description may be added to the display element.

A claim information generation unit 205a that generates claim information based on the claims in the invention document that is the analysis target of the analysis unit 205 and that is acquired by the invention document acquisition unit 2021 generates a drawing document (for example, a PDF file) corresponding to the invention document. can be acquired by the drawing document acquisition unit 2022, when the claim information contains an important phrase that is the same as the signed element name included in the invention document, the important phrase is transferred to the drawing according to the operation. Display control information for making a display element having a GUI function for displaying a portion including the code in the document (for example, a page including the code) may be added to the display element of the important phrase. This display control information defines, for example, a function name of a function of a script activated with a code as an argument according to an operation, or the function itself. For example, when the drawing document is the content of the searchable PDF file, or when the PDF file containing the drawing document can be converted to the searchable PDF file, the code is removed from the searchable PDF file. By searching, it is determined to identify. The claim information generation unit 205a has a function for searching a code from a drawing document, for example, a process of dividing a PDF file of the drawing document into pages, a process of searching for the code from each divided PDF file divided for each page, The search result may include descriptions for converting the divided PDF file whose code is detected into an image, displaying the converted image, and the like. Trademark) or various existing libraries (for example, "PyPDF2", "pdfminer", etc. provided by a third party) for manipulating PDF that can be used with JavaScript (registered trademark) may be used. In addition, in order to realize the functions of the invention document analysis system 20, the invention document analysis processing program including the portion written in Python (registered trademark), for example, is installed on a web server (for example, a web server of a local host on the same terminal device as the browser). It functions as a server), activates the browser, and can provide the browser with an HTML document related to patent application related information for display. The part of the program written in Python (registered trademark) cooperates with a script written in JavaScript (registered trademark) as one component of an HTML document that is interpreted, displayed, executed, etc. by a browser, and performs various functions. It is possible to share processing (eg, processing PDF files, etc.). For example, the Python (registered trademark) library "Eel" provided by a third party enables cooperation between the program part of Python (registered trademark) and the script part written in JavaScript (registered trademark) in the HTML document. It has the function to

For example, the complaint information generation unit 205a displays a function related to display control information for displaying a part including the code in the drawing document in response to an operation on the key word corresponding to the code, and the function is displayed on the browser and operated. Alternatively, it may be decided to display the portion of the drawing document containing the code within the range where the display element of the important phrase is not hidden. For example, the complaint information generation unit 205a divides the display screen of the browser into a plurality of display areas, and displays the complaint information display area and the display area such as a part of the drawing document displayed according to the operation in parallel. You may For example, the complaint information generation unit 205a uses the display control information added to the display element of the key word corresponding to the code to add the function activated in response to the operation on the key word to the corresponding key word in the drawing document in accordance with the further operation. It may be determined to switch and display a plurality of parts containing the code (for example, two or more pages containing the code), or reduce all the parts containing the code in the drawing document as necessary. may be determined to execute the process of batch display. For example, the claim information generating unit 205a, in response to an operation on an important phrase corresponding to a code, generates a function related to display control information for displaying a part of the drawing document that includes the code. It is also possible to set such that the code in the .

In the document for display, when the display control information for realizing the GUI function for performing processing according to the operation is added to the display element, the operation is a mouse over operation on the display element, It is not limited to a mouse click operation or the like. In addition, for example, in a function that is activated in response to a mouse click operation on a display element, a menu, pop-up screen, etc. is displayed to prompt further operations, and options displayed in the menu, pop-up screen, etc. A process corresponding to the selection operation may be executed.

The complaint information generation unit 205a generates full-width or half-width blank characters, tabs, line feeds, line feeds, and so on at the end of each line of each information part (for example, complaint information, corrected version complaint information, etc.) in a display document that is an HTML document, for example. Each character code of return, form feed, or vertical tab may be removed, and the line feed at the end of the line may be represented by the HTML tag <br> for line feed.

[3-1-5-7-2. Generating claim-based drawing information]
The claim information generation unit 205a realizes the claim-based drawing information generation process by generating claim-based drawing information based on the claims included in the invention document acquired by the invention document acquisition unit 2021. FIG. The claim-based drawing information is information indicating the drawing number of each drawing, the key phrases to be described in each drawing, the relationship between the key phrases, and the code when the key phrase corresponds to the code. Claim-based drawing information does not need to be complete enough to be used as drawings for patent application. The complaint information generation unit 205a can generate drawing type information indicating the drawing type of each drawing in association with the drawing number of each drawing in the complaint base drawing information. The drawing type includes, for example, a block diagram, a flow chart, a diagram representing the content recorded in a recording medium, and a diagram representing means, functions, etc. implemented by a program.

If the invention document acquired by the invention document acquisition unit 2021 includes a specification, the claim information generation unit 205a has a good possibility that drawing information (for example, drawing document) has already been generated. Therefore, the execution of the claim-based drawing information generation process may be omitted.

[3-1-5-7-2-1. Determination of sign]
When generating claim-based drawing information, the claim information generation unit 205a extracts the symbols from the key words and phrases extracted by the key word extraction unit 2051 from the claims of the invention document acquired by the invention document acquisition unit 2021. A code determination process for determining a code to correspond to an element represented by an important phrase that satisfies a predetermined condition to be determined is executed.

The complaint information generation unit 205a creates complaint-based drawing information by associating the important words and phrases whose symbols are determined by the symbol determination process with the symbols. If the invention document acquired by the invention document acquisition unit 2021 includes a specification, the claim information generation unit 205a may omit the code determination process.

Among the important phrases extracted by the important phrase extraction unit 2051 from the claim of the invention document, the predetermined condition related to the important phrases whose signs are to be determined in the sign determination process is, for example, the category type of the element represented by the important phrases ( For example, it is a condition related to a category type that is classified into one of programs, data, products, and methods). For example, an important phrase classified into a program or data category does not satisfy a predetermined condition for code determination, and the complaint information generation unit 205a does not determine a code corresponding to the important phrase. This is because key words that are classified into the category type of program or data can usually be understood by themselves. The category type of an important phrase among programs, data types, or methods can be specified, for example, by whether or not the important phrase includes a character string predetermined for each category at the end of the word. Keywords that do not correspond to any of these can be identified as category types of things.

For example, when elements represented by multiple key phrases specified as the category type of a method or product have structural inclusion relationships, the multiple key phrases satisfy a predetermined condition to be subject to sign determination, and the claim The information generation unit 205a determines a code corresponding to each of the plurality of important phrases. A block diagram showing the elements represented by each of the multiple key phrases usually makes it possible to understand each element. In addition, it is useful to give each element a reference numeral in the configuration diagram. Whether or not the elements represented by a plurality of key words have a compositional inclusion relationship is determined by the attribute of each key word specified by the attribute specifying unit 2056, "the element represented by the key word and another key word." This can be achieved by referring to the "compositional containment relationship with the represented element".

The complaint information generation unit 205a determines a code based on the structural inclusion relationship of the elements represented by the key words that satisfy a predetermined condition for determining the code.

As a specific example, the first For important words and phrases, codes represented by code characters, which are characters that can be used as codes, are determined. Then, the complaint information generation unit 205a adds a code character to the end of the code for the first important phrase when the element represented by the first important phrase includes the element represented by the second important phrase. is determined as the code for the second key phrase. In this example, when the complaint information generation unit 205a determines the code corresponding to the first key phrase as "10", for example, it determines the code corresponding to the second key phrase as "101", for example.

As another specific example, an element that is structurally included in the element represented by any other key phrase and is not structurally included in the element represented by any other key phrase A code represented by a string of Arabic numerals is tentatively determined for one keyword. Then, if the element represented by the first key phrase includes elements represented by each of n (n is a natural number) key phrases, the complaint information generation unit 205a generates the following for the first key phrase: The code is finally determined by adding k digits (k is a natural number) of zeros (0) to the end of the tentatively determined code. In other words, in the code determination process for determining the sign for the important phrase, the complaint information generation unit 205a determines the sign for the important phrase that represents an element that structurally includes the element represented by another important phrase. can determine its sign according to the number of elements represented by other key words (for example, n) that the element represented by the key word structurally includes. The claim information generation unit 205a adds a character string corresponding to 1 to n represented by k-digit Arabic numerals to the code provisionally determined for the first key phrase as the code for each of the n key phrases. determine the sign of In this example, the complaint information generation unit 205a provisionally determines the code corresponding to the first key phrase to be, for example, "1", and the element represented by the first key phrase is the element represented by each of the 15 key phrases, for example. is included in the configuration, the code "1" provisionally determined corresponding to the first important phrase is added with "0" for the number of two digits necessary to represent the 15 to finally determine the code "100" corresponding to the first key phrase. Subsequently, the complaint information generation unit 205a determines each code of "101" to "115" corresponding to the 15 key phrases representing the 15 elements included in the element represented by the first key phrase. do. In the above example, the first key phrase that represents an element that is structurally included in the element represented by any other key phrase and is not structurally included in the element represented by any other key phrase There may be a plurality of key phrases corresponding to .

The claim information generation unit 205a may execute the code determination process even when the invention document acquired by the invention document acquisition unit 2021 includes a specification. The complaint information generation unit 205a determines the sign by using the corresponding sign when the sign already corresponds to the key phrase that satisfies the predetermined condition for which the sign is to be determined. For example, when determining a code when a code already corresponds to an important term, the claim information generation unit 205a converts the code described in the "description of code" column of the specification of the invention document into the code of the invention document. The code may be determined by preferentially adopting it over the codes described in other parts. In addition, in the column of "explanation of the code" of the specification of the invention document, when a plurality of codes are written in association with the same important phrase, the claim information generation unit 205a Alternatively, the code may be determined by selectively adopting one of the first codes by sorting such as natural ordering. Note that the invention document analysis system 20 uses, for example, a standard library “sort” for sorting in Python (registered trademark), or a library “natsort” provided by a third party for sorting in natural order. It may be used to perform sorting. Whether or not a sign already corresponds to the key phrase can be determined based on “sign” as one attribute of the key phrase specified by the attribute specifying unit 2056 . The complaint information generation unit 205a determines that one or more of the important words and phrases that satisfy the predetermined conditions to be determined as the codes already correspond to the signs, and that one or more of the important words and phrases that satisfy the predetermined conditions are , when the code does not correspond yet, the complaint information generation unit 205a, when determining the code corresponding to the important phrase for which the code does not correspond yet, does not overlap with the code already corresponding. or to make it identifiable that the code is an automatically determined code, a predetermined character string (eg, "auto", "at ” etc.) may be added.

[3-1-5-7-2-2. Determination of drawing content]
The complaint information generation unit 205a determines the drawing content as the complaint-based drawing information generation process.

Specifically, as the claim-based drawing information generation process, the claim information generation unit 205a extracts a plurality of key words extracted by the key word extraction unit 2051 from the claim of the invention document acquired by the invention document acquisition unit 2021, for example. If there is a compositional inclusion relationship between the represented elements, a configuration diagram is generated based on the inclusion relationship. Key phrases representing each of the elements having a structural inclusion relationship are determined by the attribute specified by the attribute identification unit 2056 based on the determination result of the inter-element relationship determination unit 2058, which is the “element represented by the key term and the element represented by the other key term. It can be determined by the item of “structural inclusion relationship with”.

In the configuration diagram, for example, key phrases representing the elements on the included side are enclosed, and key phrases representing the elements on the included side are displayed outside a frame (for example, a rectangular frame) formed by connecting codes corresponding to the key phrases with lead lines. to enclose the key phrase on the containing side and the frame line related to the element on the included side, and the code corresponding to the key phrase on the containing side (for example, the code determined in the code determination process) is drawn with a leader line It is a figure which drew the frame line which connected. If the code corresponding to the important phrase contained in the configuration diagram is not decided, the code and the leader line are omitted. If the inclusion relationship is a nested structure, the borders of multiple key phrases are nested. The configuration diagram may be, for example, an incomplete drawing composed of a plurality of character strings arranged at relatively appropriate positions, omitting the above-described frame lines and leader lines.
The claim information generation unit 205a can generate the above configuration diagram as a drawing in the claim-based drawing information that is included in the patent application related information and should be displayed in the display document.

Using key phrases a, b, c, c, d, and e that represent each element related to an object, a specific example of a configuration diagram shows that the element represented by the key phrase a is the key phrase If the elements represented by b, key phrase c and key phrase d are included in parallel, and the element represented by key phrase d includes the element indicated by key phrase e, the key phrase a is shown in the drawing in the frame In the rectangular frame described in (1), each rectangular frame in which the key phrase b, the key phrase c, and the key phrase d are written without enclosing the key phrase a are arranged side by side so as not to enclose each other. A rectangular frame with key phrase d written inside a rectangular frame with key phrase d written inside a rectangular frame with key phrase e written inside the frame without surrounding key phrase d is arranged, and in each rectangular frame , When there is a code determined corresponding to the important phrase described in the frame, the code is described by being connected with the rectangular frame by a leader line.

If the "first line number" as an attribute of key phrases is defined to represent the number of the first line described in the claim of the invention document, it is arranged in parallel in the configuration diagram. Each element may be listed from top to bottom of the drawing in ascending order of "first appearance line number" as one attribute of the important phrase representing the element. As a result, for example, when the claim section is described in the enumeration type of the constituent elements, the claim information generation unit 205a generates a configuration diagram corresponding to the enumeration order, so that the generated configuration diagram can be grasped. can be easier.

In cases such as when it is assumed that each item of a claim relating to a method in an invention document is described in the form of enumerating constituent elements and arranging the constituent elements in order of operation for the purpose of facilitating understanding, When there is an inclusion relationship among the elements represented by a plurality of key phrases related to the method, the claim information generation unit 205a may generate a flow chart instead of the configuration diagram. As a specific example, when there is an inclusion relationship in which the key phrase "apparatus control method" includes the key phrase "sensing procedure", the key phrase "operation pattern determination procedure", and the key phrase "apparatus operation control procedure", If the "first appearance number" as the attribute of the important phrase is "sensing procedure", "operation pattern determination procedure", and "equipment operation control procedure" in ascending order, "equipment control processing" is shown in the drawing. Add the character string "start" to and write a rounded rectangular frame in the frame. Place a rectangular frame in which the "operation pattern determination procedure" is described, place a rectangular frame in which the "equipment operation control procedure" is described in the frame below it, and place the "operation control process" below it. A flow chart is drawn by arranging rounded rectangular frames with the character string "END" written in the frames and connecting the frames from top to bottom with line segments.

In the claim-based drawing information generation process, the claim information generation unit 205a, for example, extracts from the claim of the invention document acquired by the invention document acquisition unit 2021, between the elements represented by the key words and phrases extracted by the key phrase extraction unit 2051, When there is a relationship between the recording medium and the contents of the recording medium, a diagram representing the recording contents of the recording medium is generated based on the relationship. The key words and phrases representing each element in relation to the recording medium and the content of the recording medium are identified by the attribute specified by the attribute specifying unit 2056 based on the determination result of the inter-element relation determining unit 2058, which is the “recording of the elements represented by the key words and phrases”. It can be determined by the item of "Contents". Even if there is a relationship between the recording medium and the contents of the recording medium between the elements represented by the multiple key phrases extracted by the key phrase extraction unit 2051 from the claim of the invention document, the complaint information generation unit 205a When the contents of the recording medium are only elements classified into one program, generation of the configuration diagram can be omitted.

A diagram representing the contents recorded on a recording medium is, for example, a frame (for example, a rectangular frame) that encloses important terms representing elements of the recording medium and connects the symbols corresponding to the key terms with lead lines. FIG. 2 is a diagram showing one or more key phrases representing data, information, etc., corresponding to the recorded contents of an element, each surrounded by a minimum frame line (for example, a rectangular frame with rounded corners). It should be noted that the drawing showing the content recorded on the recording medium may be an incomplete drawing in which the above-described frame lines and leader lines are omitted.

In the claim-based drawing information generation process, the claim information generation unit 205a, for example, extracts from the claims of the invention document acquired by the invention document acquisition unit 2021, between the elements represented by the key words and phrases extracted by the key phrase extraction unit 2051, When there is a relationship between a program and its implementation contents, a diagram representing means, functions, etc. implemented by the program is generated based on the relationship. An important phrase representing each element having a relationship between the program and its implementation content is the attribute "realization content of the element represented by the important phrase" specified by the attribute specifying unit 2056 based on the determination result of the inter-element relationship determination unit 2058. It can be determined by the item.

[3-1-5-7-2-3. Determination of drawing number]
The complaint information generation unit 205a determines a drawing number for each determined drawing content as the complaint-based drawing information generation process.

As a specific example, the complaint information generation unit 205a generates the key phrase of the key phrase with the smallest “first appearance claim number” as an attribute among the key phrases representing the elements included as the content of the drawing for each drawing such as the determined configuration drawing. Identify the "first appearance claim number" as the "first appearance claim number" of the drawing. Then, the claim information generation unit 205a determines the drawing number of each drawing so that the drawing numbers are consecutive numbers starting with 1 in ascending order of the "first appearance claim number" specified for each drawing. When a plurality of drawings have the same “first-appearing claim number”, the claim information generation unit 205a, for example, based on a predetermined drawing priority order, and determine the drawing number. An example of the predetermined drawing priority order is a configuration diagram related to an object, a configuration diagram related to data, a diagram representing the contents of recording on a recording medium, a configuration diagram related to a method, a means realized by a program, a function, etc. The order of the figures is listed.

[3-1-5-7-2-4. Generation of claim-based drawing information part in display document]
When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the claim-based drawing information as a display document (for example, an HTML document), the claim information generation unit 205a outputs the display document as Generate claim-based drawing information included in patent application related information.

The claim-based drawing information portion of the patent application-related information as a document for display generated by the claim information generation unit 205a includes, for example, the drawing number of each drawing, important phrases to be described in each drawing, and the relationship between the important phrases. If a code corresponds to a key phrase, one or more display elements corresponding to the code, etc. are included. As a specific example, the claim information generation unit 205a writes claim-based drawing information sandwiched between <article> and </article> tags in an HTML document. For each drawing in ascending order, a display element indicating the drawing number of the drawing is described by sandwiching the drawing number between the <span> tag and the </span> tag, and each display element corresponding to the drawing is described. On the other hand, a code is described by sandwiching it between <span> and </span> tags that include, for example, a class name for identifying each code. For example, a browser may interpret the presentation document to display each presentation element. The complaint information generating unit 205a controls the display mode of the display elements (e.g., highlighted display, colored display, etc.) for the display elements corresponding to the drawing numbers, codes, or key words included in the complaint base drawing information portion. may add display control information for

For example, when the claim-based drawing information in the patent application-related information as a document for display is generated as an HTML document conforming to HTML5, the claim information generation unit 205a creates <canvas> in which a predetermined id attribute is added to the HTML file. Get the canvas object with the getElementById method that specifies the value of the id attribute with a function, etc., including the tag, get the drawing context with the getContext method of the canvas object, and use the fillText method, strokeRect method, and quadraticCurveTo method of the drawing context By defining processing for drawing character strings, rectangular frames, leader lines, etc., drawing of a configuration diagram can be realized.

[3-1-5-7-3. Generate claim-based statement information]
The claim information generation unit 205a realizes the claim-based specification information generation process by generating claim-based specification information based on the claims included in the invention document acquired by the invention document acquisition unit 2021. FIG. The claim-based specification information represents the content of an incomplete specification, and does not need to be complete enough to be used as a specification for a patent application. The claim-based specification information may be used to efficiently create an appropriate specification when the specification in the invention document is incomplete.

The claim-based specification information includes, for example, headings similar to those of Japanese patent application specifications (e.g., "Title of the Invention," "Problems to be Solved by the Invention," "Method for Carrying Out the Invention," etc.). ), including the content that follows each heading.

The claim information generation unit 205a extracts each claim in the claims of the invention document (for example, each claim ), all claimable origin terms are extracted. A claim that originates from a claim is a claim that does not quote other claims, or a claim that quotes other claims but whose subject matter is different from that of the claim to which it is referred.

The claim information generation unit 205a identifies, for each of the extracted claim object originating claims, key words and phrases representing the claim object of the claim object originating claim. In the important phrase extracted by the important phrase extraction unit 2051, the attribute specifying unit 2056 specifies "whether or not the element for which the claim is claimed" is specified as one attribute, so the complaint information generation unit 205a By referring to this attribute or the like, key phrases representing the claimable object of the claimable object originating claim are specified. If there are a plurality of the same key phrases as elements of the set of all the specified key phrases to be claimed, the complaint information generation unit 205a removes all the key phrases other than one of the plurality of key phrases. . Then, the claim information generating unit 205a selects the set of important phrases to be claimed (that is, the set of important phrases to be claimed that are different from each other) to be described in the "title of the invention" column of the claim-based specification information as determines the invention name string of For example, if there is only one key phrase as an element of a set of key phrases of different claim objects, the invention title character string is the character string of that one key phrase. For example, when there are a plurality of key phrases as elements of a set of key phrases to be claimed that are different from each other, the invention name character string is written in a predetermined format by listing each of the key phrases in a predetermined order. It is the placed string. As an example of a predetermined order related to this enumeration, among key words in a set of key words to be claimed that are different from each other, the first-appearing claim number specified by the attribute specifying unit 2056 as an attribute of the key words, natural number Among them, the smallest order can be mentioned. According to an example of this predetermined order of listing, an invention name character string in which important words and phrases to be claimed are listed in accordance with the order of description in claims is determined. An example of a predetermined layout format is a format in which important words and phrases other than the last are connected with comma characters "," and the last important words and phrases are connected with "and". As a specific example, if the key words in the set of key words to be claimed that are different from each other and arranged in the order of the first claim number are "lighting control device," "lighting control method," and "lighting control program." In the claim-based specification information, the invention title character string arranged in a predetermined format to be followed by the "title of the invention" is, for example, "lighting control device, lighting control method and lighting control program".

The claim information generation unit 205a uses, for example, a set of key phrases of the claim object that are different from each other, which are determined based on the key phrases that represent the claim object of each claim object originating claim, to generate the "invention Decide what to write in the “Problem to be solved by the company” column. The claim information generation unit 205a uses each important phrase in the set of important phrases to be claimed that is different from each other and a predetermined character string specified corresponding to each of the important phrases to generate a predetermined format. to generate one or more sentences connected by , and determine the generated sentences as description contents following the heading "Problems to be Solved by the Invention". The content of this predetermined character string is, for example, an incomplete message for description support indicated by incomplete message information included in the setting information acquired by the setting information acquisition unit 201 . Note that the claim information generation unit 205a determines that the elements represented by the key words in the sets of key words to be claimed that are different from each other are classified into categories such as products, methods, programs, program recording media, data structures, data recording media, and the like. Depending on which category it belongs to, a predetermined character string predetermined for each category may be specified, or a predetermined character string may be specified uniformly. As a specific example, in a case where the important words and phrases in the set of important words and phrases to be claimed that are different from each other are "lighting control device", "lighting control method", and "lighting control program", the claim information generation unit 205a For example, the contents of the description following the "problem to be solved by the invention" of the base specification information, such as "Prior art: ■ {reason etc.}, ■ {problem/effect: reduction of ~/improvement of ~ etc.} The present disclosure provides a lighting control device that can be useful for {problems/effects: reduction of ~/improvement of ~, etc.} Also, the present disclosure relates to the lighting control device provide a lighting control method and a lighting control program for Here, in the contents of the claim-based specification information related to the incomplete specification, the part shown as a format example in which the character string is sandwiched between the solid block and the opening curly bracket "■{" and the closing curly bracket "}" The incomplete description part of the description support incomplete message indicates that it is an incomplete part in order to utilize it as a patent application specification, that is, a part that should be edited as appropriate.

The claim information generation unit 205a uses, for example, a set of key phrases of the claim object determined based on the key phrases representing the claim object of each claim object originating claim, to generate the "to solve the problem" of the claim-based specification information. Determine the content of the column “Means of The claim information generation unit 205a uses at least one of the item number of each claimable originating term, each key phrase of the claimable target, and a predetermined character string specified corresponding to each key phrase to generate a One or more sentences linked in a prescribed format are generated, and the generated sentences are determined as description contents following the heading "Means for Solving the Problem". The content of this predetermined character string is, for example, an incomplete message for description support indicated by incomplete message information included in the setting information acquired by the setting information acquisition unit 201 . The claim information generation unit 205a determines that the element represented by each key word in the set of key words to be claimed belongs to any category such as a product, a method, a program, a program recording medium, a data structure, a data recording medium, etc. Depending on the category, a predetermined character string that is predetermined for each category may be specified, or a predetermined character string may be specified uniformly. As a specific example, in a case where the important words and phrases in the set of important words and phrases to be claimed that are different from each other are "lighting control device", "lighting control method", and "lighting control program", the claim information generating unit 205a For example, the description following "Means for Solving the Problems" in the book is changed to "The lighting control device in the present disclosure is (ii) claim 1. Also, the lighting control method in the present disclosure is (ii) claim 2. , the lighting control program in the present disclosure is defined as (3). This description may be split into multiple lines. In the content of this description, the part indicated by the example of the form of claim n to which a solid block "■ claim n" is added is in the content of claim n (n is a natural number) or is predetermined in the content of the description. It indicates that it is a part that can be replaced in the content that has been subjected to a predetermined conversion process (for example, a conversion process that deletes line feeds, period characters, etc.). Note that the claim information generation unit 205a converts the portion of "■ claim n" in the description content to the description content of claim n or to the content obtained by subjecting the description content to predetermined conversion processing. , may be substituted.

The complaint information generation unit 205a can determine the description contents of the "brief description of the drawing" column of the complaint-based specification information based on the complaint-based drawing information generated in the complaint-based drawing information generation process, for example. As a specific example, first, the complaint information generation unit 205a identifies the main key phrases for each drawing corresponding to the drawing type of the drawing based on the complaint base drawing information and the drawing type information. For example, in a drawing whose drawing type is a configuration diagram or a flow chart, key phrases representing elements that structurally include the most elements become main key phrases of the drawing. In addition, in a drawing whose drawing type is a drawing representing the content recorded on a recording medium, key words representing the elements that are the recording medium are the main key words of the drawing. In addition, in a drawing whose drawing type is a diagram representing means, functions, etc. realized by a program, key words representing elements that are programs become the main key words of the drawing. Then, the claim information generation unit 205a identifies a character string in a predetermined format that includes the drawing number, the identified key phrase, and the drawing type for each drawing, thereby generating claim-based specification information. Decide on the contents of the column “Brief description of the drawing” in As an example, if the main key phrase of the drawing with drawing number 1 is "control system" and the drawing type is a configuration diagram, the claim information generation unit 205a creates a "brief description of the drawing" column. In "Fig. 1" where the contents of one line are sandwiched between the opening square bracket and the closing square bracket, the sentence "Fig. 1 is a configuration diagram showing an example of the configuration of the control system." Let the following string.

The claim information generation unit 205a generates the claim-based specification information based on, for example, the item number of each item of the claim of the invention document, key phrases representing the object of the claim of the item, and a predetermined character string. A portion of the description in the "Detailed Description" column (that is, the description following the "Detailed Description" heading) may be determined. The content of this predetermined character string is, for example, an incomplete message for description support indicated by incomplete message information included in the setting information acquired by the setting information acquisition unit 201 . Note that the claim information generation unit 205a determines that the element represented by the key words of the claim object of each claim of the invention document is, for example, a product, a method, a program, a program recording medium, structured data, a data recording medium, or the like. Depending on which category it belongs to, for each category, a predetermined character string (for example, for programs, a character string referring to installation on a computer, etc.) may be specified, or a predetermined character string may be specified uniformly. A string may be specified. As a specific example, the important terms of claims 1 to 4 of the claims of the invention document are, in order, "lighting control device", "lighting control device", "lighting control method", and "lighting control program", In the case where claim 2 cites claim 1, the claim information generation unit 205a writes, for example, the following as the content to be described in a part of the column of "mode for carrying out the invention" (for example, the beginning part, etc.): “The lighting control device in the present disclosure includes: (1) Claim 1. This provides (2) {reasons, etc.}, (2) {effects: it can be done / can be done / the possibility of ~ can be increased / it can be useful for ~ etc.} Here, (1) claim 2. Thereby, (2) {reasons, etc.}, (2) {effects: can be done / can be done / the possibility of ~ can be increased / can be useful for ~ etc.}. , the lighting control method in the present disclosure includes: (1) Claim 3. Thereby, (2) {effect} Further, the lighting control program in the present disclosure includes (2) Claim 4. A device equipped with a microprocessor for executing this lighting control program , etc., the device etc. can implement {program implementation contents, etc.: lighting control method, lighting control function, etc.}.Therefore, this lighting control program can implement {effect}. The lighting control device and related technology described above may be embodied in various aspects as a whole or a part of equipment, devices, integrated circuits, systems, methods, computer programs, computer-readable recording media, etc. get.” This description may be divided into multiple lines. In the content of this description, the part indicated by the example of the format of claim n with the addition of a solid block "■ claim n" is included in the content of claim n (n is a natural number) or in advance for the content of the description. A part that can be replaced with the content that has been subjected to prescribed conversion processing (for example, conversion processing that deletes line breaks, deletes period characters, deletes quoted descriptions that cite claim paragraphs, etc.) indicate. Note that the claim information generation unit 205a converts the portion of "■ claim n" in the description content to the description content of claim n or to the content obtained by performing the above-described predetermined conversion processing on the description content. , may be replaced with Of the key words extracted by the key word extracting part 2051 in the description content after replacement, the complaint information generation unit 205a adds the corresponding code immediately after the key word whose corresponding code is determined by the code determination process. may be inserted. As a specific example of the predetermined conversion process described above, when the contents of claim 5 include the description "of a vehicle equipped with the lighting control device according to claim 1...", the description is changed to "the above-described An example of conversion to an expression that does not use "claims" is given, on the premise that the descriptions of the cited claims are described above.

The claim information generation unit 205a, for example, based on the claim-based drawing information and drawing type information generated in the claim-based drawing information generation process, and a predetermined character string, the claim-based specification information "In order to carry out the invention may determine part of the description in the "Mode" column. The content of this predetermined character string is, for example, an incomplete message for description support indicated by incomplete message information included in the setting information acquired by the setting information acquisition unit 201 . As a specific example, the claim information generation unit 205a generates each drawing number in ascending order based on the claim-based drawing information and the drawing type in order to write sequentially in a part of the "Mode for Carrying Out the Invention" column. The following statements are made in connection with the drawings. That is, the claim information generation unit 205a writes a sentence including the drawing number and the drawing type for each drawing in ascending order of the drawing number in a part of the "Mode for Carrying Out the Invention" column, following that sentence, for each element based on the relationship between the elements contained in the drawing, key words representing that element and other key words as necessary to describe the key words; Write a sentence including an incomplete message for description support for explaining the important phrase. Note that if the key phrase setting dictionary acquired by the key phrase setting dictionary acquisition unit 203 includes a sentence explaining the key phrase in association with the key phrase, the complaint information generation unit 205a In the column of "Mode for Carrying Out the Invention" of the specification information, instead of or in addition to the incomplete message for description support to explain the A sentence explaining the important phrase corresponding to the important phrase in the phrase setting dictionary may be described. Other important phrases necessary to explain the important phrases and the incomplete message for description support for explaining the important phrases are, for example, "an element represented by the Attributes of key phrases such as "structural inclusion relationship of the key phrase", "recorded content of the element indicated by the key phrase", and "realization content of the element indicated by the key phrase", etc., and the key phrase. For example, for each of a plurality of important phrases extracted by the important phrase extraction unit 2051 from the claims of the invention document, the claim information generation unit 205a is configured to determine the elements represented by the important phrases and the elements represented by the other important phrases. Based on the inclusion relationship, the recorded content of the element represented by the key phrase, or the implementation of the element represented by the key phrase, the claim is based on the incomplete writing support message to explain the key phrase. It may determine the portion of the description that follows the "Detailed Description" heading in the base specification information. The claim information generation unit 205a, for example, for each of a plurality of key phrases extracted by the key phrase extraction unit 2051 from the claim of the invention document, the element represented by the key phrase includes the element represented by the other key phrase. Or, when it is structurally included in an element represented by another key phrase, a code is determined for that key phrase based on the structural inclusion relationship of the key phrase and other key phrases. A sign determination process may be performed. The claim information generation unit 205a selects important words and phrases in the code determination process from among the important words and phrases included in at least part of the description content following the heading of "Mode for Carrying out the Invention" in the claim-based specification information. For important phrases whose codes have been determined, the codes are inserted immediately after the important phrases. As a specific example, in the claim-based drawing information, "Fig. 1" is a "configuration diagram" of the main important phrase "control system", and the "control system" is a "human sensor" and a "control content determination device". "Lighting control signal transmitter" is included in the configuration, the code corresponding to "control system" is "10", the code corresponding to "human sensor" is "11", and the "control content determination device" When the corresponding code is determined to be "12" and the code corresponding to "lighting control signal transmitting device" is determined to be "13", the complaint information generating unit 205a determines that "implementing the invention" in the complaint-based specification information In a part of the column of "Form for the purpose", "Fig. 1 is a configuration diagram showing an example of the configuration of the control system 10. The control system 10 includes: {Description of the control system 10 (function / operation / principle of operation / attribute/shape/size/material/mode/input/output/generation-related information, etc.)} The control system 10 includes a human sensor 11, a control content determination device 12, and a lighting control signal transmitter 13. The sensor 11 includes: {description of the human sensor 11} The control content determination device 12: {description of the control content determination device 12} The lighting control signal transmission device 13: {description of the lighting control signal transmission device 13} }." is described. The claim information generation unit 205a, for example, after writing a description related to "Fig. 1" in part of the "Mode for Carrying Out the Invention" column in the claim-based specification information, so as to follow the description, A description related to FIG. 2 is provided. In addition, since the same elements may be included in a plurality of drawings indicated by the claim-based drawing information, the claim information generation unit 205a may prevent redundant descriptions by adding the phrase "In order to carry out the invention" in the claim-based specification information. In the column of "Form of", sentences with the same content may not be described redundantly. For example, the claim information generation unit 205a extracts all the important phrases extracted by the important phrase extraction unit 2051 from the claims of the invention document acquired by the invention document acquisition unit 2021, in the claim-based specification information, "In order to carry out the invention If there are important words and phrases that are not used in the explanations, etc. related to the above drawings in the "Form" column, include an incomplete message for description support to explain the important words and phrases that are not used in the explanations, etc. The text may be added to the "Description of the Invention" column. As a result, the description of all important terms in the claims of the invention document can be covered in the "Modes for Carrying Out the Invention" column in the claim-based specification information.
As a modified example of the claim information generation unit 205a, the claim information generation unit 205a can, for example, not use the claim-based drawing information and the drawing type information, and can perform inclusion between important words and phrases expressed in the claims of the invention document. Based on the relationship, a sentence indicating the inclusion relationship between the important terms may be determined as part of the description content following the heading of "Mode for Carrying Out the Invention" in the claim-based specification information. Further, as another example of the complaint information generation unit 205a, the complaint information generation unit 205a extracts each of a plurality of key phrases extracted by the key phrase extraction unit 2051 from the claims of the invention document. To explain the key phrase, determined based on the compositional inclusion relationship with the element indicated by the other key phrase, the recorded content of the element indicated by the key phrase, or the actual content of the element indicated by the key phrase Part of the description content following the heading of "Mode for Carrying Out the Invention" in the claim-based specification information may be determined based on the incomplete message for description support in . For example, if the key phrase "control system" extracted from the claim includes the key phrase "human sensor", the key phrase "control content determination device", and the key phrase "lighting control signal transmitter" in terms of configuration. In addition, the complaint information generation unit 205a according to this example writes, as part of the description contents following the heading "Mode for Carrying Out the Invention", "The control system includes, for example, a human sensor and a control content determination device. The lighting control signal transmitting device may be included, or, for example, any one of the motion sensor, the control content determining device, and the lighting control signal transmitting device may not be included. Please correct this sentence as appropriate based on the determination of whether or not it is an essential element in view of the consideration and whether or not it is an element that should be included in this embodiment)}. It is also possible to describe a character string with an incomplete message for description support, which does not indicate a relationship and is used after being modified as appropriate. Also, for each key phrase in this character string, a corresponding code may be added immediately after the key phrase. As a result, inventors, etc. or patent attorneys can easily prepare specifications including examples of embodiments that can respond to future changes in independent claims based on claim-based specification information. there is a possibility.

The complaint information generation unit 205a can include a fixed phrase in the complaint-based specification information according to the fixed phrase information in the setting information acquired by the setting information acquisition unit 201, for example. Also, the complaint information generation unit 205a can insert a paragraph number, for example, into each line in the complaint-based specification information.

When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the claim-based specification information as a display document (for example, an HTML document), the claim information generation unit 205a outputs to generate claim-based specification information included in the patent application-related information of FIG. 25 shows an example of claim-based specification information in patent application related information as a display document displayed on the browser. FIG. 25 is an example of claim-based specification information generated corresponding to the claim information illustrated in FIG. In FIG. 25, part of the claim-based specification information is omitted for convenience. For example, a solid block in the claim-based specification information illustrated in FIG. The display element of the description support incomplete message "{Description of A part 11}" related to "A part") is an operation-responsive GUI element, and is acquired by the invention document acquisition unit 2021 in response to a mouse click operation, etc. The display control information is added so that the important phrase inclusion description enumeration process for listing the descriptions of each line including the important phrases related to the incomplete message for description support is executed from another invention document related to the created invention document. It can be assumed that there is This separate invention document is, for example, one or more invention documents specified by a user's designation (eg, designation in setting information). With the operation-responsive GUI element for executing the important phrase inclusion description enumeration process related to this incomplete description support message, the user (for example, an inventor or a patent attorney) can use the incomplete description support message as an existing invention document. It may become easier to revise the sentences to appropriate content that is utilized. For example, in the important phrase inclusion description enumeration process related to the incomplete message for description support " {explanation of A part 11 }" related to the important phrase "A part", for example, the important phrase "A part" includes the case particle " A description followed by "wa" or a case particle compound "towa" may be searched for in another invention document related to the invention document. As a result, by the key phrase inclusion description enumeration process, lines including sentences describing the key phrase "part A" as the subject can be listed.

The claim base specification information part of the patent application-related information as a display document generated by the claim information generation unit 205a is, for example, the claim base specification related to the incomplete specification generated by the above-described claim base specification information generation process. Contains one or more display elements corresponding to the content of each line in the specification information, and if there are one or more important phrases extracted by the important phrase extraction unit 2051 in each line of each section, each important phrase Contains one or more corresponding display elements. As a specific example, the complaint information generation unit 205a creates a claim-based specification under the <article> tag when describing the complaint-based specification information sandwiched between <article> and </article> tags in an HTML document. For each line of the claim-based specification information related to the incomplete specification generated in the document information generation process, the display element corresponding to the line is displayed with the <span> tag and the </span> tag. <span> tag and <span> tag of the display element corresponding to one line, for each important phrase in that line, the display element corresponding to the important phrase is added with <span> tag and </span> Describe by sandwiching the important phrase with a tag. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in the claim-based specification information portion enables, for example, the contents of the corresponding line to be displayed.

The complaint information generation unit 205a creates display elements corresponding to headings, important phrases, description support incomplete messages, or codes included in the complaint-based specification information portion of the document for display, for example, to display the display elements. Add display control information for controlling aspects (for example, highlighting, colored display, display transition, etc.). This display control information can be realized, for example, in the same manner as the display control information added to the display elements in the complaint information in the display document. Therefore, the display element of the important phrase described in the claim-based specification information part in the display document is, for example, to display the description part containing the important phrase in the claim information in the display document according to the operation can function as a GUI element corresponding to the operation of For example, the complaint information generation unit 205a adds display control information for controlling the display mode of the display element to the display element of the important phrase included in the complaint-based specification information in the document for display, and generates the display control information. makes the display element of the key phrase function as a GUI for displaying (for example, linking) the description part containing the key phrase in the claim information in the document for display in response to the operation of the display element belongs to. A user (for example, an inventor or a patent attorney) can efficiently create an appropriate specification by displaying claim-based specification information on a browser. In addition, the user can create an invention document including claims and a specification by including the created specification in the invention document or the like that is the basis for creating the claim-based specification information. Then, the user can cause the invention document including the claims and the specification to be analyzed again by the invention document analysis system 20, including warning information, specification information, etc. output as analysis results of the specification of the invention document. Patent application related information will be made available.

An example of the display control information added to the display element corresponding to the code included in the claim-based specification information portion of the document for display will be described below.

When a code is included in the claim-based specification information, the claim information generation unit 205a displays the code in accordance with the operation to display the part containing the same code as that in the claim-based drawing information in the document for display. The display control information for making the display element having the GUI function of the code may be added to the display element of the code. This display control information defines, for example, the function name of the function of the script that is activated with the code as an argument according to the operation, or the function itself. A part in the drawing information is determined to be identified by searching for its code. The claim information generation unit 205a, for example, in response to an operation on the code in the claim-based specification information, generates a function related to display control information for displaying a portion containing the same code as that code in the claim-based drawing information, It may be determined to display a portion containing the same code as the code in the claim-based drawing information within a range where the display element of the code displayed and operated by the browser is not hidden. For example, the complaint information generation unit 205a divides the display screen of the browser into a plurality of display areas, and the display area of the complaint-based specification information and the complaint displayed according to the operation related to the code in the complaint-based specification information. A display area such as a part of the base drawing information may be displayed in parallel. For example, the complaint information generation unit 205a uses the display control information added to the display element for the code to create a function that is activated in response to the operation of the code to the same code as that in the complaint-based drawing information in response to further operation. It may be determined to execute a process of switching and displaying multiple parts containing a code (for example, two or more drawings containing the code), or all parts containing the same code as the code in the claim-based drawing information may be defined so as to perform a process of reducing and collectively displaying the data as necessary. The claim information generation unit 205a, for example, in response to an operation on the code in the claim-based specification information, generates a function related to display control information for displaying a portion containing the same code as that code in the claim-based drawing information, It may be determined to highlight the same code as that code in the claim-based drawing information.

An example of the display control information added to the display element corresponding to the description support incomplete message included in the claim-based specification information portion of the display document will be described below.

The claim information generation unit 205a displays a display having a GUI function for changing the content of the incomplete description support message in accordance with an operation when the claim base specification information includes an incomplete message for support in description. A display element configured by adding display control information for an element (that is, an operation-responsive GUI element) to a display element (for example, a <span> tag or the like of an incomplete description support message) to the incomplete description support message. ) may be added to The addition of the display control information is realized, for example, by describing information indicating the operation and information indicating the function activated by the operation in the <span> tag added to the incomplete message for description support. This display control information is information for activating a script that executes the above-mentioned important phrase inclusion description listing process according to an operation when an important phrase is included in an incomplete message for description support, or information for exemplifying below. This is information for activating the script that executes the processing to be executed. This display control information defines, for example, the function name of the script function or the function itself that is activated with the description support incomplete message as an argument according to the operation. Displays an input field with an unfinished support message as the default value, reflects the editing operation on the input field, and replaces the text of the editing operation result with the display content of the display element instead of the original unfinished message for writing support. is defined as In addition, the complaint information generation unit 205a, for example, the incomplete message for description support following the subject "X device 1" included in the complaint-based specification information is, for example, " {description of X device 1 ( function/action/operation principle/attribute/shape/size/material/mode/input/output/generation related information, etc.)}, that is, "function/action/operation principle/attribute/shape/size/material/mode /input/output/generation related information”, display control for making the incomplete message for description support into a display element having a GUI function for enabling the selection operation of the options. Information may be added to the display elements of the incomplete writing aid message. Then, the complaint information generation unit 205a uses the function of the script related to the display control information to generate the content of the incomplete description support message when the selection operation of the displayed incomplete message for description support is performed. , another predetermined description support incomplete message suitable for the selected option (for example, function, action, operation, principle, attribute, shape, size, material, mode, input/output, or generation-related information It may be determined to change to an incomplete message for description support including one example sentence corresponding to the option among the incomplete example sentences suitable for explaining the option for each option. For example, when "input/output" is selected for the GUI of the incomplete description support message including the options in this example, the incomplete description support message including the option is changed to "input/output". Suitable for description support, for example, "■ {(what) is input from (where), X machine 1 receives the input and outputs (what) to (where) as the processing result of X machine 1}" Changed to incomplete message.

[3-1-5-7-4. Generating claim-based abstract information]
The complaint information generation unit 205a realizes the complaint-based abstract information generation processing by generating complaint-based abstract information based on the claims included in the invention document acquired by the invention document acquisition unit 2021. FIG. The claim-based abstract information represents the content of the incomplete abstract. The claim-based abstract information need not be complete enough to be used as an abstract for patent application.

The claim-based abstract information includes, for example, headings similar to those of Japanese patent application abstracts (eg, "abstract", "selection drawing", etc.), and includes descriptions following each heading.

The claim information generation unit 205a generates " Decide what to include in the “Summary” column. The content of this predetermined character string is, for example, an incomplete message for description support indicated by incomplete message information included in the setting information acquired by the setting information acquisition unit 201 . As a specific example, the claim information generation unit 205a adds, for example, "{technical problem/ Effect: provides a control system useful in reducing/improving etc.”, etc. Write a sentence containing important words and phrases, and after the heading of "Solution", convert to the contents of the first paragraph of the claim included in the invention document, such as line feed deletion processing and processing to make the object of the claim the subject. The result of the processing is described, and the code corresponding to the key word (for example, the content of "code" as one attribute of the key word) is inserted immediately after each key word in the description. As a result, the content following the heading of "Solution" is, for example, "The control system 10 includes a motion sensor 11, a control content determination device 12, and a lighting control signal transmission device 13." . For example, when the number of characters in the "summary" field exceeds a predetermined upper limit (eg, 400), the complaint information generation unit 205a may include a message to that effect in the complaint-based abstract information.

The claim information generation unit 205a sets the drawing number of a drawing representing characteristic matters related to one claim subject of a claim in a typical invention document to the column of "selected drawing" in the claim-based abstract information. "Figure 1" is described based on the presumption that there is a relatively high possibility of determining In some cases, the order of the figures used in the invention document may be used to achieve some effect, and the drawing number of the figure related to one claim object in the invention document does not necessarily have to be 1.

As another example, the claim information generation unit 205a may include important words and phrases included in the first paragraph of the claim following the characters "drawing" in the column "selected drawing" in the claim-based abstract information. The drawing number of the drawing containing the most elements represented by the key words extracted by the extraction unit 2051 is described.

The claim information generation unit 205a adds the Japanese abstract for the US application ( In other words, it is possible to include description contents corresponding to the Japanese manuscript for translation of the abstract. The claim information generating unit 205a adds, for example, the content of the first paragraph of the claim included in the invention document to the description content corresponding to the Japanese version of the abstract for the US application, the line feed deletion processing, and the object of the claim as the subject. The result of conversion processing such as conversion processing is used. The claim information generation unit 205a, for example, causes the translation unit 2054 to machine-translate the content corresponding to the Japanese version of the abstract for the US application, and the number of words resulting from the machine translation exceeds a predetermined upper limit (for example, 150 words). In some cases, a message indicating that it is desirable to reduce the number of characters may be included in the claim-based abstract information.

The claim information generation unit 205a adds the incomplete abstract of the Japanese international application to the claim-based abstract information generated by the claim-based abstract information generation process, in addition to the incomplete abstract of the Japanese patent application. It is also possible to include description contents corresponding to The claim information generation unit 205a, for example, deletes line feeds from the content of the first paragraph of the claim included in the invention document, and deletes the subject of the claim as the description content corresponding to the incomplete abstract of the Japanese international application. Immediately after each key phrase, the result of conversion processing such as the processing of ) is inserted between the opening and closing parentheses.

When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the claim-based abstract information as a display document (for example, an HTML document), the claim information generation unit 205a outputs generates claim-based abstract information included in the patent application related information of

The claim-based abstract information portion of the patent application-related information as a display document generated by the claim information generation unit 205a is, for example, the contents of each line of the claim-based abstract information generated in the above-described claim-based abstract information generating process. If there are one or more key phrases extracted by the key phrase extraction unit 2051 in each row, one or more display elements corresponding to each of the key phrases are displayed. include. As a specific example, the complaint information generating unit 205a creates a complaint-based abstract under the <article> tag when describing the complaint-based abstract information sandwiched between <article> and </article> tags in an HTML document. For each line that is the content of the claim-based abstract information generated in the document information generation process, the display element corresponding to that line is described by sandwiching the content of that line between the <span> tag and the </span> tag. Then, under the <span> tag of the display element corresponding to one line, for each key phrase in that line, the display element corresponding to the key phrase is displayed with the <span> tag and the </span> tag. Write with important words in between. Of each line of claim-based abstract information, if the content of that line includes a heading, an incomplete message to support description, or a code, the display elements of that line are the heading and the incomplete message to support description , or a display element corresponding to the code. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in the claim-based abstract information portion, for example, enables the contents of the corresponding line to be displayed.

The complaint information generation unit 205a creates display elements corresponding to headings, key phrases, description support incomplete messages, or codes included in the complaint-based abstract information portion of the display document. Display control information for controlling the mode (for example, highlighting, coloring, etc.) is added.

[3-1-5-7-5. Generation of Modified Complaint Information]
The complaint information generation unit 205a realizes the modified complaint information generation processing by generating modified complaint information obtained by modifying the claims included in the invention document acquired by the invention document acquisition unit 2021. FIG. The modified complaint information is obtained by partially modifying the complaint information generated by the complaint information generating process. The user can, for example, use the content of the modified version claim information as a claim of an invention document, and cause the invention document to be analyzed again by the invention document analysis system 20, thereby generating new warning information including invention document evaluation information. It becomes possible to obtain the configured patent application related information.

[3-1-5-7-5-1. Correction of inappropriate descriptions and deletion of unnecessary descriptions]
The claim information generation unit 205a has a correction method determined in advance when the description in the claim of the invention document acquired by the invention document acquisition unit 2021 is the object for which the warning information generation unit 2059 generates indication information. If so, the modified version of the claim information is generated by modifying the description according to the modification method. A specific example of generating modified claim information by correcting the description of a claim will be described below.

For example, the claim information generation unit 205a converts the description in the claim of the invention document acquired by the invention document acquisition unit 2021 into the invention document standard specification for translation acquired by the invention document standard specification acquisition unit 204 for translation (see FIG. 14). ), if it corresponds to the pattern indicated by the pattern information of the conditional item to which the modification information is added, by modifying the description in the claim based on the modification information, the modified claim information representing the modified claim Generate.

The claim information generation unit 205a, for example, obtains the number of each claim of the claim of the invention document acquired by the invention document acquisition unit 2021 (for example, the "n" part of the headline "Claim n" in the first line of each claim). If the number represented by the string of Arabic numerals) is not consecutively numbered along the line order, correct the number of each claim so that it is consecutively numbered starting from 1 along the line order, and further , if there is a reference to other paragraphs that refer to other paragraphs in any claim section, modify the reference number in the reference to other paragraphs so that it corresponds to the number of each paragraph after modification. By doing so, the modified complaint information is generated.

The claim information generation unit 205a, for example, obtains the number of each claim of the claim of the invention document acquired by the invention document acquisition unit 2021 (for example, the "n" part of the headline "Claim n" in the first line of each claim). If half-width characters and full-width characters are mixed in the number represented by the character string), correct the number of each item of the claim so that it is one of the types of characters (for example, full-width characters), and further, If any claim section contains a statement that refers to another paragraph in which the referenced paragraph number in the reference to another paragraph is not one of the types of characters, By modifying the reference item number to one of the types of characters (for example, double-byte characters), the modified claim information is generated.

For example, when the claims of the invention document acquired by the invention document acquisition unit 2021 include a description of a mathematical formula represented by a heading such as "number n" written in square brackets, the claim information generation unit 205a , when the numbers of the mathematical expressions are not continuous even after considering branch numbers along the order of lines, corrected claim information is generated by correcting them so that they are continuous numbers along the order of lines. The claim information generation unit 205a can, for example, correct chemical formulas or tables in the same way as correcting the numerical formulas.

For example, the complaint information generation unit 205a determines that the complaint of the invention document acquired by the invention document acquisition unit 2021 has a comment line or comment that can be specified based on the comment specification information of the setting information acquired by the setting information acquisition unit 201. Generate modified claim information by deleting the comment line or comments, if any. Whether to execute or suppress the function of deleting the comment line or comment in the complaint in the modified complaint information may be specified in the setting information acquired by the setting information acquiring unit 201.

For example, the claim information generation unit 205a determines whether the claim of the invention document acquired by the invention document acquisition unit 2021 includes a description of continuous comma characters "," or a description of continuous period characters "." In this case, the corrected claim information is generated by correcting the comma characters "," to one or the period characters "." to one.

For example, if a full-width or half-width blank character or tab is included at the end of the line of the claim of the invention document acquired by the invention document acquisition unit 2021, the complaint information generation unit 205a deletes the blank character or tab. By doing so, the modified complaint information is generated. If the line feed code at the end of the line of the complaint is not the predetermined code for the end of the line, the complaint information generation unit 205a corrects it to the predetermined code for the end of the line, thereby generating the modified version of the complaint information. may be generated. This predetermined code for the end of line is, for example, a code configured by arranging 0x0d and 0x0a in this order. The predetermined code for the end of line may be designated by setting information or the like acquired by the setting information acquisition unit 201 . The claim information generation unit 205a, for example, corrects the line feed code to a predetermined code for the end of the line, only when the patent application related information is output as a text file, etc., instead of as a document for display. It may be executed.

For example, if the claim of the invention document acquired by the invention document acquisition unit 2021 contains half-width characters, the complaint information generation unit 205a changes the half-width characters to the corresponding full-width characters to correct the claims. Generate edition claim information. In this case, the claim information generation unit 205a does not change to full-width characters when the claims of the invention document include half-width alphabetic characters sandwiched between opening and closing parentheses. good. In addition, when the number of each item of claims in the invention document is all unified with single-byte characters, the claim information generation unit 205a may not change the number of each item to full-width characters. If half-width characters are included in the claim of the invention document, the type of half-width characters to be changed to full-width characters (for example, alphabetic characters, katakana characters, symbols, etc.), the character code range, etc. are obtained by the setting information acquisition unit 201. According to the specification, the complaint information generation unit 205a may change half-width characters in the complaint to full-width characters for generating modified complaint information. Conversely, if the claim of the invention document contains full-width characters, the type of full-width characters to be changed to half-width characters, the character code range, etc., are set in the setting information acquired by the setting information acquisition unit 201. , and according to the specification, the complaint information generation unit 205a may change full-width characters in the complaint to half-width characters for generating modified complaint information.

For example, if one or more single-byte blank characters are included at the beginning of each line of the claim of the invention document acquired by the invention document acquisition unit 2021, the complaint information generation unit 205a By changing the blank character to one double-byte blank character, the modified complaint information is generated.

For example, if two or more single-byte blank characters are consecutively included in a portion other than the beginning of each line of a claim of an invention document acquired by the invention document acquisition unit 2021, the complaint information generation unit 205a By changing two or more single-byte blank characters to one single-byte blank character, modified complaint information is generated. This can be useful, for example, to correct a description that mistakenly puts multiple spaces between English words. For example, assuming that it is necessary to write English sentences intentionally with multiple spaces at the end of each sentence, etc., in the claims of the invention document, the user is instructed not to make this correction by setting information, etc. can be selected, and this modification can be inhibited according to the setting information.

[3-1-5-7-5-2. Modifications to conform to the specified format]
If the setting information acquired by the setting information acquiring unit 201 includes information specifying the format of the complaint in the modified version of the complaint information, the complaint information generating unit 205a converts the claim of the invention document into the specified format. By correcting it so that it becomes, the corrected version claim information is generated.

An example of the information that is included in the setting information and specifies the format of the complaint in the modified complaint information is whether or not to add the code to the word in the complaint when there is a code corresponding to the word. information When there is a code corresponding to a word or phrase, when there is a code determined by the code determination process for the word or phrase, in the invention document (e.g., claim, specification, etc.) acquired by the invention document acquisition unit 2021 For example, if there is a description with a code added to the word or phrase, or if there is a description of the code corresponding to the word or phrase in the column of "Description of Code" in the specification of the invention document.

When the setting information acquired by the setting information acquisition unit 201 includes information designating that a code corresponding to a word or phrase in a complaint is added to the word or phrase, the complaint information generation unit 205a , of the important phrases extracted by the important phrase extraction unit 2051 in the claim of the invention document, for the description part where the important phrase with the corresponding code is not given a code, immediately after the description part of the important phrase Generate modified claim information by inserting the code description between the parenthesis and the closing parenthesis. Note that if there are a plurality of codes corresponding to the important phrase, the complaint information generation unit 205a selects one of the first codes by sorting the plurality of codes in natural order or the like, and selects the first code. A single code may be used for insertion after key phrases. If the setting information acquired by the setting information acquisition unit 201 includes information designating not to add the code to the word in the complaint when there is a code corresponding to the word in the complaint, the complaint information generation unit 205a is a description related to the code (for example, The description of the code sandwiched between the opening and closing parentheses) is deleted to generate the modified claim information.

In the setting information acquired by the setting information acquisition unit 201, as information specifying the format of the complaint in the modified version of the complaint information, for example, in each item of the claim, the description of the object of the claim or the specification of the cited paragraph to the object of the claim. a statement where the preceding statement portion "includes", "comprises" a first portion of any of "and", "and" and abbreviations and a second portion of any of line breaks and abbreviations; When the third part of either "characterized by" or "characterized by including" and the fourth part of either line break or omission are connected in this order , 1st to 4th parts, the claim information generation unit 205a converts the claim of the invention document into a format that conforms to the specification. By modifying as follows, the modified claim information is generated.

[3-1-5-7-5-3. Addition of claim section]
For example, the claim information generation unit 205a determines that the claim of the invention document acquired by the invention document acquisition unit 2021 has an independent claim that describes a claim subject that belongs to the product category in the constituent feature enumeration type, and that the claim belongs to the method category. If there is no claim that describes the subject of a claim, the independent claim that describes the subject of the claim that belongs to the product category is processed to be similar to the independent claim to some extent by performing a predetermined character string conversion process. The amended version of the claim information is generated by generating a claim that describes the claimed subject matter belonging to the category of method, and adding the generated claim after the last claim of the invention document. The claim information generation unit 205a can determine whether or not the claim section of the invention document is an independent claim based on the claim citation relation information held by the claim citation relation detection unit 2057, for example. The claim information generation unit 205a may use any method to determine whether or not the statement in the claim section of the invention document is of the constituent element enumeration type. For example, if there is a character string "to" or "to," at the end of any line of a claim section of an invention document, the claim information generation unit 205a determines that the description of that section is a constituent feature enumeration type. can be presumptively determined to be

For example, the claim information generation unit 205a determines that the claim of the invention document acquired by the invention document acquisition unit 2021 has an independent claim that describes a claim subject belonging to the category of method in the enumeration type of constituent features, and the category of program or program When there is no claim describing the claimed subject matter belonging to the recording medium category, by performing a predetermined character string conversion process on the independent claim describing the claimed subject matter belonging to the method category, Alternatively, by performing the process of generating a claim citing the independent claim, a claim that describes a claimed subject belonging to the program category or the program recording medium category that expresses the same content to some extent as the independent claim. A modified version of the claim information is generated by generating a clause that describes the claimed subject matter to which it belongs and adding the generated clause after the last clause of the claim in the invention document.

To the setting information acquired by the setting information acquisition unit 201, add a claim item describing a claim object belonging to any of the above-described method category, program category, and program recording medium category to the modified version claim information. In accordance with the specification, the complaint information generation unit 205a may execute or suppress the addition of the complaint section to the modified complaint information.

When adding a claim section to the modified version of the claim information, the claim information generating section 205a causes the claim citation relationship detection section 2057, for example, to generate claims representing the citation relationships between claims in the claim information. In addition to the citation relationship information, modified claim citation relationship information representing citation relationships between claims in the revised claim information is generated and held.

[3-1-5-7-5-4. Addition of claims corresponding to each region where the application can be filed]
The claim information generation unit 205a performs the modified version claim information generation process described above, corrects the above-described inappropriate statements, deletes unnecessary statements, and corrects the claims included in the invention document to conform to the specified format. , After generating amended claim information representing amended claims by adding a claim section, etc., based on the description of the amended claims, corresponding to each possible destination region (e.g., the United States, Europe, etc.) Claims may be generated and each generated claim may be further included in the modified claim information.

The claim information generation unit 205a includes, for example, in the setting information acquired by the setting information acquisition unit 201, correction information that defines a correction method to be used when generating corrected version claim information for the region planned as the filing destination. In this case, the claims modified according to the modification information may be added to the modified version of the claim information.

Further, for example, the setting information acquired by the setting information acquisition unit 201 may include information specifying a possible application area where a complaint should be generated, so that the complaint information generation unit 205a can correspond to the specified area. A modified claim may be generated and added to the revised claim information. This added claim can be used as a claim in the Japanese manuscript for translation for the patent application to the applicant. Further, for example, the setting information acquired by the setting information acquisition unit 201 may include information specifying the contents of modification of the claims that will be useful for filing an application in a potential filing destination area where claims should be generated. The generation unit 205a may generate a complaint corresponding to the content of modification of the specified complaint and add it to the revised complaint information. Examples of information designating the content of claim amendments include information designating that a single term citing multiple terms in a claim should be changed to a single term citing only one of the multiple terms; information designating that a term citing multiple terms in a claim shall be changed to an equal number of terms, each citing only a different one of the multiple terms, citing multiple terms in a claim specify that if any of the terms to which the single term cited in the above quotes multiple terms, that single term should be changed to a single term citing only one of the multiple terms. information and the like. In response to the specification of these setting information, the complaint information generation unit 205a specifies the items of complaints (that is, the complaint set) to be added to the modified complaint information by the configuration information. A corresponding heading may be added. Examples of headings for claim sets to be added to the modified claim information include "Claim for the United States," "Claim for Europe," "Multiple Dependency Resolving Claims," and "Multiple Multiple Dependency Resolving Claims."

A specific example of how the claim information generating unit 205a generates a claim corresponding to each potential application destination region will be described below.

If the setting information acquired by the setting information acquisition unit 201 includes information designating the United States as a potential filing destination, or if one term citing multiple terms in a claim is replaced with one of the multiple terms If the claim information generating unit 205a includes information designating that it should be changed to a single term quoting only the above, the claim information generation unit 205a may generate, for example, amended version claim information representing a corrected claim (that is, a claim in a state in which the above-mentioned amendments have been made). information) contains a paragraph that recites more than one paragraph, each paragraph of the claim with that paragraph changed to a paragraph that cites only the one with the lowest paragraph number of the plurality of paragraphs. , and also add to the amended claim information representing the original amended claim. Further, when the setting information acquired by the setting information acquiring unit 201 includes information designating the United States as a possible filing destination, the complaint information generating unit 205a determines that the number of claims has a predetermined number (for example, 20). to the extent that it does not exceed a single paragraph citing multiple paragraphs in a claim, e.g. Each paragraph of the claim that has been changed to two paragraphs, one with only a minor citation, may also be added to the amended claim information representing the original amended claim. It should be noted that, in US patent applications, it is not necessarily inappropriate to refer to multiple terms in a claim, but such changes may be useful in some cases.

In the setting information acquired by the setting information acquiring unit 201, when any of the quoted clauses of one clause that quotes multiple clauses in a claim, that one clause is referred to as the plurality of clauses. When the claim information generating unit 205a includes information specifying to change to one term quoting only one of the If any of the clauses citing a single clause citing multiple clauses cites multiple clauses, that one clause is assigned to the clause that cites the clause with the lowest number among the multiple clauses. If the term with the lowest number refers to more than one term, the term with the lowest number refers to the term with the lowest number. to add each modified claim section to the amended claim information that also represents the original amended claim.

When the setting information acquired by the setting information acquisition unit 201 includes information designating the United States as a potential filing destination, the claim information generation unit 205a generates, for example, A claim that includes a claim that describes a claimed subject belonging to the category of program, and a claim that describes a claimed subject that belongs to the category of program recording media that includes a description of a program whose correlation with the description of the program in that clause is higher than a predetermined standard. is included separately, each paragraph of the claim after deleting the paragraph describing the claimed subject matter belonging to that category of program is also added to the amended claim information representing the original amended claim.

When the setting information acquired by the setting information acquisition unit 201 includes information designating the United States as a potential filing destination, the claim information generation unit 205a generates, for example, A claim that includes a claim that describes a claimed subject belonging to the category of program, and a claim that describes a claimed subject that belongs to the category of program recording media that includes a description of a program whose correlation with the description of the program in that clause is higher than a predetermined standard. is not included separately, the content of the clause describing the claimable object belonging to the category of the program is converted into a category of the program by performing a predetermined character string conversion process. The recording medium that non-temporarily recorded the claimed object is changed to the claimed object claim, and each claim after the change is further added to the modified claim information representing the original corrected claim.

When the setting information acquired by the setting information acquiring unit 201 includes information designating Europe as a possible filing destination, the claim information generating unit 205a generates, for example, Of the important phrases extracted by the important phrase extraction unit 2051 in the claims, for the description part where the key phrase with the corresponding code is not assigned the code, the opening and closing parenthesis are added immediately after the description part of the important phrase. and insert each section of the inserted claim in addition to the amended claim information representing the original amended claim. The code corresponding to the key phrase is, for example, the code determined by the code determination process, or the code added to the key phrase in the invention document (eg, claim, specification, etc.) acquired by the invention document acquisition unit 2021. It is the code where there is a description, or the code where there is a description of the code corresponding to the important term in the column of "description of code" in the specification of the invention document. Note that if there are a plurality of codes corresponding to the important phrase, the complaint information generation unit 205a selects one of the first codes by sorting the plurality of codes in natural order or the like, and selects the first code. A single code may be used for insertion after key phrases.

When the claim information generation unit 205a adds each claim item (that is, claim set) corresponding to each region where the application can be filed to the modified claim information, for example, the claim citation relationship detection unit 2057 In addition to the claim citation relationship information that represents the citation relationship between each claim section in the claim information, the modified claim citation relationship that represents the citation relationship between each claim section for each claim set in the modified claim information Generate and retain information.

[3-1-5-7-5-5. Generating Modified Claim Information Portion in Display Document]
When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the modified claim information as a display document (for example, an HTML document), the claim information generation unit 205a outputs the display document as Generate modified claim information included in patent application related information.

The amended claim information portion of the patent application related information as a display document generated by the claim information generation unit 205a corresponds to, for example, the content of each line of each item of the amended claim in the amended claim information. If there are one or more important phrases extracted by the important phrase extraction unit 2051 in each line of each item, one or more display elements corresponding to each of the important phrases, If a heading such as "Claim n" (where n is a natural number) is included in each line of a paragraph, one or more display elements corresponding to the heading are included. As a specific example, the complaint information generation unit 205a, when describing the corrected complaint information sandwiched between <article> tag and </article> tag in the HTML document, creates the corrected complaint information under the <article> tag. For each line of each paragraph of the amended claim as, the display element corresponding to that line is described by sandwiching the contents of that line between the <span> and </span> tags, and in that one line Under the <span> tag of the corresponding display element, for each key phrase in the line, the display element corresponding to the key phrase is described by sandwiching the key phrase between the <span> tag and the </span> tag. do. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line of each section included in the modified claim information portion, for example, enables the contents of the corresponding line to be displayed.

To give a specific example of a display element of one key phrase in the modified complaint information in the display document generated by the complaint information generation unit 205a, a plurality of key phrases “equipment control unit” are described in the modified complaint information. The display element corresponding to the fourth "equipment control unit" in the case where the . In this example, the identification code of the key word "equipment control unit" is "c003", and the value of the id attribute of the <span> tag of the display element is the identification code "revclaiminfo" of the modified claim information and the key word A character string including the identification code "c003" and the number "004" in order of description is defined. Also, in this example, when a mouse click operation is performed on a display element, the wordProc function is called with the value of the id attribute as an argument. As a result, in the wordProc function, for example, it is possible to specify the display element from the argument and refer to the character string of the important phrase related to the display element. By extracting the identification code "c003" of the phrase, the number "004" in the order of description, etc., for example, the id attribute of the leading display element of the same important phrase is specified as "revclaiminfo-c003-001". It is possible to display the first display element. For example, replace the display contents of the display elements of all the important phrases "equipment control unit" in the modified complaint information with the character strings entered by the user. It is possible to realize a process for

When each display element of the modified claim information portion in the display document is displayed by a browser, for example, the displayed content (for example, content of multiple lines) can be copied and pasted by the user to create and edit the document. It is constructed so that it can be taken into an application program (for example, a text editor, etc.) having a function, and utilized as a claim for a patent application or a Japanese manuscript for translation of the claim for a patent application. For example, the user can freely edit part or all of the content of the imported modified claim information portion or output it to a file by operating an application program having a document creation/editing function. In addition, through operations such as copy & paste, editing, output, etc., the user can transfer the content of part or all of the modified claim information portion, or the edited result, to an application program for patent application (for example, Internet application software). can be incorporated into In addition, the user causes the invention document acquisition unit 2021 of the invention document analysis system 20 to acquire the invention document including the edited version of the claim information, etc., and causes the invention document acquisition unit 2021 of the invention document analysis system 20 to analyze it again. Application related information is available.

The complaint information generation unit 205a controls the display mode of the headline or the key phrase (for example, Add display control information for highlighting, colored display, display transition, etc.). The display control information is, for example, the same as the display control information added to the display element of the claim information portion in the patent application related information as the document for display.

The claim information generation unit 205a uses the description portion corrected from the claim of the invention document, which is included in the corrected claim information portion of the display document, as a display element, and emphasizes the display element by adding an underline or the like. Display control information for adjusting text-decoration property, border-bottom property, etc. as display attributes may be added to the display element so as to display it. In the modified version of the claim information in the display document, for the description part corrected by deleting from the claim of the invention document, the display attribute border in the display element composed of <span></span> tags without character strings It is also possible to add display control information such as displaying a boundary line with a width different from others by adjusting properties. In the amended version of the claim information, the description part that is amended from the claim of the invention document is not always properly amended, so the amended description part should be displayed in a display mode that emphasizes it. Therefore, it becomes relatively easy for the user to refer to the warning information and the complaint information, confirm whether or not the correction in the revised complaint information is appropriate, and then utilize the contents of the revised complaint information.

[3-1-5-8. Statement information generation unit]
The description information generation unit 205b executes description information generation processing for generating description information included in the patent application related information output by the output unit 208 of the invention document analysis system 20. FIG. The specification information is information relating to the specification in the invention document.

The description information generation unit 205b can execute a description heading list generation process for generating a description heading list included in the patent application related information output by the output unit 208 of the invention document analysis system 20, for example. The description heading list is a list listing various headings in the description of the invention document.

The description information generating unit 205b generates, for example, revised specification information obtained by modifying the specification of the invention document, which is included in the patent application related information output by the output unit 208 of the invention document analysis system 20. book information generation processing can be executed.

If the invention document acquired by the invention document acquisition unit 2021 does not include a specification, the specification information generation unit 205b performs specification information generation processing, specification heading list generation processing, and modified version specification information. Omit execution of generation processing.

The specification information generation unit 205b can execute, for example, a code list generation process for generating a code list included in the patent application related information output by the output unit 208 of the invention document analysis system 20. FIG.

[3-1-5-8-1. Generate statement information]
The specification information generation unit 205b realizes the specification information generation process by generating specification information representing the specification included in the invention document acquired by the invention document acquisition unit 2021. FIG. The specification information may be a part of the specification included in the invention document acquired by the invention document acquisition unit 2021, which is corrected. As an example of this modification, if the specification contains a predetermined control code such as "0x07" for bell control, the predetermined control code is converted to a predetermined character such as "●". .

When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the specification information as a display document (for example, an HTML document), the specification information generation unit 205b outputs the Generate specification information included in patent application related information.

The description information part of the patent application-related information as a display document generated by the description information generation unit 205b includes, for example, one or more display elements corresponding to the contents of each line of the description, and in each line If there is one or more key words extracted by the key word extraction unit 2051, one or more display elements corresponding to each of the key words and phrases are included, and each line contains "Title of the invention", "Invention "Mode for Carrying Out", headings such as each paragraph number (for example, descriptions with opening and closing brackets added), or if comments are included, the headings, or Contains one or more display elements that correspond to comments. As a specific example, the description information generation unit 205b, when description information is sandwiched between an <article> tag and a </article> tag in an HTML document, creates each line of the description under the <article> tag. , the display element corresponding to the line is described by sandwiching the content of the line between the <span> tag and the </span> tag, and the display element corresponding to the one line <span> tag , for each key phrase in the line, the display element corresponding to the key phrase is described by sandwiching the key phrase between the <span> tag and the </span> tag, and added to the key phrase in the line For a code, a display element corresponding to the code is described by sandwiching the code between <span> and </span> tags. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in the description information portion enables display of the contents of the corresponding line, for example.

The description information generation unit 205b corresponds to headings, comments, key phrases, drawing number descriptions (for example, "Fig. 1", "Fig. 2", etc.) or codes included in the description information portion of the display document. Display control information for controlling the display mode (e.g., highlighted display, colored display, display transition, etc.) of, for example, headings, comments, key phrases, drawing number descriptions, or symbols is added to display elements. . For example, the description information generation unit 205b extracts the key phrase extraction range according to the key phrase extraction range information in the setting information acquired by the setting information acquisition unit 201, out of the key phrases and codes included in the specification information part. The display control information may be added only to important phrases and codes described in (for example, "Mode for Carrying out the Invention" and "Example").

As a specific example of generating display control information to be added to a key phrase in order to display different key phrases in different display modes (for example, display in different colors), the description information generation unit 205b , when the important phrase is described between <span> and </span> tags in the HTML file of the HTML document, the <span> tag distinguishes the important phrase from other important phrases. An example of assigning a class name as the identification information defined as follows is given. The description information generation unit 205b defines the class name as the identification information of the key phrase so that it is possible to distinguish whether or not the key phrase is described in the claim of the invention document, for example. Note that the description information generation unit 205b determines whether or not the key phrase is described in the claim of the invention document by determining whether the value of the "first-appearance claim number" as one attribute of the key phrase specified by the attribute specifying unit 2056 is is other than zero. To give a specific example of the class name of each key phrase, the class names of a plurality of different key phrases described in the claims are respectively "c001", "c002", "c003", etc. , and the class names of a plurality of different important terms that are not described in the claims are respectively "s001", "s002", "s003", and so on. In such an example, the CSS file of the HTML document contains information (that is, the By including information indicating color) in the specification information part, for example, mutually different key words that are also described in the claims can be compared with the colors added to each key word in the claim information part. Different key words and phrases that are displayed in the same color and are not stated in the claims are displayed in different colors according to the manner in which colors different from those of the key words and phrases that are also stated in the claims are added. To give a specific example, in the specification information, mutually different important terms that are also described in the claims have a certain amount of width, for example, due to the border-left property, similar to the display mode in the claim information. However, mutually different key words that are displayed in a display mode with a left border painted in a mutually different color (that is, a display color) and are not described in the claims are separated from each other by, for example, the background-color property, The characters are displayed in a display mode in which mutually different character background colors are added. As a result, when displayed on a browser, it becomes easy to grasp whether or not the important phrases in the specification information in the document for display are the important phrases described in the claims. It should be noted that, for example, in the case of highlighting an important phrase described in a claim by adding a left boundary line with a certain width, the description information generation unit 205b generates the description in the claim in the description information. For mutually different key phrases that are not specified, for example, without adding a somewhat wide left border, the background-color property allows the character background color of the key phrases in the claims to be different from the character background color of the same The display control information or the like may be determined so that the display is displayed in a display mode in which the character background color of is added. This allows the claimed key phrases to be sufficiently emphasized by having a left border line relative to the non-claimed key phrases in the specification information. That is, for each of the multiple key phrases in the specification information, if the key phrase is the same as any one of the multiple key phrases composed of mutually different character strings in the claim information, The display control information related to the important phrase in the specification information has the same display color as the display color of the left boundary line related to the display mode of the above-mentioned one important phrase in the claim information and has a predetermined width. Control to display in a display mode with a left border added, and if the key phrase in the specification information is different from any of the aforementioned multiple key phrases in the claim information, the key phrase in the specification information The display control information relating to may be for controlling the important phrase to be displayed in a display mode in which the left boundary line is not added. FIG. 26 shows an example of specification information in patent application related information as a display document displayed on the browser. In the example of FIG. 26, of the important words and phrases in each line of the specification information in the display document, the important words and phrases described in the claims are indicated by a colored left border line represented by a pattern in the figure. , but not claimed, the same character background color represented by a rectangular frame in the figure is added without adding a left border line.

The description information generating unit 205b performs display control in order to add, for example, a function as a GUI for performing display transitions related to important phrases in response to operations on the browser, to the display elements corresponding to the important phrases. Information can be added. The description information generation unit 205b adds, for example, a GUI function corresponding to an operation to key phrases in a manner similar to that of the complaint information generation unit 205a (that is, the display elements of the key phrases are treated as GUI elements corresponding to operations). can generate display control information for

To give a specific example of a display element of one key phrase in the specification information in the display document generated by the specification information generation unit 205b, a plurality of key phrases of the claim “equipment control unit” are described in the specification information. The display element corresponding to the 11th "equipment control unit" in the case where the ")' title="... (contents of display with additional information)...">equipment control section</span>" and the like. In this example, the identification code of the important phrase "equipment control unit" is "c003", and the value of the id attribute of the <span> tag of the display element is the identification symbol "specinfo" of the specification information and the important phrase A character string including an identification code "c003" and a number "011" in order of description is defined. Also, in this example, when a mouse click operation is performed on a display element, the wordProc function is called with the value of the id attribute as an argument. As a result, in the wordProc function, for example, it is possible to specify the display element from the argument and refer to the character string of the important phrase related to the display element. By extracting the identification code "c003" of the phrase, the number "011" in order of description, etc., for example, the id attribute of the leading display element of the same important phrase is specified as "specinfo-c003-001". It is possible to realize the processing of displaying the first display element, for example, the display contents of the display elements of all the important phrases "equipment control unit" such as claim information, corrected version claim information, specification information, etc. can be displayed to the user. It is possible to realize a process of replacing with an input character string or the like.

The description information generating unit 205b, for example, displays the display elements corresponding to the headings such as "Mode for Carrying Out the Invention" and each paragraph number contained in the description information part for highlighting, or Display control information can be added in order to add a function as a GUI for performing display transition to a display element corresponding to, for example, an immediately preceding or succeeding headline in response to an operation on the browser. The description information generation unit 205b generates display control information for adding a GUI function corresponding to an operation to a headline, for example, in the same manner as the complaint information generation unit 205a.

If, for example, the description information portion includes inappropriate description indicated by the warning information generated by the warning information generation unit 2059, the description information generation unit 205b removes the inappropriate description. may be sandwiched between, for example, <span> and </span> tags, and display control information for highlighting the inappropriate description may be added to the display element. The highlighting of the display element related to the character string with the <span> tag is, for example, display control that adjusts the values of the text-decoration property, font-weight property, border property, color property, background-color property, etc. in CSS It is feasible with information.

A description information generation unit 205b that generates description information based on the description of the invention document that is the analysis target of the analysis unit 205 acquired by the invention document acquisition unit 2021 generates a drawing document (for example, PDF file) can be acquired by the drawing document acquisition unit 2022, when the description information includes key words that are the same as the signed element names included in the invention document, the key words are manipulated. Add display control information to the display element of the important phrase to make it a display element having a GUI function for displaying the part containing the code in the drawing document (for example, the page containing the code) according to the may be In addition, the description information generation unit 205b also provides a display having a GUI function for displaying a code included in the description information and a portion of the drawing document containing the code (for example, a page containing the code) in response to an operation. The display control information for the element may be added to the display element of the code in the specification information. This display control information defines, for example, a function name of a function of a script activated with a code as an argument according to an operation, or the function itself. For example, when the drawing document is the content of the searchable PDF file, or when the PDF file containing the drawing document can be converted to the searchable PDF file, the code is removed from the searchable PDF file. By searching, it is determined to identify. For example, the description information generation unit 205b, in response to an operation on a code, generates a function related to display control information for displaying a portion including the code in the drawing document, and generates a function of the code displayed and operated on the browser. It may be determined to display the part including the code in the drawing document in a range where the display element is not hidden. For example, the description information generation unit 205b divides the display screen of the browser into a plurality of display areas, and displays the description information display area and the display area such as a part of the drawing document displayed according to the operation in parallel. may be displayed in For example, the description information generation unit 205b uses the display control information added to the display element of the code to generate a function that is activated in response to an operation on the code, and generates a plurality of functions including the code in the drawing document in response to further operations. It may be determined to switch and display a part (for example, two or more pages containing the code), or all the parts containing the code in the drawing document are reduced as necessary and displayed collectively. It may be determined to execute processing. For example, the description information generation unit 205b, in response to an operation on the code, generates a function related to display control information for displaying the part containing the code in the drawing document, and generates the code in the part containing the code in the drawing document. It may be determined to be highlighted. FIG. 27 shows an example of a pop-up screen displayed in response to a mouse click operation on display elements of symbols added to important terms in specification information of patent application related information displayed on the browser. The pop-up screen illustrated in FIG. 27 is displayed when a mouse click operation is performed on the code "12" following the important phrase "B part" in the specification information, and the drawing "FIG. 1" containing the code "12" is displayed. , and the symbol "12" in the drawing "FIG. 1" is highlighted.

A specific example of the display element of one code in the specification information in the display document generated by the specification information generation unit 205b is 3 The display element corresponding to the th "123" is, for example, "<span class="sign" id="specinfo-sign123-003" onclick='refSignProc ("specinfo-sign123-003")'>123</span >”, etc. In this example, "sign" is defined as the class name of the <span> tag of the display element with the third code "123" in the specification information, and the specification information identification symbol "specinfo" is specified as the value of the id attribute. , code identification information “sign123”, and a number “003” in order of description. Also, in this example, it is determined that the refSignProc function is called with the value of the id attribute as an argument when a mouse click operation is performed on the display element. As a result, in the refSignProc function, for example, it is possible to specify the display element from the argument and refer to the character string of the code related to the display element. Replace the display contents of all display elements of the code "123" in the book information, etc. with a character string representing the new code entered by the user, and include the code "123" as the content of the "code" of the attribute information It is possible to realize a process of replacing the content of the "code" of the attribute information of the key phrase with a new code.

For example, when the specification information portion as a document for display includes a column of "Brief description of the drawing", the specification information generation unit 205b inserts the column between the opening corner bracket and the closing corner bracket of the column. The description part related to the drawn drawing number is treated as one display element, and the description about the drawing with that drawing number in the specification information is displayed on that display element in response to the operation on the drawing number (for example, mouse click operation, etc.) Display control information may be added in order to provide a function as a GUI for retrieving each line containing the search result and displaying each line of the search result in a enumerated manner. Further, for example, when the specification information portion as a document for display includes drawing number description including "figure n" (n is a natural number), the description information generation unit 205b converts the drawing number description into one As a display element, according to the operation (for example, mouse click operation) on the drawing number, each line containing the drawing number description indicating the same drawing number as the drawing number in the specification information is searched and searched. Display control information may be added to provide a GUI function for listing and displaying each line of the result. Further, for example, when the description of the drawing number is included in the description information portion as the document for display, the description information generation unit 205b treats the description of the drawing number as one display element, and performs the operation ( For example, according to mouse click operation, etc.), each line containing drawing number description in the specification information is searched regardless of the drawing number, and each line of the search result is listed and displayed. Display control information may be added in order to

The description information generation unit 205b, for example, in the description information part as a document for display, such as "■ claim n", to the description content of claim n (n is a natural number), or to the description content It is a part that can be replaced with the content that has been subjected to predetermined conversion processing (for example, deletion of line feeds, deletion of period characters, deletion of quoted descriptions that cite claims, etc.). If there is a statement indicating that the In order to have a function as a GUI for replacing and displaying the content of the element with the description content of claim n or with the content obtained by performing the above-described predetermined conversion processing on the description content, Display control information may be added.

The description information generation unit 205b generates, for example, full-width or half-width blank characters, tabs, line feeds, and The return, page feed, or vertical tab character codes may be removed, and the line feed at the end of the line may be represented by the line feed HTML tag <br>.

[3-1-5-8-2. Generate statement heading list]
The description information generation unit 205b implements the description headline list generation processing by generating a description headline list based on the description included in the invention document acquired by the invention document acquisition unit 2021. FIG. The description headline list is a list in which all the lines including the description of the headline in the description of the invention document are listed in the order of description in the description of the invention document.

The description information generation unit 205b treats, for example, a line including a description sandwiched between an opening square bracket and an ending square bracket as a line including a heading description. The description information generation unit 205b further inserts one or more types of predetermined brackets (eg, round brackets, square brackets, angle brackets, etc.) at the beginning of the line or at the position following one or more blank characters at the beginning of the line. ) is regarded as a line containing a description of a heading, either unconditionally or on the condition that there is no period character "." at the end of the line. It is also possible to do so. Accordingly, for example, (Embodiment 1), (Embodiment 2), [1-1. Configuration of X device], [1-2. Effect, etc.] are listed in the description heading list, and a user who browses the description heading list in the output patent application related information can read the numbers and character strings described in the various headings It is possible to relatively easily confirm whether or not is appropriate.

The description information generation unit 205b extracts, for example, the important phrase extraction unit 2051 within the paragraph range of the paragraph number for the line including the description of the heading representing the paragraph number among the lines listed in the description heading list. If there is an important phrase that has been written, all of the important phrase may be added to that line. In this case, the description information generation unit 205b may additionally add only one of the same important phrase so that the additional important phrases do not overlap. Also, in this case, the description information generation unit 205b may additionally add only the important words and phrases described in the claim of the invention document among the important words and phrases within the paragraph range. Further, when there are a plurality of important phrases to be added, the description information generation unit 205b may add the important phrases in the order of importance determined by the importance determination unit 2055, or add the important phrases within the paragraph range. The more important words and phrases described in the document, the more important words and phrases may be added so that the more important words and phrases are placed in front, and the more important words and phrases described in the claims of the invention document may be added than the important words and phrases not described in the claims. It may be added so that it is positioned forward. Further, the description information generation unit 205b may exclude lines including descriptions of headings representing paragraph numbers from the lines listed in the description heading list. For example, if the setting information acquired by the setting information acquiring unit 201 defines whether or not paragraph numbers are listed in the specification heading list, the specification information generating unit 205b acquires the setting information Accordingly, it may be determined whether or not to include a line including a paragraph number in the lines listed in the description heading list, and the description heading list generating process may be executed. In addition, the description information generation unit 205b creates drawing number descriptions in lines that are not headings but include drawing number descriptions (eg, "Fig. 1", "Fig. 2", etc.) in the lines listed in the description heading list Lines with contents other than those removed (for example, if there are multiple drawing number descriptions, a line in which the drawing number descriptions are separated by commas or other delimiters) are mixed with the heading line to appear in the specification of the invention document. You can list them in order. For example, if the setting information acquired by the setting information acquisition unit 201 defines whether or not the description of the drawing number is listed in the specification heading list, the specification information generation unit 205b According to the information, it may be determined whether or not to include the drawing number description in the lines listed in the description heading list, and the description heading list generation processing may be executed.

The description heading list is used, for example, to check whether the description format of various headings in the invention document, the description of each drawing number, etc., is correct, to check the important words and phrases for each paragraph, and to overview the outline of the description. can be useful for

For example, the description information generation unit 205b regards a line whose description is a paragraph number among lines including a description sandwiched between an opening bracket and an ending bracket as not a line including a heading description. It is also possible to do so. In addition, the description information generation unit 205b interweaves lines including descriptions of headings in the description heading list in order of description, and adds a predetermined number of characters from the beginning of each line that does not include descriptions of headings in the specification of the invention document. Each line may be included after removing all but the string (eg, up to 30 characters).

When the output unit 208 in the invention document analysis system 20 outputs the patent application related information including the specification heading list as a display document (for example, an HTML document), the specification information generation unit 205b outputs generates a list of specification headings included in the patent application related information of

The description heading list portion of the patent application-related information as a display document generated by the description information generation unit 205b includes, for example, one or more display elements corresponding to the contents of each line of the description heading list, If a heading is included in each line (eg, a description with an opening and closing bracket), one or more display elements corresponding to the heading are included. As a specific example, the description information generation unit 205b creates a description heading list under the <article> tag when describing a description heading list sandwiched between <article> and </article> tags in an HTML document. For each line of the list, the display element corresponding to that line is described by sandwiching the contents of that line between the <span> tag and the </span> tag. Under the tag, a display element corresponding to the heading in the line is described by sandwiching the heading between the <span> tag and the </span> tag. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in the description heading list portion enables, for example, the contents of the corresponding line to be displayed.

The description information generation unit 205b controls the display mode (e.g., highlighted display, colored display, display transition, etc.) of the display elements corresponding to the headings included in the description heading list portion of the display document. ) is added. The description information generating unit 205b generates a portion of the description information corresponding to the heading (that is, the heading in the description information) in the display element corresponding to the heading, for example, according to the operation of the browser. Display control information can be added in order to add a function as a GUI for performing display transition to the portion representing the line of the specification of the invention document).

28 and 29 show an example of a specification heading list in patent application related information as a display document displayed on the browser. FIG. 28 shows an example in which paragraph numbers are not listed in the specification heading list. FIG. 29 lists paragraph numbers in the description heading list, lists drawing numbers mixed with each heading in the description heading list in order of appearance, and describes information in each line indicating the paragraph number in the description heading list. shows an example of listing the key phrases contained in the paragraph of that paragraph number.

When the description headline list portion of the document for display includes key phrases, the description information generation unit 205b determines display elements corresponding to the key phrases, and uses the display elements for highlighting or Display control information can be added for adding a GUI function corresponding to an operation to the important phrase.

[3-1-5-8-3. Generate modified description information]
The specification information generation unit 205b realizes the modified specification information generation processing by generating modified specification information obtained by modifying the specification included in the invention document acquired by the invention document acquisition unit 2021. FIG. The revised specification information is part of the specification information generated by the specification information generation process. In the modified specification information generation processing by the description information generation unit 205b, among the modifications to the claims in the modification version complaint information generation processing by the claim information generation unit 205a, corrections that are applicable to the specification of the invention document are performed. (eg, corrections where numbers in mathematical formulas, chemical formulas, etc. are not consecutive numbers, etc.) may be performed as well. The user, for example, uses the content of the revised specification information as the specification of the invention document, and causes the invention document to be analyzed again by the invention document analysis system 20, thereby newly creating warning information including invention document evaluation information. It is possible to obtain patent application related information composed of

[3-1-5-8-3-1. Correction of inappropriate descriptions and deletion of unnecessary descriptions]
The description information generation unit 205b determines in advance the correction method in the case where the description in the specification of the invention document acquired by the invention document acquisition unit 2021 is the object for which the warning information generation unit 2059 generates indication information. When defined, the modified specification information is generated by modifying the description according to the modification method. A specific example of generation of revised specification information by correcting the description of the specification will be described below.

For example, the description information generation unit 205b converts the description in the specification of the invention document acquired by the invention document acquisition unit 2021 into the standard specification for translation of the invention document acquired by the invention document standard specification for translation acquisition unit 204 (Fig. 14), when the pattern information of the condition item to which the correction information is added corresponds to the pattern indicated, the description in the specification is corrected based on the correction information, thereby representing the corrected specification Version specification information may be generated. As a specific example, the description information generating unit 205b adds, for example, to the description of the invention document, "Other expressions in the US application" in the standard specification for invention documents for translation acquired by the standard specification for invention documents for translation acquisition unit 204 If there is a description such as "What are the characteristics of the present invention" that corresponds to the pattern indicated by the pattern information in the condition item with the condition item name "character string that may be desirable to be changed", such description should be included in the condition item. According to the correction information, the modified specification information representing the corrected specification is generated by modifying the description such as "the feature of the embodiment example in the present disclosure". Further, for example, the specification information generation unit 205b generates invention document In the specification, there are multiple figures separated in one drawing, such as "(1) in FIG. 2 is a diagram showing ... and (2) in FIG. 2 is ..." When there is a description indicating the possibility of existence, the description is changed according to the correction information defined in the condition item, for example, "Fig. 2A is a diagram showing . . . ” etc. to generate the revised specification information representing the revised specification. For example, the description information generation unit 205b determines whether the description in the description of the invention document acquired by the invention document acquisition unit 2021 is "characters presumed to be Search for descriptions of character strings that correspond to the pattern indicated by the pattern information (e.g., "only", "preferably", etc.) to extract inappropriate descriptions related to the condition items in the "column", and characters that correspond to the pattern When the description of the column is detected, the modified specification information is generated by removing the character string. Note that the content of the standard specification of invention documents for translation is not limited to the content illustrated in FIG. By following the modification information of the conditional items of the Standard Provisions for Invention Documents for Translation, which defines the conditional items including the pattern information defined as applicable, for example, "preferably, if... may be changed to "for example, you may..." to generate the revised specification information.

For example, when the paragraph numbers of the specification of the invention document acquired by the invention document acquisition unit 2021 are not consecutive numbers along the order of lines, the description information generation unit 205b converts the numbers into consecutive four-digit numbers along the order of lines. Generate revised specification information by correcting the paragraph number of the specification so that it becomes a number, or if the number of all paragraph numbers is not enough with 4 digits, it becomes a 5-digit consecutive number. . For example, when half-width characters and full-width characters are mixed in the paragraph numbers of the description of the invention document acquired by the invention document acquisition section 2021, the description information generation unit 205b selects one of the types of characters ( By correcting the paragraph number of the specification so that it becomes double-byte characters, for example, the revised specification information is generated.

For example, when the description of the invention document acquired by the invention document acquisition unit 2021 does not include paragraph numbers, the description information generation unit 205b generates appropriate predetermined positions and predetermined paragraph numbers. The revised specification information may be generated by continuously adding paragraph numbers to each of a predetermined number of lines, which is a reference for adding numbers. The description information generation unit 205b adds the paragraph number only when, for example, the setting information acquired by the setting information acquisition unit 201 includes information designating the addition of the paragraph number. good too. The information designating addition of paragraph numbers may include, for example, designation of a predetermined number of lines that serves as a reference for adding the above-mentioned paragraph numbers. For example, if the setting information acquired by the setting information acquiring unit 201 includes information specifying deletion of the paragraph number, the description information generation unit 205b By deleting the description of, the modified specification information may be generated.

For example, when the specification of the invention document acquired by the invention document acquisition unit 2021 includes a column of "brief description of the drawing", the description information generation unit 205b arranges the drawing numbers in that column in line order. Accordingly, if the drawing numbers are not continuous even after considering the branch numbers, the revised specification information is generated by correcting the drawing numbers so that they are continuous in line order. If the drawing number in the "Brief description of the drawing" column is corrected, the description information generation unit 205b will change the description of the drawing number in other columns of the specification (for example, the drawing part of a character string in which one or more characters that can be used for a number are consecutive) is corrected by replacing the character string so as to correspond to the correction of the drawing number in the "Brief description of the drawing" column. , to generate modified specification information. As a result, for example, a user who wants to change the drawing number in the specification can enter each drawing number in the "brief description of the drawing" column of the specification in the invention document to be acquired by the invention document acquisition unit 2021 of the invention document analysis system 20. Only by correcting the arrangement order of each line corresponding to , it is possible to obtain the corrected specification information in which the descriptions of all the drawing numbers in the specification are corrected.

For example, when the specification of the invention document acquired by the invention document acquisition unit 2021 does not include the column of "brief description of the drawing", the specification information generation unit 205b adds "figure n" ( n is a natural number), if the drawing numbers are not consecutively numbered in the order of the first appearance of the drawing numbers, even after considering branch numbers, the drawing numbers should be consecutively numbered in the order of the first appearance. , and add the "Brief description of the drawing" column to the appropriate position so that it includes the contents of the description line of the drawing number in the order of the drawing number or the contents listing the incomplete messages for description support By doing so, the modified specification information may be generated. For example, when half-width characters and full-width characters are mixed in the drawing number in the drawing number description portion of the specification of the invention document acquired by the invention document acquisition section 2021, the description information generation unit 205b By correcting the drawing number so that it becomes one type of characters (for example, double-byte characters), the corrected specification information is generated.

For example, when the description of the invention document acquired by the invention document acquisition unit 2021 includes half-width characters, the description information generation unit 205b changes the half-width characters to the corresponding full-width characters. , to generate modified specification information. In this case, the description information generating unit 205b generates the description of the invention document when the "Non-Patent Literature" column contains English half-width characters, When a half-width alphabetic character is included, the half-width alphabetic character may not be changed to a full-width character. Further, when the paragraph numbers or drawing numbers of the specification of the invention document are all unified with half-width characters, the description information generation unit 205b may not change the numbers to full-width characters. When half-width characters are included in the specification of the invention document, the type of half-width characters to be changed to full-width characters (for example, alphabetic characters, katakana characters, symbols, etc.), character code range, etc. are obtained by the setting information acquisition unit 201. The specification information generation unit 205b may change half-width characters to full-width characters in the specification for generating modified version description information according to the specification, which can be specified by acquired setting information, etc. . Conversely, if the description of the invention document contains full-width characters, the type of full-width characters to be changed to half-width characters, the character code range, etc. are set in the setting information acquired by the setting information acquisition unit 201. etc., and the specification information generating unit 205b may change full-width characters to half-width characters in the specification for generating revised specification information according to the specification.

The description information generation unit 205b adds, for example, to the description of the invention document acquired by the invention document acquisition unit 2021, the description content of claim n (n is a natural number), such as "■ claim n", or its Can be replaced with content that has been subjected to predetermined conversion processing (e.g., deletion of line feeds, deletion of period characters, and deletion of quoted descriptions that cite claim paragraphs) If there is a description that indicates that the part is The revised specification information may be generated by replacing the content with the content that has been subjected to a predetermined conversion process. The description information generation unit 205b performs this replacement, for example, by replacing the description of the replaceable part in the claim with the description representing the content of the claim in the setting information acquired by the setting information acquisition unit 201. This may be done only when the specified information is included. The description information generating unit 205b extracts important words and phrases extracted by the important word and phrase extraction unit 2051 from the description content after replacement, where there is a description with a code added to the important words and phrases in the invention document. For words and phrases, or key words and phrases where the code corresponding to the key words and phrases is described in the column of "Description of Codes" in the specification of the invention document, insert the code corresponding to the key words and phrases immediately after the key words and phrases. It is also possible to If there are a plurality of codes corresponding to the key phrase, the description information generating unit 205b uses, for example, a list of the plurality of codes separated by commas for insertion after the key phrase. Alternatively, one of the first codes may be selected by sorting the plurality of codes in natural order, etc., and the selected one code may be used for insertion after the important phrase. good.

For example, the description information generation unit 205b detects that the description of the invention document acquired by the invention document acquisition unit 2021 includes a description portion (that is, a so-called claim copy portion) that is substantially the same as the content of the claim section. If it is included, a comment with a character string that includes the item number n of the claim item in a predetermined format such as "■ (claim n)" immediately before or after that part may be inserted. The specification information generation unit 205b inserts the comment, for example, in the setting information acquired by the setting information acquisition unit 201, which includes information designating insertion of a comment related to the item number in the complaint copy part. It may be done only in certain cases. The information specifying the insertion of a comment related to the item number into the complaint copy portion that can be included in the setting information may include information specifying the format of the comment to be inserted.

[3-1-5-8-3-2. Generation of Modified Description Information Part in Document for Display]
When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the revised specification information as a display document (for example, an HTML document), the specification information generation unit 205b outputs the display document Generate the modified specification information included in the patent application related information as.

The corrected version specification information part of the patent application related information as a display document generated by the specification information generation unit 205b is, for example, one If there are one or more important phrases extracted by the important phrase extraction unit 2051 in each row, one or more display elements corresponding to each of the important phrases are included, and each row includes one or more display elements. , "Title of the Invention", "Detailed Description", etc., and one or more display elements corresponding to the headings, if any, and one or more symbols within each line. contains one or more display elements that correspond to each symbol when . As a specific example, the description information generation unit 205b, when describing the revised description information sandwiched between <article> tag and </article> tag in the HTML document, writes the revised version under the <article> tag. For each line of the revised specification as specification information, the display element corresponding to that line is described by sandwiching the contents of that line between the <span> tag and the </span> tag. Under the <span> tag of the display element corresponding to, for each key phrase in the line, the display element corresponding to the key phrase is sandwiched between the <span> tag and the </span> tag. For the heading in the line, the display element corresponding to the heading is described by sandwiching the heading between the <span> tag and the </span> tag, and the code in the line corresponds to the code A display element is described by sandwiching the code between the <span> tag and the </span> tag. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in the revised specification information portion enables, for example, the contents of the corresponding line to be displayed.

To give a specific example of a display element of one key phrase in the revised specification information in the display document generated by the specification information generation unit 205b, the key phrase of the claim in the revised specification information, “equipment control unit ” is described, the display element corresponding to the ninth “device control unit” is, for example, “<span class="c003" id="revspecinfo-c003-009" onclick='wordProc("revspecinfo -c003-009")' title="... (display content with additional information)...">equipment control unit</span>" and the like. In this example, the identification code of the important phrase "equipment control unit" is "c003", and the value of the id attribute of the <span> tag of the display element is the identification symbol "revspecinfo" of the revised specification information and the important A character string including a phrase identification code “c003” and a number “009” in order of description is defined. Also, in this example, the wordProc function is called with the value of the id attribute as an argument when a mouse click operation is performed on the display element. As a result, in the wordProc function, for example, it is possible to specify the display element from the argument and refer to the character string of the important phrase related to the display element. By extracting the identification code "c003" of the phrase, the number "009" in the order of description, etc., for example, the id attribute of the top display element of the same important phrase is specified as "revspecinfo-c003-001". It is possible to realize the processing to display the first display element, for example, display elements of all important words "equipment control unit" such as claim information, modified claim information, specification information, modified specification information, etc. It is possible to realize a process of replacing the displayed content with a character string or the like input by the user.

When each display element of the modified specification information part in the display document is displayed by the browser, the user copies and pastes the displayed contents to an application program (for example, text Editor, etc.), etc., and can be used as a specification for patent application or a Japanese manuscript for translation of the specification for patent application. The user can, for example, freely edit a part or all of the imported modified specification information part or output it to a file by operating an application program having document creation and editing functions. . In addition, through operations such as copy & paste, editing, output, etc., the user can import the content of part or all of the modified specification information portion, or the edited result thereof, into the patent application application program. can. In addition, the user causes the invention document acquisition unit 2021 of the invention document analysis system 20 to acquire the invention document including the edited result of the modified specification information, etc., and causes the invention document acquisition unit 2021 of the invention document analysis system 20 to analyze it again, thereby including the warning information etc. as the analysis result. Patent application related information is available.

The description information generation unit 205b adds, for example, Display control information for controlling the display mode (for example, highlighting, colored display, display transition, etc.) is added. The display control information is, for example, the same as the display control information added to the display element of the specification information portion in the patent application related information as the document for display.

The description information generation unit 205b emphasizes the description part corrected from the description of the invention document, which is included in the modified version description information part of the display document, as a display element by adding an underline or the like to the display element. Display control information for adjusting text-decoration property, border-bottom property, etc. as display attributes may be added to the display element so as to display in the display mode. In the modified specification information in the display document, the description part that has been corrected by deleting it from the specification of the invention document is displayed at the display element composed of <span></span> tags without character strings. It is also possible to add display control information such as displaying a border with a width different from others by adjusting the border property or the like. In the revised specification information, since the description part that is revised from the description of the invention document is not necessarily appropriately revised, the revised description part should be displayed in a display mode that emphasizes it. By doing so, the user can refer to the warning information and the description information to confirm whether or not the correction in the revised description information is appropriate, and then utilize the contents of the revised description information. easier.

[3-1-5-8-4. Code list generation]
The specification information generation unit 205b realizes the code list generation processing by generating a code list based on the specification etc. included in the invention document acquired by the invention document acquisition unit 2021. FIG.

The code list lists the codes that follow the element name represented by the key phrase extracted by the key phrase extraction unit 2051 from the specification of the invention document, and associates the code with the corresponding key phrase. is a list. The description information generation unit 205b generates the code list in a format that can be described in the "description of code" column of the specification for Japanese patent applications, for example. As a code list, the description information generation unit 205b creates, for example, one key phrase and one or more codes corresponding to the key phrase in one line. Enter with a blank character. When describing a plurality of codes corresponding to one key phrase in one line of the code list, the description information generating unit 205b separates the plurality of codes with delimiters such as punctuation characters "," and commas. They can be described by separating them and arranging them in order according to the result of sorting such as natural order. The delimiter in the code list may be set by setting information acquired by the setting information acquisition unit 201 . For example, the description information generation unit 205b arranges each line of the code list in line order according to the result of sorting, such as natural order, for the first code in the line.

For example, when a description in which a sign is added to the key phrase extracted by the key phrase extraction unit 2051 does not exist in the specification of the invention document, the description information generation unit 205b adds the sign to the key phrase. When such a statement is present in a claim of an invention document, the code appended to that key word in that claim may be included in the code list in association with that key word.

For example, when a description in which a code is added to the key phrase extracted by the key phrase extraction unit 2051 does not exist in the invention document, the description information generation unit 205b determines that the element represented by the key phrase is another element. When it is structurally included or structurally included in another element, for that key phrase, the code determined by the code determination processing by the claim information generation unit 205a is associated with the key phrase and included in the code list. obtain.

For example, the description information generating unit 205b refers to the “first-appearance claim number” specified by the attribute specifying unit 2056 as one attribute of each key phrase associated with the code in the code list, thereby identifying the key phrase. The code list may be generated to identifiably express whether or not a phrase is a claimed key phrase of the invention document.

For example, the description information generating unit 205b may add a corresponding translation word or a translation word candidate set to each key word/phrase associated with the code in the code list.

When the output unit 208 in the invention document analysis system 20 outputs the patent application related information including the code list as a document for display (for example, an HTML document), the description information generation unit 205b outputs the patent as a document for display. Generate a code list that is included in the application related information.

The code list part of the patent application-related information as a display document generated by the specification information generation unit 205b includes, for example, one or more display elements corresponding to the contents of each line of the code list, and in each line It includes one or more display elements corresponding to each symbol and key phrase. As a specific example, when describing a code list sandwiched between <article> and </article> tags in an HTML document, the description information generation unit 205b adds an , the display element corresponding to the line is described by sandwiching the content of the line between the <span> tag and the </span> tag, and under the <span> tag of the display element corresponding to one line, For each code or key phrase in the line, a display element corresponding to the code or key phrase is described by sandwiching the code or key phrase between <span> and </span> tags. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each row included in the code list portion, for example, enables the contents of its corresponding row to be displayed. Part of FIG. 30 shows an example of a code list in patent application related information as a display document displayed on the browser. Note that FIG. 30 includes an example of a drawing code list, which will be described later.

The description information generation unit 205b controls the display mode (e.g., highlighting, coloring, etc.) of the code or key phrase in the display element corresponding to each code or key phrase included in the code list portion of the document for display. display, display transition, etc.) is added.

For example, the description information generating unit 205b adds the display control information to be added to the display elements corresponding to the important terms in the code list portion of the display document to the display elements corresponding to the key terms in the description information portion of the display document. It can be generated in the same manner as the additional display control information.

For example, the description information generating unit 205b generates the display element corresponding to the code in the code list portion of the document for display, in response to the operation (for example, mouse click operation) of the display element, in the complaint information or the modified version of the complaint information. It is possible to add display control information for providing a function as a GUI for displaying each line containing a code and the contents of each line containing that code in the specification information or modified specification information.

Specific examples of the display elements of the codes in the code list in the display document generated by the specification information generation unit 205b include the display element of the code "123" described in the code list, for example, "< span class=”sign” id=”signlist-sign123” onclick='refSignProc(“signlist-sign123”)'>123</span>” and so on. In this example, "sign" is defined as the class name of the <span> tag of the display element of the code "123" in the code list, and the value of the id attribute is the identification symbol "signlist" of the code list and the A character string including identification information "sign123" is defined. Also, in this example, it is determined that the refSignProc function is called with the value of the id attribute as an argument when a mouse click operation is performed on the display element. As a result, in the refSignProc function, for example, it is possible to specify the display element from the argument and refer to the character string of the code related to the display element. Replace the display contents of all display elements with the code "123" in the list, description information, etc. with a character string representing the new code entered by the user, and replace the code "123" with the "code" It is possible to implement a process of replacing the content of the "code" of the attribute information of the important phrase included as the content with a new code.

For example, the description information generating unit 205b generates display elements corresponding to the codes in the code list portion of the display document generated based on the invention document, depending on the operation of the display element. Display control information can be added to provide a function as a GUI for displaying the part of the drawing document acquired by the drawing document acquisition unit 2022 where the code is indicated. The description information generation unit 205b, for example, converts the display control information added to the display element of the code so that when the code is operated by the GUI, the part where the code is expressed in the drawing document is highlighted. , may be generated. FIG. 31 shows an example of a pop-up screen displayed in response to a mouse click operation on a code display element in the code list of patent application related information (see FIG. 30) displayed on the browser. The pop-up screen illustrated in FIG. 31 is displayed when a mouse click operation is performed on the code "30a" following the key word "processing unit" in the code list, and the drawing "FIG. 5" including the code "30a" is displayed. and the symbol "30a" in the drawing "FIG. 5" is highlighted.

[3-1-5-9. Claim tree generator]
The claim tree generation unit 205c executes claim tree generation processing for generating a claim tree that can be included in the patent application related information output by the output unit 208 of the invention document analysis system 20. FIG. The claim tree is information expressing the citation relationship of each item of claims represented in the claim information in the patent application related information in the form of a tree structure.

The claim tree generation unit 205 c can execute a modified claim tree generation process for generating a modified claim tree that can be included in the patent application related information output by the output unit 208 of the invention document analysis system 20 . The modified claim tree is information that expresses the citation relationship of each item of claims represented in the modified claim information in the patent application related information in the form of a tree structure.

If the invention document acquired by the invention document acquisition unit 2021 does not include any claims, the claim tree generation unit 205c omits the execution of the claim tree generation process and the modified claim tree generation process.

[3-1-5-9-1. Generate Claim Tree]
The claim tree generation unit 205c performs the claim tree generation process by referring to the claim citation relation information held by the claim citation relation detection unit 2057 and generating a claim tree expressing the citation relation of each item of the claim in the claim information. Realize.

The claim tree generation unit 205c replaces each line of each claim in the claim information in ascending order of the claim number, and adds information indicating which claim number the claim refers to, such as a symbol, claim number, or the like. Generate a claim tree by notating by .

The claim tree generation unit 205c, for example, among the claims in the claim information, the claim target starting point (that is, the claim that does not quote other claims, or the claim destination that (a claim whose subject matter is different from that of the claim), a line in the claim tree that indicates the subject matter of the claim that originates the claim, or a line that describes the number of the claim that originates the subject matter of the claim. Insert a line immediately above and enter a phrase representing the claimed subject matter in the claim originating from the claimed subject matter in the inserted line.

For example, if the line immediately preceding the item in each item of the claim in the claim information representing the claim of the invention document is a comment line, the claim tree generating unit 205c converts the content of the comment line into the corresponding item in the claim tree. Append to the line that describes the item number of the item. In addition, for example, when the line immediately preceding the item is not a comment line among the items of the item in the claim information representing the claim of the invention document, the claim tree generating unit 205c generates the header of the item (for example, a comment line between square brackets). If a comment is written on the same line as the "claim n" (where n is a natural number), in a predetermined format, such as between opening and closing parentheses, the contents of the comment to the line in the claim tree that lists the item number for that item. The claim tree generation unit 205c can identify the comment line and the comment based on the comment identification information in the setting information acquired by the setting information acquisition unit 201, for example.

For example, the claim tree generation unit 205c determines whether, among the claims in the claim information representing the claims of the invention document, the line immediately preceding the claim is not a comment line, and the comment is written in the same line as the heading of the line. If there is one or more key phrases described in that section of the claim of the invention document and extracted by the key phrase extraction unit 2051, at least one of each of the one or more key phrases is included in the claim. Append to the line that describes the item number of that item in the tree. As an example of this case, the claim tree generation unit 205c determines whether any of the important phrases described in the paragraph and extracted by the important phrase extraction unit 2051 are written in any of the other paragraphs preceding that paragraph of the claim. A key phrase that does not have a claim may be preferentially selected and appended to the line in the claim tree that describes that section's section number. Further, in this case, as an example of when there are a plurality of important phrases described in the section and extracted by the important phrase extraction unit 2051, the claim tree generation unit 205c determines that each of the plurality of important phrases described in the section is If the represented elements have a compositional inclusion relationship, write a description that expresses the relationship between key phrases (for example, write key phrases related to the included side in parentheses following key phrases related to the containing side) , may be added to the line that lists the item number of that item in the claim tree.

[3-1-5-9-2. Generate Modified Claim Tree]
The claim tree generation unit 205c refers to the modified claim citation relationship information held by the claim citation relationship detection unit 2057, and performs the modified claim tree generation process by referring to the modified claim citation relationship information to generate a modification that expresses the citation relationship of each item of the claims in the modified claim information. This is achieved by generating a version claim tree. When the modified claim information indicates the citation relationship of each claim item in each of a plurality of claim sets, the claim tree generation unit 205c performs the modified claim tree generation process for each claim set of the modified claim information as follows: This is achieved by generating a modified claim tree that expresses the citation relationship of each claim clause in the claim set.

The method of generating a modified claim tree indicating the citation relationship of each item of the claims in the modified claim information in the claim tree generation unit 205c is the above-described method of generating a claim tree indicating the citation relationship of each item of the claims of the claim information. is similar to

[3-1-5-9-3. Generating Configuration Claim Trees and Modified Configuration Claim Trees]
When the invention document acquired by the invention document acquisition unit 2021 includes a claim, the claim tree generation unit 205c generates a claim related to the claim information included in the patent application related information output by the output unit 208 of the invention document analysis system 20. Tree and modified claim tree for modified claim information, or as a further addition to patent application related information, a constituent claim tree for claim information and modified claim information A modified configuration claim tree may be generated.

The claim tree generating unit 205c, for example, refers to the claim citation relation information held by the claim citation relation detection unit 2057, and generates a constituent claim tree representing the citation relation of each item of the claim in the claim information.

The claim tree generation unit 205c rearranges the lines in ascending order of the item number for each item of the claim in the claim information, and generates information indicating which item number the item is citing as an expression for the citation relationship. symbol (for example, "└"), item number, etc., and when there are one or more key words written in the item and extracted by the key word extracting unit 2051, each key word is composed A configuration claim tree is generated by appending to the line that describes the item number of that item in the claim tree. In this case, when there are a plurality of important phrases described in the section and extracted by the important phrase extraction unit 2051, the claim tree generation unit 205c determines that the elements represented by the plurality of important phrases described in the section are separated from each other. If there is a compositional inclusion relationship, a description that expresses the relationship between key terms (for example, a key term related to the included side is described in parentheses following the key term related to the containing side) should be included in the constituent claim tree. Add a note to the line that describes the item number of that item in .

The claim tree generating unit 205c, for example, refers to the modified claim citation relationship information held by the claim citation relationship detection unit 2057, and generates a modified configuration claim tree that expresses the citation relationship of each item in the modified claim information. do.

The claim tree generating unit 205c rearranges the lines in ascending order of the item number for each item of the claims in the modified version of the claim information, and generates information indicating which item number the item is citing. If there is one or more important phrases written in the section and extracted by the important phrase extraction unit 2051, each of the important phrases is added to the modified configuration claim tree. By adding a note to the line that describes the item number of that item in , a modified configuration claim tree is generated. In this case, when there are a plurality of important phrases described in the section and extracted by the important phrase extraction unit 2051, the claim tree generation unit 205c determines that the elements represented by the plurality of important phrases described in the section are separated from each other. If there is a compositional inclusion relationship, a description that expresses the relationship between important phrases (for example, a key phrase related to the included side is described in parentheses following the important phrase related to the containing side) is added to the modified configuration Append to the line that describes the item number of that item in the claim tree.

[3-1-5-9-4. Generating Various Claim Tree Parts in Documents for Display]
In the invention document analysis system 20, the output unit 208 outputs patent application-related information including at least one of various claim trees such as a claim tree, a modified claim tree, a configuration claim tree, and a modified configuration claim tree to a display document ( For example, when outputting as an HTML document), the claim tree generation unit 205c generates various claim trees included in the patent application related information as a document for display.

Various claim tree portions of the patent application related information as a display document generated by the claim tree generating unit 205c are, for example, one or more display elements corresponding to the contents of each line in various claim trees (e.g., constituent claim trees). , and in each line, if there is a section number, one or more display elements corresponding to each section number, and if there are symbols for expressing citation relationships, one or more displays corresponding to each symbol If there are one or more important phrases extracted by the important phrase extraction unit 2051, one or more display elements corresponding to each of the important phrases are included. As a specific example, the claim tree generation unit 205c creates a , for each line in its various claim trees (for example, constituent claim trees), the display element corresponding to that line is described by sandwiching the content of that line between <span> and </span> tags, and one Under the <span> tag of the display element corresponding to the line, the display element corresponding to the item number in the line, each symbol for expressing the citation relationship, or each important phrase is added with the <span> tag and </span. It is described by inserting the item number, a symbol for expressing the citation relationship, or an important phrase between the > tag. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in each portion of the various claim trees, for example, enables the contents of that corresponding line to be displayed.

The claim tree generating unit 205c adds, for example, the item number and the expression of the citation relationship to the display elements corresponding to the item numbers, the symbols for expressing the citation relationships, or the key phrases included in the various claim tree portions in the document for display. Display control information for controlling the display mode (for example, highlighted display, colored display, display transition, etc.) is added for the symbol for , or for important phrases. The display control information added to the display elements corresponding to the important words and phrases of the various claim tree parts in the document for display is, for example, the display control information added to the display elements for the important words and phrases of the claim information part of the document for display. It is the same.

For example, the claim tree generation unit 205c generates a display element for the item number of the claim tree portion or the component claim tree portion in the document for display, in accordance with the operation of the display element. Display control information is added so that the display element has a function as a GUI for displaying the description part of the numbered item. For example, the claim tree generation unit 205c creates a modified claim tree portion in the display document or a display element for the item number of the modified claim tree portion in the display document according to the operation of the display element. Display control information is added so that the display element has a function as a GUI for displaying the description portion of the item number of the version claim information.

For example, the claim tree generation unit 205c applies an operation ( (for example, a mouse click operation), the display control information is added so that the display element has a function as a GUI for executing a citation relationship disconnection process that disconnects the citation relationship represented by the symbol. . The citation relation disconnection process executed in response to the operation on the display element for the symbol for expressing the citation relation is, for example, the process of updating the content of the modified claim information in the display document for the citation relation disconnection. and updating the content of the modified claim tree portion or the modified configuration claim tree portion so as to match the content of the modified claim information after the update, and the processing for expressing the citation relationship as the display element. a process of changing the symbol to a predetermined symbol (for example, "x") to express that the citation relationship has been cut, and redisplaying the display element. In the process of updating the content of the amended claim information in the display document for severing the citation relationship, for example, from the citation including the citing paragraph number in the corresponding section of the amended claim information, the citing paragraph number In any section of the claim represented by the amended claim information, if the statement of Deletion of the reference to the referenced paragraph number is carried out only when it does not create an inappropriate situation of not being described in the paragraph to which the section or the paragraph references or the paragraph to which the reference is chained. If an inappropriate state occurs, a message to that effect is displayed to suppress the execution of the citation relationship severing process, and the patent application-related information as a document for display is returned to the state before the citation relationship severance process was executed. . In this citation relationship disconnection process, if the description related to the cited item number is deleted from the cited description (eg, "any one of claims 1 to 3") containing the cited item number (eg, 2), the above-mentioned Whether or not an inappropriate state occurs depends on the reference word/phrase detection processing performed by the warning information generation unit 2059 by referring to the claim citation relationship information held by the claim citation relationship detection unit 2057 (that is, The condition that the same referenced term as the term following the reference string must be stated in the part of the section preceding the reference string or in the section to which the section is cited. can be determined by the same method as the processing for detecting that a description related to a reference character string that does not satisfy is included).

FIG. 32 shows an example of a configuration claim tree in patent application related information as a display document displayed on a browser. In addition, FIG. 33 shows that, in response to a mouse click operation on display elements of symbols for expressing citation relations in the claim tree constituting the patent application-related information displayed on the browser, the display elements indicate that the citation relations have been cut. Show a modified example in what you represent. The example of FIG. 33 shows the state after the two symbols "└" for expressing the citation relation shown in FIG. └” is changed to a symbol “×” that expresses that the citation relationship has been cut in FIG. The configuration claim tree illustrated in FIG. 32 indicated that the fourth term of the claim cited each of the first to third terms, but after two mouse click operations illustrated in FIG. constituent claim tree shows that claim 4 refers only to claim 1. In the state exemplified in FIG. 33, by the citation relation disconnection processing corresponding to the mouse click operation, the fourth term of the claim is corrected so as not to cite the second and third terms, and the revised claim information is updated. There will be

[3-1-5-10. Classification Department]
The classification unit 2053 is a partial modification of the classification unit 1053 shown in the first embodiment, and is the same as the classification unit 1053 except for points not specifically shown here.

The classification unit 2053 performs group classification for each of the plurality of invention documents acquired by the invention document acquisition unit 2021 .

For example, for each of the plurality of invention documents acquired by the invention document acquisition unit 2021, the classification unit 2053 uses the key phrase group, which is a plurality of key phrases extracted by the key phrase extraction unit 2051. Based on the correlation between key phrase groups, group classification is performed to specify which of the plurality of groups each of the plurality of invention documents belongs to. The classification unit 2053 weights each key phrase of the key phrase group extracted from each of the plurality of invention documents according to the degree of importance determined by the importance determination unit 2055 corresponding to the key phrase. Then, a calculation can be made of the correlation between key phrase groups. The classification unit 2053 classifies, for example, each key phrase of the key phrase group extracted from each of the plurality of invention documents into a predetermined value for the importance determined by the importance determination unit 2055 corresponding to the key phrase. Lower key phrases may be ignored and the correlation between key phrase groups may be calculated. In order to evaluate the correlation between the important phrase groups, the classification unit 2053 uses an algorithm for counting the number of the same important phrases common to both important phrase groups and a synonym dictionary to identify the same or similar in both important phrase groups. Algorithm for counting the number of important phrases, each of the character strings assumed to be used as important phrases in a sufficient number (for example, thousands, tens of thousands, etc.) for each of the important phrase groups A vector that defines an element value greater than 0 and 1 or less that corresponds to the importance of the key phrase when the element character string exists as a key phrase, and an element value of 0 if it does not exist as the key phrase. Any algorithm may be used, such as algorithms that define data and calculate correlation coefficients between the vector data. Further, the classification unit 2053 may classify the important phrases of each invention document into groups using any one of various algorithms related to clustering techniques. The classification unit 2053 classifies, for example, a somewhat sufficient number (for example, several tens, hundreds, etc.) of inventions as character strings that are assumed to be used as key phrases in a somewhat sufficient number (for example, several thousands, tens of thousands, etc.). Documents are acquired by the invention document acquisition unit 2021 of the invention document analysis system 20, and the key phrases extracted from each invention document by the key phrase extraction unit 2051 are integrated without duplication, and each element of the set of key phrases is used. be able to.

The classification unit 2053 includes a technical field identification unit 20531 that classifies the technical field for identifying to which of a plurality of technical fields each invention document belongs as one of the group classifications of each invention document. The classification unit 2053 can perform various group classifications, not limited to technical fields as one type of group. For example, the classification unit 2053 may classify the invention documents into groups according to the departments to which the inventors belong, according to the user's designation or the like. The group classification unit, method, etc. are used by each user who mutually communicates the invention document analysis system 20 operation unit (for example, invention document, bilingual dictionary information, or information output by the invention document analysis system 20). It can be useful to be unified in each invention document analysis system 20).

The technical field specifying unit 20531 is a partial modification of the technical field specifying unit 10531 shown in the first embodiment, and is the same as the technical field specifying unit 10531 in terms of points not particularly shown here.

For each of a plurality of technical fields, the technical field identification unit 20531 acquires one or more invention documents known to be related to the technical field by the invention document acquisition unit 2021 in the past, and extracts important words by the important phrase extraction unit 2051 By using the result of extracting the word group in the past, the important word/phrase extracting unit 2051 extracts from the invention document for which the technical field is not specified and which is acquired by the invention document acquiring unit 2021 among a plurality of technical fields. Any technical field whose correlation with the group of important words and phrases obtained is greater than or equal to a predetermined degree is specified as a technical field corresponding to the invention document whose technical field is not specified. The technical field identification unit 20531 weights each key phrase of the key phrase group extracted from each of the plurality of invention documents according to the degree of importance determined by the importance determination unit 2055 corresponding to the key phrase. , the correlation between key phrase groups can be calculated. As a result, elements of correlation calculated between key phrases with relatively high weighting are evaluated relatively high, and correlation factors calculated between key phrases with relatively low weighting are evaluated relatively high. Elements are rated relatively low. Therefore, for example, when a group of key phrases with a relatively high degree of importance in invention document A and a group of key phrases with a relatively high degree of importance in invention document B are substantially the same, the correlation between the two invention documents is For example, the group of key words and phrases evaluated as relatively high and having relatively high importance in invention document A and the group of key words and phrases having relatively high importance in invention document B are completely different, and invention document A If the group of key phrases with relatively low importance in the invention document B and the group of key phrases with relatively low importance in invention document B are generally the same, the correlation between the two invention documents is evaluated as relatively low. . For example, the technical field specifying unit 20531 determines in advance the importance determined by the importance determination unit 2055 corresponding to each key phrase of the key phrase group extracted from each of the plurality of invention documents. Important words below a predetermined value may be ignored, and the correlation between important word groups may be calculated. A technical field is represented by IPC, for example. The technical field specifying unit 20531 may use classification up to any level of the IPC as the technical field, and may handle it as one technical field using, for example, only sections or only sections and classes. Also, the technical field identification unit 20531 may express the technical field using all of the IPC sections, classes, subclasses, main groups and subgroups. For example, if the technical field is to be distinguished only by the section of the IPC, the technical field identification unit 20531 acquires a plurality of invention documents belonging to each section of the IPC using patent gazettes, etc., and Each invention document is acquired by the invention document analysis system 20, and the important phrase group corresponding to the section extracted by the important phrase extraction unit 2051 can be obtained. For example, by using the group of key phrases for each section obtained in the past, the technical field specifying unit 20531 extracts from the invention documents for which the section as the technical field is not specified, which is acquired by the invention document acquiring unit 2021. A section that is evaluated to have a correlation with a group of key phrases extracted by the key phrase extraction unit 2051 that is equal to or greater than a predetermined level can be specified as the technical field of the invention document.

The technical field identification unit 20531 identifies the technical field to which the invention document belongs based on the group of key words extracted from the invention document, for example, by performing predetermined arithmetic processing using the learning model for technical field identification. You can do it. In addition, the technical field identification unit 20531, for example, includes data corresponding to one or more existing technical term dictionary item groups (that is, headword groups) for each of a plurality of technical fields, and key words and phrases extracted from invention documents. The technical field to which the invention document belongs may be identified by comparing the groups and counting and evaluating the number of matching words.

The technical field information, which is information indicating the technical field (for example, IPC) identified by the technical field identifying unit 20531 corresponding to the invention document obtained by the invention document obtaining unit 2021, is, for example, the patent Included in application related information.

In addition, the group identified by the classification unit 2053 to which the invention document belongs, or the technical field identified corresponding to the invention document by the technical field identification unit 20531, is used for translation by the translation unit 2054, for example. , bilingual dictionary information for each group or for each technical field. Also, the group classification by the classification unit 2053, including the technical field classification by the technical field identification unit 20531, can be used by the machine learning unit 207 to generate a translation learning model for each group.

[3-1-5-11. Translation Department]
The translation unit 2054 receives the complaint information and the modified version of the complaint information generated by the complaint information generating unit 205a and the description information and the modified version of the description information generated by the description information generating unit 205b as input, The content of each claim represented in the claim information and the modified version of the claim information, and the description information and the revised version of the description information, are calculated by calculation processing predetermined for translation using the learning model. Perform machine translation of the content of the specification to be submitted. Depending on the content of the invention document acquired by the invention document acquisition unit 2021, any one of the claim information, the modified claim information, the specification information, and the revised specification information may not be generated. For this reason, the translation unit 2054 executes machine translation by using only the generated information among the claim information, the modified claim information, the specification information, and the modified specification information as input.

The learning model for translation is a model for machine translation that is generated by machine learning using multiple pairs of invention documents and translation result documents as the result of translation by translators etc. based on the invention documents as training data. Learning model. Here, as an example, the learning model for translation is explained as a learning model used for machine-translating a Japanese invention document into an English document. It may be a learning model used for machine translation into Chinese or other language documents.

When there is a learning model for translation for each of a plurality of groups or technical fields, the translation unit 2054, for example, classifies the group or technical field to which the invention document acquired by the invention document acquisition unit 2021 belongs to the classification unit 2053 or the technical field. Claim information and modified claim information generated based on the invention document by selectively using the learning model for translation corresponding to the group or technical field to which the invention document belongs, specified by the field specifying unit 20531 It is also possible to perform machine translation of all or part of the claims represented in , and all or part of the specification represented in the specification information and the modified specification information. Machine translation in the case where the learning model for translation includes a learning model for translation of important phrases is to translate each word in the sentence by arithmetic processing using the learning model for translation of important phrases. , and arithmetic processing using the learning model for translation on the result (for example, arithmetic processing including arithmetic processing according to the grammar of the language to be translated, such as selecting either singular or plural for the translated phrase) This is realized by generating sentences in the language to be translated by performing A learning model for translating for each group or for a certain technical field may include a learning model for translating important phrases for that group or for that technical field.

The translation unit 2054 can acquire and use the translation assistance information based on the information for specifying the translation assistance information in the setting information acquired by the setting information acquisition unit 201, for example.

For example, the translation unit 2054 acquires translation assistance information corresponding to other invention documents that are somewhat related to the invention document acquired by the invention document acquisition unit 2021, and acquires the translation assistance information by the invention document acquisition unit 2021. It may also be used for machine translation of claim information, modified version claim information, specification information, or modified version specification information related to an invention document that has been created. The degree of relationship between invention documents is determined, for example, based on the key phrase group information indicating each key phrase extracted from each invention document by the key phrase extraction unit 2051, and the correlation between the key phrase groups represented by the key phrase group information. The determination can be made on the basis of gender, the percentage of the same key phrases in the key phrase groups, the relevance between the technical fields to which the invention documents specified from the key phrase groups belong, and the like.

The translation unit 2054, for example, translates the translation assistance information generated in the past by the invention document analysis system 10 shown in the first embodiment, the translation assistance information generated in the past by the invention document analysis system 20, or these translation assistance information. Acquire any of the translation assistance information as a result of collecting and integrating according to the operation mode of the system, and apply the acquired translation assistance information to the invention document acquired by the invention document acquisition unit 2021 It may be used for machine translation of the claim information, modified claim information, specification information, or modified specification information. The translation unit 2054 can acquire the translation assistance information based on the identification information of the translation assistance information in the setting information acquired by the setting information acquisition unit 201, for example.

The translation unit 2054 is represented in the above-described complaint information and modified complaint information by arithmetic processing predetermined for translation of key phrases using an important phrase translation learning model for translation of key phrases. Execution of machine translation of claims and important phrases (that is, important phrases extracted by the important phrase extraction unit 2051) included in all or part of the specification represented in the specification information and the revised specification information may be Based on the result of this machine translation, a corresponding translated word for the key phrase can be determined. In addition, the translation unit 2054 acquires the above-described translation assistance information and uses the translation assistance information, or translates one or more important phrases acquired by the important phrase setting dictionary acquisition unit 203 into corresponding translations. By using a key phrase setting dictionary that associates words, all or part of the claims represented by the claim information and the modified version of the claim information, and the specification represented by the specification information and the modified version of the specification information It is also possible to determine a corresponding translation word for the included key words. When the translation unit 2054 determines the corresponding translation word for the important phrase, the translation unit 2054 updates the important phrase management information held by the analysis unit 205 so as to reflect the determined corresponding translation word. The translation assistance information may be classified by group or technical field, and the translation unit 2054 selectively selects the translation assistance information corresponding to the group or technical field to which the invention document acquired by the invention document acquisition unit 2021 belongs. may be used to determine corresponding translation words for key words, perform machine translation, and the like.

The translation unit 2054, for example, converts key phrases included in each tree into the constituent claim tree and the modified constituent claim tree generated by the claim tree generating unit 205c, and converts the key phrases included in each tree into machine processing using a learning model for key phrase translation. The post-replacement claim tree that has been replaced may be included in the translation result or in the corresponding translated word based on the translation assistance information.

The translation unit 2054 translates all or part of the claims represented by the above-described claim information and modified version claim information, and all or part of the specification represented by the description information and revised version description information It is also possible to execute machine translation using a learning model for translation by using a result obtained by replacing each included key word with a machine translation result as an input.

Further, the translation unit 2054, for example, translates all or part of the claims represented by the above-described claim information and modified version claim information, and all or part of the specification represented by the description information and revised version description information. Alternatively, machine translation is performed by replacing each key phrase contained in a part with a machine translation result as an input to a predetermined machine translation program and obtaining the translation result output by this predetermined machine translation program. You can do it. In this predetermined machine translation program, all or In the machine translation of each sentence related to a part, the machine translation result for each key phrase is changed to the appropriate plural form or singular form according to the content of each sentence, and machine translation is performed. Any translation algorithm can be used. The predetermined machine translation program is, for example, a program that outputs sentences as translation results for Japanese sentences input using existing machine translation technology. May exist outside. For example, a predetermined machine translation program operates on a server device (that is, a computer) that can communicate with a terminal device that constitutes the invention document analysis system 20 through a network such as the Internet and that provides, for example, an API for translation, etc. The translation unit 2054 encrypts information to be input to a predetermined machine translation program and transmits it to the server device, and the server device encrypts information output from the predetermined machine translation program and transmits it to the terminal device. 2054 may receive and decode information output by a predetermined machine translation program. Any encryption method may be used in this encryption and decryption.

The learning model for translation and the learning model for important phrase translation that the translation unit 2054 uses for machine translation may be generated by any method. The learning model for translation and the learning model for important phrase translation used by the translation unit 2054 for machine translation are, for example, those generated by the machine learning unit 207 in the past, or the output unit 208 by another invention document analysis system 20 in the past. It may be output from

[3-1-5-11-1. Generation of various translation information]
The results of machine translation of the claims represented in the claim information by the translation unit 2054 can be included in the patent application related information output by the invention document analysis system 20 as claim translation information, for example. The claim translation information includes, for example, each line of the claim information, and for each line of the included claim information or each claim term, the content of that line or claim term is immediately followed by the content of that line or claim term. It may be a line representing the result of machine translation corresponding to , or a paragraph of the claim. In the claim translation information, the content of one line or section representing the result of machine translation corresponding to the content of the line or section of the claim information is a translation line consisting of one or more lines, and the translation line is the claim information. It may be a complete translation line that expresses the entire line or paragraph of the claim information in the target language, or only the translatable important phrases contained in the line or paragraph of the claim information are expressed in the corresponding translation language and translatable The part other than the important words may be a partially translated line in which the Japanese description is left as it is. In a line containing a key word of the claim information or a complete translation line representing the entire paragraph in the target language, the word corresponding to the key word in the target language can be treated as a corresponding translated word. Therefore, the complaint translation information can also be said to be information representing the result of replacing key words and phrases included in the contents of the complaint information with corresponding translation words corresponding to the key words and phrases. When including a complete translation line in the claim translation information, the translation unit 2054 further inserts a partially translated line corresponding to the line to be translated of the complete translation line immediately before or after the complete translation line. good too. The translation unit 2054 sets the setting acquired by the setting information acquisition unit 201 as to whether each line of the complaint information is mixed in the complaint translation information or only the translated line (that is, the completely translated line or the partially translated line) is mixed with the complaint translation information. A decision may be made based on the specification in the information and the claim translation information may be generated according to the decision. When the claim translation information includes each line of the claim information, the invention document analysis system 20 may treat the claim translation information as claim information and include it in the patent application related information.

The results of machine translation of the claims represented in the modified claim information by the translation unit 2054 can be included in the patent application related information output by the invention document analysis system 20 as modified claim translation information, for example. The modified claim translation information includes, for example, each line of the modified claim information, and for each line of the included modified claim information, a line indicating the result of machine translation corresponding to that line is added immediately after that line. It may be inserted. In the modified claim translation information, one line representing the result of machine translation corresponding to the line of the modified claim information may be a complete translation line representing the entire line of the modified claim information in the target language. However, only the translatable key words and phrases contained in the lines of the modified claim information are expressed in the corresponding translated words, and the parts other than the translatable key words and phrases are left as they are in Japanese. good too. When a complete translation line is included in the modified claim translation information, the translation unit 2054 further inserts a partially translated line corresponding to the line to be translated of the complete translation line immediately before or after the complete translation line. You can do it. The translation unit 2054 selects whether each line of the corrected complaint information is mixed in the corrected complaint translation information, or only the completely translated line or the partially translated line without mixing is set in the setting information acquired by the setting information acquisition unit 201. may be determined based on the specification in , and the modified claim translation information may be generated in accordance with the determination. When the modified claim translation information includes each line of the modified claim information, the invention document analysis system 20 treats the modified claim translation information as the modified claim information and includes it in the patent application related information. It is also possible to let

The result of machine translation of the specification represented in the specification information by the translation unit 2054 can be included in the patent application related information output by the invention document analysis system 20 as specification translation information, for example. Description translation information includes, for example, each line of description information, and for each line of the included description information, a line representing the result of machine translation corresponding to that line is inserted immediately after that line. may be In the description translation information, one line representing the result of machine translation corresponding to the line of the description information is a translation line, and the translation line is a complete translation of the entire line of the description information in the target language. It may be a translation line, or only the translatable key phrases contained in the line of the specification information are expressed in the corresponding translated words, and the parts other than the translatable key phrases are left as they are in Japanese. It may be a partially translated line. In the complete translation line that represents the entire line containing the key phrase of the specification information in the translation destination language, the phrase in the translation target language corresponding to the key phrase can be treated as the corresponding translated word. Therefore, the specification translation information can also be said to be information representing the result of replacing the key words included in the contents of the specification information with corresponding translated words corresponding to the key words. When including a fully translated line in the specification translation information, the translation unit 2054 further inserts a partially translated line corresponding to the line to be translated of the fully translated line immediately before or after the fully translated line. may be The setting information acquisition unit 201 acquires whether each line of the specification information is mixed in the specification translation information or only the translation line (that is, the completely translated line or the partially translated line) is used without mixing. It is also possible to determine based on the specification in the set information, and generate the specification translation information according to the determination. In addition, when the specification translation information includes each line of the specification information, the invention document analysis system 20 treats the specification translation information as specification information and includes it in the patent application related information. good.

The result of machine translation of the specification represented in the revised specification information by the translation unit 2054 can be included in the patent application-related information output by the invention document analysis system 20, for example, as the revised specification translation information. . The modified specification translation information includes, for example, each line of the modified specification information, and for each line of the included modified specification information, immediately after that line, the machine translation result corresponding to that line It is also possible to insert a line representing In the modified specification translation information, one line representing the result of machine translation corresponding to the row of the modified specification information is a complete translation line representing the entire line of the modified specification information in the target language. Alternatively, it is a partial translation in which only the translatable key phrases contained in the lines of the modified specification information are expressed in the corresponding translated words, and the parts other than the translatable key phrases are left as they are in Japanese. can be a line. When including a complete translation line in the revised specification translation information, the translation unit 2054 further inserts a partially translated line corresponding to the line to be translated of the complete translation line immediately before or after the complete translation line. It is also possible to The setting information acquisition unit 201 acquires whether the translation unit 2054 mixes each line of the revised specification information in the revised specification translation information, or only the completely translated line or the partially translated line without mixing each line. It may be determined based on the specification in the setting information, and the revised specification translation information may be generated according to the determination. When the revised specification translation information includes each line of the revised specification information, the invention document analysis system 20 handles the revised specification translation information as the revised specification information. It may be included in the related information.

For example, in generating a partially translated line, if a corresponding translated word corresponding to an important word in the line to be translated cannot be identified, the translation unit 2054 converts the important word in the line to be translated into a translation word candidate set for that important word. , is generated as a partial translation line.

When the translation destination language is English, for example, the translation unit 2054 generates claim translation information, corrected version claim translation information, description translation information, or partial translation line or Codes in the complete translation line can be written in half-width characters if they can be expressed in half-width characters, and half-width spaces are inserted before and after the codes.

When the translation destination language is English, for example, the translation unit 2054 generates claim translation information, modified version claim translation information, description translation information, or partially translated lines or complete translations in the revised version description translation information. When there is a blank character at the beginning of the line to be translated, the blank character is replaced with a predetermined number of single-byte blank characters and included at the beginning of the line in the partially translated line or the completely translated line. can be written as The predetermined number as the number of half-width blank characters that can be written at the beginning of the partially translated line or the fully translated line may be determined by the setting information acquired by the setting information acquiring unit 201, for example.

For example, the setting information acquired by the setting information acquisition unit 201 sets the format of the translated sentence in English (the number of half-width spaces to be inserted at the end of the sentence, etc.) when the language to be translated is English. Alternatively, the translation unit 2054 may generate each translation in the specification translation information, the revised version specification translation information, etc. according to the format set by the setting information.

For example, the translation unit 2054 adds a heading ( For example, a description part that starts with an opening corner bracket and ends with an end bracket with a corner) is described, the translation result of the heading is included by translating the heading according to a predetermined bilingual table of headings. Alternatively, a partially translated line or a fully translated line may be generated. A predetermined bilingual table of headlines (that is, a table in which each of a plurality of Japanese headlines is associated with a predetermined translation result of the headline) is obtained by, for example, setting information acquired by the setting information acquisition unit 201. It may be defined. For example, when the language to be translated is English, as an example of a bilingual table of headings, for each Japanese heading (e.g., "Title of the Invention", "Mode for Carrying out the Invention", etc.), the Japanese A correspondence between the headings and the English text of the headings for international applications conforming to the agreements of the Trilateral Offices may be mentioned.

Translation unit 2054 includes translation word candidate set identification unit 20541 . The translation word candidate set identification unit 20541 is a partial modification of the translation word candidate set identification unit 1052 shown in the first embodiment, and is the same as the translation word candidate set identification unit 1052 except for the points not shown here. be.

The translation word candidate set specifying unit 20541 can acquire and hold the bilingual dictionary information based on the bilingual dictionary information specifying information of the setting information, for example. The translation word candidate set identification unit 20541 may hold bilingual dictionary information in advance, for example.

The translation word candidate set identification unit 20541 uses the bilingual dictionary information for each of the key words extracted by the key word extraction unit 2051 from the invention documents acquired by the invention document acquisition unit 2021 to identify corresponding translated words for the key words. A translation word candidate set, which is a set of candidates for . The translation word candidate set identification unit 20541 can perform various processes for each key phrase so that the number of elements in the translation word candidate set corresponding to the key phrase is 1 or more as much as possible. It is possible that the number of elements in the translation word candidate set corresponding to the important phrase is zero. Examples of these various types of processing include processing for synthesizing bilingual translations obtained from bilingual dictionary information by decomposing a compound word into a plurality of key phrases for which no element of the candidate translation set is found; If the stem of the important phrase for which no element is found contains a prescribed limiting phrase (e.g. ordinal number, various numerals, limited character string "predetermined", etc.), the Japanese prescribed limiting phrase and its important phrase A process of synthesizing bilingual translations obtained from bilingual dictionary information for parts other than the stem, and a predetermined ending character string (e.g., "part", "means", etc.) If it is included, the bilingual dictionary information for the portion other than the ending of the important phrase, and the predetermined Japanese ending character string, or the bilingual dictionary information corresponding to the predetermined ending character string A process of synthesizing a parallel translation and the like can be mentioned. This predetermined ending string may be one or more technical term-specific ending strings indicated by the technical term-specific ending information included in the setting information acquired by the setting information acquisition unit 201 .

The elements of the translation word candidate set for the important phrase specified by the translation word candidate set specifying unit 20541 may partially include Japanese words. For each key phrase, the translation word candidate set identification unit 20541 adds the corresponding translation word associated with the key phrase in the translation assistance information to the translation word candidate set corresponding to the key phrase, unless it overlaps with an existing element. It may be added as a new element. The translation word candidate set identification unit 20541 executes predetermined arithmetic processing using the key phrase translation learning model for each key phrase, and based on the calculation result, a translation word candidate set corresponding to the key phrase. may be specified or modified (for example, addition of machine translation results generated by the arithmetic processing). In addition, for each key word, the translation word candidate set identification unit 20541 extracts each line containing the key word from the invention document from which the key word is to be extracted, and inputs each line to a predetermined machine translation program. , of the translation results output by this predetermined machine translation program, obtain one or more parallel translations corresponding to the portion where the key phrase is translated, and convert each of the parallel translations into a set of translation word candidates corresponding to the key phrase. It may be added as an element of

The translation word candidate set identification unit 20541 updates the important phrase management information held by the analysis unit 205 so as to reflect the translation word candidate set when the translation word candidate set for the important phrase is identified or corrected. .

An example of a translation word candidate set that the translation word candidate set identifying unit 20541 identifies an important word based on bilingual dictionary information when the target language is English is the translation word for the important word "screwdriver". Candidate set "screwdriver", translation word candidate set "processor, handler" for important phrase "processing part", translation word candidate set "judgment" for important phrase "judgement part" that can be decomposed into "judgment" and "part" A set of candidate translation words for the important phrase "variation, amount of change", and a translation for the important phrase "predetermined criteria" that can be decomposed into "predetermined" and "standard" A word candidate set "predetermined standard, predetermined basis, predetermined criterion", a translation word candidate set "support processing, backing processing, aid processing" for the important phrase "support processing" that can be decomposed into "support" and "processing", important Examples include a translation word candidate set "letter, character, writing" for the word "letter".

The translation word candidate set identification unit 20541, for example, classifies the group identified by the classification unit 2053 as belonging to the invention document or the technical field identified corresponding to the invention document by the technical field identification unit 20531 by group or by technology. Bilingual dictionary information for specifying a translation word candidate set is used to select from among a plurality of field-specific bilingual dictionary information. In each of the plurality of bilingual dictionary information, for example, the order (that is, correspondence One or more bilingual words/phrases corresponding to the important words/phrases are ordered in descending order of validity as translation words, and the translation word candidate set identification unit 20541 matches the order of the words/phrases in the selected bilingual dictionary information. Alternatively, the arrangement order of the elements of the translation word candidate set may be determined. When the translation word candidate set is output (eg, displayed) as part of the patent application-related information, the arrangement order of the elements of the translation word candidate set can be arranged and output (eg, displayed) in that order. Each of the plurality of bilingual dictionary information by group or by technical field is configured so that the more frequently used important words and phrases in the group or technical field are searched, the more quickly, in order to improve the search efficiency of the bilingual dictionary information. You may do so.

An example of a plurality of pieces of bilingual dictionary information for each technical field when the target language is English is an element of a translation word candidate set for the important word "transplant" in the bilingual dictionary information corresponding to the field of computer technology. , the validity of "porting" is relatively high, and the validity of "transplant" is relatively high in the element of the translation word candidate set for the important word "transplant" in the bilingual dictionary information corresponding to the field of medical equipment. Among the elements of the translation word candidate set for the important word "molecule" in the bilingual dictionary information corresponding to the fields of Among the elements of the translation word candidate set for the phrase "molecule", there is an example in which "numerator" is relatively highly appropriate.

An example of a plurality of bilingual dictionary information for each group of the inventor's department when the target language is English is, for example, the translation policy (e.g., rules for translation expressions) related to the invention document for each department. Due to differences, etc., the elements of the translation word candidate set for each of the important words "analysis process" and "control process" in the bilingual dictionary information corresponding to the first department are not valid for "analysis process" and "control process", respectively. The elements of the translation word candidate set for each of the key phrases “analyzing step” and “controlling step” in the bilingual dictionary information corresponding to the second category are “analyzing step” and “controlling The validity of "step" is determined to be the highest, and the elements of the translation word candidate set for each of the important words "analyzing process" and "control process" in the bilingual dictionary information corresponding to the third category are "analyzing" , an example that best defines the validity of "controlling" is given.

[3-1-5-11-2. Generating Various Translation Information Parts in Documents for Display]
In the invention document analysis system 20, the output unit 208 outputs patent application related information including at least one of various translation information such as claim translation information, modified claim translation information, specification translation information, and modified specification translation information, When outputting as a display document (for example, an HTML document), the translation unit 2054 converts the claim translation information, modified claim translation information, specification translation information, or correction Generate version specification translation information.

Claim translation information, modified claim translation information, specification translation information, or modified specification translation information of patent application-related information as a document for display generated by the translation unit 2054 is, for example, the claim translation information , containing one or more display elements corresponding to the content of each line in the modified version of the claim translation information, the specification translation information, or the modified version of the specification translation information. If there is one or more key phrases, one or more display elements corresponding to each key phrase are included, and if there are machine translation results in which one or more key phrases are translated in each line, each machine Contains one or more display elements corresponding to translation results. As a specific example, the translation unit 2054 translates the complaint translation information, the modified version of the complaint translation information, the specification translation information, or the modified version of the specification translation information into the <article> tag and the </article> tag in the HTML document. In the case of sandwiching, under the <article> tag, for each line in the claim translation information, the modified version of the claim translation information, the specification translation information, or the modified version of the specification translation information, the display element corresponding to that line is displayed. , <span> tag and </span> tag to describe the content of the line, and under the <span> tag of the display element corresponding to the line, an important phrase in the line or an important Regarding the machine-translated result of translated words, the corresponding display element is described by sandwiching the important word or the machine-translated result between the <span> tag and the </span> tag. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in various translation information portions in the display document makes it possible, for example, to display the contents of the corresponding line.

The translation unit 2054 adds key words and phrases included in various translation information portions in the document for display, or display elements corresponding to the machine translation results into which the key words and phrases have been translated. , display control information for controlling the display mode (for example, highlighted display, colored display, display transition, etc.) is added. For display control information added to display elements corresponding to important words and phrases of various translation information parts in a document for display, or to display elements corresponding to machine translation results in which the important words and phrases are translated, It is similar to the display control information added to display elements for words.

For example, the translation unit 2054 translates each of a plurality of important phrases having different character strings constituting the important phrases of various translation information portions in the document for display in mutually different display modes (for example, modes in which mutually different colors are added). As displayed, display control information may be defined to be attached to the display element corresponding to each key phrase. In addition, the translation unit 2054, for example, of the various translation information parts in the document for display, at least a part ( For example, the display control information to be added to each display element can be determined so that the color of the left boundary line that is added to the important phrase or machine translation result and has a certain width) is the same. To give a specific example, the translation unit 2054, as information to be added to the display element of the result of the machine translation for which the important words and phrases in the claim translation information and the specification translation information are the object of machine translation, adds the important words and phrases to the important words and phrases in the claim information. In the case where a character string constituting a phrase is the same key phrase as each of multiple key phrases that are different from each other, at least part of the display mode of the result of the machine translation is that of the key phrase in the claim information and specification information. The result of machine translation so as to be the same as at least part of the display mode (for example, the display color added to the result of machine translation of the key phrase is the same as the display color added to the key phrase) Define display control information for controlling the display mode of For example, if the display control information related to the key phrase in the claim information is for controlling the key phrase to be displayed in a display mode in which a left border line having a predetermined width is added, The display control information related to the result of machine translation of the key phrase in the claim translation information and the description translation information to be translated is the display of the left border line related to the display mode of the key phrase. This is for controlling to display in a display mode in which a left boundary line having the same display color as the color and having a predetermined width is added. As a result, in the various translation information parts as the display document, in the case where the machine translation target and the machine translation result are alternately described for each line or each claim, The user can relatively easily comprehend the correspondence relationship between the key phrases in various translation information portions and the machine translation result in which the key phrases are translated.

The translation unit 2054 adds display control information related to the function as a GUI according to the operation to be added to the display elements of key words in various translation information parts in the display document. It can be determined in the same manner as the display control information related to the function as a GUI according to the operation, which is added to the display element of the important phrase of the specification information part in . In addition, the translation unit 2054 adds display control information related to a function as a GUI according to an operation to be added to the display element of the machine translation result in which the important phrase is translated in various translation information parts in the document for display, for example, It can be defined in the same manner as the display control information related to the function as a GUI according to the operation, which is added to the display element of the important phrase.

The translation unit 2054 has a function as a GUI for displaying the key words in response to the operation of the display element, for example, on the display element of the machine translation result in which the key word is translated in the various translation information parts in the document for display. Display control information may be added.

The translation unit 2054 displays the machine-translated results of the key words of the various translation information parts in the document for display on the display elements of the machine-translated results of the translated key words, for example, in response to the operation of the display elements. may add display control information including translation word candidate information in order to have a GUI function for displaying different sets of translation word candidates. A translation word candidate set identification unit 20541 identifies a translation word candidate set for an important phrase. The GUI function for displaying the translation word candidate set may display a selection menu with options for each element of the translation word candidate set. may be added, or the elements may be arranged and displayed in descending order of validity. When the translation unit 2054 selects one element from the translation word candidate set for the key phrase displayed as a result of the operation on the GUI related to the display element, the translation unit 2054 translates the content of the display element of the machine translation result into the selected element. Display control information to be added to the display element may be determined so as to change to the element selected by the selection operation. The translation unit 2054 changes the machine translation result, for example, when the translation target language is English, depending on whether the machine translation result to be changed is singular or plural, the selected element is the same, This can be accomplished by converting to singular or plural forms and making changes to the elements after conversion. The translation unit 2054 further converts the display control information into machine-translation of the key phrase in various translation information parts in the display document when an operation is performed to select one element from the translation word candidate set for the key phrase. It may be determined that the contents of each display element of all the machine translation results that are the same as the result are collectively changed to the element selected by the selection operation. In addition, when the translation unit 2054 selects one element from the translation word candidate set for the key phrase displayed as a result of the operation on the GUI related to the display element, the translation unit 2054 The display control information to be added to the display element may be determined so that the combination with one element is transmitted to the machine learning unit 207 as teacher data for machine learning for generating a learning model for important phrase translation. . FIG. 34 shows an example of claim translation information in patent application related information as a display document displayed on the browser. In the example of FIG. 34, the content of the claim and the partial translation line corresponding to the content are alternately displayed for each item of the claim. FIG. 35 shows translated words displayed in response to a mouse click operation on display elements of translated words (for example, machine translation results) corresponding to important words in partial translation lines of claim translation information of patent application-related information displayed on the browser. An example of a selection menu for elements of the candidate set is shown. When one element is selected from the selection menu illustrated in FIG. 35, for example, the selected element replaces the translation word for the important word in each partial translation line and is displayed.

The translation unit 2054, for example, in various translation information portions as a document for display, in the case where the machine translation target and the machine translation result are alternately described for each line or each item of the claim, the machine translation At least part (eg, character background color) in the display mode of the display element of the target line and the display mode of the display element of the machine translation result line (eg, partial translation line or complete translation line) is different, Display control information to be attached to each of the display elements may be defined. For example, the claim translation information and the description translation information include the display mode of at least a part of the display element of the machine translation target in the claim translation information and the description translation information, and at least a part of the machine translation result corresponding to the machine translation target Control so that the display mode of the display element is at least partially different (for example, at least one of the character background color, character color, character decoration, font size, font style, and font weight) To do so, display control information is added to each display element.

For example, the translation unit 2054, in response to an operation, translates the line into a display element of a partially translated line in various translation information portions as a document for display by a translation site (for example, a predetermined machine translation program) accessible via a network such as the Internet. It is also possible to add display control information that has a function as a GUI for translation by a server device that executes the above.

[3-1-5-11-3. Generate important phrase list]
The translation unit 2054 extracts each key phrase extracted by the key phrase extraction unit 2051 from the invention document acquired by the invention document acquisition unit 2021, and the translation word candidate set identification unit 20541 An important phrase list generation process is executed to generate an important phrase list configured by associating the identified translation word candidate set (that is, the content represented by the translation word candidate information corresponding to the important phrase). The important phrase list generated by the translation unit 2054 is included in the patent application related information output by the invention document analysis system 20, for example.

The translation unit 2054 generates an important phrase list as a list in which, for example, one important phrase and a set of translation word candidates corresponding to the important phrase are described in each line, with new lines for each important phrase. For example, the translation unit 2054 adds a translation word candidate set to the line describing the key phrase for the key phrase associated with the corresponding translation word in the key phrase setting dictionary acquired by the key phrase setting dictionary acquisition unit 203. You may describe a corresponding translation word instead of . In addition, for example, for an important phrase associated with a corresponding translated word in the important phrase setting dictionary acquired by the important phrase setting dictionary acquisition unit 203, the translation unit 2054 adds the corresponding translation to the line describing the important phrase. A word and a translation word candidate set may be described in an identifiable expression. The translation unit 2054 limits the important phrases to be listed in the important phrase list to those for which the degree of importance determined by the importance determination unit 2055 is higher than a predetermined degree. may be

For example, if the number of elements of the translation word candidate set described in association with the key phrase in each line of the key word list is 0, the translation unit 2054 assigns the translation word candidate set to that line. Do not list. For example, when the number of elements of the translation word candidate set described in correspondence with the key phrase of each line of the key phrase list is two or more, the translation unit 2054 translates each element of the translation word candidate set may be appended with a validity value representing the evaluation value of the degree of validity as a translation of the key phrase, or the elements of the translation word candidate set may be listed in descending order of validity. This validity value is, for example, a plurality of pieces of translation assistance information output in the past by the invention document analysis system 20 (that is, information in which important words and phrases are associated with corresponding translation words selected by the user from the translation word candidate set). can be calculated by predetermined arithmetic processing based on data generated by collecting and integrating (for example, a learning model for machine translation of important phrases by machine learning generated from translation auxiliary information) is. For example, based on data generated by collecting and integrating a plurality of pieces of translation auxiliary information, the translation unit 2054 selects, among the elements of the set of translation word candidates for one key phrase, as a corresponding translation word for that key phrase: An element selected by a relatively large number of users may be associated with a relatively high value of relevance.

For example, the translation unit 2054 predetermines the degree of importance determined by the importance determination unit 2055 for the important phrases described in each line of the important phrase list that is generated for each important phrase. If the level is lower than the specified level, a predetermined notation (for example, the symbol "?") indicating that the usefulness of the important phrase is doubtful may additionally be described in that line. In each line of the key phrase list, the translation unit 2054 determines whether or not the key phrase described in the line is the key phrase described in the claim, and whether or not the key phrase is the key phrase in the specification. A notation may be added to make it identifiable whether or not it is described in the form. This example key phrase list allows, for example, to understand which key phrases are described in the "Detailed Description" of the specification in relation to the key phrases described in the claims, In addition, it may be possible to presume key terms that are not currently stated in the claims but may be stated in the claims in the future due to postscripts, amendments, division of applications, applications claiming priority, and the like. It should be noted that whether or not the key phrase is described in the complaint is determined by the "first appearance claim number" as one attribute of the key phrase specified by the attribute specifying unit 2056 among the attribute information in the key phrase management information held by the analysis unit 205. ”, and whether or not the key phrase is described in the “Mode for Carrying Out the Invention” depends on one attribute of the key phrase, namely, “whole invention document, claim part, specification It can be identified by the content of the item "number of uses in parts and invention embodiment parts".

In each line of the important phrase list, if there is a code corresponding to the important phrase described in that line, the translation unit 2054 adds one or more codes corresponding to the important phrase to that line. For example, when the description of the invention document includes a part in which the key words and phrases are given a code and a part in which the key words and phrases are not given a code, the code A notation indicating that there is no description may be added to the line. It should be noted that the code corresponding to the key phrase, or the mixture of signed and unsigned description of the key phrase in the specification of the invention document is attribute It can be specified by the contents of the item of “sign” as one attribute of the important phrase specified by the specifying unit 2056 .

As a result of determination by the inter-element relation determination unit 2058, when the attribute information in the key phrase management information held by the analysis unit 205 includes the item "lower-level conceptual element of the element represented by the key phrase", the translation unit 2054 By referring to the contents of the item, in each line of the key phrase list, if there is a subordinate concept element corresponding to the key phrase described in that row, one or more It is also possible to add a subordinate concept element of

The translation unit 2054 adds, in each row of the important phrase list, the content of the item as one or more attributes in the attribute information specified by the attribute specifying unit 2056 for the important phrase described in that row. good too. For example, the translation unit 2054 can add the content of the item related to "number" as one attribute of each key phrase in the key phrase list. The translation unit 2054 may add the importance determined by the importance determining unit 2055 to each line of the important phrase list for the important phrase described in that line.

Various types of information added by the translation unit 2054 to each important phrase in the important phrase list can be useful for a translator or the like to select or determine a corresponding translated word corresponding to the important phrase.

The translation unit 2054, for example, arranges each line of the important phrase list in a predetermined order. The translation unit 2054, for example, divides each line of the important phrase list so that the elements represented by the important phrases described in each row belong to categories (for example, methods, products, programs, etc.), and then sorts them in a predetermined order. It is also possible to arrange by . Specific examples of the predetermined order include an example in which the important words and phrases described in each line are arranged in descending order of importance determined by the importance determining unit 2055, and a result of sorting the important words and phrases described in each line in the order of character codes, etc. Examples of arranging according to the order of priority, and examples of arranging in descending order of the number of uses in the invention document or the number of uses in the claims of the invention document of the important terms described in each line, and the arrangement shown in these examples can be used in combination according to a predetermined order of priority. may The translation unit 2054 may generate, for example, a plurality of important word lists in which the lines of the important word list are arranged in different orders as those included in the patent application related information.

The translation unit 2054 uses the information for specifying the key phrase setting dictionary in the setting information acquired by the setting information acquisition unit 201 as the top line of the key phrase list included in the patent application related information by the output unit 208. It is also possible to insert a predetermined heading (for example, "list of important phrases"). As a result, it is possible to include in the invention document the result of the user's editing of the key phrase list of the patent application related information output from the invention document analysis system 20, and to cause the invention document analysis system 20 to analyze the invention document again. can. In this case, in the invention document analysis system 20, the list of important words and phrases edited by the user is treated as an important word setting dictionary. Since the translation words corresponding to the important words are determined based on the word list, the accuracy of the machine translation of the invention document may be improved.

[3-1-5-11-4. Generating Important Phrase List Part in Document for Display]
When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the key word list as a display document (for example, an HTML document), the translation unit 2054 outputs the patent application-related information as the display document. Generate a list of key phrases contained in information.

The important phrase list portion of the patent application-related information as a display document generated by the translation unit 2054 includes, for example, one or more display elements corresponding to the contents of each line in the important phrase list, and in each line , if there is an important phrase extracted by the important phrase extraction unit 2051, it includes a display element corresponding to that important phrase, and if each line contains a translation word candidate set corresponding to that important phrase, it corresponds to the translation word candidate set. If there is a corresponding translated word corresponding to the important phrase in each line, a display element corresponding to the corresponding translated word is included. As a specific example, the translation unit 2054, when describing an important phrase list sandwiched between <article> and </article> tags in an HTML document, translates each line of the important phrase list under the <article> tag. , the display element corresponding to the line is described by sandwiching the content of the line between the <span> tag and the </span> tag, and the display element corresponding to the one line is described under the <span> tag , the important phrase, the candidate translation word set, or the corresponding translation word in the line, the corresponding display element is displayed by the <span> tag and the </span> tag, the important phrase, the translation word candidate set, or the corresponding translation Described by inserting words. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in the important phrase list portion of the document for display enables, for example, the contents of the corresponding line to be displayed.

As the content of the line of the important phrase list of the patent application related information generated by the translation unit 2054, for the important phrase, the importance of the important phrase, the number of descriptions in the "mode for carrying out the invention" of the specification, the code , when adding information such as whether or not there is a mixture of descriptions without symbols and descriptions with symbols, etc., the set of translation word candidates for the key phrase and information on the corresponding translation word should be added to the next line. may be written in Translator 2054 may use multiple lines for a key phrase to represent information about the key phrase.

The translation unit 2054 adds, for example, the important phrase, the candidate translation word set, or the corresponding translation to the display element corresponding to the important phrase, the candidate translation word set, or the corresponding translation word included in the important phrase list in the document for display. Display control information for controlling the display mode of words (for example, highlighting, colored display, display transition, etc.) is added. The display control information added to the display elements corresponding to the important phrases in the important phrase list portion of the document for display is, for example, the display control information added to the display elements for the important phrases of the specification information portion of the document for display. is similar to

Specific examples of the display elements of key phrases included in the key phrase list in the document for display generated by the translation unit 2054 include the following display elements: For example, "<span class="c003" id="keywordlist-c003" onclick='wordProc ("keywordlist-c003")' title="... (display content with additional information)...">Device control unit < /span>”. In this example, the identification code of the key word “equipment control unit” is “c003”, and the value of the id attribute of the <span> tag of the display element is the key word list identification symbol “keywordlist” and the key word list A character string including an identification code "c003" is defined. Also, in this example, when a mouse click operation is performed on a display element, the wordProc function is called with the value of the id attribute as an argument. As a result, in the wordProc function, for example, it is possible to specify the display element from the argument and refer to the character string of the important phrase related to the display element. By extracting the identification code "c003" of the phrase, for example, the display contents of the display elements of all the important phrases "equipment control unit" such as claim information, modified claim information, specification information, and modified specification information, etc. It is possible to realize a process of replacing with a character string or the like input by the user.

For example, the translation unit 2054 selectably displays each element of the candidate translation word set on the display element corresponding to the translation word candidate set including a plurality of elements included in the key phrase list in the display document. Display control information is added to provide a function as a GUI for executing translation word candidate set selection processing corresponding to the selected element. This display control information is, for example, a function of a script that is activated with the elements of the selected translation word candidate set and important phrases related to the translation word candidate set as arguments in response to the user's selection operation on the translation word candidate set. or the function itself, and the function associates, for example, the elements of the argument with key words, and retrieves the key word setting dictionary acquired by the key word setting dictionary acquisition unit 203 (for example, This is a function for executing translation word candidate set selection processing including processing for listing key words and reflecting them in a file or the like in which translation words corresponding to key words can be added. The process of associating the elements of the translation word candidate set with key words and reflecting them in the key word setting dictionary is, for example, when the key word is already included in the key word setting dictionary. It may include processing for allowing the user to select whether or not to overwrite the information related to the important phrase. In addition, the translation word candidate set selection process executed by the function uses pairs of elements and key phrases that are arguments of the function as teacher data for machine learning for generating a learning model for key phrase translation, A process of transmitting to the machine learning unit 207 may be included.

FIG. 36 shows an example of an important phrase list in patent application related information as a display document displayed on the browser. FIG. 37 shows an example in which a translation word candidate set in the important word list of the patent application related information displayed on the browser is changed to the corresponding translation word in response to a mouse click operation for selecting one element. In the example shown in FIG. 37, the element "processor" is selected from among the elements "processor" and "handler" of the translation word candidate set corresponding to the important phrase "processing section" illustrated in FIG. It shows a state in which "processor" has been determined as a corresponding translated word corresponding to the word "processing unit". For example, when the user has set that the <list of important phrases> in the invention document is used as the important phrase setting information in the important phrase setting dictionary identification information in the setting information, as shown in FIG. By copying and pasting the important phrase list to the invention document file, the invention document file can include the important phrase list, and the invention document file can be edited with a text editor or the like. The invention document file containing the word list can be analyzed again by the invention document analysis system 20 .

FIG. 38 shows another example of an important phrase list in patent application related information as a display document displayed on the browser. In the example of FIG. 38, the contents of each line of the key word list include key words, the importance of the key words, and the number of descriptions of the key words in the "Mode for Carrying Out the Invention" of the specification. , if there is a code corresponding to the key phrase, the code, and information indicating whether or not there is a mixture of descriptions without a code and description with a code for the key phrase by the presence or absence of the symbol "●" , and a translation word candidate set for the important phrase. In this example, the degree of importance is represented by a value of 6 levels from 0 to 5 with the character "Level" attached. Each line is arranged in alphabetical order of the important phrases (that is, sorted in ascending order of character codes). The important phrase "control program" in the example of FIG. 38 may be a typographical error of the important phrase "control program." Including a list of important terms in alphabetical order in whole or in part of the .

The translation unit 2054 has, for example, a GUI function for executing non-important phrase conversion processing for important phrases in response to an operation on display elements corresponding to important phrases included in a list of important phrases in a document for display. Display control information may be added. This display control information defines, for example, the function name of the script function or the function itself that is activated with the important phrase as an argument in response to the user's operation on the important phrase. A menu is displayed that allows the user to select non-important phrases for the important phrases in the argument. It is a function for executing non-important phrase conversion processing to delete from the acquired key phrase setting dictionary and add to the non-key phrase setting dictionary. , a process for re-analyzing the invention document acquired by the invention document acquisition unit 2021 may be included.

[3-1-5-11-5. Generation of drawing code list]
The translation unit 2054 extracts, for example, the content of the drawing document acquired by the drawing document acquisition unit 2022 and the attribute information of each key phrase extracted by the key phrase extraction unit 2051 from the invention document acquired by the invention document acquisition unit 2021. A drawing code list generation process for generating a drawing code list is executed based on the items such as "code". The drawing code list generated by the translation unit 2054 is included in the patent application related information output by the invention document analysis system 20, for example.

As drawing code list generation processing, the translation unit 2054 performs drawing code list generation processing for each drawing in the drawing document acquired by the drawing document acquisition unit 2022 from, for example, a searchable PDF file, in the order of the drawing number. A drawing code list is generated that lists each code that is used, key phrases corresponding to each code, and a corresponding translation word or translation word candidate set corresponding to the key phrase. Each code for each drawing in the drawing code list is described in a predetermined order (for example, an order according to sorting results such as natural order). As a specific example, the first line of the drawing code list is "Figure 1: 1 biological information processing system, 10 biological sensor biometric sensor, 20 recording unit storage unit, 30 processing unit processing unit, ... , and the second line is "Fig. 2: S101 sensing step, S102 recording step, storing step, S103 processing step, ...".

For each drawing in the drawing document, the translation unit 2054 stores in the drawing code list the character strings described in the drawing other than the important words and phrases corresponding to the code, and the character strings using a learning model for translation or the like. The result of translation may also be added. As a result, the drawing code list can be useful information for translating drawings (that is, translating explanations in the drawings).

[3-1-5-11-6. Generation of drawing code list part in display document]
When the output unit 208 in the invention document analysis system 20 outputs the patent application related information including the drawing code list as a display document (for example, an HTML document), the translation unit 2054 outputs the patent application related information as the display document. Generate a drawing code list included in the information.

The part of the drawing code list of the patent application related information as a display document generated by the translation unit 2054 includes, for example, one or more display elements corresponding to the contents of each line in the drawing code list, and in each line , if there is a drawing number, it contains a display element corresponding to that drawing number, if there is an important phrase extracted by the important phrase extraction unit 2051 in each line, it contains a display element corresponding to that important phrase, and in each line contains a display element corresponding to the corresponding translation word or translation word candidate set if there is a corresponding translation word or translation word candidate set corresponding to the important phrase, and if there is a code in each line, a display corresponding to the code contains elements. As a specific example, when a drawing code list is described sandwiched between <article> and </article> tags in an HTML document, the translation unit 2054 adds each line of the drawing code list under the <article> tag. , the display element corresponding to the line is described by sandwiching the content of the line between the <span> tag and the </span> tag, and the display element corresponding to the one line <span> tag , the drawing number, important phrase, corresponding translation word, translation word candidate set, or code in that line, the corresponding display element is displayed with the <span> tag and </span> tag. A translation word, a translation word candidate set, or a description with a code in between. For example, a browser may interpret the presentation document to display each presentation element. Each display element corresponding to each line included in the drawing code list portion of the display document allows, for example, the contents of the corresponding line to be displayed. Part of FIG. 30 shows an example of a drawing code list in patent application related information as a display document displayed on the browser.

The translation unit 2054 translates the drawing numbers, key words, corresponding translation words, translation word candidate sets, or display elements corresponding to the codes included in the drawing code list in the document for display into, for example, the drawing numbers, key words, correspondence Display control information for controlling the display mode (for example, highlighted display, colored display, display transition, etc.) of a translation word, a translation word candidate set, or a code is added. For the display control information added to the display elements corresponding to the key phrases or codes in the drawing code list portion of the document for display, for example, This is the same as display control information. For the display control information added to the display element corresponding to the drawing number in the drawing code list part of the display document, for example, the display added to the display element for the description of the drawing number in the specification information part of the display document Similar to control information. The display control information added to the display element corresponding to the corresponding translation word or translation word candidate set of the drawing code list part in the display document is, for example, the corresponding translation word or translation of various translation information parts in the display document It is similar to the display control information added to display elements for word candidate sets.

[3-1-5-11-7. Generating important word-related translation information]
For example, based on the important phrase relation information generated by the inter-element relation determination unit 2058, the translation unit 2054 converts the important phrases in the important phrase relation information into corresponding translation words or a translation word candidate set corresponding to the important phrases. Generate the replaced key phrase related translation information. The translation unit 2054 may, for example, add a corresponding key word to the corresponding translation word or translation word candidate set in the key word related translation information. The key word related translation information generated by the translation unit 2054 is included in the patent application related information output by the invention document analysis system 20, for example.

The important word relation translation information generated by the translation unit 2054 includes inclusion relation translation information obtained by replacing the key words in the inclusion relation information generated by the inter-element relation determination unit 2058 with corresponding translation words or a translation word candidate set. The important phrase relational translation information generated by the translation unit 2054 can include, for example, record relation translation information obtained by replacing the key phrases in the record relation information generated by the inter-element relation determination unit 2058 with corresponding translation words or translation word candidate sets. . The important phrase relation translation information generated by the translation unit 2054 is, for example, the program realization relation translation information obtained by replacing the important phrases in the program realization relation information generated by the inter-element relation determination unit 2058 with corresponding translation words or translation word candidate sets. can contain. The important phrase relationship translation information generated by the translation unit 2054 can include, for example, equivalent relationship translation information obtained by replacing the important phrases in the equivalence relationship information generated by the inter-element relationship determination unit 2058 with corresponding translation words or translation word candidate sets. . The important phrase relationship translation information generated by the translation unit 2054 is, for example, the hierarchical concept relationship translation information in which the important phrases in the hierarchical concept relationship information generated by the inter-element relationship determination unit 2058 are replaced with corresponding translation words or translation word candidate sets. can contain.

When the output unit 208 in the invention document analysis system 20 outputs the patent application-related information including the key word related translation information as a display document (for example, an HTML document), the translation unit 2054 outputs the patent as a display document. Generate key word related translation information included in the application related information. The key word-related translation information portion of the patent application-related information as a document for display generated by the translation unit 2054 includes, for example, display elements corresponding to corresponding translation words or sets of translation word candidates for key words. For example, a browser may interpret the presentation document to display each presentation element. For example, the translation unit 2054 can add display control information for controlling the display mode, etc., to display elements corresponding to corresponding translation words or translation word candidate sets for important phrases.

[3-1-5-12. Generate Aggregate Information]
The analysis unit 205 can generate aggregate information representing values calculated based on the invention documents acquired by the invention document acquisition unit 2021, for example. The aggregated information generated by the analysis unit 205 can be included in the patent application related information output by the output unit 208 .

The analysis unit 205 expresses, for example, the number of claims in the invention document acquired by the invention document acquisition unit 2021, the number of independent claims, the number of characters in each term, and the like, in an identifiable manner, and aggregates them. Include in information.

For example, the analysis unit 205 identifies count results such as the number of lines, the number of sentences, the number of paragraphs, the total number of characters, the average number of characters per sentence, etc. of the specification of the invention document acquired by the invention document acquisition unit 2021. Expressed as possible and included in aggregate information.

Analysis unit 205, for example, the sum of the number of words in all the complete translation lines in the claim translation information or the modified version of the claim translation information, Count results such as the sum of the number of words, the average number of words per sentence of all completely translated lines in the translation information of the specification or the translation information of the revised specification are identifiably expressed and included in the total information.

The analysis unit 205, for example, for each key phrase extracted by the key phrase extraction unit 2051 from the claims in the invention document acquired by the invention document acquisition unit 2021, the specification of the invention document " The results of counting the number of entries of the key phrase in the "Form" column are included in the aggregated information.

For example, the analysis unit 205 analyzes the above-described various information (for example, The number of claims, the average number of characters per sentence in the specification, etc.) are included in the aggregated information.

For example, the analysis unit 205 extracts key phrases from each invention document among a plurality of invention documents acquired by the invention document acquisition unit 2021 based on the specification by the user or the specification in the setting information acquired by the setting information acquisition unit 201. The correlation evaluation value (for example, the calculation result of the correlation coefficient) calculated based on each important word/phrase group extracted by the extraction unit 2051 is included in the total information. For example, in calculating the correlation evaluation value, the analysis unit 205 may calculate the evaluation value by weighting each key phrase in the key phrase group based on the degree of importance determined by the importance determination unit 2055. .

For example, the analysis unit 205 extracts key phrases extracted by the key phrase extraction unit 2051 from the invention documents acquired by the invention document acquisition unit 2021, and for key phrases for which corresponding translated words have been determined by a selection operation or the like, Indicate the corresponding translation word, each corresponding translation word determined by selection operation etc. corresponding to the important word in a plurality of different invention documents belonging to the same classification group as the invention document, and the ratio of the determination, Corresponding translation word/phrase comparison information may be included in total information.

[3-1-5-13. Generate charge information]
For example, the analysis unit 205 can calculate various costs required to file a patent application in Japan for the invention document acquired by the invention document acquisition unit 2021, and generate fee information indicating the calculation result. . The fee information generated by the analysis unit 205 can be included in the patent application related information output by the output unit 208 .

The analysis unit 205 includes, for example, the patent application fee in the fee information. The analysis unit 205, for example, calculates the examination request fee according to the number of claims in the invention document and includes it in the fee information. The analysis unit 205 calculates, for example, according to the number of claims in the claims in the amended claim information representing the amended claims of the invention document, the application examination request fee when the amended claim information is used in the application, It may be added to the charge information. For example, the analysis unit 205 calculates the patent fee for each period according to the number of terms in the claims of the invention document and includes it in the fee information. For example, the analysis unit 205 calculates the patent fee for each period when the modified claim information is used in the application, which is calculated according to the number of terms in the claims in the modified claim information that represents the claims of the invention document by modifying. may be added to the charge information.

For example, the analysis unit 205 analyzes the invention document acquired by the invention document acquisition unit 2021 by using the number of claims based on the invention document, the number of independent claims, and various other aggregated results, etc., to the United States and other regions. It is possible to calculate the various costs required for filing a patent application, express the calculation results in a way that they can be identified from the various costs related to filing a patent application in Japan, and add them to the fee information. .

[3-1-6. Machine Learning Department]
The machine learning unit 207 is a partial modification of the machine learning unit 107 shown in the first embodiment, and is the same as the machine learning unit 107 except for points not specifically shown here.

The machine learning unit 207 uses the analysis results of the analysis unit 205 for each of a plurality of invention documents to generate learning models related to the processing of invention documents by machine learning, and holds and manages the learning models. This machine learning, for example, uses a general machine learning algorithm, and has a certain correlation with the invention document or the sentence of the invention document and the corresponding translation result document or the sentence in the translation result document or realized by arithmetic processing using a set of important phrases and their corresponding translated words as teaching data, or important phrases extracted from invention documents. This is realized by arithmetic processing using pairs of groups and technical fields to which invention documents belong as teacher data.

The learning model generated by the machine learning unit 207 includes, for example, a translation learning model for machine translation of invention documents, and a key phrase translation model for machine translation of key phrases extracted from invention documents by the key phrase extraction unit 2051. It is a learning model, or a learning model for specifying a technical field for specifying the technical field to which an invention document belongs. The learning model generated by the machine learning unit 207 is, for example, a data group that can be used for processing such as calculation, and can be implemented, for example, as a data group in a database.

The machine learning unit 207 uses, for example, various Python (registered trademark) machine learning libraries (eg, a scikit-learn library provided by a third party) for processing such as machine learning learning model generation.

Machine learning unit 207 includes document evaluation unit 2071 , teacher data storage unit 2072 , and learning model management unit 2073 .

[3-1-6-1. Generation of learning model for translation]
Focusing on the learning model for translation generated by the machine learning unit 207, the machine learning unit 207 and related units will be described below.

The document evaluation unit 2071 evaluates the invention document acquired by the invention document acquisition unit 2021 based on invention document evaluation information generated as an analysis result by the analysis unit 205 . For example, if the evaluation value included in the invention document evaluation information generated by the warning information generation unit 2059 for the invention document is represented by a numerical value from 0 to 1, the document evaluation unit 2071 Use for generating a learning model for translation by evaluating whether or not the invention document is appropriate enough to be used for generating a learning model for translation based on whether or not it exceeds a predetermined threshold value (for example, 0.8). Select invention documents that can be Inappropriate invention documents may hinder accurate translation, and as a result, the translation may generate a translation result document with content slightly different from the content of the invention document. May not be suitable for use. Therefore, in the machine learning unit 207, the document evaluation unit 2071 converts the selected invention documents (in other words, invention documents evaluated as appropriate) into part of the teacher data for machine learning for generating the learning model for translation. Use as

The teacher data accumulation unit 2072 is based on the assumption that the document evaluation unit 2071 provides the invention document evaluated as appropriate enough to be used for generating a learning model for translation and, for example, the translation result document corresponding to the invention document. , the combination of the translation result document that is assumed to correspond to the invention document acquired by the translation result document acquisition unit 2023 is used as teacher data for machine learning for generating a learning model for translation, and is stored in a recording medium, etc. stored in and retained. For example, if an invention document evaluated as appropriate and a translation result document generated by a translator based on the invention document are acquired by the invention document acquisition unit 2021 and the translation result document acquisition unit 2023, respectively, the teacher The data accumulation unit 2072 accumulates the combination of the invention document and the translation result document as teacher data. In addition, when the translation destination language is English, for example, the invention document acquisition unit 2021 acquires the international publication of the international application written in Japanese as the invention document, and the document evaluation unit 2071 determines that the invention document is correct. by the office of the designated country, etc., in which the content equivalent to the translation result document translated into English in order to enter the national phase of the designated country that uses English, such as the United States, when it is evaluated as By causing the translation result document acquisition unit 2023 to acquire the published document, the training data accumulation unit 2072 accumulates a combination of the invention document and the translation result document as training data.

In the translation of an inappropriate invention document, there is a possibility that the translator will correct the inappropriate description content of the invention document and translate it, and the translator may There is a possibility that the content of the part cannot be understood and translated incorrectly. Therefore, there is a possibility that an inappropriate invention document and a translation result document generated by translating the invention document have different contents in addition to different languages. On the other hand, there is a relatively high possibility that the invention document evaluated as appropriate by the document evaluation unit 2071 and the translation result document, which is the translation result thereof, have the same content except for the language. , the combination of the invention document and the translation result document is relatively likely to be suitable for training data for machine learning.

By repeatedly using the invention document analysis system 20, a plurality (for example, hundreds, thousands, etc.) of invention documents and translation result documents are acquired, and the teacher data storage unit 2072 stores a plurality of teacher data. It can be stored in a recording medium or the like. Note that the training data accumulation unit 2072 collects and additionally stores training data accumulated in several other invention document analysis systems 20 in a recording medium or the like storing training data. is also possible. Also, a set of an invention document and a translation result document as teacher data for machine learning may be in units of sentences. In other words, the teacher data storage unit 2072 may store, as teacher data for machine learning, a set of each sentence of the invention document and a corresponding sentence of the translation result document. A sentence in the invention document can be separated by, for example, a line feed, a period character ".", etc., and a sentence in the English translation result document can be separated by, for example, a line feed, a period ".", or the like.

The training data accumulation unit 2072 stores, for example, a code corresponding to one of the important phrases extracted by the important phrase extraction unit 2051 in each set of invention document and translation result document as training data. If there is, the code may be removed, and the combination of the invention document and the translation result document after removal may be stored in a recording medium or the like as teacher data for machine learning. As a result, a machine for generating a learning model for translation when omission of description of a code occurs at the translation stage, or when a code is added at the translation stage to an omission of description of a code in an invention document. It may be possible to avoid adversely affecting learning.

The machine learning unit 207 performs machine learning using a plurality of teacher data for machine learning for generating a learning model for translation, which are accumulated in the teacher data accumulation unit 2072. Generate a learning model. The learning model for translation generated by the machine learning unit 207 can be used to predict a sentence as a translation result based on the sentence of the invention document, and can be used for machine translation in the translation unit 2054, for example.

The teacher data storage unit 2072 stores pairs of invention documents and translation result documents stored as teacher data as pairs of claims of the invention documents and translation result documents, and specifications of the invention documents and translation result documents. You may distinguish between a set of In this case, the machine learning unit 207 generates a translation learning model for translating the claims of the invention document by machine learning using training data related to a plurality of claims accumulated in the training data accumulation unit 2072, A translation learning model for translating the specification of an invention document can be generated by machine learning using teacher data relating to a plurality of specifications accumulated in the teacher data accumulation unit 2072 . The machine learning unit 207 may generate a learning model for translation by machine learning using teacher data at any time. The machine learning unit 207, for example, every time there is a change in the teacher data as the content of the recording area of the recording medium storing the teacher data in the teacher data storage unit 2072, the machine learning unit 207 performs translation learning by machine learning using each teacher data. It is also possible to generate a model, or to check the variation of the teacher data as the content of the recording area at a certain period, and when the variation is confirmed, machine learning using each teacher data is used for translation. A learning model may be generated.

The teacher data storage unit 2072 stores a set of the complaint information generated by the complaint information generation unit 205a for the invention document and the complaint of the translation result document instead of the set of the complaint of the invention document and the complaint of the translation result document. , may be stored as training data, or a set of the modified complaint information generated by the complaint information generation unit 205a for the invention document and the complaint of the translation result document may be stored as training data. . The teacher data accumulation unit 2072 selects the complaint information and the modified version complaint information based on the number of each clause of the complaint and the predetermined commonality determination criteria such as the citation relationship of each clause, and compares the complaint with the complaint of the translation result document. It is also possible to select the one with the highest commonality, and accumulate a set of the selected one and the complaint of the translation result document as training data. In addition, the teacher data storage unit 2072 performs machine translation on the complaint information and the corrected version complaint information using a translation learning model that has already been generated, and the difference between the result of the machine translation and the complaint in the translation result document is small. A set of one of the complaint information and the modified version complaint information, which is the basis of the machine translation of the first machine translation, and the complaint of the translation result document may be stored as teacher data.

The teaching data storage unit 2072 stores the specification information generated by the specification information generation unit 205b for the invention document, instead of the set of the specification of the invention document and the specification of the translation result document to be stored as training data, A combination of the translation result document and the specification may be stored as training data, or the modified specification information generated by the specification information generation unit 205b for the invention document and the translation result document specification may be stored. may be stored as teacher data. The teacher data accumulation unit 2072 selects the translation result document from the specification information and the revised specification information based on predetermined commonality determination criteria such as the total number of lines and paragraph numbers in the specification. It is also possible to select the one with the highest degree of commonality, and accumulate a set of the selected one and the specification of the translation result document as teacher data. In addition, the training data accumulation unit 2072 performs machine translation using the translation learning model that has already been generated on the specification information and the corrected version specification information, and the result of the machine translation and the specification of the translation result document. A set of one of the specification information and the corrected version specification information, which is the basis of the machine translation with the smaller difference, and the specification of the translation result document may be stored as teacher data.

The learning model management unit 2073 stores and manages the learning model for translation generated by the machine learning unit 207 in a recording medium or the like. When the machine learning unit 207 generates a translation learning model for claim translation and a translation learning model for translation of the specification separately, the learning model management unit 2073 records them separately. Store and manage on media, etc. Each time the machine learning unit 207 generates a translation learning model, the learning model management unit 2073 may overwrite and update the already held translation learning model with the generated translation learning model. , A plurality of generated translation learning models (for example, a predetermined number of translation learning models in order of newest), including the latest translation learning model, may be held in association with each generation date and time. . The learning model management unit 2073 may manage, for example, a translation learning model by registering it in a database. The learning model for translation held by the learning model management unit 2073 can be output by the output unit 208 .

[3-1-6-2. Generation of learning model for key phrase translation]
The machine learning unit 207 and related units will be described below, focusing on the important phrase translation learning model generated by the machine learning unit 207 .

The training data storage unit 2072 stores key words and phrases to which corresponding translated words are added and their corresponding translations in the key word setting dictionary acquired by the key word setting dictionary acquisition unit 203 (for example, a part of an invention document, other files, etc.). Pairs with words are accumulated and held in a recording medium or the like as teacher data for machine learning for generating a learning model for important phrase translation. The teacher data accumulation unit 2072 acquires the translation assistance information based on the identification information of the translation assistance information in the setting information acquired by the setting information acquisition unit 201, for example. may be accumulated and held in a recording medium or the like as teacher data for machine learning for generating a learning model for important phrase translation.

By the way, in the invention document analysis system 20, the translation word candidate set identified by the translation word candidate set identification section 20541 for the key phrase extracted by the key phrase extraction section 2051 from the invention document acquired by the invention document acquisition section 2021. is generated as a display element, and the display element is displayed by a browser or the like. Display control information for executing a GUI function for selecting an element of a translation word candidate set is added to the display elements by the translation unit 2054, and the user can select a translation word candidate set for an important phrase. A selection operation can be made of one element from . In response to this, the teacher data storage unit 2072 generates a document for display based on the invention document selected by the document evaluation unit 2071 (that is, the invention document evaluated as appropriate) and stores it in the translation word candidate set. As a result of displaying such GUI elements, a set of an important phrase and one element selected and operated from the translation word candidate set for the important phrase is used for machine learning for generating a learning model for translation of the important phrase. can be stored and held in a recording medium or the like as teaching data. Note that the training data accumulation unit 2072, for example, generates a display document based on the invention document without relying on the evaluation by the document evaluation unit 2071, and displays key phrases as a result of displaying the GUI elements related to the translation word candidate set. and one element selected from the translation word candidate set for that key word is stored in a recording medium or the like as teacher data for machine learning for generating a learning model for key word translation. , may be held. Since it is assumed that an invention document evaluated as appropriate by the document evaluation unit 2071 is likely to be properly understood, the important words in the invention document evaluated as appropriate are selected from the translation word candidate set. The selection related to the operation may be a selection with relatively high validity, and using the selection result as teacher data can be useful for generating a learning model for important phrase translation more appropriately.

Further, the teacher data storage unit 2072 translates each key phrase extracted by the key phrase extraction unit 2051 from the invention document evaluated as appropriate by the document evaluation unit 2071 based on the key phrase and the invention document. A machine learning teacher for generating a learning model for translation of important words and phrases is a set of translation words and phrases corresponding to the important words and phrases extracted from the translation result document generated by the person and acquired by the translation result document acquisition unit 2023. As data, it can be stored and held in a recording medium or the like. The teacher data storage unit 2072 extracts translation words in the translation result document corresponding to important words in the invention document, based on, for example, existing parsing techniques. As a specific example of a case where the language of the translated phrase is English, in a certain line of the invention document, a sentence in which two important phrases are represented by A and B, respectively, is "A does B." , it can be assumed that this sentence will be translated into SVO (that is, subject, verb, object) sentence pattern, and the sentence in the corresponding position line in the translation result document, in which the translation words are represented by S, V, and O, is "SVO .”, it is assumed that the key word A corresponds to the translated word S and the key word B corresponds to the translated word O. Based on such an estimation result, the teacher data storage unit 2072 can extract translation words in the translation result document that correspond to important words. In addition, the training data storage unit 2072 extracts translation words in the translation result document corresponding to the important words followed by the code in the invention document. It may also be done by searching for the phrase followed by .

By repeating the use of the invention document analysis system 20, the teacher data storage unit 2072 accumulates a plurality (for example, thousands, tens of thousands, etc.) of sets of important words and corresponding translated words as teacher data in a recording medium or the like. obtain. Note that the training data accumulation unit 2072 collects and additionally stores training data accumulated in several other invention document analysis systems 20 in a recording medium or the like storing training data. is also possible.

The training data storage unit 2072, for example, stores training data for machine learning for generating a learning model for translation of key phrases, including key phrases extracted from the invention document by the key phrase extraction unit 2051. The group classified by the classification unit 2053 or the technical field identified by the technical field identification unit 20531 may be associated with each other and stored in the recording medium. Thereby, the teacher data storage unit 2072 can store each teacher data for machine learning for generating a learning model for key phrase translation in a recording medium, for example, for each group or technical field.

The machine learning unit 207 performs machine learning using a plurality of teacher data for machine learning for generating a learning model for important phrase translation, accumulated in the teacher data storage unit 2072, for machine translation of important phrases. Generate a learning model for key phrase translation. When the training data storage unit 2072 stores a plurality of training data for machine learning for generating a learning model for translation of important phrases in a recording medium or the like for each group or technical field, the machine learning unit 207 , for each group or technical field, by machine learning using a plurality of teacher data for machine learning for generating a learning model for important phrase translation for each group or technical field, accumulated in the teacher data accumulation unit 2072, Generate a learning model for key phrase translation for machine translation of key phrases.

The key phrase translation learning model generated by the machine learning unit 207 can be used to predict the translation result phrase corresponding to the key phrase of the invention document based on the key phrase. , to determine corresponding translations by machine translation of key words. The machine learning unit 207 may generate a learning model for important phrase translation by machine learning using teacher data at any time. The machine learning unit 207 detects, for example, when there is a change in the teacher data for machine learning for generating a learning model for translation of important phrases, which is the contents of the recording area of the recording medium storing the teacher data in the teacher data storage unit 2072. Each time, by machine learning using each teacher data, it is possible to generate a learning model for important phrase translation, or at a fixed cycle, to generate a learning model for important phrase translation as the contents of the recording area. It is also possible to check the variation of the training data for machine learning and, if the variation is confirmed, generate a learning model for important phrase translation by machine learning using each training data. In addition, the machine learning unit 207 prepares a learning model for translation of key phrases (for example, a plurality of sets of key phrases of various key phrases and the result of machine translation based on the learning model for translation of key phrases) for translation learning. A learning model for translation may be generated by using it as teacher data for machine learning for model generation. Note that the machine learning unit 207 may generate a learning model for translation that includes the learning model for translation of important phrases.

The learning model management unit 2073 stores and manages the key phrase translation learning model generated by the machine learning unit 207 in a recording medium or the like. When the machine learning unit 207 generates learning models for translating key phrases by classifying them by group or technical field, the learning model management unit 2073 separates the learning models for translating key words by group or technical field. Store and manage in a recording medium, etc. Every time the machine learning unit 207 generates a learning model for translating important phrases, the learning model management unit 2073 overwrites and updates the already held learning model for translating important phrases with the generated learning model for translating important phrases. Alternatively, a plurality of generated learning models for translating important phrases, including the latest learning model for translating important phrases (for example, a predetermined number of important phrases in order of newest learning model for translation). The learning model management unit 2073 may, for example, register and manage important phrase translation learning models in a database. The important phrase translation learning model held by the learning model management unit 2073 can be output by the output unit 208 .

[3-1-6-3. Generation of learning model for technical field identification]
The machine learning unit 207 and related units will be described below with a focus on the technical field identification learning model generated by the machine learning unit 207 .

The possibility that the same key words are commonly stated in multiple invention documents that describe inventions in the same technical field does not mean that the same key words are commonly stated in multiple invention documents that describe inventions in different technical fields. Higher than the likelihood that the phrase will be listed. The machine learning unit 207 performs machine learning based on the correlation between the technical field and the important phrase group in the invention document. It is possible to identify the technical field to which the invention document belongs, based on the group of important words extracted from the invention document, by predetermined arithmetic processing using the technical field identification learning model. This specified technical field may be expressed by IPC or by F-term according to the F-term classification system, and classification up to any hierarchy of IPC (for example, classification of only sections and classes, etc.) may be expressed using

When the invention document acquired by the invention document acquisition unit 2021 contains technical field information such as IPC and F-term, the training data accumulation unit 2072 extracts each key phrase extracted from the invention document by the key phrase extraction unit 2051. A set of a set of important words and phrases and technical field information such as IPCs and F-terms described in the invention document is used as training data for machine learning for generating a learning model for identifying a technical field, as a recording medium. etc., and hold it. As an example of the case where the invention document includes technical field information such as IPC, if the invention document includes an application form (for example, the contents of the application form of a Japanese patent application including the "International Patent Classification" column), the invention document If it is a patent publication, or the publication number (for example, the publication number related to the publication of the patent application) is described in the "patent document" column of the prior art document in the specification of the invention document, and it is based on that publication number , and cases where the IPC or the like can be obtained as a result of searching for patent publications via the Internet or the like.

Important words and phrases extracted from invention documents in the teacher data for machine learning for generating a learning model for technical field identification accumulated in the teacher data accumulation unit 2072 are added to each important word by the importance determination unit 2055 It may be a data group to which the determined importance is added. A specific example of a group of key phrases extracted from an invention document is that each of a predetermined number (for example, several thousands, tens of thousands, etc.) of predetermined character strings are elements, and the character strings of the elements are, for example, invention documents. Predetermined number of element values with an order, with an element value representing importance expressed by a value greater than 0 and less than or equal to 1 when it exists as an important phrase in a document, and an element value of 0 when it does not exist as an important phrase is vector data containing

The machine learning unit 207 identifies a technical field from a group of important words and phrases by machine learning using a plurality of teacher data for machine learning for generating a learning model for identifying a technical field, which is accumulated in the teacher data accumulation unit 2072. Generate a learning model for important phrase translation for

When the important phrase group in the training data for machine learning for generating the learning model for technical field identification accumulated in the training data accumulation unit 2072 is data in which the importance is added to each important phrase, the machine The learning unit 207, for example, based on a plurality of teacher data for machine learning for generating a learning model for specifying a technical field, accumulated in the teacher data accumulation unit 2072, for each important phrase, with the corresponding importance A learning model for important phrase translation is generated by performing machine learning using each of the weighted data and multiple sets of technical fields as training data.

The technical field identification learning model generated by the machine learning unit 207 can be used to predict the technical field from the group of key words extracted from the invention document. It can be used, for example, to identify a technical field from a group of key phrases related to. The machine learning unit 207 may generate the technical field identifying learning model by machine learning using the teacher data at any time. The machine learning unit 207 detects, for example, when there is a change in the teacher data for machine learning for generating the learning model for specifying the technical field, which is the content of the recording area of the recording medium storing the teacher data in the teacher data storage unit 2072. Each time, a learning model for specifying a technical field may be generated by machine learning using each teacher data, or for the purpose of generating a learning model for specifying a technical field as the contents of the recording area at a fixed cycle. It is also possible to check the variation of the teacher data for machine learning and, if the variation is confirmed, generate the learning model for technical field identification by machine learning using each teacher data.

The learning model management unit 2073 stores and manages the technical field identification learning model generated by the machine learning unit 207 in a recording medium or the like. The learning model management unit 2073 overwrites and updates the already held learning model for specifying the technical field with the generated learning model for specifying the technical field each time the learning model for specifying the technical field is generated by the machine learning unit 207. Alternatively, a plurality of generated learning models for identifying technical fields, including the latest learning model for identifying technical fields, in association with each generation date and time (for example, a predetermined number of technical fields in order of newest identification learning model). The learning model management unit 2073 may manage, for example, the learning model for specifying the technical field by registering it in a database. The learning model for technical field identification held by the learning model management unit 2073 can be output by the output unit 208 .

[3-1-7. Output part]
The output unit 208 is a partial modification of the output unit 108 shown in the first embodiment, and is the same as the output unit 108 except for points not particularly shown here.

The output unit 208 outputs information generated based on the analysis result of the analysis unit 205 for the invention document acquired by the invention document acquisition unit 2021 . The output unit 208 outputs, for example, information generated based on each of the multiple key phrases extracted by the key phrase extraction unit 2051 from the invention document acquired by the invention document acquisition unit 2021 . The output unit 208 uses a plug-in module that executes processing for outputting the result of performing predetermined arithmetic processing on the various analysis results (various information on important terms, symbols, etc.) generated by the analysis unit 205. and output. The output unit 208 outputs, for example, an API that makes various analysis results generated by the analysis unit 205 available to the plug-in module, and information generated by the plug-in module. It is also possible to provide an API or the like for adding to part of the patent application-related information to be submitted.

The output unit 208 includes a learning model output unit 2081, a patent application related information output unit 2082, a display document generation unit 2083, and a display unit 2084 having a function as a browser for displaying display documents.

[3-1-7-1. Learning model output unit]
The learning model output unit 2081 outputs various learning models held and managed by the learning model management unit 2073 .

For example, the learning model output unit 2081 outputs a learning model for translation, a learning model for key phrase translation, or a learning model for technical field identification to the outside of the invention document analysis system 20 in response to an instruction from a user who has specified a destination. can be output by sending it to the specified destination. For example, the learning model output unit 2081 outputs a learning model for translation, a learning model for translation of important phrases, or a learning model for specifying a technical field in response to an instruction from a user who has specified a learning model output file, and outputs the specified learning model. It can be output as the contents of the output file.

The learning model for translation output by the learning model output unit 2081 or the learning model for important phrase translation is, for example, another invention document analysis system 20, or a machine translation system for translation of invention documents or machine translation It can be used in a program, a general machine translation system, or the like. The learning model for technical field identification output by the learning model output unit 2081 can be used, for example, in another invention document analysis system 20 or a system for identifying the technical field from invention documents.

The learning model output unit 2081 may, for example, output teacher data for machine learning, which is accumulated in the teacher data accumulation unit 2072 and serves as a basis for generating various learning models. The teacher data output by the learning model output unit 2081 of the invention document analysis system 20 may be used for storage in the teacher data storage unit 2072 of another invention document analysis system 20, or may be used for machine learning in other systems. may be used for the execution of

[3-1-7-2. Patent application related information output unit]
The patent application related information output unit 2082 outputs patent application related information (see FIG. 15) generated based on the analysis result of the analysis unit 205 for the invention document acquired by the invention document acquisition unit 2021 .

For example, the patent application related information output unit 2082 includes information obtained by adding a line number to each line of the invention document acquired by the invention document acquisition unit 2021 and analyzed by the analysis unit 205 in the patent application related information. The line number in the information in which the line number is added to each line of the invention document is the same as the indication of the warning information and the invention document when the indication information in the warning information includes the line number of the description part of the invention document that was the subject of indication. It is useful for making it possible to grasp the correspondence with the description part. The patent application related information output unit 2082, for example, when the information obtained by adding the line number to each line of the invention document includes a predetermined control code (for example, a code within the range of "0x00" to "0x1f") Alternatively, the predetermined control code may be converted into a predetermined character such as "●".

The patent application related information output unit 2082 includes, for example, warning information including invention document evaluation information in the patent application related information.

For example, the patent application related information output unit 2082 causes the patent application related information to include an important phrase list, important phrase related information, and important phrase related translation information. The patent application related information output unit 2082 can include, for example, inclusion relationship information, recording relationship information, program implementation relationship information, equivalence relationship information, and hierarchical concept relationship information in the important term relationship information. The patent application related information output unit 2082 can include, for example, inclusive relationship translation information, recording relationship translation information, program realization relationship translation information, equivalent relationship translation information, and hierarchical concept relationship translation information in the key phrase relationship translation information. .

For example, the patent application related information output unit 2082 includes, as the patent application related information, claim information, claim translation information, modified claim information, modified claim translation information, claim base drawing information, claim base specification information, and claim base Abstract information may be included.

The patent application related information output unit 2082 can include, for example, a claim tree, a modified claim tree, a configuration claim tree, and a modified configuration claim tree in the patent application related information.

The patent application related information output unit 2082 can include, for example, specification information, specification translation information, revised specification information, revised specification translation information, and a specification heading list in the patent application related information.

The patent application related information output unit 2082 can include, for example, a code list, a drawing code list, technical field information, fee information, and total information in the patent application related information.

The patent application related information output unit 2082 outputs the patent application related information, for example, as the content of the output file. The output file can be recorded on a recording medium or the like. The output file may be, for example, a file in a format mainly used for various application programs having a document creation and editing function such as Microsoft (registered trademark) Word, a text file, or an XML file. It may be a PDF file. Also, the output file may be a display document (for example, an HTML document) composed of one or more files. In addition, the patent application related information output unit 2082 may output the patent application related information as a plurality of output files in different formats (for example, text file and HTML document). Documents for display may include documents written in a markup language. The display document may be an HTML document whose contents are interpreted by a browser or the like and displayed, or an XML document whose contents are interpreted and displayed by a display application program (for example, one XML file or an XML document). A file and a set of one or more files referenced from the XML file), or an XML document that can be converted into an HTML document by an existing conversion application program.

The patent application related information output unit 2082, for example, refers to the information for specifying the storage location of the output file in the setting information acquired by the setting information acquisition unit 201, and specifies a predetermined folder in the file system. An output file containing patent application related information may be stored in a predetermined folder.

When the patent application-related information is generated as a display document (for example, an HTML document), the patent application-related information output unit 2082 outputs each part ( For example, important phrase list part, claim information part, specification information part, etc.) is transmitted to the display document generation unit 2083, and the output of the patent application related information as the display document is sent to the display document generation unit 2083. entrust The patent application related information as a display document generated by the display document generation unit 2083 can be output by being displayed by the display unit 2084 having a function as a browser.

The patent application-related information as a display document generated by the display document generation unit 2083 is recorded in a recording medium or the like as a file group (for example, an HTML file, a CSS file, a script file, etc.) as an HTML document, for example. can be output with The output HTML document may be interpreted and displayed by the display unit 2084 of the invention document analysis system 20 or may be interpreted and displayed by a browser external to the invention document analysis system 20 .

In the case where the invention document analysis system 20 has the configuration shown in FIG. It is interpreted and displayed by an application program for realizing a browser function under the OS of the terminal device. In this case, the local file, which is the HTML file of the HTML document output by the display document generation unit 2083, may be read by an application program for realizing the browser function, and the HTML document may be interpreted and displayed. The display document generation unit 2083 provides the HTML document at a predetermined port of the local host used as a web server, and the application program for realizing the browser function is transmitted to that port of the local host. An HTML document may be acquired, interpreted, and displayed by accessing via HTTP (Hypertext Transfer Protocol) communication.

In the case where the invention document analysis system 20 has a configuration as shown in FIG. acquired, interpreted, and displayed by a browser in a terminal device capable of communicating with the

The output of the patent application-related information by the patent application-related information output unit 2082 is not limited to the output as an output file. Writing patent application-related information, writing patent application-related information to a recording medium external to the invention document analysis system 20, transmitting a signal indicating patent application-related information, displaying patent application-related information on a display device, patent application-related It may be printing information, outputting voice representing patent application related information using voice synthesis technology, causing other physical phenomena representing patent application related information, and the like. For example, when all or part of the invention document analysis processing program that realizes the functions of the invention document analysis system 20 is executed on a Microsoft (registered trademark) Windows (registered trademark) command prompt, patent application related information may be output, for example, by display in a command prompt window.

An HTML document, which is an example of a display document generated by the display document generation unit 2083, includes an HTML file. It may also contain a script file corresponding to the specifications in the file. When the display document generation unit 2083 generates an HTML document as an example of a display document related to patent application related information, the display document generation unit 2083 generates a display document according to each invention document to be analyzed by the invention document analysis system 20. Although the contents of the HTML files that make up the HTML document generated by the unit 2083 can change, for example, the contents of the CSS file and script file that make up the HTML document are unchanged regardless of differences between invention documents. obtain.

The display document generation unit 2083 controls, for example, an HTML file containing each part of the patent application related information (see FIG. 15) as a display document generated by the analysis unit 205, and a display mode of display elements in the HTML file. and a script file including functions written in JavaScript (registered trademark). The display document generation unit 2083, for example, under the <body> tag, a plurality of parts of the patent application related information (for example, invention document, warning information, important phrase list, claim information, specification information, etc.) are included as descriptions sandwiched between <article> and </article> tags. Write the menu in between. This menu includes, for example, menu items representing titles, names, etc. of contents under each <article> tag (for example, "invention document", "warning information", "important phrase list", "claim information", "description information", etc.), and among the contents under each <article> tag, the contents under the <article> tag corresponding to the menu item selected by the user can be displayed. Display control information defining a function for switching the content under each <article> tag between a non-display state and a display state is added to display elements of menu items. On the display screen illustrated in FIG. 17, a menu described between <nav> and </nav> tags is displayed in the menu column, and the content under the <article> tag selected according to the menu is It is displayed in the content display column of the item of the patent application related information corresponding to the menu selection. The menu may include a menu item that links to a setting information display document (for example, an HTML file as a setting information display document) that displays and edits the setting information acquired by the setting information acquisition unit 201. .

For example, the display document generation unit 2083 sets the default value of the display attribute of the content under the <article> tag corresponding to each of the plurality of parts of the patent application related information in the HTML document, for example, with a CSS file, etc., with a white background color. The background color, character color, etc. may be defined such that the character color is black, and the like. It is also possible to define functions that change the background color, text color, etc., such as changing the background color from white to black and the text color from black to white according to the mouse click operation on the element, etc. . Thus, in a document for display, using a bright character color (for example, white) against a dark background color (for example, black) or using a dark character color for a bright background color improves the visibility of the display content. can let In addition, the user can switch between a combination of a dark background color and a bright character color and a combination of a bright background color and a dark character color according to the brightness of the environment around the display device in the invention document analysis system 20. can be useful for improving the visibility of displayed content.

In the display unit 2084 or other browsers that interpret and display HTML documents, for example, important phrases under the <article> tag are selected from the background color, character color, etc. as default values of the contents under the <article> tag. Background colors, character colors, and the like defined for individual display elements, such as , can be preferentially applied.

The display document generation unit 2083 may generate a display document so as to display the contents under a plurality of <article> tags side by side. The content under each <article> tag in the display document is displayed or hidden by processing the function described in the script file when the display document is interpreted and displayed by the browser. In addition to being able to specify transparency, display size, display position, etc., it is possible to display. When the display document is interpreted and displayed by the browser, the display document generation unit 2083 generates an Internet The script file describes the process of searching for web pages containing the important words on a search site on the network such as, or the process of translating the important words on a translation site on the network such as the Internet In the case of using a function or the like, the screen related to the search site, the translation site, etc. is displayed in a different display area (for example, in the display screen shown in FIG. 17) from the screen for displaying the display document. (“Item Display Field for Operation Corresponding GUI Elements”), a separate window, or a separate tab.

For example, the display document generation unit 2083 adds display control information to the display document related to the patent application related information to make the display element a GUI element for re-analyzing the invention document according to the operation. element may be included. As a result, when the setting information acquired by the setting information acquiring unit 201 and the key phrase setting dictionary acquired by the key phrase setting dictionary acquiring unit 203 are updated, the invention document can be analyzed again. can be easier.

In this embodiment, as an example, each part of the patent application-related information (for example, claim information, specification information, claim tree, important phrase list, etc.) as an HTML document conforming to HTML5 is placed under a separate <article> tag. , but the tags used to describe each part of the patent application-related information are not limited to the <article> tag, and other tags (e.g., <section> tags, etc.). Further, the HTML document related to the patent application related information generated by the display document generation unit 2083 does not necessarily have to conform to HTML5.

The display document generation unit 2083 converts the codes that cannot be used in the HTML file in each part of the patent application related information as the display document generated by the analysis unit 205, and converts the code into an HTML file. Generate. For example, if the display document generation unit 2083 is implemented by a computer that executes a program written in the Python (registered trademark) language, this code conversion can be performed by a function of the Python (registered trademark) standard library. xml. sax. saxutils. It can be implemented using escape. In some existing browser applications, when patent application-related information is displayed as a display document, in order to properly execute multi-line copy and paste of the display content, the display document For example, when each part of the patent application-related information as a document for display generated by the analysis unit 205 contains a half-width blank character, the generation unit 2083 replaces the half-width blank character with a predetermined code “&nbsp;”. For example, when the <br> tag is not added to the end of each part of the patent application related information as a display document generated in the analysis unit 205, the <br> tag may be added.

As a specific example of outputting the generated display document by the display document generation unit 2083, for example, the display document generation unit 2083 includes information indicating the analysis date and time of the invention document in a predetermined folder. A subfolder with a defined subfolder name is created, and an HTML file containing patent application related information is stored in the subfolder as the main part of the HTML document as the document for display. This predetermined folder may be, for example, the folder indicated by the information for specifying the storage destination of the output file in the setting information acquired by the setting information acquisition unit 201, or the folder specified by the user of the invention document analysis system 20. It may be a folder, or a folder or the like in which an invention document analysis processing program is installed in a terminal device or the like having a microprocessor that constitutes the invention document analysis system 20 . For example, when the invention document is obtained from a file by the invention document obtaining unit 2021, the subfolder name containing the information indicating the analysis date and time of the invention document includes the file name of the file, Alternatively, when the invention document is acquired from the clipboard by the invention document acquisition unit 2021, a phrase indicating the clipboard may be included. The display document generation unit 2083 further determines one subfolder in the predetermined folder as the storage destination of the common resource, and displays the display added to the display element related to the patent application related information as a part of the HTML document. A CSS file for controlling the display mode and a script file, which are resources that function in response to the control information, are stored in the subfolder of the common resource storage destination only if they are not yet stored. According to this example, in the invention document analysis system 20, each subfolder in a predetermined folder is sorted by subfolder name, and, for example, a subfolder storing an HTML file containing patent application related information based on the analysis result of the invention document is stored. It is possible to arrange and display the folder names in order from the newest. For example, the HTML files in each subfolder may include patent application-related information as an analysis result of the invention document with different content, but each HTML file is stored in one subfolder where the common resource is stored. A CSS file and a script file are combined to form an HTML document. Note that the display unit 2084 displays a list listing each subfolder in the above-mentioned predetermined folder, and in response to a selection operation for one subfolder, includes the HTML files in the subfolder related to the selection operation. It is also possible to display a GUI screen in which the configured HTML document is the target of interpretation and display by the browser, and in the GUI screen, any subfolder can be displayed according to the user's operation. It is also possible to display an operation corresponding GUI element for performing a process of deleting including . The display of this GUI screen may be realized by an HTML document such as an HTML file, or a hyperlink may be provided to transition the display contents to the corresponding HTML file in accordance with the selection operation for one subfolder. The operations of the display document generation unit 2083, the display unit 2084, etc. are realized by installing and executing the above invention document analysis processing program in a terminal device equipped with a microprocessor. It is good also as comprising a part of analysis processing.

FIG. 39 is a diagram showing an example of a display screen as a GUI screen displayed by the display unit 2084. As shown in FIG. The display screen illustrated in FIG. 39 displays GUI elements for acquiring the invention document to be analyzed by selecting the invention document file or from the clipboard. The selection of the invention document file can be realized, for example, by designating file with the type attribute in the HTML <input> tag. On the display screen illustrated in FIG. 39, as an analyzed invention document list, a subfolder name (for example, the analysis date and time of the invention document and the file name or character column "clipboard") and, to the left of each subfolder name, displays a push button to invoke a function for deleting that subfolder. For example, when a mouse click operation is performed on a subfolder name displayed on this display screen, a display transition related to a link occurs, and an HTML file containing patent application-related information as an HTML document stored in the subfolder is displayed. The display contents based on the file (see FIG. 17) are displayed. When display elements of important words in claim information, specification information, etc. in patent application-related information as HTML documents stored in one subfolder within a predetermined folder are GUI elements for operation, displayed by a browser, etc. The important phrase inclusion description enumeration process described above, which can be executed in response to an operation on the operation-responsive GUI element, can be performed, for example, in each subfolder other than the one subfolder in the predetermined folder. From the claim information and specification information in the patent application related information as , collect the contents of each line in which the key words are described by searching for the key words, list each line that is the collection result, and list each line It may be a process of emphasizing and displaying an important phrase in the text. As a result, the user can obtain claim information and specifications in one or more pieces of patent application-related information that have already been generated based on invention documents that have been analyzed by the invention document analysis system 20 in the past, for important terms in the patent application-related information. It becomes possible to refer to each line describing the important phrase included in the document information. The subfolder deletion function is written in, for example, JavaScript (registered trademark), and calls a subfolder deletion processing function written in, for example, Python (registered trademark) operating on the local host.

As another specific example, the display document generation unit 2083 includes information indicating the analysis date and time of the invention document in the predetermined folder indicated by the information for specifying the storage destination of the output file in the setting information. A subfolder with a given subfolder name is created, and an HTML file, a CSS file, and a script file, which constitute an HTML document as a display document related to patent application related information, are stored in the subfolder. According to this example, the content of the subfolder is recorded on a portable recording medium and transferred, or the content of the subfolder is compressed, for example, and sent, so that the transfer destination or transmission Various terminals (for example, desktop PCs, notebook PCs, smartphones, etc.) having the aforementioned browser function can view and utilize patent application-related information as documents for display.

If the inventor or patent attorney determines that the patent application-related information output from the invention document analysis system 20 based on the analysis result of the invention document is not appropriate, the invention acquired by the invention document acquisition unit 2021 By correcting the document, the setting information acquired by the setting information acquisition unit 201, the key phrase setting dictionary acquired by the key phrase setting dictionary acquisition unit 203, and the like, and causing the invention document analysis system 20 to re-analyze the invention document, the patent Application-related information can be updated to have more appropriate content. A translator who has been provided with patent application-related information, for example, as a display document updated to have appropriate content from an inventor or patent attorney, may, based on the appropriate patent application-related information, etc. It may be possible to perform the translation work properly or efficiently. In addition, a translator who can use the invention document analysis system 20 can use the invention document analysis system 20 to The patent application related information can be obtained, and based on the patent application related information and the like, translation work can be performed properly or efficiently.

When the display document generation unit 2083 generates, as a display document, patent application-related information including information in which line numbers are added to each line of the invention document, for example, each display element corresponding to each line of the invention document is Display control information that determines whether the line is displayed in a different manner (for example, the character color of the character string of the line) depending on whether or not the line is the line pointed out by the warning information. It may be added. Alternatively, when the display document generating unit 2083 generates, as a display document, patent application related information including information in which line numbers are added to each line of the invention document, for example, the line number in each line of the invention document is one display element, and the line number of the line pointed out by the warning information and the line number of the line not pointed out by the warning information are displayed in the display element corresponding to each line number. It is also possible to add display control information that is determined to display with different modes (for example, character colors of line numbers). In addition, when the display document generation unit 2083 generates, as a display document, patent application related information including information in which line numbers are added to each line of the invention document, for example, each line of the invention document is indicated by warning information. When the inappropriate description that is the target of the above is included, one display element is associated with the inappropriate description in each line, and the character string of the inappropriate description is displayed differently from the other character strings. It is also possible to add display control information that is determined to be displayed by changing the character string to be displayed (for example, character strings with inappropriate descriptions are highlighted in red).

The display unit 2084 displays the patent application related information as a display document generated by the display document generation unit 2083 . The display unit 2084 is, for example, a browser that interprets an HTML document based on HTML5 and displays display elements defined by the HTML file according to a CSS file or the like. When the display document generation unit 2083 generates the display document related to the patent application related information as an HTML document not conforming to HTML5 (that is, an HTML document conforming to other standards other than HTML5), The display unit 2084 has a function as a browser conforming to a standard that can interpret and display the HTML document generated by the display document generation unit 2083 . In addition, all or part of the display contents displayed by the browser in the patent application related information as the display document can be selected by the user's operation and can be copied and pasted or cut and pasted. By pasting, it is possible to include the content of a document or the like used by a certain application program running on the terminal device that constitutes the invention document analysis system 20 . In addition, when the content displayed by the browser changes as a result of the execution of the processing executed in response to the user operation on the GUI element related to the patent application related information, all or part of the display content after the change may also be changed by the user. Depending on the operation, it can be selected and can be the target of copy and paste.

The display unit 2084 has a function as a browser that interprets and displays a document for display, and also has a function for displaying patent application-related information output as a file (for example, a text file) other than a document for display. Furthermore, it has a function of editing and outputting the displayed patent application-related information according to the user's operation, like a conventional application program (for example, a text editor) having a document creation and editing function. You may have When executing a function of editing and outputting patent application-related information in accordance with a user's operation, the display unit 2084 displays a plurality of key phrases included in the important word list in the patent application-related information in order to assist the user's input. It is also possible to provide a function of inputting one important phrase selected by the user from a pop-up screen or the like displaying important phrases listed in a predetermined order (for example, in order of importance) at the cursor position.

Display unit 2084 includes operation reception unit 20841 . For example, if the display control information added to the display element defined in the HTML file indicates that the display element is an operation-responsive GUI element (that is, a GUI element that activates processing according to an operation) function is given to the display element), the user's operation is accepted and the function or the like determined by the display control information is executed.

As a specific example, the operation receiving unit 20841, for example, from the display element related to the translation word candidate set added to the key words in the key word list part of the patent application related information as the display document, out of the translation word candidate set receives a selection operation of one element of , activates a predetermined function with that element as an argument, and executes a process of determining a corresponding translated word for an important phrase. The operation reception unit 20841 receives the user's selection operation from the translation word candidate set for the key phrase, and the selected element is paired with the key phrase, for example, to generate a learning model for translation of the key phrase. can be stored in the teacher data storage unit 2072 as teacher data for machine learning for . In addition, for each of the one or more key words, the output unit 208 outputs the key word and the corresponding translation word determined by the operation reception unit 20841 according to the user's selection from the translation word candidate set for the key word. may generate and output translation assistance information containing a set of .

Further, the operation reception unit 20841 receives an operation on a display element corresponding to an important phrase in, for example, an important phrase list portion in the patent application related information as a document for display, and uses the important phrase as an argument according to the operation. A predetermined function is activated as , and non-important phrase conversion processing is executed for the important phrase. In the non-important phrase conversion process, a part of the sentence in which the important phrase is described in the invention document (for example, the part delimited by comma characters and full stop characters) is associated with the important phrase, and a non-important phrase setting dictionary is created. may be included in In the invention document analysis system 20, from the contents of the important phrase setting dictionary and the non-important phrase setting dictionary updated by this non-key phrase processing, a part of the sentence or phrase to be input is converted into a part of the sentence or phrase generates teacher data for machine learning to generate a learning model for extracting important phrases for predicting whether or not contains important phrases, and if so, the important phrases, the machine learning unit 207 may generate a learning model for extracting important phrases, or the learning model output unit 2081 may produce a learning model for extracting important phrases. This important phrase extraction learning model can be used, for example, in the important phrase extraction unit 2051 to extract important phrases from invention documents.

[3-1-7-3. Display setting information display document]
For example, the display document generation unit 2083 generates a setting information display document such as an HTML document for displaying all or part of the setting information acquired by the setting information acquisition unit 201. good too. In the setting information display document, for example, various types of information included in the setting information are included as display elements, and the display elements for some of the various types of information are used as operation-responsive GUI elements. display control information may be added. The display document generation unit 2083 adds the invention document standard for translation acquired by the invention document standard specification for translation acquisition unit 204 to the setting information display document based on the specifying information of the invention document standard specification for translation in the setting information. All or part of the content of each condition item in the regulation may be included as a display element, and display control information for making the display element an operation-responsive GUI element may be added to the display element.

An example of a display element that is an operation-responsive GUI element in the setting information display document generated by the display document generation unit 2083 is a modification used when generating a modified version of claim information for a region planned as a filing destination. Modification information that defines the method is included. As a specific example of the operation-responsive GUI element of this correction information, a check box is added to each of a plurality of correction methods and displayed, and the correction method whose check box is checked by operation is selected as the content of this correction information. An example of updating configuration information to Examples of this multiple amendment method include: ``If there is a claim that claims a program, change that claim to a claim that is a program recording medium,'' If any of the paragraphs to which a claim refers to multiple terms, change that one term to a single term that refers to only one of the multiple terms”, “Multiple terms in a claim change a quoted term to a term that quotes only one of those terms,” “change a term that quotes multiple terms in a claim to each other Cite only one that is different, change to the same number of terms as the plurality of them", "In the case where a reference sign corresponding to the element represented by the key phrase is described in the specification, add the reference sign to the key phrase in the claim and the like. The setting information display document can be interpreted and displayed by a browser.

The display unit 2084 can display, for example, a setting information display document. In a state where the display elements of the setting information display document are displayed by the display unit 2084, for example, the user can edit the contents of various information (for example, condition information) included in the setting information by the operation corresponding GUI elements. In order to narrow down the condition items to be used for the evaluation as the basis for generating the invention document evaluation information, the user can select the condition items among the condition items in the invention document standard specifications for translation. The operation accepting unit 20841 accepts operations such as editing and selection by the user, and executes predetermined processing according to the display item to be operated and the operation. As this process, for example, the contents of the setting information (for example, reference character string pattern information, specific particle character string pattern information, and the modification method used when generating modified claim information for the region planned as the application destination are defined. correction information, etc.) (for example, updating a setting information file containing setting information), updating inappropriate description conditions of invention documents used to generate warning information, and translations used to generate invention document evaluation information It is possible to narrow down the condition items in the invention document standard specifications for use, and the like.

[3-1-7-4. Output of important phrase group information]
The output unit 208 can output, for example, important phrase group information listing a plurality of important phrases extracted by the important phrase extraction unit 2051 from the invention document acquired by the invention document acquisition unit 2021 .

The output unit 208 may add the importance determined by the importance determining unit 2055 to each important phrase in the important phrase group information by referring to the important phrase management information held by the analysis unit 205, Attribute information specified by the attribute specifying unit 2056 may be added. The output unit 208 may include in the important phrase group information information about only the important phrases whose importance exceeds a predetermined value among the important phrases extracted by the important phrase extraction unit 2051. good.

For each key phrase in the key phrase group information, the output unit 208 outputs the corresponding translation word determined by the translation unit 2054 corresponding to the key phrase, or An element selected by the operation reception unit 20841 from among the elements of the identified translation word candidate set may be added.

Important phrase group information output based on invention documents can be used, for example, to classify multiple invention documents, determine correlations between invention documents, generate important phrase setting dictionaries, and generate translation assistance information. .

[3-2. Invention document analysis processing example according to the second embodiment]
An example of invention document analysis processing executed by the invention document analysis system 20 having the above configuration will be described.

FIG. 40 is a flowchart showing an example of invention document analysis processing.

As the invention document analysis process, the invention document analysis system 20 performs, for example, acquisition of setting information (step S11), acquisition of key phrase setting dictionary (step S12), and invention document standard for translation, as shown in FIG. Acquisition of regulations (step S13), acquisition of invention documents (step S14), acquisition of drawing documents (step S15), citation relationship analysis processing for claims (step S16), and important phrase extraction processing (step S17) , element relation determination processing (step S18), identification of attribute information of each key phrase (step S19), importance determination processing of each key phrase (step S20), and translation word candidate set identification processing ( step S21), technical field identification processing (step S22), key phrase display color determination processing (step S23), warning information generation processing (step S24), complaint information generation processing (step S25). , claim tree generation processing (step S26), specification information generation processing (step S27), various translation information generation processing (step S28), important phrase list generation processing (step S29), and patent application Related information generation processing (step S30), display document generation processing (step S31), and patent application related information output processing (step S32) are executed. The example of FIG. 40 is merely an example, and the invention document analysis system 20 may execute the invention document analysis process by omitting or changing some of the steps shown in FIG. 40 may be executed by adding some processing steps to the plurality of steps shown in FIG. 40, the execution order of the plurality of steps shown in FIG. may be performed in parallel.

Hereinafter, each process shown in FIG. 40 will be described with reference to the drawings as needed.

In the setting information acquisition process (step S11), the setting information acquisition unit 201 acquires setting information.

In acquisition of the important phrase setting dictionary (step S12), the important phrase setting dictionary acquisition unit 203 acquires the important phrase setting dictionary based on the setting information, for example.

In the acquisition of the invention document standard specification for translation (step S13), the invention document standard specification acquisition unit 204 for translation acquires the invention document standard specification for translation based on the setting information, for example.

In the acquisition of the invention document (step S14), the invention document acquisition unit 2021 acquires the invention document to be analyzed by the analysis unit 205 of the invention document analysis system 20 according to the specification of the user of the invention document analysis system 20 or the like.

In the drawing document acquisition (step S15), the drawing document acquisition unit 2022 acquires the drawing document including the drawings corresponding to the invention document acquired by the invention document acquisition unit 2021, for example, according to the user's designation.

In the claim citation relationship analysis process (step S16), the claim citation relationship detection unit 2057 executes a citation relationship analysis process for analyzing the citation relationships between the claims of the invention document acquired in step S14.

FIG. 41 is a flow chart showing an example of the citation relationship analysis process (step S16). As a citation relationship analysis process, the claim citation relationship detection unit 2057 searches for a preceding item number description portion corresponding to a predetermined citation destination item number description pattern for each claim item in an invention document, and finds the preceding item number description. If there is a part, it is extracted (step S161), and one or more item numbers are specified from the extracted preceding item number description part (step S162). Then, as the citation relation analysis process, the claim citation relation detection unit 2057 updates, for each claim term, claim citation relation information including information that associates that term with the set of item numbers specified in step S162. By saving and holding the claim citation relationship information, storage management of the claim citation relationship information is performed (step S163).

In the important phrase extraction process (step S17), the important phrase extraction unit 2051 extracts important phrases from the claims of the invention document acquired in step S14 based on the setting information acquired in step S11. and a specification key phrase extraction process for extracting key phrases from the specification of the invention document.

FIG. 42 is a flow chart showing an example of an important complaint phrase extraction process. As the claim key phrase extraction process, the key phrase extraction unit 2051 extracts, for example, from the claims of the invention document, the same key phrases as the key phrases included in the key phrase setting dictionary acquired in step S12 (step S1711), The object of the claim is extracted as an important phrase (step S1712), and the character string corresponding to the important phrase candidate character string pattern immediately before the character string (that is, code) corresponding to the code character string pattern in the claim is extracted as an important phrase. (step S1713), the character string corresponding to the key phrase candidate character string pattern subsequent to the character string corresponding to the reference character string pattern in the complaint is extracted as an important phrase (step S1714), and the key phrase candidate characters in the complaint are extracted. Of the character strings (that is, key phrase candidates) that correspond to the column pattern, those that satisfy a certain condition (for example, when the description range of multiple key phrase candidates has a description inclusion relationship, Among them, the inclusion side) is extracted as an important phrase (step S1715). Note that the example of FIG. 42 is merely an example, and the important phrase extraction unit 2051 may execute processing in which some steps shown in FIG. 42 are omitted or modified as the complaint important phrase extraction processing. 42 may be executed by adding some processing steps to the plurality of steps shown in FIG. 42, the execution order of the plurality of steps shown in FIG. All or part of multiple steps may be performed in parallel.

FIG. 43 is a flow chart showing an example of a specification key phrase extraction process. As the specification key phrase extraction process, for example, the key phrase extraction unit 2051 extracts the same key phrases as the key phrases included in the key phrase setting dictionary acquired in step S12 from the specification of the invention document (step S1721). ), if there is an important phrase extracted by the claim important phrase extraction process in the specification, extract the important phrase (step S1722), is extracted as an important phrase (step S1723). A character string corresponding to the string pattern is extracted as an important phrase (step S1724). Among the candidates for key phrases in (1725), those that include the key phrases extracted in the claim key phrase extraction process at the end of words) are extracted as key phrases (step S1725). Note that the example in FIG. 43 is merely an example, and the important phrase extraction unit 2051 may execute a process in which some of the steps shown in FIG. Some processing steps may be added to the plurality of steps shown in FIG. 43 and executed, or the execution order of the plurality of steps shown in FIG. All or some of the steps shown may be performed in parallel.

In the inter-element relationship determination process (step S18), the inter-element relationship determination unit 2058 determines the relationship between elements represented by each of the multiple key words extracted in the key word extraction process (step S17).

FIG. 44 is a flow chart showing an example of the inter-element relationship determination process (step S18). As the inter-element relationship determination processing (step S18), the inter-element relationship determination unit 2058 determines, for example, the structural inclusion relationship between the elements represented by the multiple key phrases extracted in the key phrase extraction processing (step S17). Execute inclusion relation determination processing (step S181), and execute recording relation determination processing for determining whether or not the elements represented by each of the plurality of key words have a relationship between the recording medium and the contents of the recording medium (step S182). , a program realization relationship determination process for determining whether the elements represented by each of the key phrases have a relationship between the program and the content realized by the program (step S183), Equivalent relationship determination processing for determining that there is a relationship is executed (step S184), and hierarchical conceptual relationship determination processing is performed for determining that there is a conceptual hierarchical relationship between elements represented by a plurality of important terms (step S185). ). Then, the inter-element relationship determination unit 2058 determines the inclusion relationship information indicating the result of the inclusion relationship determination process, the recording relationship information indicating the result of the recording relationship determination process, and the program realization relationship information indicating the result of the program realization relationship determination process. , important phrase relationship information including equivalent relationship information indicating the result of the equivalent relationship determination process and hierarchical concept relationship information indicating the result of the hierarchical concept relationship determination process (step S186). The example of FIG. 44 is merely an example, and the inter-element relationship determination unit 2058 may execute processing in which some steps shown in FIG. 44 are omitted or modified as the inter-element relationship determination processing. Some processing steps may be added to the plurality of steps shown in FIG. 44 and executed, or the execution order of the plurality of steps shown in FIG. All or some of the steps shown may be performed in parallel.

In specifying the attribute information of each key phrase (step S19), the attribute specifying unit 2056 determines the results of the inter-element relationship determination processing (step S18) for each key phrase extracted in the key phrase extraction processing (step S17). is used to identify the attribute information of the key phrase (see FIG. 19).

In the process of determining the importance of each important phrase (step S20), the importance determining unit 2055 determines the importance of each of the important phrases extracted in the important phrase extraction process (step S17).

FIG. 45 is a flow chart showing an example of the process of determining the importance of each key phrase (step S20). As the process of determining the importance of each important phrase (step S20), the importance determining unit 2055 performs, for example, the attribute identifying unit 2056 in step S19 for each important phrase extracted in the important phrase extraction process (step S17). Based on the attribute information obtained, the importance of the important phrase is determined (step S201). The importance is re-determined so that (step S202). Note that the example of FIG. 45 is merely an example, and the importance determining unit 2055 may execute processing with some of the steps shown in FIG. Alternatively, some processing steps may be added to the plurality of steps shown in FIG. 45 and executed, the execution order of the plurality of steps shown in FIG. 45 may be changed and executed, All or part of the steps shown in FIG. 45 may be performed in parallel.

In the translation word candidate set identification processing (step S21), the translation word candidate set identification unit 20541 uses the bilingual dictionary information to identify each key phrase extracted in the key phrase extraction processing (step S17). A translation word candidate set, which is a set of corresponding translation word candidates, is identified. In the translation word candidate set identification process (step S21), the translation word candidate set identification unit 20541, for example, uses the key phrase as an input and uses the key phrase translation learning model to perform arithmetic processing for each key phrase. The generated machine translation result can be added to the translation word candidate set for the key phrase.

In the technical field identification process (step S22), the technical field identification unit 20531 extracts from the invention document acquired in step S14 in the important phrase extraction process (step S17) based on the important phrase group, which is a set of important phrases. to identify the technical field of the invention document. In the technical field identification process (step S22), the technical field identification unit 20531 identifies technical fields in each of a plurality of invention documents whose correspondence with the technical field is known, and extracts key phrases extracted from the invention documents in the past by the key phrase extraction process. Identify the technical field of the invention document whose technical field is unknown by using the relationship with the group of important words and phrases. In the technical field identification process (step S22), the technical field identification unit 20531 performs predetermined arithmetic processing using, for example, the learning model for technical field identification, based on the key phrase group extracted from the invention document. can identify the technical field to which the invention document belongs.

In the key phrase display color determination process (step S23), for example, the analysis unit 205 extracts the key phrases extracted in the key phrase extraction process (step S17) as part of the patent application-related information as a document for display. The information is included as a display element in various information, and the display control information added to the display element includes an identification code including a serial number determined in ascending order based on the first appearance number of the important phrase, and analyzed The unit 205 or the display document generation unit 2083 determines the display control information so that the display colors as the display modes of the display elements whose serial numbers of the identification codes are relatively close have a relatively large difference. . Here, for example, for a plurality of important phrases in which the character strings constituting the important phrases in the claim information representing the claim are different from each other, the serial number included in the identification code of the important phrases is, for example, the same characters as the important phrases. The key phrases in columns are arranged in ascending order of the earliest position (eg, the first appearance line number of the key phrase) in the claim. In this example, the display control information for each of a plurality of key phrases in which the character strings constituting the key phrase in the complaint information are different from each other is a serial number associated with the identification code in the identification information for each key phrase for each of the plurality of key phrases. key phrases with consecutive numbers (for example, differences in hue components, differences in RGB value components, etc.) should be larger than the difference in display colors between key phrases with non-consecutive serial numbers. It may be for controlling the display color added to the phrase. For example, the RGB values (here, each RGB component 0 to 255 (0xff), which can have 256 levels of values. The RGB values of the display colors added to the important phrase by the display control information are red 0, green "255" (0xff), and blue "0", and the important phrase is displayed by the display control information of the important phrase whose sequence number is 3. The RGB value of the display color added to is red "0", green "0", blue "255" (0xff), and the display added to the important phrase by the display control information of the important phrase whose serial number is 4 The RGB values of the color are red "153" (0x99), green "0", and blue "0". Assuming that red is "0", green is "153" (0x99), and blue is "0", two of the important phrases in the first group whose serial number is equal to or less than a predetermined number (3 in this example) The minimum value of the difference in the display color added to each important phrase in each set of phrases in all sets is the number of important phrases in the second group and the important phrases in the first group whose sequence number is greater than a predetermined number. The difference in the display color added to each key phrase in each of two key phrase sets among multiple key phrases in a mixed group in which words and phrases are mixed is greater than the minimum value in all sets. Assuming that the RGB values are the respective components of the three orthogonal axes, the difference in the display colors can be calculated by finding the distance between the RGB values of the display colors added to each of the two important phrases. View the claim information when each key phrase in the claim information in the patent application related information as a display document is displayed by the display control information of the important phrase, which controls the difference in the display color added to the For translators, etc. who have done so, it is possible to quickly identify each key phrase in the claim information.Adjustment of the display color based on the serial number related to the identification information of the key phrase (that is, the first appearance number of the key phrase) as described above , is useful for improving the distinguishability between important words and phrases in relatively important parts near the beginning of claim information (for example, description parts of claims with relatively small item numbers).
As another example, for example, the display color added to the important phrases of the first group with a serial number from 1 to a first predetermined number (for example, 200) of 216 or less is "0" as the value of each component of the RGB value, to differ from each other using any of '51' (0x33), '102' (0x66), '153' (0x99), '204' (0xcc), and '255' (0xff) The display color that is determined and added to the important phrases of the second group whose sequence number is greater than the first predetermined number (for example, 200) and up to the second predetermined number (for example, 300) is "34" as the value of each component of the RGB values. (0x22), "85" (0x55), "136" (0x88), "187" (0xbb), and "238" (0xee) are defined to be mutually different, The display color added to the important phrases of the third group whose serial number is greater than the second predetermined number (for example, 300) and up to the third predetermined number (for example, 400) is "17" (0x11 ), ``68'' (0x44), ``119'' (0x77), ``170'' (0xaa), and ``221'' (0xdd). good. In this example as well, among the plurality of key phrases in the first group whose sequence number is equal to or less than the first predetermined number (200 in this example), the difference in the display color added to each key phrase in each of the two key phrase pairs is , the minimum value in all pairs is a mixture of the second group, or a mixture of a plurality of important phrases of the second and third groups with a serial number larger than a predetermined number, and a plurality of important phrases of the first group. The difference in the display color added to each key word in each of the two key word sets of the multiple key words in the group is greater than the minimum value for the entire set. In the group in which the minimum value of the difference in the display color of each important phrase is large, each of the important phrases can be identified relatively quickly and correctly due to the difference in display color. In this example, when each key phrase in the claim information in the patent application-related information as a display document is displayed, it appears relatively near the beginning of the claim information for translators who browse the claim information. Each of the key phrases of the first group of phrases being identified can be relatively quickly or correctly identified from each other.
The display control information added to various display elements in the patent application related information as a display document changes the display color of the display element to emphasize the display element, makes the character string of the content of the display element bold, Display elements may be emphasized by changing the character size, etc., or information addition display that adds information to the contents of the display elements (for example, adding the importance of important words and phrases, attribute information, etc.) may be performed), the display element may be a GUI element for performing information addition display according to the operation, or the display element may be a search based on the contents of the display element according to the operation , a GUI element for performing processing such as translation, etc., or a GUI element for performing display transition so as to display information related to the content of the display element according to the operation of the display element. It may be something to do.

In the warning information generation process (step S24), the warning information generation unit 2059 generates the invention acquired in step S14 based on the setting information acquired in step S11, the invention document standard specification for translation acquired in step S13, and the like. Generate warning information including indication information pointing out inappropriate descriptions in the document.

FIG. 46 is a flow chart showing an example of the warning information generation process (step S24). As the warning information generation process (step S24), the warning information generation unit 2059 causes the warning information to include, for example, indication information pointing out if the description of the invention document does not comply with the "invention document standard specification for translation" (step S24). S241), referring to the claim citation relationship information, and if there is no precedent word corresponding to the reference description in the claim of the invention document, the warning information includes pointing information indicating that fact (step S242), and the invention document If there is any deficiencies in the description format of claims, specifications, etc., drawing numbers, paragraph numbers, etc., the warning information includes pointing information pointing out that fact (step S243), and deficiencies in the text of the invention document, code If there is any one or more of inadequacies related to, inconsistency in notation, and the possibility of clerical errors, the warning information includes indication information pointing out that fact (step S244), and the warning information in the display document Display control for functioning as a GUI element for display transition to the line of the invention document that is the object of indication, the claim information section related to the indication, or the paragraph of specification information for the display element related to each indication information Information is added (step S245), invention document evaluation information is generated, and added to the warning information (step S246). Note that the example of FIG. 46 is merely an example, and the warning information generation unit 2059 may execute processing in which some of the steps shown in FIG. 46 are omitted or modified as the warning information generation processing. 46 may be executed by adding some processing steps to the plurality of steps shown in FIG. 46, the execution order of the plurality of steps shown in FIG. may be performed in parallel.

In the claim information generating process (step S25), the claim information generation unit 205a generates claim information and the like to be included in the patent application related information based on the claims of the invention document acquired in step S14.

FIG. 47 is a flow chart showing an example of the complaint information generation process (step S25). As the complaint information etc. generation process (step S25), the complaint information generation unit 205a executes, for example, a complaint information generation process (step S251), a sign determination process (step S252), and a complaint base drawing information generation process. execution (step S253), execution of claim-based specification information generation processing (step S254), execution of claim-based abstract information generation processing (step S255), and execution of modified version claim information generation processing (step S256) .

FIG. 48 is a flow chart showing an example of the complaint information generation process (step S251). As the complaint information generation process (step S251), the complaint information generation unit 205a generates complaint information representing the complaint based on the complaint in the invention document acquired in step S14 (step S2511), and generates the complaint information as a document for display. For the display elements of each key phrase in the claim information in the patent application related information, basically different display colors are added for each key phrase, and information related to the key phrase is added and displayed according to the operation. Display control information is added (step S2512) in order to provide a GUI function and to provide a GUI function for executing processing such as retrieval and translation of key words in response to another operation (step S2512). Display control information is added to the display elements of the headings in each section in order to have a GUI function corresponding to operations such as highlighting and display transition to the next heading (step S2513). Display control information is added for highlighting, etc., to the display element of the reference character string in the complaint information (step S2514), and display is performed for highlighting, etc., to the display element of the comment in the complaint information. Control information is added (step S2515), and display control information is added for highlighting or the like to the display element of the portion pointed out by the warning information in the complaint information (step S2516).

FIG. 49 is a flow chart showing an example of the code determination process (step S252). As the code determination process (step S252), the complaint information generation unit 205a selects the important words and phrases extracted from the claims in the invention document acquired in step S14 by the important word and phrase extraction process (step S17). If the category type of the element represented by the word is either product or method, it is selected as a code determination target (step S2521), and the important word selected as a code determination target corresponds to the code in the "description of code" in the invention document. If so, the code is adopted with the highest priority (step S2522), and if the important phrase selected as the object of code determination is given a code in the specification of the invention document, the code is given the highest priority. (step S2523), and for each important phrase selected as a sign determination target, based on the structural inclusion relationship of the elements represented by the important phrase, the character string of the sign of the important phrase on the including side and the included The code is determined so that it has a predetermined relationship such as an inclusion relationship between the character strings with the character string of the key phrase code on the side (step S2524).

FIG. 50 is a flow chart showing an example of the claim-based drawing information generation process (step S253). As the claim-based drawing information generation process (step S253), the claim information generation unit 205a, for example, extracts the claims expressed by the important words and phrases extracted from the claims in the invention document acquired in step S14 by the important word and phrase extraction process (step S17). If the target includes elements represented by other key words, a configuration diagram is generated in which rectangular frames surrounding each key word are arranged according to the inclusion relationship (step S2531), and is recorded on the recording medium represented by the key words of the claim. If the relevant element records an element represented by another key phrase, a diagram listing the recording contents of the recording medium is generated (step S2532), and the element related to the program represented by the key phrase of the claim is When realizing the function, processing, etc. of the element represented by , a diagram showing a set of elements related to the function to be realized is generated (step S2533), and the important element whose code is determined by the code determination process (step S252) As for the words, a code connected by a leader line is added from the drawing contents (for example, a rectangular frame) related to the important words in the figure (step S2534). A drawing number is determined in order (step S2535), and display control is performed by code search corresponding to the display element of each code in the claim-based drawing information (for example, control to highlight the code by performing display transition so as to display the code). is added (step S2536).

FIG. 51 is a flow chart showing an example of the claim-based statement information generation process (step S254). As the claim-based specification information generation process (step S254), the claim information generation unit 205a generates, for example, the "title of the invention , ``problem to be solved by the invention'' and ``means for solving the problem'' (step S2541), and in the claim-based drawing information generated in the claim-based drawing information generation process (step S253) Based on the above, the contents of the "brief description of the drawings" are generated (step S2542), and for each item of the claim, the contents and the incomplete message for supporting the description of the corresponding effect are included in the "for carrying out the invention form" (step S2543), and based on the key word relationship information generated in step S186 and the claim base drawing information, the order of explanation of each key word is determined (step S2544) and determined In accordance with the order of explanation, each key phrase is the subject, a code is added to the key phrase whose code has been determined, and if necessary, an incomplete message for supporting description is added to the sentence "Form for Carrying Out the Invention" ” (step S2545), and control of the display mode such as highlighting etc. is added to the display elements of the important phrases, symbols and incomplete messages for description support in the claim-based specification information in the patent application related information as the display document , display control information is added for control to have a function as an operation corresponding GUI element (step S2546).

FIG. 52 is a flow chart showing an example of the claim-based abstract information generation process (step S255). As the claim-based abstract information generation process (step S255), the claim information generation unit 205a, for example, acquires setting information in the "problem" column under "summary" in the same format as the abstract of the Japanese patent application. Write an incomplete message for description support based on the incomplete message information of the setting information acquired in (step S11) (step S2551), and fill in the "solution means" column of the claim in the invention document acquired in step S14. Include the content of the first term, add a code to the important phrase whose code has been determined in the code determination process (step S252) (step S2552), and enter "Fig. 1" in the "selected drawing" column. (step S2553), describe the contents of the first paragraph of the claim as an abstract of the Japanese version for the US application (step S2554), and write the first paragraph of the claim as an abstract of the Japanese international application format , and the sign is added in parentheses following the important words and phrases whose signs have been determined in the sign determination process (step S252) (step S2555), and the patent application related information as a document for display Display control information for highlighting and the like is added to display elements such as key words and phrases in the claim-based abstract information (step S2556).

FIG. 53 is a flow chart showing an example of the modified complaint information generation process (step S256). As the corrected complaint information generation process (step S256), the complaint information generation unit 205a generates the warning information generated in the warning information generation process (step S24) based on the complaint information generated in the complaint information generation process (step S251), for example. Based on the correction information, etc., of the inappropriate description pointed out by the warning information, corrected complaint information is generated (step S2561). The program is modified to conform to the format specified by the acquired setting information (for example, specification such as using double-byte characters for numbers, adding signs to key words, etc.) (step S2562), and based on the setting information, the program is executed. Modified claim information, such as a claim describing the claimed object belonging to the category, is added to the claim (step S2563), and each claim description (for example, claim information (Description of each item after processing, such as changing the item citing multiple items in the paragraph to the item citing the singular item) is added to the modified claim information (step S2564), and the patent application as a display document Display control information is added to display elements such as key phrases in the modified claim information in the related information in order to highlight the display elements, or to make the display elements into operation-responsive GUI elements ( step S2565).

47 to 53 are merely examples, and the complaint information generating unit 205a may execute processing in which some of the steps shown in FIGS. 47 to 53 are omitted or changed. , several processing steps may be added to the steps shown in FIGS. 47 to 53, or the execution order of the steps shown in FIGS. Alternatively, all or part of the steps shown in FIGS. 47 to 53 may be executed in parallel.

In the claim tree generation process (step S26), the claim tree generator 205c generates, for example, a claim tree, a modified claim tree, a constituent claim tree, and a modified claim tree.

FIG. 54 is a flow chart showing an example of the claim tree generation process (step S26). As the claim tree etc. generating process (step S26), the claim tree generating unit 205c, for example, refers to the claim citation relationship information, and generates the claim information generated in the claim information generating process (step S251) and the modified version claim information generating process ( Based on each of the modified claim information generated in step S256), a claim tree and a modified claim tree are generated (step S261), and a constituent claim tree is generated based on the claim information and inclusion relationship information (step S262). ), generate a modified configuration claim tree based on the modified claim information and inclusion relationship information (step S263), and use it to represent the citation relationships in the generated various claim trees in the patent application related information as a display document. Display control information is added to the display elements of each of the symbols and important phrases in order to highlight the display element or to make the display element an operation-responsive GUI element (step S264). Note that the example of FIG. 54 is merely an example, and the claim tree generation unit 205c may execute processing in which some of the steps shown in FIG. 54 may be executed by adding some processing steps to the plurality of steps shown in FIG. 54, the execution order of the plurality of steps shown in FIG. All or part of multiple steps may be performed in parallel.

In the description information generation process (step S27), the description information generation unit 205b generates, for example, description information, a description heading list, a code list, and modified version description information.

FIG. 55 is a flow chart showing an example of the statement information generation process (step S27). As the specification information generation process (step S27), the specification information generation unit 205b generates specification information representing the specification based on the specification of the invention document acquired in step S14, for example. processing (step S271), a description heading list generation process for extracting the description information headings and generating a description heading list is performed (step S272). A code list generation process is performed to generate a code list in which the codes are sorted and enumerated (step S273). Corrected specification information generation processing is performed to generate corrected specification information by correcting inappropriate descriptions in the content (step S274). Note that the example of FIG. 55 is merely an example, and the statement information generation unit 205b may execute processing in which some of the steps shown in FIG. 55 are omitted or changed as the statement information generation processing. 55 may be executed by adding some processing steps to the plurality of steps shown in FIG. 55, or the plurality of steps shown in FIG. All or part of the steps shown in can be executed in parallel.

In the various translation information generation processing (step S28), the translation unit 2054, for example, corresponds to each of the claim information, the modified claim information, the specification information, and the modified specification information, and translates the contents of the information. Generate claim translation information, modified claim translation information, specification translation information, and modified specification translation information, including at least a partial translation result.

FIG. 56 is a flowchart showing an example of processing for generating various translation information (step S28). As the various translation information generation processing (step S28), the translation unit 2054, for example, the claim information (that is, claim information, corrected version claim information, specification information, and corrected version specification information) section or line, For that paragraph or line, claim translation information etc. that alternately include partially translated lines in which important phrases have been machine-translated using a learning model for translation of important phrases generated by the invention document analysis system 20 in the past (that is, Claim translation information, modified claim translation information, specification translation information, and modified specification translation information) are generated (step S281). Machine translation using the generated learning model for translation or machine translation using another machine translation program or the like is performed to generate complete translation lines (step S282), and partial translation of claim translation information, etc. Replace the line with the fully translated line or add the fully translated line to the partially translated line (step S283), and display elements of the corresponding translated words corresponding to each important word in the claim translation information of the patent application related information as the display document , display control information for displaying in a display mode having commonality with the display elements of the original key words (step S284), and display elements of the corresponding translated words corresponding to the key words in the claim translation information, etc. is added display control information for operation-responsive GUI elements that include GUI functions related to the original key phrase and display a translation word candidate set for the key phrase (step S285). Note that the example in FIG. 56 is merely an example, and the translation unit 2054 may execute processing in which some of the steps shown in FIG. may be executed by adding some processing steps to the plurality of steps shown in FIG. 56, the execution order of the plurality of steps shown in FIG. may be performed in parallel.

In the important word list generation process (step S29), the translation unit 2054 generates, for example, an important word list, a drawing code list, and important word related translation information.

FIG. 57 is a flowchart showing an example of the important phrase list generation processing (step S29). In the important phrase list generation process (step S29), the translation unit 2054, for example, extracts each important phrase from the invention document acquired in step S14 in the important phrase extraction process (step S17), An important phrase list generation process is executed to generate an important phrase list configured by associating the translation word candidate set or the corresponding translation word (step S291), and the important phrases in the patent application related information as the document for display are generated. Display control information for controlling the display mode etc. is added to each display element of the important words in the list, the corresponding translation words, and the translation word candidate set (step S292), and the drawing document acquired in step S15 is added. Drawing code list generation for generating a drawing code list based on the "code" item of the attribute information specified in step S19 for each key word extracted from the content and the invention document in the key word extraction process (step S17) Processing is executed (step S293), and the display mode of each display element of the drawing number, key words, corresponding translation words, translation word candidate set, and code in the drawing code list in the patent application related information as the document for display is added (step S294), and the important phrases in the important phrase relation information generated in step S186 are replaced with corresponding translation words or translation word candidate sets corresponding to the important phrases. Word-related translation information is generated (step S295). Note that the example in FIG. 57 is merely an example, and the translation unit 2054 may execute processing in which some of the steps shown in FIG. 57 may be executed by adding some processing steps to the plurality of steps shown in FIG. 57, the execution order of the plurality of steps shown in FIG. may be performed in parallel.

In the process of generating patent application related information (step S30), the patent application related information output unit 2082 outputs, for example, information obtained by adding a line number to each line of the invention document acquired in step S14 and analyzed by the analysis unit 205. , important phrase relationship information generated in the inter-element relationship determination process (step S18), technical field information indicating the technical field identified in the technical field identification process (step S22), and warning information generation process (step S24) The warning information generated in , the claim information generated in the claim information generation process (step S25), the claim-based drawing information, the claim-based specification information, the claim-based abstract information, and the modified version claim information, and the claim The claim tree, modified claim tree, configuration claim tree, and modified configuration claim tree generated in the tree generation process (step S26), and the specification information generated in the specification information generation process (step S27) , specification heading list, code list, and modified specification information, claim translation information generated in the process of generating various types of translation information (step S28), modified claim translation information, specification translation information, and correction Version specification translation information, key phrase list generated in the key phrase list generation processing (step S29), drawing code list, key phrase related translation information, and invention document etc. are generated by the analysis unit 205. Patent application related information (see FIG. 15) is generated by including the charged fee information and totalized information.

In the process of generating a document for display (step S31), each piece of information that is part of the patent application-related information as a document for display generated by the analysis unit 205 is integrated to form a document for display (for example, an HTML document). to generate

In the patent application related information output process (step S32), for example, the display unit 2084 displays the patent application related information as the display document generated in the display document generation process (step S31). Output the application-related information, or the patent application-related information output unit 2082 outputs the display document related to the patent application-related information generated in the display document generation process (step S31) as one or more files. Alternatively, the patent application related information output unit 2082 outputs the patent application related information generated in the patent application related information generating process (step S30) as a text file or other file.

[3-3. Important phrase translation learning model generation processing example according to the second embodiment]
The invention document analysis system 20 can execute an important phrase translation learning model generation process for generating an important phrase translation learning model for machine translation of important phrases in invention documents. An example of the important phrase translation learning model generation process will be described below.

FIG. 58 is a flow chart showing an example of important phrase translation learning model generation processing.

For example, as shown in FIG. 58, the invention document analysis system 20 acquires setting information (step S11), acquires an important word/phrase setting dictionary (step S12), translates Acquisition of invention document standard specifications (step S13), acquisition of invention documents (step S14), acquisition of drawing documents (step S15), citation relationship analysis processing related to claims (step S16), and important phrase extraction processing (step S17), inter-element relationship determination processing (step S18), identification of attribute information of each key phrase (step S19), importance determination processing of each key phrase (step S20), translation word candidate set identification processing (step S21), technical field identification processing (step S22), important phrase display color determination processing (step S23), warning information generation processing (step S24), and warning information generation processing (step Evaluation (step S51) of the evaluation value based on the invention document evaluation information in the warning information generated in step S24) is performed. case), the process returns to step S14 to acquire another invention document. If the evaluation in step S51 is correct (that is, if the evaluation value exceeds the threshold), the invention document analysis system 20 performs patent application related information generation processing (step S52) and display document generation processing (step S53), classification of invention documents into groups (step S54), display of patent application-related information (step S55), acceptance of selection of translation word candidate set elements (step S56), key phrases and selection results as training data. (step S57), generation of a learning model for translation of important phrases (step S58), and output of a learning model for translation of important phrases (step S59). Note that the example of FIG. 58 is merely an example, and the invention document analysis system 20 may execute a process in which some of the steps shown in FIG. 58 are omitted or changed as the important phrase translation learning model generation process. However, some processing steps may be added to the plurality of steps shown in FIG. 58 and executed, or the execution order of the plurality of steps shown in FIG. All or some of the steps shown at 58 may be performed in parallel. The invention document analysis system 20 can, for example, repeat the processing in steps S56 and S57 in FIG. 58 multiple times according to the user's operation. Also, the invention document analysis system 20 may execute the processes in steps S58 and S59 after repeatedly executing the processes in steps S14 to S57 in FIG. 58 for a certain number of times or for a period of time.

The processing in steps S11 to S24 in the example of FIG. 58 is the same as the processing in steps S11 to S24 in the invention document analysis processing described above in accordance with the example of FIG.

In the evaluation of the evaluation value based on the invention document evaluation information in the warning information generated in the warning information generation process (step S24) in step S51, the document evaluation unit 2071 of the machine learning unit 207 obtained in step S14 Based on whether or not the evaluation value included in the invention document evaluation information exceeds a threshold value, whether the invention document is appropriate enough to be used for generating a learning model for translation of important phrases is evaluated.

The generation of patent application related information (step S52) in the example of FIG. 58 is the process in step S30 executed after the processes in steps S25 to S29 in the invention document analysis process described above in accordance with the example in FIG. is similar to

The display document generation process (step S53) in the example of FIG. 58 is the same as the process in step S31 in the invention document analysis process described above with reference to the example of FIG.

In the group classification of invention documents (step S54), the classification unit 2053 extracts the important phrase group extracted in the important phrase extraction process (step S17) for the invention documents currently acquired in step S14, and Group classification is performed based on the correlation between the extracted key words and phrases, etc., and in step S14, the group to which the currently acquired invention document belongs is specified, or the group is classified by the user (for example, a translator). Identify the group to which the invention document belongs according to the specification. The group specified for the invention document by the group classification in step S54 may be, for example, the technical field.

In displaying the patent application related information (step S55), the display unit 2084 having a browser function interprets the display document (for example, HTML document) for the patent application related information as a display document, and displays the patent application related information on the display device. Display application-related information (see FIG. 17).

In accepting the selection of a translation word candidate set element (step S56), the operation accepting unit 20841 asks the user ( For example, a translator) accepts a selection operation. For example, the processing in step S57 may be executed each time an operation for selecting an element from the translation word candidate set is accepted for each important phrase.

In accumulating the key words and the selection result as training data (step S57), the training data storage unit 2072 of the machine learning unit 207 receives the key words and the translation word candidate set corresponding to the key words received in step S56. A set of elements selected by the above operation (that is, a corresponding translated word corresponding to the key phrase) is stored in a recording medium or the like as teacher data for machine learning for generating a learning model for key phrase translation. Note that the teacher data storage unit 2072 may store teacher data in association with the group to which the invention document identified in step S54 belongs. In addition, the training data storage unit 2072 generates a learning model for translation of important phrases by, for example, combining key phrases to which the corresponding translated words are added and the corresponding translated words in the important phrase setting dictionary acquired in step S12. may be accumulated in a recording medium or the like as teacher data for machine learning for

In the key word translation learning model generation (step S58), the machine learning unit 207 generates a plurality of machine learning models for generating key word translation learning models, which are stored in a recording medium or the like by the teacher data storage unit 2072. We generate a learning model for machine translation of important phrases by machine learning using the training data. When a plurality of pieces of teacher data for machine learning for generating a learning model for translation of key phrases are associated with groups and stored in a recording medium or the like by the teacher data storage unit 2072, the machine learning unit 207 By machine learning using a plurality of teacher data for machine learning for generating a learning model for important phrase translation for each group, accumulated in the teacher data accumulation unit 2072, for each group, important phrases for machine translation Generate a learning model for key phrase translation of For example, if the groups are classified according to the department to which the inventor belongs, the set of the important phrase "receiving unit" and the corresponding translated word "receiving unit", the important phrase "controlling unit" and the corresponding translated word "controlling unit" ”, and pairs of the key phrase “transmitting unit” and the corresponding translated word “transmitting unit” as training data. etc. may be reflected, and if machine translation is performed with the key phrase "processing unit" as input by arithmetic processing using the key phrase translation learning model, a machine translation result such as "processing unit" will be generated. can be expected. In addition, for groups related to different departments with different translation policies, etc., a set of the important phrase "receiving part" and the corresponding translated word "receiving circuit", and the important phrase "control part" and the corresponding translated word "controlling circuit" ”, and pairs of the key phrase “transmitting part” and the corresponding translated word “transmitting circuit” as training data. It is predicted that, for example, machine translation results such as "processing circuit" will be generated when the key phrase "processing part" is input and machine-translated by arithmetic processing using the key phrase translation learning model. obtain. In addition, corresponding to a group related to another department having a different translation policy, etc., a set of the important phrase "receiving part" and the corresponding translated word "receiver", the important phrase "controller" and the corresponding translated word "controller" The group's translation policy is reflected in the learning model for important phrase translation generated by machine learning using training data such as pairs of important phrases "transmitting part" and the corresponding translation word "transmitter". There is a possibility, and it can be predicted that, for example, a machine translation result of "processor" will be generated by machine-translating the key phrase "processing unit" as an input by arithmetic processing using the key phrase translation learning model. The machine learning unit 207 stores and manages the generated learning model for translation of key phrases in a recording medium or the like by the learning model management unit 2073 . The generated key word translation learning model is used for the key word translation when the invention document analysis system 20 executes the translation word candidate set identification process (step S21) in the invention document analysis process (see FIG. 40). It can be used to determine the elements of the candidate set, or to machine-translate key words when executing various translation information generating processes (step S28).

In the output of the important phrase translation learning model (step S59), the learning model output unit 2081 outputs the important phrase translation learning model held by the learning model management unit 2073, for example, as the contents of a file specified by the user. Output. The output learning model for translation of important phrases is used when another invention document analysis system 20 executes various translation information generation processing (step S28) in the invention document analysis processing (see FIG. 40). A machine translation system for translating invention documents or for machine translation that can be used for machine translation, and once machine-translates important words in the invention document and then machine-translates the entire invention document using the result program, or a general machine translation system or the like.

[3-4. Example of translation learning model generation processing according to the second embodiment]
The invention document analysis system 20 can execute a translation learning model generation process for generating a translation learning model for machine translation of an invention document. An example of the learning model generation process for translation will be described below.

FIG. 59 is a flow chart showing an example of a learning model generation process for translation.

For example, as shown in FIG. 59, the invention document analysis system 20 performs, as a translation learning model generation process, a setting information acquisition process (step S11), an important phrase setting dictionary acquisition process (step S12), an invention translation Acquisition of document standard provisions (step S13), acquisition of invention documents (step S14), acquisition of drawing documents (step S15), citation relationship analysis processing related to claims (step S16), and important phrase extraction processing (step S17), inter-element relationship determination processing (step S18), identification of attribute information of each key phrase (step S19), importance determination processing of each key phrase (step S20), and warning information generation processing (step S24) and an evaluation (step S51) related to the evaluation value based on the invention document evaluation information in the warning information generated in the warning information generation process (step S24). If so (that is, if the evaluation value does not exceed the threshold), the process returns to step S14 to acquire another invention document. If the evaluation in step S51 is correct (that is, if the evaluation value exceeds the threshold), the invention document analysis system 20 generates a modified version of the invention document (step S61) and acquires the translation result document (step S62). Then, group classification of invention documents (step S63), accumulation of revised invention documents and translation result documents as training data (step S64), generation of a learning model for translation (step S65), and creation of a learning model for translation output (step S66). Note that the example of FIG. 59 is merely an example, and the invention document analysis system 20 may execute a process in which some of the steps shown in FIG. 59 are omitted or changed as the translation learning model generation process, Some processing steps may be added to the plurality of steps shown in FIG. 59 and executed, or the execution order of the plurality of steps shown in FIG. All or some of the steps shown may be performed in parallel. For example, the invention document analysis system 20 may execute the processes in steps S65 and S66 after repeatedly executing the processes in steps S14 to S64 in FIG. 59 for a certain number of times or for a period of time.

Steps S11 to S20 and S24 in the example of FIG. 59 are the same as steps S11 to S20 and S24 in the invention document analysis process described above with reference to the example of FIG. The processing in step S63 in the example of FIG. 59 is the same as the processing in step S54 in the example of FIG.

In the evaluation of the evaluation value based on the invention document evaluation information in the warning information generated in the warning information generation process (step S24) in step S51, the document evaluation unit 2071 of the machine learning unit 207 obtained in step S14 Based on whether or not the evaluation value included in the invention document evaluation information exceeds a threshold value, whether the invention document is appropriate enough to be used for generating a learning model for translation of important phrases is evaluated.

In generating the modified invention document (step S61), the machine learning unit 207 integrates the modified claim information generated by the claim information generating unit 205a and the modified specification information generated by the specification information generating unit 205b. to generate a modified invention document. The modified invention document is generated based on the invention document for which the evaluation value included in the invention document evaluation information exceeds the threshold in step S51. Since there is a possibility that the content of the invention document is more consistent with the translation result document, a modified version of the invention document is generated.

In obtaining the translation result document (step S62), the translation result document obtaining unit 2023 obtains the translation result corresponding to the invention document currently obtained in step S14 by receiving a designation from the user (for example, a translator). Get the result document.

In accumulating the modified invention document and the translation result document as training data (step S64), the training data storage unit 2072 of the machine learning unit 207 stores the modified invention document generated in step S61 and the modified invention document obtained in step S62. A combination with the translation result document is stored in a recording medium or the like as teacher data for machine learning for generating a learning model for translation. The training data accumulation unit 2072 may accumulate training data in association with the group to which the invention document identified in step S63 belongs. If the modified invention document generated in step S61 has a plurality of claim sets in the modified claim information generated by the claim information generating unit 205a, the teacher data storage unit 2072 stores the plurality of claims in the modified invention document. After removing all claim sets other than one claim set that is highly consistent with the translation result document from the modified version of the invention document, the combination of the modified version of the invention document and the translation result document is used as a learning model for translation. It is stored in a recording medium or the like as teacher data for machine learning for generation. As an example of a specific method for identifying one claim set that is highly consistent with the translation result document from among the multiple claim sets in the modified version of the invention document, the claim set between the claims in the translation result document and the The sameness of the number of items, the sameness of the item number of each cited item in the description of each item of the claim, and the sameness of whether or not each item of the claim includes a description containing a reference sign in parentheses. Identifies the claim set in the modified invention document that has the highest overall, e.g., all of the items of identity are identical, as the highly consistent claim set. . Note that the training data accumulation unit 2072 stores a set of the revised invention document from which the code description has been removed and the translation result document from which the code description has been removed as a machine learning teacher for generating a learning model for translation. It may be stored as data in a recording medium or the like. Further, the training data accumulation unit 2072 stores, for each sentence in the modified invention document, a set of the sentence and the corresponding sentence in the translation result document as training data for machine learning for generating a learning model for translation. As such, it may be stored in a recording medium or the like.

In generating a learning model for translation (step S65), the machine learning unit 207 stores a plurality of teacher data for machine learning for generating a learning model for translation, which are stored in a recording medium or the like by the teacher data storage unit 2072. The machine learning used generates a translation learning model for machine translation of invention documents. When a plurality of teacher data for machine learning for generating a learning model for translation are stored in a recording medium or the like in association with a group by the teacher data storage unit 2072, the machine learning unit 207 stores the teacher data By machine learning using a plurality of teacher data for machine learning for generating a learning model for translation for each group accumulated in the accumulation unit 2072, learning for translation for machine translation of invention documents for each group Generate a model. The machine learning unit 207 stores and manages the generated learning model for translation in a recording medium or the like by the learning model management unit 2073 . The generated learning model for translation is used when the invention document analysis system 20 executes the various translation information generation process (step S28) in the invention document analysis process (see FIG. 40). It can be used to machine-translate specification information and the like.

In outputting the learning model for translation (step S66), the learning model output unit 2081 outputs the learning model for translation held by the learning model management unit 2073, for example, as the contents of a file specified by the user. The output learning model for translation is used when another invention document analysis system 20 executes various translation information generation processing (step S28) in the invention document analysis processing (see FIG. 40). It can be used to machine-translate information, specification information, etc., and can be used in a machine translation system or a machine translation program for translating invention documents, or in a general machine translation system.

[3-5. Effects of Invention Document Analysis System According to Second Embodiment]
Since the invention document analysis system 20 is a part of the invention document analysis system 10 shown in the first embodiment, many of the effects of the invention document analysis system 10 described above can be exhibited.

The invention document analysis system 20 uses the analysis unit 205 to extract key phrases from invention documents created by the inventors or patent attorneys in the key phrase extraction unit 2051 based on the setting information, and performs various analyzes based on each key phrase. , and the output unit 208 outputs the patent application-related information including various information generated as the analysis result. There is a possibility that Promoting the understanding of the invention document is useful for translators to translate the invention document appropriately or efficiently.

The patent application-related information generated based on the analysis result of the invention document in the invention document analysis system 20 is, for example, highlighted by the display document generation unit 2083 or the like, such as headings, comments, important phrases, symbols, etc., and displayed according to the operation. Output unit 208 as a display document such as an HTML document added with display control information for realizing the display of GUI elements for performing various searches based on key words, etc., or selecting corresponding translation words from a translation word candidate set. For translators, etc., it is possible to view patent application-related information on various terminal devices with a browser function. A quick comprehension of the document may be possible, and the determination of the corresponding translation corresponding to the key phrase may be efficiently performed. In addition, the patent application-related information as a display document (for example, an HTML document) generated based on the analysis result of the invention document in the invention document analysis system 20 is displayed by the display unit 2084. By viewing patent application-related information, highlighting key words, etc., and operating GUI elements related to key words, etc., it is possible to quickly understand invention documents, and to determine corresponding translations corresponding to key words. can be done efficiently. The content of patent application-related information displayed by a browser, etc., can be copied and pasted. It can be edited with an application program such as an editor that has document creation and editing functions.

The invention document analysis system 20 outputs, for example, the patent application-related information generated based on the analysis result of the invention document as an HTML document (for example, an HTML file and a file specified by the HTML file, etc.). This makes it possible to browse patent application-related information using various browsers that support HTML. Even without a system, a special application program, etc., a terminal device having a browser function (for example, a PC executing a browser as an application program) can be used to browse patent application-related information.

The patent application related information as a display document (for example, HTML document) generated based on the analysis result of the invention document in the invention document analysis system 20 includes, for example, claim information representing the claims in the invention document, and the specification of the invention document. Each key phrase described in the description information, etc., is displayed in a display mode (for example, display color) that distinguishes whether it is the key phrase described in the claim or not, and the key phrases with different contents are displayed in different colors. Since it is displayed with a left border line or the like attached to it, it is possible for the translator or the like to quickly grasp each important phrase.

The patent application-related information generated and output based on the analysis result of the invention document in the invention document analysis system 20 includes, for example, warning information, and the warning information indicates whether the invention document conforms to the invention document standards for translation. In the case of inappropriate descriptions such as not included, it includes indication information pointing out that fact, and also includes invention document evaluation information including the evaluation value related to the conformity of the invention document to the standard provisions for invention documents for translation. By referring to the warning information, the inventor or patent attorney who prepared the invention document may be able to modify the invention document so that it can be easily translated. In addition, for example, a translator who receives an invention document and patent application-related information from an inventor, etc. or a patent attorney and is requested to translate the invention document can expect to be provided with an appropriate invention document. It may be possible to translate properly or efficiently. In addition, for example, when the translator has the invention document analysis system 20, the invention document, setting information, important phrase setting dictionary, and drawing document are provided by the inventor or the patent attorney and used. As a result, the invention document analysis system 20 outputs the patent application-related information, and by referring to the patent application-related information, it may be possible to translate the invention document properly or efficiently. If it is assumed that the translator will use the invention document analysis system 20, or if it is assumed that the patent application related information will be provided to the translator, the translator who receives and translates the invention document By viewing the application-related information, it may be possible to translate the invention document properly or efficiently. can be ignored. The inventors, etc. or the patent attorney can provide the translator with information (for example, a key phrase setting dictionary) that designates the corresponding translation words for the key phrases in the invention document as necessary, and the translator can By referring to the information related to the corresponding translation word for the phrase, it may be possible to translate the important phrase appropriately or efficiently. In addition, the inventors, etc. or the patent attorney may use the information specifying the corresponding translated words for the key words in the invention document as the key words in the patent application related information output as a result of analyzing the invention document with the invention document analysis system 20. By referring to, editing, etc., a list (for example, a list listing pairs of key phrases and translation word candidate sets) can be generated relatively easily. In addition, the translator, etc., can view the patent application-related information as a display document displayed on a browser, etc., and operate the important words and phrases displayed as operation-responsive GUI elements in the patent application-related information. , descriptions such as key phrases in one or more other invention documents related to the invention document on which the patent application-related information is based, or translation assistance information, etc. in one or more other invention documents can be confirmed, the part related to important words and phrases in the drawing document corresponding to the invention document that became the basis of the patent application related information can be confirmed, and the definitions of important words and phrases displayed on search sites etc. Translated words and phrases can be confirmed. As a result, the translator or the like can understand the important words and phrases of the invention document sufficiently and translate them appropriately or efficiently.

The patent application-related information as display documents generated based on the analysis results of the invention documents in the invention document analysis system 20 includes, for example, claim information, modified version claim information, and specification information in which important words and phrases are highlighted. , specification heading list, modified specification information, claim tree, modified claim tree, constituent claim tree, and modified constituent claim tree. It may be possible to quickly grasp the contents of For example, the inventors or patent attorneys can easily determine whether or not the headings of the specification of the invention document are appropriate by browsing the description heading list in the patent application related information. For example, the inventor or patent attorney predefines, in the setting information, information specifying a region (for example, the U.S.) that can be the filing destination where claims should be generated, and the patent application related information output by the invention document analysis system 20. By providing a brief communication to the translator to refer to the modified claim tree or modified constituent claim tree in the In addition, it is possible to clearly understand how to modify the statement of the citation in each claim section of the invention document based on the modified claim information, the modified claim tree, or the modified configuration claim tree. can be possible.

The patent application-related information generated and output based on the analysis results of the invention documents in the invention document analysis system 20 includes, for example, a list of key words and phrases, key word relationship information (e.g., inclusion relationship information, record relationship information, program realization relationship information, equivalent relationship information, and hierarchical concept relationship information), and important phrase relationship translation information (for example, inclusion relationship translation information, record relationship translation information, program implementation relationship translation information, equivalence relationship translation information, and hierarchical concept relationship translation information), it may be possible for translators, etc., to appropriately or efficiently determine corresponding translated words corresponding to key words. The patent application-related information as a document for display generated based on the analysis result of the invention document in the invention document analysis system 20 includes, for example, an important phrase list in which a set of translation word candidates is associated with important phrases. Display control information for providing a GUI function for determining one element from the translation word candidate set as a corresponding translation word according to an operation is added to the display elements of the set. By selecting the elements of the translation word candidate set displayed by , it is possible to efficiently determine the corresponding translation word corresponding to the key phrase.

The patent application related information generated and output based on the analysis result of the invention document in the invention document analysis system 20 includes, for example, a code list and a drawing code list, so for translators etc., important words corresponding to the code and efficiently refer to the contents of the drawings corresponding to the reference numerals.

The patent application related information generated based on the analysis result of the invention document in the invention document analysis system 20 includes, for example, claim translation information, modified claim translation information, specification translation information, and modified specification translation information, By referring to this information, the translator may be able to translate the invention document properly or efficiently.

The patent application-related information generated and output based on the analysis results of the invention documents in the invention document analysis system 20 can include, for example, claim-based drawing information, claim-based specification information, and claim-based abstract information. . As a result, for example, an inventor or a patent attorney who has created an invention document including claims and not including a specification and having the invention document analysis system 20 analyze the claim-based drawing information, the claim-based specification information, and the claim By referring to, correcting, and using the base abstract information, it is possible to efficiently generate invention documents including drawing documents, claims, specifications, and the like. For example, inventors, etc. or patent attorneys may be able to efficiently generate specifications in invention documents by correcting the incomplete message part for description support written in a prescribed format in the claim-based specification information. There is The inventor or patent attorney analyzes the invention document generated by referring to the claim-based drawing information, the claim-based specification information, and the claim-based abstract information in the invention document analysis system 20, and outputs It may be possible to modify the invention document more appropriately by referring to the patent application related information.

The patent application-related information generated and output based on the analysis results of the invention documents in the invention document analysis system 20 includes, for example, technical field information, fee information, and aggregate information, so that inventors or patent attorneys can , may revise the invention document as necessary by referring to the patent application related information.

The invention document analysis system 20, for example, generates and outputs an invention document based on the acquired invention document standard specification for translation, in the warning information of the patent application related information, which publishes the invention document standard specification for translation. The prescribed access information required to access the standard specifications for invention documents for translation, such as the network address of the site, may also be included. As a result, the translator or the like can access the invention document standard specification for translation and view its contents by referring to the specified access information in the warning information.
The invention document analysis system 20 acquires, for example, a new version of the invention document standard specification for translation if it is available, and generates and outputs the invention document based on the acquired invention document standard specification for translation. The informational warning information includes, for example, version information indicating the version of the used invention document standard specification for translation. As a result, it is possible to respond to the refinement and revision of the standard specifications for invention documents for translation over time, and translators, etc. can refer to the version information of the standard specifications for invention documents for translation in the warning information to determine which version It becomes possible to confirm whether the invention document standard provisions for translation of the document have been used.

The invention document analysis system 20 includes, for example, a program module responsible for determining whether or not an invention document conforms to each of a plurality of items of the invention document standard specifications for translation, and a process for extracting important words. Each plug-in module such as a program module is acquired and used, version information of the plug-in module is managed, and if a new version of the plug-in module is available, it is acquired and used. As a result, new plug-in modules that have been refined over time are used, and it may be possible to perform various processes more appropriately.

A learning model output unit 2081 that outputs various learning models generated by the machine learning unit 207 of the invention document analysis system 20 outputs, for example, a learning model for specifying a technical field. By using this technical field identification learning model, it is possible to identify the technical field to which the invention document belongs by performing predetermined arithmetic processing with the important phrase group extracted from the invention document as input. .

The learning model output unit 2081 of the invention document analysis system 20 outputs the learning model for important phrase translation generated by the machine learning unit 207, for example. By using this learning model for translating important phrases, it is possible to obtain machine translation results for the important phrases by inputting each of the important phrases extracted from the invention documents and performing predetermined arithmetic processing. obtain.

The learning model output unit 2081 of the invention document analysis system 20 outputs the learning model for translation generated by the machine learning unit 207, for example. By using this learning model for translation, it is possible to obtain the result of machine translation of the invention document by performing predetermined arithmetic processing with the invention document as an input.

The invention document analysis system 20 classifies invention documents into groups by the classification unit 2053 based on, for example, the correlation between key phrase groups extracted from each of a plurality of invention documents by the key phrase extraction unit 2051, or on the basis of designation by the user. , and the machine learning unit 207 generates a learning model for translating key words for each group by machine learning using a plurality of sets of key words extracted from invention documents and corresponding translation words as training data. As a result, it is possible to machine-translate each of the important phrases in the invention document by arithmetic processing using the important phrase translation learning model adapted to the group to which the invention document belongs. Further, the invention document analysis system 20 machine-translates the key words extracted from the invention documents by, for example, arithmetic processing using the key word translation learning model adapted to the group to which the invention documents belong, and the key words and their It is also possible to output patent application related information including a list of important words and phrases listing pairs with translation word candidate sets including machine translation results. By referring to this key phrase list, the translator may be able to efficiently or properly translate the key phrases of the invention document. The invention document analysis system 20 may generate a learning model for important phrase translation without performing group classification. Even if a learning model for important phrase translation that is not classified into groups is used, there is a possibility that appropriate machine translation of important phrases in invention documents can be realized.

The invention document analysis system 20 classifies invention documents into groups by the classification unit 2053 based on, for example, the correlation between key phrase groups extracted from each of a plurality of invention documents by the key phrase extraction unit 2051, or on the basis of designation by the user. , and the machine learning unit 207 generates a translation learning model for each group by machine learning using pairs of the invention document and the corresponding translation result document as training data. As a result, for example, in a machine translation system or the like, it is possible to machine-translate an invention document by arithmetic processing using a translation learning model suitable for the group to which the invention document belongs among the translation learning models for each group. In addition, the invention document analysis system 20 machine-translates at least a part of the invention document by arithmetic processing using, for example, a translation learning model suitable for the group to which the invention document belongs among the translation learning models for each group. , the patent application related information including the machine translation result may be output. By referring to such machine translation results of the invention document, the translator may be able to translate the invention document efficiently or properly. The invention document analysis system 20 may generate a learning model for translation without performing group classification. Appropriate machine translation of invention documents may be realized even if a learning model for translation that is not classified into groups is used.

The invention document analysis system 20, for example, analyzes an invention document used for accumulating teacher data for machine learning for generating a learning model for translation or a learning model for important phrase translation, according to the evaluation result by the document evaluation unit 2071. This may allow generation of an appropriate learning model for translation or a learning model for important phrase translation. Being able to generate an appropriate learning model for translation or a learning model for important phrase translation can be useful in improving the accuracy of machine translation using these learning models.

The invention document analysis system 20, for example, is a set of a modified invention document generated based on the invention document and a translation result document, or for each sentence of the modified invention document, the sentence and the translation corresponding to that sentence. A combination of the resulting document and the sentence may be used as teacher data for machine learning, which may generate a more appropriate learning model for translation. The invention document analysis system 20, for example, removes the code from the invention document and the translation result document used for the training data to obtain the training data. It is possible to suppress the discrepancy between the contents of both documents that occurs when a document is created, and it is possible to generate an appropriate learning model for translation. can be useful for improvement.

The invention document analysis system 20 is configured, for example, by installing an invention document analysis processing program for executing invention document analysis processing as illustrated in FIG. 40 in a device having a microprocessor. When the invention document analysis processing program is started in the invention document analysis system 20, the invention document analysis processing is executed. The invention document analysis processing program may contain data used for the invention document analysis processing. For a translator or the like, referring to the information output by the invention document analysis process (for example, patent application-related information as a display document) may facilitate understanding of the invention document. Facilitating the understanding of the invention document is useful for translators to translate the invention document appropriately or efficiently.

(other embodiments, etc.)
As described above, the invention document analysis systems 10 and 20 and the like have been described in the first and second embodiments as examples of the technology of the present disclosure. However, the technology in the present disclosure is not limited to this, and can be embodied as an embodiment in which modifications, replacements, additions, omissions, etc. are made as appropriate to the first or second embodiment described above.

In the above-described embodiments, the invention document analysis systems 10 and 20 acquire setting information, invention document standard specifications for translation, important phrase setting dictionaries, invention documents, drawing documents, translation result documents, and the like. Acquisition of such various types of information may be realized by any method. Acquisition of various types of information may be achieved, for example, by receiving an information signal from an external communicable device, or by reading information from a removable recording medium such as a memory card. , keyboard, mouse, voice input device or other input device to acquire information input from the user (for example, inventors, patent attorneys, translators, etc.), including imaging by an image sensor Acquisition of information as a result of sensing by various sensors may be possible. Further, in the above-described embodiments, the invention document analysis systems 10 and 20 exemplify receiving operations on the operation-responsive GUI elements in the document for display. good. Acceptance of operation is, for example, by acquiring some information input from a user (for example, inventors, patent attorneys, translators, etc.) via a keyboard, pointing device, touch pad, voice input device, or other input device. Alternatively, it may be acquisition of some information (for example, a predetermined gesture) obtained from the user as a result of sensing by various sensors including imaging by an image sensor. Also, the users shown in the above embodiments are not necessarily limited to humans, and may be robots or the like having functions similar to some functions of humans.

Also, the above-described functional allocation of each part in the invention document analysis systems 10 and 20 described above is merely an example, and can be changed arbitrarily, and a plurality of parts may be integrated. Further, the invention document analysis systems 10 and 20 perform part of invention document analysis processing, processing related to generation of various learning models, etc. to an external device capable of communicating with the devices constituting the invention document analysis systems 10 and 20. You can share it. In addition, all or part of the function of each part in the invention document analysis system 10, 20 is implemented by IC (Integrated Circuit), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), LSI (Large Scale Integration), etc. It may be realized by a semiconductor device, and the semiconductor device may include a memory and a microprocessor in which a program for realizing all or part of the functions of each part is recorded. All or part of the various processes in the invention document analysis systems 10 and 20 may be realized by hardware such as a dedicated electronic circuit, or may be realized by using a microprocessor and software (for example, programs and information used in the programs). may A program (for example, an invention document analysis processing program) for realizing all or part of the processing of the invention document analysis systems 10 and 20 is recorded on a non-temporary recording medium such as a computer-readable ROM, optical disk, or hard disk. may be distributed or distributed as When a program for realizing all or part of the processing of the invention document analysis system 10, 20 is distributed, the program is installed on a device equipped with a microprocessor, and the microprocessor of the device on which it is installed By executing it, it is possible to cause the device to perform all or part of the processing. The program may be stored in advance in a recording medium provided in the invention document analysis systems 10 and 20, or may be distributed and supplied to the recording medium via a wide area communication network including the Internet. may Also, a computer may be regarded as a device having a microprocessor, regardless of how the computer performs processing. Also, the program for realizing all or part of the processing of the invention document analysis systems 10 and 20, such as the invention document analysis processing program, may be a program written in any language, an interpreter, a runtime It may be a program executed via a compiler (Just-In-Time Compiler) or the like, or a program that operates on an OS or various existing execution environments. In addition, the invention document analysis processing program may consist of a plurality of programs, each of which may be distributed on a plurality of computers and run on a plurality of execution environments different from each other. may be In order to implement all or part of the processing of the invention document analysis systems 10 and 20, a plurality of programs written in different languages may work together.

In addition, the above-described invention document analysis system 20 extracts a plurality of key phrases from the claim of the invention document by the key phrase extraction unit 2051, and based on the structural inclusion relationship between the elements represented by each of the extracted plurality of key phrases, Then, a code determination process is executed to determine codes corresponding to some of the plurality of important phrases, and various relationships between elements represented by each of the extracted plurality of important phrases (for example, relationships represented by important phrase relation information) Based on, for each drawing that can be specified by a drawing number, execute a drawing content determination process for determining key words related to the content to be described in the drawing, and each key word extracted from the claim of the invention document, Based on the results of the code determination process and the drawing content determination process, a specification content determination process for determining the contents to be described in the specification, and outputting the specification of the contents determined by the specification content determination process Description content output processing may be executed. In the specification content determination process, the invention document analysis system 20 generates an invention name character string that is the content of the "Title of invention" column based on key words that are claimed in the claims of the invention document. Based on the results of the determination process and the drawing content determination process, for each key phrase related to the content to be described in each drawing in the order of the drawing number, a code is attached to the key phrase, and the attribute of the key phrase (for example, (attribute represented by the attribute information shown in FIG. 19) (for example, a sentence attached to the key phrase in the key phrase setting dictionary, or a sentence including an incomplete message for writing support) may be generated as the contents of the "Mode for Carrying Out the Invention" column. Further, the invention document analysis system 20 extracts a plurality of key phrases from the invention document using the key phrase extraction unit 2051, and if there is a structural inclusion relationship between the elements represented by each of the extracted plurality of key phrases, For example, inclusion relationship information (see FIG. 20), such as a diagram representing inclusion relationships between elements, may be output. In addition, the invention document analysis system 20 generates a claim tree including lines or symbols representing citation relationships between claim terms based on the claims of the invention document, and the lines representing citation relationships between claim terms. Or display the claim tree using symbols as GUI elements, and according to the user's operation on the GUI elements, the content of the claim that cuts the citation relationship between the claims represented by the lines or symbols related to the GUI elements. It is also possible to generate modified claim information containing each term and output the modified claim information. In addition, the invention document analysis system 20 extracts a plurality of key phrases from the claim of the invention document using the key phrase extraction unit 2051, and displays each of the extracted plurality of key phrases in a different display mode (for example, display mode in which a left border line with a different color and width is added to key phrases), and the invention document including the key phrases related to the GUI element in response to the operation of the GUI element by the user It is also possible to display a list listing each line or sentence of the GUI element, or to display an invention document other than the invention document (for example, It is also possible to display a list listing each line or each sentence in the invention document specified by the user, or it is included in the important phrase management information (see FIG. 18) about the important phrases related to the GUI element. Information may be displayed. In addition, the invention document analysis system 20 displays specification information representing the specification of the invention document, displays the code in the specification information as a GUI element, and displays the GUI element according to the user's operation on the GUI element of the code. It is also possible to display the drawing in which the code is described or the drawing number of the drawing in the drawing document containing the code.

Further, when the translation result document acquisition unit 2023 acquires a translation result document generated as a result of translation based on the invention document, the invention document analysis system 20 described above outputs translation result information representing the translation result document. It may be included in the patent application related information as a display document such as an HTML document output by the unit 208 . In this case, the invention document analysis system 20, for each key phrase extracted from the invention document by the key phrase extraction unit 2051, translates the translated phrase in the translation result document corresponding to the key phrase into the key phrase translation model. Based on the result of machine translation based on, the translation result of the document for display is specified by arithmetic processing based on key phrase setting dictionary, translation auxiliary information, etc., or by searching for descriptions with the same sign as key phrase Display control information added to the display element of the key phrase in the claim information portion, specification information portion, etc. of the document for display, and the display element of the specified translated phrase in the information portion as a display element. It is also possible to add display control information for controlling a similar display mode (for example, highlighting by adding a colored left boundary line with the same display color, making display elements into operation-responsive GUI elements, etc.). By turning display elements of translated words corresponding to key words into operation-responsive GUI elements, all translated words corresponding to the same key word are replaced with user-specified words by a function activated in response to an operation. It may be possible to realize processing such as When the invention document analysis system 20 includes the translation result information in the patent application-related information as a display document such as an HTML document output by the output unit 208, the heading whose description format is fixed in the translation result information (e.g. headings of claims, paragraph numbers of descriptions) are used as display elements, and corresponding display elements in the display elements of the headings correspond to the corresponding claim information, description information, etc. according to the operation. Display control information for displaying GUI elements (for example, the content of the corresponding claim section, the content of the corresponding paragraph of the specification, etc.) may be added. For example, when the translation result information is displayed in the "content display column of the item of the patent application related information corresponding to the menu selection" shown in FIG. is operated (for example, a mouse click operation), the corresponding paragraph number part in the specification information is displayed in the "display field for matters corresponding to the operation of the operation-responsive GUI element" shown in FIG. It is possible to define script functions related to display control information added to display elements. For example, the translator can check the validity of the translation result document and respond to important phrases by viewing and operating the display content in the translation result information part of the patent application related information as a display document displayed on a browser etc. It may be possible to efficiently correct translated words and phrases. In addition, the invention document analysis system 20 determines the number of claims in the translation result document, the number of lines, the number of sentences, the number of paragraphs, etc. in the specification of the translation result document, or the number of lines, the number of sentences in the translation result document, etc. number of words, the number of all words, etc., or the number of translation words and phrases corresponding to the important words and phrases in the description of the embodiment of the specification in the translation result document, or the number of code descriptions in the translation result document, etc. Then, each count result may be expressed in an identifiable manner and included in the tally information in the patent application related information output by the output unit 208 . For example, the translator can compare the number of lines of the specification in the invention document with the number of lines of the specification in the translation result document by referring to the aggregated information of the patent application related information. It may be possible to efficiently confirm validity and the like.

In addition, the invention document analysis system 20 described above executes invention document analysis processing. Acquire an invention document, which is a document describing claims or specifications for a patent application expressed in Japanese, perform analysis processing to analyze the invention document based on the setting information, and generate based on the analysis processing result The analysis process includes an extraction process for extracting important words from the invention document based on the condition information, and the output process includes a plurality of important words extracted by the extraction process. Information generated based on each word may be output.

Further, the scope of the present disclosure also includes forms realized by arbitrarily combining the components and functions shown in the above-described embodiments.

(Modification Group 1)
The invention document analysis system according to the present disclosure includes a setting information acquisition unit that acquires setting information including condition information indicating conditions for extracting key phrases, and claims or specifications for patent applications expressing technical ideas in Japanese. A document acquisition unit that acquires an invention document that is a written document, an analysis unit that analyzes the invention document acquired by the document acquisition unit based on the setting information, and an invention document acquired by the document acquisition unit and an output unit for outputting information generated based on the analysis result by the analysis unit, wherein the analysis unit extracts key phrases based on the setting information from the invention document acquired by the document acquisition unit. An invention document analysis including an important phrase extraction unit, wherein the output unit outputs information generated based on each of a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit. System.

Here, for example, the condition information includes key word candidate character string pattern information indicating key word candidate character string patterns representing character string patterns that are key word candidates, and key word candidate character string pattern information used to refer to previously described character strings. and reference character string pattern information indicating a reference character string pattern representing a reference character string pattern, wherein the important phrase extracting unit extracts information corresponding to the reference character string pattern from the invention document acquired by the document acquiring unit. a first extraction unit for extracting a character string identical to the second character string as an important phrase when a second character string corresponding to the important phrase candidate character string pattern exists subsequent to the first character string, , when a claim is included in the invention document acquired by the document acquisition unit, and a period character exists following the third character string corresponding to the important phrase candidate character string pattern in the claim , and a second extraction unit that extracts the same character string as the third character string as an important phrase.

As a result, for example, when there is an expression that refers to a word in the invention document, the key word extraction unit treats the referenced word as a key word under certain conditions, and Because words and phrases are treated as key words under certain conditions, words that are written with enough attention to reference and words that describe the claimed subject matter of a claim may be treated as key words. It is assumed that there is a good tendency to have punctuation following the claimed subject matter in the claims of ordinary invention documents. Therefore, information can be output by the output unit based on the key phrases that the invention document analysis system presumes to be important in the invention document, so the output information can be useful.

Further, for example, the condition information includes code string pattern information indicating a code string pattern representing a pattern of a code string appended after a character string representing an element name, and a character string that is a predetermined particle. and specific particle character string pattern information indicating a specific particle character string pattern representing a string pattern, wherein the important phrase candidate character string pattern information includes at least a predetermined character string whose first character is a Chinese character, and the first character. is determined to correspond to the key phrase candidate character string pattern, and the reference character string pattern information is such that at least the character string "said" is the reference character string pattern and the coded character string pattern information is defined so that at least a predetermined character string whose first character is a number corresponds to the coded character string pattern, and the specific particle In the character string pattern information, at least any character of "wo", "ni", "ga", "to", "from", "he" and "wa" corresponds to the specific particle character string pattern. The important phrase extraction unit extracts the code character string pattern following the fourth character string corresponding to the important phrase candidate character string pattern from the invention document acquired by the document acquisition unit. a third extraction unit for extracting a character string identical to the fourth character string as an important phrase when a fifth character string corresponding to When the sixth character string corresponding to the candidate character string pattern is followed by the seventh character string corresponding to the specific particle character string pattern, the character string identical to the sixth character string is extracted as an important phrase. A fourth extractor may be included.

As a result, the important phrase extraction unit treats, for example, phrases (for example, noun phrases) that precede a predetermined particle in the invention document as important phrases under certain conditions, and the phrases that are marked with a code in the invention document are treated as important phrases. Since they are treated as important words under certain conditions, relatively important words such as subjects and objects and words representing elements presumed to be illustrated in drawings related to the invention document can be treated as important words. Since the invention document is written in Japanese, it is quite possible that words starting with kanji or katakana are key words. Therefore, since the invention document analysis system can output information by the output unit based on key phrases estimated to be important in the invention document, the output information can be useful.

Further, for example, the output unit outputs patent application-related information generated based on the analysis result of the analysis unit for the invention document acquired by the document acquisition unit, and the patent application-related information is the document For each of the plurality of key phrases extracted by the key phrase extraction unit from the invention document acquired by the acquisition unit, information obtained by adding additional information related to the key phrase to the key phrase may be included. Examples of additional information include highlighting related to important phrases, display with additional information, display control information for executing display transition and other processing, corresponding translated words corresponding to important phrases, candidates for corresponding translated words for important phrases, etc. Examples include a translation word candidate set as a set, attribute information of key words and phrases, and the like.

As a result, by obtaining the patent application-related information output by the invention document analysis system, translators, etc., can grasp multiple important words and phrases in the invention document, and the translator can use the additional information to translate the invention document. In this way, it may be possible to efficiently or properly determine a translated phrase corresponding to a key phrase, which is the target language of the same meaning as the key phrase.

Further, for example, in the patent application related information, the additional information related to each of the key words and phrases added to each of the plurality of key words and phrases extracted from the invention document acquired by the document acquisition unit is the key word and phrase It may be translated word information as information on a corresponding translated word, which is a translated word expressing the meaning of . A translated phrase is, for example, a phrase expressed in one kind of language other than Japanese (for example, English, Chinese, etc.). The translation word information may be, for example, information representing the corresponding translation word itself, or information representing a translation word candidate set as a set of candidates for the corresponding translation word.

As a result, by referring to the translation word information included in the patent application-related information output by the invention document analysis system, the translator can efficiently or appropriately determine translation words corresponding to important words. obtain.

Further, for example, for each of the important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit, the analysis unit obtains a translation word which is a set of corresponding translation word candidates for the relevant important phrase. a translation word candidate set identification unit for identifying a candidate set, wherein the translation word information as the additional information related to the key words of the invention document acquired by the document acquisition unit is obtained by the translation word candidate set identification unit; may include translation word candidate information representing a translation word candidate set for the relevant important phrase specified by .

As a result, by referring to the translation word candidate information included in the patent application related information output by the invention document analysis system, the translator can select one translation word from the translation word candidate set corresponding to the important word. , it may be possible to efficiently or properly determine translation terms corresponding to key terms.

Further, for example, the document acquisition unit acquires a plurality of invention documents including a first invention document, and the analysis unit extracts a plurality of key phrases by the key phrase extraction unit for each of the plurality of invention documents. A classifying unit that extracts word groups and performs group classification for specifying to which of a plurality of groups each of the plurality of invention documents belongs, based on the correlation between the extracted groups of important words and phrases. , the translation word candidate set identifying unit, for each of the plurality of groups, among bilingual dictionary information for each group, which associates Japanese words and phrases in invention documents belonging to the group with words and phrases in a language to be translated, using the bilingual dictionary information of the group to which the first invention document belongs according to the group classification of the classification unit, translation of each of the important phrases extracted from the first invention document by the important phrase extraction unit. Identification of a set of word candidates may also be performed.

As a result, in the invention document analysis system, the bilingual dictionary information of the group suitable for the invention document is used, so that a suitable set of translation word candidates can be specified for the key words.

Further, for example, the classification unit uses the result of extracting a group of key phrases by the key phrase extraction unit from each of one or more invention documents known to be related to each of a plurality of technical fields. any one of the plurality of technical fields in which the correlation with the group of key words and phrases extracted from the first invention document by the key word extraction unit is equal to or greater than a predetermined degree; A technical field specifying unit for specifying a first technical field corresponding to the first invention document, wherein the translation word candidate set specifying unit specifies, for each of a plurality of technical fields, Japanese words and phrases in the relevant technical field and the translation destination language Using the bilingual dictionary information for the first technical field identified by the technical field identifying unit from among the bilingual dictionary information for each technical field associated with the words of the first invention document, the important A translation word candidate set may be specified for each of the important words extracted by the word extracting unit.

As a result, in the invention document analysis system, the bilingual dictionary information corresponding to the technical field to which the invention document belongs is used, so that an appropriate set of translation word candidates can be specified for the key words.

Further, for example, the patent application-related information includes, as content to be displayed, each of a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit. The additional information related to the important phrase extracted from the invention document, which is output as a document (for example, an HTML document), is obtained by manipulating any element of the translation word candidate set for the relevant important phrase. Display control information for displaying the translation word candidate set as a GUI element so as to be selectable, and the display control information included in the additional information related to the important phrase is displayed as the GUI element. a script for executing a determination process for determining an element selected in accordance with an operation from the translation word candidate set for the relevant important phrase in the state of being a corresponding translated word corresponding to the relevant important phrase; a script for executing a process of generating and outputting translation assistance information, which is information that associates each important phrase whose corresponding translated word is determined as a result of the process with the corresponding translated word; and the translation word candidate set identification unit, for each of the one or more invention documents other than the first invention document acquired by the document acquisition unit, based on the analysis result of the invention document by the analysis unit Generated for each important phrase in each of the one or more invention documents as a result of outputting the display document related to the generated patent application related information to the output unit and using it for display The translation word candidate set may be identified for each of the important phrases extracted by the important phrase extraction unit from the first invention document based on the translation auxiliary information.

As a result, the translator can easily determine the corresponding translation word corresponding to the important word from the translation word candidate set by selecting the GUI element of the document for display. Further, the translator can easily obtain the determined corresponding translation word from the display contents of the display document by a browser or the like by so-called copy & paste, so-called cut & paste, or the like. In addition, copy & paste or cut & paste generally selects data to be copied (i.e. duplicated) or cut (i.e. By this operation, the data to be copied or cut is held in a predetermined memory area under the control of the OS, etc., and by the paste operation, the data is transferred from the predetermined memory area to the paste destination. is pasted at the specified location. In addition, the result of the translator's selection of the GUI elements of the document for display subsequently improves the validity of identifying a translation word candidate set corresponding to the key words by the invention document analysis system via the translation auxiliary information. there is a possibility.

Further, for example, the patent application-related information includes, as content to be displayed, each of a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit. The additional information related to the key words and phrases that are output as a document and are extracted from the invention document make it possible to select any element of the translation word candidate set for the key words and phrases according to an operation. , display control information for displaying the translation word candidate set as a GUI element, and the display control information included in the additional information related to the important phrase is a A script for executing a determination process for determining an element selected according to an operation from the translation word candidate set for the word as a corresponding translated word corresponding to the key word, and correspondence as a result of the execution of the determination process. and a script for executing a process of generating and outputting translation assistance information, which is information in which each key phrase for which a translation word has been determined is associated with the corresponding key phrase and the corresponding translation word. .

As a result, the translation assistance information output by the invention document analysis system can be utilized, and this utilization can improve the validity of subsequent identification of the translation word candidate set corresponding to the important phrase by the invention document analysis system. can be possible.

Further, for example, the document acquisition unit acquires a plurality of invention documents, and the output unit displays each of the display documents output for each of the plurality of invention documents acquired by the document acquisition unit. generated by machine learning using pairs of key phrases and corresponding translation words in each of the plurality of translation auxiliary information generated as a result as training data for machine learning for translation of key phrases A learning model output unit for outputting a learning model for translation of important phrases, which is a learning model, may be included.

As a result, the machine translation of the important phrases in the invention document can be realized by the arithmetic processing of inputting the important phrases using the learning model for the translation of the important phrases. By referring to the results of this machine translation, the translator may be able to efficiently or properly determine the translated words for the important words in the invention document.

Further, for example, the patent application-related information includes, as content to be displayed, each of a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit. The setting information includes information for specifying an important phrase setting dictionary listing important phrases to be extracted, and in the important phrase setting dictionary, for at least some of the listed important phrases, The invention document analysis system includes an important phrase setting dictionary acquisition unit that acquires the important phrase setting dictionary based on the setting information, and the important phrase extraction unit includes the important phrase extraction unit. When the important phrases listed in the phrase setting dictionary are included in the invention document acquired by the document acquisition unit, the important phrases are extracted from the invention document, and the important phrase extraction unit extracts the important phrases When an important phrase associated with a corresponding translated word in the phrase setting dictionary is extracted from the invention document acquired by the document acquisition unit, the important phrase extracted from the invention document in the patent application related information The additional information related to the phrase represents the corresponding translated word, and the important phrase extracting unit extracts important phrases other than the important phrases associated with the corresponding translated word in the important phrase setting dictionary from the document acquisition unit. When extracted from the acquired invention document, the additional information related to the key phrase extracted from the invention document in the patent application related information is any of a translation word candidate set of the key phrase display control information for displaying the translation word candidate set as a GUI element so that the element of can be selected according to the operation, and the display control information is displayed as the GUI element, A script for executing a determination process for determining an element selected in accordance with an operation from the translation word candidate set for the key word as a corresponding translation word corresponding to the key word, and a result of the determination process and a script for executing update processing for updating the important phrase setting dictionary so as to include information in which each important phrase for which a corresponding translated word has been determined is associated with the relevant translated word and the corresponding translated word. may be

As a result, for example, when an inventor, etc. or a patent attorney who created an invention document wants to define specific words as key words, or when he wants to define corresponding translations for key words, he or she can set key words and phrases. By generating a dictionary in advance, the invention document analysis system can output appropriate patent application related information. Therefore, the translator may be able to translate the invention document efficiently or properly by referring to the patent application-related information. In addition, by creating a key phrase setting dictionary in cases such as when the translator has defined corresponding translation words for key phrases, invention documents provided by inventors or patent attorneys can be processed by the invention document analysis system. Appropriate patent application-related information can be output when analyzed.

Further, for example, the document acquisition unit acquires a first invention document and a plurality of invention documents other than the first invention document, and the document acquisition unit further acquires each of the acquired plurality of invention documents. Obtaining a translation result document, which is a translation result of an invention document, the analysis unit extracts a group of key phrases, which are a plurality of key phrases, by the key phrase extraction unit for each of the first invention document and the plurality of invention documents. Then, based on the correlation between the groups of important words and phrases extracted from each group, the classifying unit performs group classification for specifying to which of a plurality of groups the first invention document and each of the plurality of invention documents belong. and the translation word candidate set identification unit extracts from the plurality of invention documents belonging to the group identified by the group classification of the classification unit to which the first invention document belongs and the corresponding translation result documents , Key phrase translation learning, which is a learning model generated by machine learning using multiple pairs of key phrases and corresponding translation words corresponding to the key phrases as training data for machine learning for key phrase translation. The machine translation using the model may specify the elements of the translation word candidate set for each key phrase extracted by the key phrase extraction unit from the first invention document.

As a result, the invention document analysis system can appropriately identify a translation word candidate set.

Further, for example, the patent application-related information is output as a document for display, and when claims are included in the invention document acquired by the document acquisition unit, the patent application-related information is output as the document for display. and the claim information representing the content of the claim of the invention document acquired by the document acquisition unit is extracted from the invention document by the key phrase extraction unit. Display control information for controlling the display mode of the key phrase may be included as the additional information related to the key phrase for each of the multiple key phrases in the claim.

As a result, for example, a translator or the like may be able to identify important words and phrases whose display mode is controlled in the claim information of the patent application related information related to the document for display displayed by the browser or the like.

Further, for example, for each of a plurality of key words in the claim extracted by the key word extracting part, the claim information representing the content of the claim of the invention document acquired by the document acquiring part contains The display control information as the related additional information is further added with information for displaying the degree of importance, attribute information, a corresponding translation word or a set of translation word candidates, or the search result of the relevant important phrase for the relevant important phrase. Information for display and information for displaying the key phrase as a GUI element for executing the information-added display related to the key phrase according to an operation may be included. The key phrase search may be, for example, a search within the invention document, a search within another invention document, or a search at a search site or the like on a network such as the Internet.

As a result, translators, etc., who view claim information in the patent application-related information related to display documents displayed on a browser, etc., can access information such as importance, attribute information, search results, etc. by operating the displayed key words. As such, it may be possible to efficiently or properly understand key terms in an invention document. This may allow the translator to efficiently or properly determine translation terms for key terms.

Further, for example, when the display document is an HTML document including an HTML file written in HTML (Hypertext Markup Language), and a specification is included in the invention document acquired by the document acquisition unit, , the patent application related information includes specification information representing the content of the specification to be displayed in the display document, and the specification representing the content of the specification of the invention document acquired by the document acquisition unit; The information is, as the additional information related to each of the key words in the specification extracted by the key word extracting unit from the invention document, display control for controlling the display mode of the key words. The display control information for controlling the display mode of each of the plurality of important phrases extracted by the important phrase extraction unit in the claim information and the specification information, including information, is the display including highlighting information for making the display mode of the key phrase corresponding to the control information different from the display mode of words and phrases other than the plurality of key phrases in the claim information and the specification information; Each of the display control information for controlling the display mode corresponding to each of a plurality of key words and phrases having different character strings constituting the words is arranged to display each of the plurality of key words and phrases in different display modes. the display control for controlling the display mode of each of the plurality of key phrases extracted by the key phrase extracting unit in the specification information, including identification information different from each other, for controlling If the relevant important phrase is the same as any of the multiple important phrases in the claim extracted by the important phrase extraction unit in the claim information, the information is such that if the relevant important phrase is the same as the same Displayed in the same display mode as the key phrase, and if the key phrase is different from any of the plurality of key phrases in the claim extracted by the key phrase extraction unit in the claim information, the key phrase is displayed. , and information for controlling to display in a display mode different from any of the plurality of important phrases in the complaint information.

As a result, a translator or the like can browse the patent application-related information as a display document, which is an HTML document, using a PC, smartphone, or other computer equipped with an HTML-compatible browser. Translators, etc., who have viewed the patent application-related information as a display document displayed by a browser, etc., may find that each key phrase described in the specification information in the patent application-related information is the key phrase described in the claim. It is possible to identify whether a plurality of important phrases are the same or different, and it may be possible to quickly grasp whether a plurality of important phrases are the same or different, depending on the display mode of each of the important phrases. In addition, in the invention document analysis system, if, for example, highlighting (for example, displaying in bold) is performed as a control of the display mode of the important words, the translator, etc. can quickly grasp the important words in the claim information. can be.

Further, for example, the claim information representing the content of the claim of the invention document acquired by the document acquisition unit may include the key phrases in the content of the claim in addition to the content of the claim to be displayed in the document for display. For each of the plurality of key words extracted by the extracting unit, the invention document includes content in which the part of the key word in the content of the claim is replaced with a corresponding translated word or a set of candidate translation words corresponding to the key word. The specification information representing the content of the specification includes, in addition to the content of the specification to be displayed in the display document, each of a plurality of key phrases extracted by the key phrase extraction unit in the content of the specification. , the part of the relevant key phrase in the content of the specification may be included in the corresponding translation word or translation word candidate set corresponding to the relevant key phrase.

As a result, the translator can efficiently translate the invention document by editing the part where the important words in the claim information and specification information are replaced with the corresponding translated words or a set of candidate translated words. can be.

Further, for example, the document acquisition unit further acquires a drawing document corresponding to the invention document acquired by the document acquisition unit, and a drawing document generated based on the analysis result of the invention document acquired by the document acquisition unit An element name described with a code added in the invention document, among a plurality of key phrases extracted from the invention document by the key phrase extraction unit, in the claim information or the specification information of the patent application related information , the display control information as the additional information related to the important phrase is to display the important phrase in the drawing document corresponding to the invention document according to the operation. It may include information for displaying as a GUI element for displaying the part in which the code related to the word is described.

As a result, translators, etc., who have browsed the patent application-related information related to the display document displayed by a browser, etc., can operate the GUI elements of the key words displayed in the claim information or the specification information, and , the part corresponding to the element represented by the important phrase can be displayed and confirmed, and the important phrase can be understood efficiently or properly.

Further, for example, the output of the patent application-related information by the output unit is performed by displaying the patent application-related information, and when the invention document acquired by the document acquisition unit contains a claim, The patent application related information includes claim information representing the content of the claim, and the claim information representing the content of the claim of the invention document acquired by the document acquisition unit contains the relevant information extracted by the key phrase extraction unit. For each of the plurality of key words in the claim, the additional information related to the key word indicates a color to be added to the key word, and the specification is included in the invention document acquired by the document acquisition unit. In the case, the patent application related information includes specification information representing the content of the specification, and the specification information representing the content of the specification of the invention document acquired by the document acquisition unit includes the important The additional information related to each of the key phrases in the specification extracted by the phrase extraction unit indicates the color added to the key phrase, and the output unit extracts the claim information and The display mode of the plurality of key phrases extracted by the key phrase extraction unit in the description information is displayed in a manner different from the display mode of the phrases other than the plurality of key phrases, and the output unit displays a plurality of key phrases extracted by the key phrase extracting unit and having different character strings constituting the key phrases are displayed in different colors, and the output unit outputs the specification information; for each of the plurality of key phrases extracted by the key phrase extraction unit in the above, if the key phrase is the same as any of the plurality of key phrases extracted by the key phrase extraction unit in the claim information, the specification The key phrase in the information is displayed in the same display color as the same key phrase in the claim information, and the key phrase in the specification information is extracted by the important phrase extraction unit in the claim information. If it is different from any of the plurality of key phrases, the key phrase in the description information is displayed in a display mode different from any of the plurality of key phrases in the claim information, and the output unit displays the claim For each of the plurality of key phrases extracted by the key phrase extraction unit in the information, the key phrase is displayed as a GUI element for executing information addition display related to the key phrase in response to an operation, The information-added display may be to display the degree of importance, attribute information, corresponding translated words, a set of translated word candidates, or search results for the important words/phrases. Addition of color to important phrases includes, for example, addition of character color to important phrases, addition of character background color to important phrases, all sides or any one side of a rectangular frame surrounding the important phrases, colored line width , and the like.

As a result, translators, etc., who view the patent application-related information as a document for display displayed by a browser, etc., can determine whether or not each key phrase indicated in the patent application-related information is the key phrase described in the claim. can be identified, and whether a plurality of key words are the same or different can be quickly grasped by the color added to each key word.

Further, for example, the invention document analysis system includes an invention document standard specification acquisition unit for acquiring an invention document standard specification for translation that defines a plurality of conditions to be satisfied by an invention document to be translated, and the analysis unit , determining whether or not the invention document acquired by the document acquisition unit satisfies at least part of each of the plurality of conditions defined in the invention document standard specification for translation; Based on the results, warning information is generated for pointing out potentially inappropriate parts in the invention document, and the patent application-related generated based on the analysis results of the invention document by the analysis unit The information may include the warning information.

Accordingly, by referring to the patent application-related information output by the invention document analysis system, the inventor or the like or the patent attorney who prepared the invention document can correct the invention document if necessary. In addition, the translator, for example, receives invention documents to be translated and patent application-related information from the inventors, etc. or patent attorneys, so that even if the warning information in the patent application-related information remains pointed out, Since it can be presumed that the inventor, etc. or the patent attorney determined that there is no particular need to deal with the indication, it is possible to obtain an appropriate invention document to be translated, and as a result, the translation of the invention document can be done efficiently or properly.

Further, for example, the warning information in the patent application-related information generated based on the analysis result of the invention document is invention document evaluation information indicating conformity of the invention document to the invention document standards for translation. may be included. Suitability is represented, for example, by an evaluation value or the like as a result of suitability evaluation.

Accordingly, by referring to the invention document evaluation information included in the patent application related information output by the invention document analysis system, the inventor or patent attorney may be able to appropriately correct the invention document. Further, by checking the invention document evaluation information, the translator can recognize whether or not the invention document is suitable for translation. Invention documents that include inappropriate descriptions, for example, are likely to cause translation errors, and it is possible that a translator may revise and translate the invention document in order to obtain appropriate rights (for example, to obtain patent rights). . Therefore, if the warning information in the patent application-related information generated based on the invention document includes invention document evaluation information indicating relatively low conformity with the standard provisions for invention documents for translation, It can be judged that there is a high possibility that there may be discrepancies in content between the invention document and the translation result document, which is the result of translation based on the invention document, other than the language being different. It may be possible to determine that it is not useful to use the combination of the invention document and the translation result document as teacher data for machine learning in order to generate the translation learning model to be used.

In addition, for example, the Standard Provisions of Invention Documents for Translation represent, as information that defines conditions to be satisfied by invention documents to be translated, patterns of character strings for possibly inappropriate description parts that do not satisfy the conditions. Inappropriate character string pattern information indicating the inappropriate character string pattern obtained by the analysis unit is associated with correction information regarding a method of correcting the description part, and satisfies the conditions stipulated by the standard specification of the invention document for translation by the analysis unit. The determination as to whether or not is carried out based on whether or not there is a character string corresponding to the inappropriate character string pattern indicated by the inappropriate character string pattern information, and is defined in the Standard Provisions for Invention Documents for Translation If a character string corresponding to the inappropriate character string pattern indicated by the inappropriate character string pattern information related to the condition exists in a claim in the invention document acquired by the document acquisition unit, the patent application related information includes modified claim information generated by modifying the claim so as to satisfy the conditions based on the claim and the modification information associated with the inappropriate character string pattern information, A character string corresponding to the inappropriate character string pattern indicated by the inappropriate character string pattern information related to the conditions stipulated in the Standard Provisions of Invention Documents for Translation is included in the specification of the invention document acquired by the document acquisition unit. If it exists, the patent application related information corrects the specification to satisfy the condition based on the specification and the correction information associated with the inappropriate character string pattern information. It may include the modified version specification information generated by.

As a result, inventors, etc. or patent attorneys who have created invention documents can efficiently It may be possible to modify the invention document. In addition, the translator can efficiently or properly translate the invention document by being provided with the invention document as amended by referring to the amended claim information and the amended specification information. In addition, a translator who receives an invention document and patent application-related information from an inventor, etc. or a patent attorney and is further instructed to translate based on the amended claim information and amended specification information may It may be possible to perform the translation work efficiently or properly by referring to the revised claim information and revised specification information included in the application-related information.

In addition, for example, in the case where the invention document acquired by the document acquisition unit contains a claim, if a predetermined clause of the claim cites multiple clauses, the analysis result of the invention document The patent application-related information generated based on the Amended claim information representing the result of amending a claim and the citation relationship between each claim clause represented by the amended claim information are mapped using lines or symbols between the clause numbers of mutually quoting clauses. The representation may include the modified claim tree as the information presented.

As a result, translators who have received patent application-related information from inventors, etc. or patent attorneys and have been informed that the claims of the invention document should be translated based on the modified version of the claim information can It is possible to translate efficiently without hesitation about whether or not to correct the paragraphs quoting , and if so, how to correct them. In addition, the translator or the like can quickly grasp the citation relationship of each item of the claims represented in the modified claim information from the modified claim tree.

Further, for example, the patent application related information includes important phrase relation information indicating the relationship between each of a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit, The important phrase relationship information may include inclusion relationship information indicating structural inclusion relationships between elements represented by each of a plurality of important phrases.

As a result, translators who have obtained the patent application-related information output by the invention document analysis system can relatively quickly grasp the relationships between multiple key words in the invention document based on the key word relationship information in the patent application-related information. By grasping the relationship, it may be possible to efficiently or properly determine translation words corresponding to each key word, and as a result, it may be possible to translate the invention document efficiently or properly.

Further, for example, the document acquisition unit acquires a plurality of invention documents and a plurality of translation result documents that are translation results of each of the plurality of invention documents, and the analysis unit acquires each of the plurality of invention documents a group of key words and phrases, which are a plurality of key words and phrases, are extracted by the key word extraction unit, and based on the correlation between the groups of key words and phrases extracted, each of the plurality of invention documents belongs to which group among the plurality of groups The invention document analysis system includes, for each of the plurality of groups, for each invention document classified into the group among the plurality of invention documents, Including a machine learning unit that generates a learning model for translation, which is a learning model for machine translation, by machine learning using each set of the invention document and the translation result document that is the translation result of the invention document as training data may be

As a result, for example, in a machine translation system, an invention document analysis system, etc., the invention document is machine-translated by arithmetic processing using the translation learning model suitable for the group to which the invention document belongs among the translation learning models for each group. becomes possible.

Further, for example, the document acquisition unit acquires a plurality of invention documents and a plurality of translation result documents that are translation results of each of the plurality of invention documents, and the invention document analysis system acquires the invention to be translated. An acquisition unit for acquiring invention document standard specifications for translation that defines a plurality of conditions to be satisfied by a document; A judgment is made as to whether or not at least some of the conditions among the plurality of conditions stipulated in the Standard Provisions for Invention Documents for Translation are satisfied, and among the plurality of invention documents, the conditions for which the judgment is made are selected. A set of a document evaluation unit that selects an invention document whose degree of satisfaction exceeds a predetermined degree, an invention document selected by the document evaluation unit, and a translation result document corresponding to the invention document is used as teacher data. a machine learning unit that generates a translation learning model, which is a learning model for machine translation, by using machine learning, and the output unit outputs the translation learning model generated by the machine learning unit It is good also as including a learning model output part.

As a result, it becomes difficult to use a combination of an invention document containing inappropriate descriptions and a translation result document whose content is inconsistent with the invention document due to a translation error or the like generated based on the invention document as training data. An appropriate learning model for translation can be output from the invention document analysis system. Therefore, for example, in a machine translation system or the like, it is possible to machine-translate an invention document by arithmetic processing using an appropriate learning model for translation output from the invention document analysis system. By referring to the result of machine translation of the invention document, the translator may be able to translate the invention document efficiently or properly.

Further, for example, the invention document analysis system includes an invention document standard specification acquisition unit for acquiring an invention document standard specification for translation that defines a plurality of conditions to be satisfied by an invention document to be translated, Document standard provisions indicate inappropriate character string patterns representing the character string patterns of potentially inappropriate descriptions that do not satisfy the conditions as information that defines the conditions that the invention document to be translated should satisfy. Inappropriate character string pattern information and correction information relating to a method of correcting the description portion are associated with each other, and the invention document analysis system adds the invention document standard for translation to the invention document acquired by the document acquisition unit. If there is a character string corresponding to the inappropriate character string pattern indicated by the inappropriate character string pattern information related to the conditions stipulated by the regulations, the contents of the invention document and the inappropriate character string pattern information A set of a modified version of the invention document generated by modifying the contents of the invention document so as to satisfy the conditions based on the associated correction information and the translation result document corresponding to the invention document A machine learning unit that generates a translation learning model, which is a learning model for machine translation, by machine learning used as teacher data, and the output unit outputs the translation learning model generated by the machine learning unit. It is good also as including the learning model output part which outputs.

As a result, there is a possibility that the modified invention document and the translation result document used as training data for machine learning will have reduced discrepancies in their contents, so the invention document analysis system can A learning model may be output. Therefore, for example, in a machine translation system or the like, it is possible to machine-translate an invention document by arithmetic processing using an appropriate learning model for translation output from the invention document analysis system. By referring to the result of machine translation of the invention document, the translator may be able to translate the invention document efficiently or properly.

Further, for example, the analysis unit includes a translation unit that executes machine translation, and for each of the plurality of invention documents, extracts a group of key phrases, which are a plurality of key phrases, from the invention documents in the same manner as the key phrase extraction unit. Based on the correlation between the groups of important phrases extracted and extracted, group classification is performed to specify which of the plurality of groups each of the plurality of invention documents belongs to, and the group classification is performed. For each of the plurality of invention documents, by machine learning using each set of the invention document and the translation result document that is the translation result of the invention document for each invention document classified into the group as teacher data, In a state where a learning model for translation, which is a learning model for machine translation, is generated, the document acquisition unit acquires a predetermined invention document, and the translation unit extracts the important phrase from the predetermined invention document. Based on the group of important phrases, which are a plurality of important phrases extracted by Machine translation of at least part of the predetermined invention document is performed using the corresponding learning model for translation, and the output unit is generated based on the analysis result of the predetermined invention document by the analysis unit. It is also possible to output patent application related information including the result of the machine translation by the translation unit.

As a result, the translator can efficiently or properly translate the invention document by referring to the result of machine translation of at least part of the predetermined invention document in the patent application related information output by the invention document analysis system. can be possible.

(Modification Group 2)
An invention document analysis system according to the present disclosure is a system for analyzing an invention document, which is a document containing a description of a claim for a patent application in which a technical idea is expressed in Japanese. A setting information acquisition unit that acquires setting information including condition information indicating a condition, a document acquisition unit that acquires an invention document, and an analysis unit that analyzes the invention document acquired by the document acquisition unit based on the setting information. and an output unit configured to output information generated based on the result of analysis by the analysis unit of the invention document acquired by the document acquisition unit, wherein the analysis unit outputs the invention acquired by the document acquisition unit. an important phrase extraction unit for extracting important phrases from a document based on the setting information, wherein the output unit extracts each of the plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit. It is an invention document analysis system that outputs information generated based on.

As a result, the invention document analysis system outputs information based on the results of analysis of invention documents including claims prepared by the inventors or patent attorneys, for example. For example, the inventors or patent attorneys may be able to efficiently complete the invention documents more appropriately by referring to the output information. An invention document that has been completed to be more appropriate is useful for a translator who translates the invention document in order to translate it appropriately or efficiently.

In addition, for example, the condition information is used for reference to important phrase candidate character string pattern information indicating an important phrase candidate character string pattern representing a character string pattern that is a candidate for an important phrase, and for reference to previously described character strings. including reference character string pattern information indicating a reference character string pattern representing a reference character string pattern and specific particle character string pattern information indicating a specific particle character string pattern indicating a character string pattern that is a predetermined particle, The key phrase candidate character string pattern information is defined so that at least a predetermined character string whose first character is Kanji and a predetermined character string whose first character is Katakana correspond to the important phrase candidate character string pattern. The reference character string pattern information is defined so that at least the character string "above" corresponds to the reference character string pattern, and the specific particle character string pattern information is at least "to , "ni", "ga", "to", "kara", "he" and "wa" are determined to correspond to the specific particle character string pattern, and the important The word/phrase extraction unit detects that the invention document acquired by the document acquisition unit has a second character string corresponding to the important word candidate character string pattern following the first character string corresponding to the reference character string pattern. In this case, a character string identical to the second character string is extracted as an important phrase, and a third character string corresponding to the important phrase candidate character string pattern is included in the claim of the invention document acquired by the document acquisition unit. If a period character is subsequently present, the same character string as the third character string is extracted as an important phrase, and characters corresponding to the important phrase candidate character string pattern are added to the invention document acquired by the document acquisition unit. If there is a specific particle character string that is a character string that corresponds to the specific particle character string pattern following an important phrase candidate character string that is a string, the same character string as the important phrase candidate character string is used as an important phrase. In the extraction of important phrases, the important phrase extraction unit extracts, in the case where a plurality of character strings correspond to the important phrase candidate character string pattern, one of the plurality of character strings is included in the description of the invention document, the remaining character string excluding the one character string from among the plurality of character strings is selected and extracted as an important phrase, and the analysis unit generates claim-based specification information representing the content of an incomplete specification based on each key phrase extracted by the key phrase extraction unit from the claims of the invention document acquired by the document acquisition unit; The output unit outputs patent application related information generated based on the analysis result of the analysis unit for the invention document acquired by the document acquisition unit, and the patent application related information is acquired by the document acquisition unit. each of the plurality of key phrases extracted from the invention document by the key phrase extracting unit is output as a display document containing content to be displayed, and the patent application related information is displayed in the display document. and the claim base specification information, which represents the content of the claims of the invention document acquired by the document acquisition unit. The claim information includes display control information for controlling the display mode of each of a plurality of key phrases in the claim extracted by the key phrase extraction unit from the invention document, and , for each of the plurality of key phrases extracted by the key phrase extracting unit, the display control information for controlling the display mode of the key phrase corresponds to the display mode of the key phrase corresponding to the display control information, including highlighting information for differentiating the display mode of words other than the plurality of key words in the complaint information, wherein the character strings constituting the key words in the claim information correspond to each of the plurality of key words different from each other Each of the display control information for controlling the display mode may include different identification information for controlling the plurality of important phrases to be displayed in different display modes.

As a result, inventors, etc. or patent attorneys who browse patent application-related information can quickly identify key words with different character strings extracted from the claims of the invention documents in the claim information. By referring to the claim-based specification information that can be efficiently confirmed and that is generated based on the key words extracted from the claims, there is a possibility that the specification of the invention document can be efficiently generated or updated.

Also, for example, the analysis unit causes the claim-based specification information to be generated to include a heading similar to the heading of the specification of the Japanese patent application, and the analysis unit adds each item in the claim of the invention document extract all of the claimable originating claims, identify the key words and phrases representing the claimable object of each of the extracted claimable originating claims, and if the identified key words and phrases contain the same multiple key words and phrases, From a set of key phrases representing mutually different claimable objects remaining as a result of removing all but one key phrase out of a plurality of key phrases, the elements of the set are listed in a predetermined order and in a predetermined format The arranged character string is determined as the invention title character string following the heading of "title of the invention" in the claim-based specification information, and the claimed originating claim is a claim that does not cite other claims, or Claims that quote other claims but differ in claimed subject matter from the cited claim, and the analysis unit determines, based on key phrases representing the claimed subject matter for each of said all claimed subject-originating claims, Using the set of key words and phrases representing mutually different billing objects, each key word and phrase in the set and the incomplete message for description support specified corresponding to each of the key words and phrases are linked in a predetermined format (1). Generate one or more sentences, determine the generated sentences as description contents following the heading "Problem to be Solved by the Invention" in the claim-based specification information, and the incomplete message for description support is , including a character string sandwiched between an unfinished portion start symbol and an unfinished portion end symbol, indicating that it is an incomplete description portion, and the analysis unit includes the item number of each of the claim object originating claims, and the Each key phrase in the set of key words representing mutually different claimed subjects, which is determined based on the key words representing the claimed subject matter for each of all claimable originating claims, and description support identified corresponding to each of the key words. Generate one or more sentences concatenated with the incomplete message for use in a predetermined format, and follow the generated sentences after the heading "Means for Solving the Problem" in the claim-based specification information and the analysis unit determines the claim based on the claim number of each claim of the invention document, the key words representing the claim object of the claim, and the incomplete message for supporting description Determining a part of the description content following the heading of "Mode for Carrying out the Invention" in the base specification information, For each key phrase, the compositional inclusion relationship between the element indicated by the key phrase and the element indicated by other key phrases, the recorded content of the element indicated by the key phrase, or the actual content of the element indicated by the key phrase Based on the incomplete message for description support to explain the key phrase defined based on and the analysis unit determines, for each of a plurality of key phrases extracted by the key phrase extraction unit from the claim of the invention document, whether the element represented by the key phrase includes the element represented by another key phrase or, when it is structurally included in an element represented by another key phrase, sign determination that determines the sign for the key phrase based on the structural inclusion relationship between the key phrase and the other key phrase processing, and among the important words and phrases included in at least a part of the description content following the heading of "Mode for Carrying out the Invention" in the claim-based specification information, the key words and phrases are signed in the code determination process is determined, the determined code may be inserted immediately after the key phrase.

As a result, the inventors, etc. or the patent attorney can correct the incomplete message for description support in the claim-based specification information (for example, correct the part of the character string sandwiched between the incomplete part start symbol and the incomplete part end symbol). ), it may be possible to efficiently and appropriately generate or update the specification of the invention document.

Further, for example, in the sign determination process for determining the sign for the important phrase, in the case of determining the sign for the important phrase representing an element that structurally includes an element represented by another important phrase, the important phrase The code may be determined according to the number of elements represented by other important words and phrases that are structurally included in the elements represented by the words.

As a result, the code determination process allows, for example, the sign of an important phrase representing an element containing n (n is a natural number) elements expressed by other important phrases to be k digits (where k is (Natural number) can be determined as a number with zeros "0" added to the end of the number of digits. For example, if n is 10 or more and 99 or less, k becomes 2, and the code for key phrases that contain n elements (n is a natural number) that other key phrases represent has two digits of zero added to the end. number, such as "500", for example. For example, the code for each important phrase representing an element included in the element represented by the important phrase to which the code "500" is added is, for example, "501", "502", ..., "510", ..., "599". and so on. Therefore, the sign of each key phrase can be determined so that the inclusion relationship between the elements represented by each key phrase can be easily recognized at a glance.

Further, for example, the analysis unit adds display control information for controlling a display mode of the display element to the display element of the important phrase included in the claim-based specification information in the display document, and The control information is a graphical user interface (GUI) for displaying the relevant display elements of the relevant important phrases, and the description part containing the relevant important phrases in the claim information in the display document in accordance with the operation of the relevant display elements. and the analysis unit, when at least one description support incomplete message included in the claim-based specification information in the display document is a message listing a plurality of options, Display control information for controlling the display mode of the display element is added to the display element of the incomplete message for supporting description, and the display control information controls the display element of the incomplete message for supporting description. Functioning as a GUI for enabling the selection operation of the plurality of options of the incomplete description support message, and displaying the display element when the selection operation of any one of the plurality of options is performed It may be for changing the incomplete message for description support as the content to another predetermined incomplete message for description support suitable for the option for which the selection operation has been performed.

As a result, inventors or patent attorneys who have viewed the claim-based specification information in the patent application-related information as a display document can , by performing a selection operation of one option related to the matter to be described in the specification, another description support unfinished message suitable for the selected option as a result of changing the description support unfinished message Completion messages can be viewed. For this reason, the inventors, etc. or the patent attorney, for example, utilize the claim-based specification information displayed after the selection operation (for example, copy and paste the claim-based specification information to a text editor, etc., and modify it as appropriate). etc.), it may be possible to efficiently and appropriately generate or update the specification of the invention document.

Further, for example, the analysis unit generates claim-based drawing information based on the claims of the invention document acquired by the document acquisition unit, and the patent application related information is displayed in the display document. Claim-based drawing information is included, and the claim-based drawing information includes one or more drawing numbers of each drawing, important phrases to be described in each drawing, relationships between the important phrases, and codes corresponding to the important phrases. and the analysis unit extracts from the claim of the invention document acquired by the document acquisition unit, the key phrase extraction unit extracts structurally between the elements represented by the key phrases. If there is an inclusion relationship, based on the inclusion relationship, the inclusion side element is displayed outside the frame line that encloses the key phrase that represents the included element and connects the code corresponding to the key phrase with a leader line. The important words and phrases are arranged to enclose the important words and phrases on the including side and the frame lines related to the elements on the included side, and the codes determined in the code determination process are connected to the important words and phrases on the including side with a leader line. A configuration diagram depicting a frame line is generated as a drawing in the claim-based drawing information, and the analysis unit adds the display element to the display element of the code included in the claim-based specification information in the display document Display control information for controlling the display mode of is added, and the display control information changes the display element of the code according to the operation of the display element, the code in the claim-based drawing information in the display document The display control information related to the display element of the code included in the claim-based specification information is to function as a GUI for displaying the part containing the same code as may define the function name or the function itself of a script that is started with the code as an argument and specifies the part in the claim-based drawing information that includes the code of the argument by searching the code.
As a result, claim-based drawing information including drawings is generated based on the inclusion relationship between important terms extracted from the claims of the invention document. , it is possible to efficiently generate appropriate drawings. In addition, the inventors, etc. or the patent attorney operate the GUI related to the code included in the claim-based specification information of the patent application-related information as a display document, and the claim-based drawing information in which the code is described. Since it is possible to quickly check the contents, it may be possible to appropriately generate or update the specification of the invention document efficiently by utilizing claim-based specification information and the like.

(Modification Group 3)
The invention document analysis system in the present disclosure is an invention document analysis system that analyzes an invention document that is a document describing a claim or a specification for a patent application in which a technical idea is expressed in Japanese, A setting information acquiring unit for acquiring setting information including condition information indicating extraction conditions, a document acquiring unit for acquiring an invention document, and an invention document acquired by the document acquiring unit is analyzed based on the setting information. and an output unit configured to output information generated based on an analysis result of the invention document acquired by the document acquisition unit, wherein the analysis unit outputs information acquired by the document acquisition unit. an important phrase extraction unit for extracting important phrases from the invention document based on the setting information, and the output unit extracts a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit It is an invention document analysis system that outputs information generated based on each word.

As a result, the invention document analysis system outputs information based on the results of analysis of invention documents created by, for example, inventors (for example, inventors or their related parties) or patent attorneys. For a translator or the like (for example, a translator or other person who uses the invention document) to refer to the output information, there is a possibility that the understanding of the invention document will be promoted. Promoting the understanding of the invention document is useful for translators to translate the invention document appropriately or efficiently. Information generated based on key words in an invention document can be useful in cases where a translator determines corresponding translation words corresponding to key words in the invention document before translating the entire invention document.

Here, for example, the output unit outputs patent application-related information generated based on the analysis result of the analysis unit for the invention document acquired by the document acquisition unit, and the patent application-related information is the for each of a plurality of key phrases extracted by the key phrase extracting unit from the invention document acquired by the document acquisition unit, information in which additional information related to the key phrase is added to the key phrase; In the information, the additional information related to the key words and phrases added to each of the plurality of key words and phrases extracted from the invention document acquired by the document acquisition unit is a translated word and phrase representing the meaning of the key words and phrases. including translation word information as information related to corresponding translation words, the analysis unit extracting corresponding translations for each of the key words extracted by the key word extraction unit from the invention document acquired by the document acquisition unit; a translation word candidate set specifying unit for specifying a translation word candidate set that is a set of word candidates, and included in the additional information related to the important phrase of the invention document acquired by the document acquisition unit; The translated word information as information about the translated word includes the translated word candidate information representing the translated word candidate set for the key word specified by the translated word candidate set identification unit, or the corresponding translated word. good too. A translated phrase is, for example, a phrase expressed in one kind of language other than Japanese (for example, English, Chinese, etc.).

As a result, by obtaining patent application-related information output by the invention document analysis system, translators, etc. can grasp multiple important words and phrases of invention documents, and translators can use additional information to translate invention documents. In this way, it may be possible to efficiently or properly determine a translated phrase corresponding to a key phrase, which is the target language with the same meaning as the key phrase. In addition, by referring to the translation word information included in the patent application related information output by the invention document analysis system, the translator can efficiently or appropriately determine the translation words corresponding to the important words. . In addition, by referring to the translation word candidate information or the corresponding translation words included in the patent application related information output by the invention document analysis system, the translator can, for example, refer to the translation word candidate set represented by the translation word candidate information corresponding to the key phrase. It may be possible to efficiently or properly determine the translation word corresponding to the key word, such as by selecting one translation word from the list.

Further, for example, the patent application-related information includes, as content to be displayed, each of the plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit. The additional information related to the key words and phrases extracted from the invention documents, which is output as a technical document, is such that any element of the translation word candidate set for the key words and phrases can be selected according to an operation. (b) includes display control information for displaying the translation word candidate set as a graphical user interface (GUI) element, and the display control information included in the additional information related to the important phrase is the GUI A script for executing determination processing for determining an element selected in accordance with an operation from the set of candidate translation words for the key phrase displayed as elements as a corresponding translation word corresponding to the key phrase and the determination process of determining the element selected from the candidate translation word set as the corresponding translated word includes a process of replacing the displayed candidate translation word set with the corresponding translated word and displaying it. You can do it.

As a result, the translator can easily determine the corresponding translation word corresponding to the important word from the translation word candidate set by selecting the GUI element of the document for display. Also, the translator can easily obtain, for example, the corresponding translated words displayed by the determination process from the display contents of the display document by a browser or the like by so-called copy & paste, so-called cut & paste, or the like. In addition, copy & paste or cut & paste generally selects data to be copied (i.e. duplicated) or cut (i.e. By this operation, the data to be copied or cut is held in a predetermined memory area under the control of the operating system (OS), etc., and by the paste operation, the data is transferred to that area. It is pasted from a predetermined memory area to a location specified as a paste destination.

In addition, for example, the condition information is used for reference to important phrase candidate character string pattern information indicating an important phrase candidate character string pattern representing a character string pattern that is a candidate for an important phrase, and for reference to previously described character strings. Reference character string pattern information that indicates the reference character string pattern that indicates the pattern of the reference character string, and the code that indicates the character string pattern of the code appended after the character string that indicates the element name Code that indicates the character string pattern Character string pattern information and specific particle character string pattern information indicating a specific particle character string pattern representing a pattern of a character string that is a predetermined particle, and the important phrase candidate character string pattern information includes at least the first character A predetermined character string of Chinese characters and a predetermined character string whose first character is Katakana are determined to correspond to the key phrase candidate character string pattern, and the reference character string pattern information is at least " The character string "said" is defined to correspond to the reference character string pattern, and the code character string pattern information is such that at least a predetermined character string whose first character is a number corresponds to the code character string pattern. is defined as applicable, and the specific particle character string pattern information is at least one of "wo", "ni", "ga", "to", "from", "he" and "ha" is determined to correspond to the specific particle character string pattern, and the important phrase extraction unit extracts the first character corresponding to the reference character string pattern from the invention document acquired by the document acquisition unit. a first extraction unit for extracting a character string identical to the second character string as an important phrase when a second character string corresponding to the key phrase candidate character string pattern exists subsequent to the string; In the case where a claim is included in the invention document acquired by the division, if the claim contains a period character following the third character string corresponding to the important phrase candidate character string pattern, the third a second extraction unit for extracting a character string identical to the character string as an important phrase; a third extraction unit for extracting a character string identical to the fourth character string as an important phrase when a fifth character string corresponding to a code character string pattern exists; , when there is a seventh character string corresponding to the specific particle character string pattern following the sixth character string corresponding to the important phrase candidate character string pattern, the character string identical to the sixth character string is regarded as important and a fourth extracting unit for extracting as a word, wherein the important word extracting unit, in the extraction of the important word/phrase, extracts the plurality of character strings when a plurality of character strings correspond to the important word/phrase candidate character string pattern. When one of the character strings is included in another character string in the description of the invention document, the remaining character strings after excluding the one character string among the plurality of character strings are selected and key words are selected. Selected and extracted, the setting information includes information for specifying an important phrase setting dictionary listing important phrases to be extracted, and in the important phrase setting dictionary, at least some of the listed important phrases include The invention document analysis system includes an important phrase setting dictionary acquisition unit that acquires the important phrase setting dictionary based on the setting information, and the important phrase extraction unit includes the When the key words listed in the key word setting dictionary are included in the invention document acquired by the document acquisition unit, the key words are extracted from the invention document, and the key word extraction unit extracts the When the key phrases associated with the corresponding translated words in the key phrase setting dictionary are extracted from the invention document acquired by the document acquisition unit, the key phrase extracted from the invention document in the patent application related information The additional information related to the important phrase represents the corresponding translated word, and the important phrase extracting unit extracts important phrases other than the important phrases associated with the corresponding translated word in the important phrase setting dictionary from the document acquisition unit. When extracted from the invention document obtained by, the display control information included in the additional information related to the key phrase extracted from the invention document in the patent application related information is the translation word candidate set including information for displaying the translation word candidate set as a GUI element so that any element of the translation word candidate set of the important phrase identified by the identification unit can be selected according to an operation; The display control information determines an element selected according to an operation from the translation word candidate set of the key word displayed as the GUI element as a corresponding translation word corresponding to the key word. A script for executing the decision process may be included.

As a result, for example, when there is an expression that refers to a word in the invention document, the key word extraction unit treats the referenced word as a key word under certain conditions, and Because words and phrases are treated as key words under certain conditions, words that are written with enough attention to reference and words that describe the claimed subject matter of a claim may be treated as key words. It is assumed that there is a good tendency to have punctuation following the claimed subject matter in the claims of ordinary invention documents. Therefore, information can be output by the output unit based on the key phrases that the invention document analysis system presumes to be important in the invention document, so the output information can be useful. In addition, the important phrase extraction unit, for example, treats phrases that are part of descriptions of other important phrases so as not to extract them as important phrases, and phrases (for example, noun phrases) that precede predetermined particles in invention documents are fixed. Under certain conditions, it is treated as an important word, and the words written with a code in the invention document are treated as important words under certain conditions. can be treated as key words. Since the invention document is written in Japanese, there is a good chance that words starting with kanji or katakana are key words. Therefore, since the invention document analysis system can output information by the output unit based on key phrases estimated to be important in the invention document, the output information can be useful. In addition, with this, for example, the inventor, etc. or the patent attorney who created the invention document can, for example, specify important words and phrases when they want to specify specific words and phrases as important words, and when they want to decide the corresponding translation words for important words and phrases. By generating a word setting dictionary in advance, the invention document analysis system can output appropriate patent application related information. Therefore, the translator may be able to translate the invention document efficiently or properly by referring to the patent application-related information. In addition, by creating a key phrase setting dictionary in cases such as when the translator has defined corresponding translation words for key phrases, invention documents provided by inventors or patent attorneys can be processed by the invention document analysis system. Appropriate patent application-related information can be output when analyzed.

Further, for example, when the important phrase extraction unit extracts important phrases other than the important phrases associated with the corresponding translated words in the important phrase setting dictionary from the invention document acquired by the document acquisition unit, the The display control information included in the additional information related to the important phrase extracted from the invention document in the patent application related information is the important A script may be included for executing update processing for updating the important phrase setting dictionary so as to include information that associates the phrase with the corresponding translated word.

As a result, the content of the important phrase setting dictionary can be updated to the content that is more appropriately utilized in the subsequent analysis of the invention document by performing the selection operation of the translation word candidate set.

Further, for example, the patent application related information includes, for each key phrase extracted by the key phrase extraction unit from the invention document acquired by the document acquisition unit, the key phrase and the corresponding translated word for the key phrase, Alternatively, an important phrase list configured by associating a translation word candidate set for the relevant important phrases with the important phrases in the important phrase list in the patent application-related information as the display document, and the corresponding translated words , and display control information for controlling the display mode of the display element may be added to each display element of the translation word candidate set as the additional information related to the important phrase.

As a result, the translator can quickly grasp the important phrases contained in the invention document by referring to the important phrase list, and can translate efficiently. In addition, inventors, patent attorneys, or translators can efficiently , it is possible to generate, update, etc. the important phrase setting dictionary.

Further, for example, when claims are included in the invention document acquired by the document acquisition unit, the patent application related information is claim information representing the content of the claims to be displayed in the display document. , and claim translation information representing the result of machine translation of the claim represented in the claim information, and representing the result of machine translation for one line or one item of the claim information in the claim translation information. One line or one paragraph is a complete translation line that expresses the entire line or paragraph of the claim information in the target language, or a key phrase included in the line or paragraph of the claim information, and the corresponding translation corresponding to the key phrase or a partial translation line that is the result of replacement in the translation word candidate set for the key word, and if the specification is included in the invention document acquired by the document acquisition unit, the patent The application-related information includes specification information representing the content of the specification to be displayed in the display document, and specification translation information representing the result of machine translation of the specification represented by the specification information. Including, in the description translation information, one line representing the result of machine translation for one line of the description information is a complete translation line representing the entire line of the description information in the target language, or , a partially translated line that is the result of replacing key phrases contained in the line of the specification information with a corresponding translated word corresponding to the key phrase or a translation word candidate set for the key phrase, and the document The claim information representing the content of the claim of the invention document acquired by the acquisition unit is a display mode of the key phrase for each of a plurality of key phrases in the claim extracted from the invention document by the key phrase extraction unit. The description information, which includes display control information for controlling and represents the content of the description of the invention document acquired by the document acquisition unit, is extracted from the invention document by the important phrase extraction unit. for each of a plurality of key phrases, including display control information for controlling the display mode of the key phrase, and for each of the plurality of key phrases extracted by the key phrase extraction unit in the claim information and the specification information , the display control information for controlling the display mode of the key phrases is such that the display mode of the key phrases corresponding to the display control information is changed to the display mode of the key phrases other than the plurality of key phrases in the claim information and the specification information The display control for controlling the display mode, which includes highlighting information for differentiating the display mode of the words and phrases, and corresponds to each of a plurality of important words and phrases in which the character strings constituting the important words and phrases are different from each other in the complaint information. Each piece of information includes different identification information for controlling to display each of the plurality of important phrases in different display modes, The display control information for controlling the display mode of the key phrase for each key phrase is that the key phrase is the plurality of key phrases in the claim information in which the character strings constituting the key phrase are different from each other , the key phrase is displayed in the same display mode as the same key phrase in the claim information, said claim translation information including information for controlling to display said key phrase in a display mode different from any of said plurality of key phrases in said claim information if said key phrase differs from any of said plurality of different key phrases; And, in the description translation information, for the same key phrase as each of the plurality of key phrases in which the character strings constituting the key phrase in the claim information are different from each other, the result of machine translation with the key phrase as the target of machine translation As information to be added to the display elements of the machine, the machine translation results are displayed so that at least part of the display mode is the same as at least part of the display mode of the important phrase in the claim information and the description information. Display control information for controlling the display mode of the translation result may be included.

As a result, for example, translators, etc., can identify key words whose display mode is controlled in the claim information and specification information of the patent application-related information related to the display document displayed by the browser, etc. , the translation results of key phrases whose display mode is controlled in the claim translation information and the specification translation information, and it is possible to quickly grasp which translation result corresponds to which key phrase. In addition, translators, etc., who have browsed the patent application-related information, can identify whether each key phrase described in the specification information in the patent application-related information is the key phrase described in the claim. , it may be possible to quickly grasp whether a plurality of key words are the same or different, depending on the display mode of each key word. In addition, in the invention document analysis system, if, for example, highlighting (for example, displaying in bold) is performed as a control of the display mode of the important words, the translator, etc. can quickly grasp the important words in the claim information. can be.

Further, for example, the display document is an HTML document including an HTML file written in HTML (Hypertext Markup Language) including the patent application related information as content to be displayed, and is acquired by the document acquisition unit. For each of the plurality of key words in the claim extracted by the key word extracting unit, the display control information related to the key word is a plurality of key phrases in the specification extracted by the important phrase extraction unit, including the specification information representing the content of the specification of the invention document acquired by the document acquisition unit. For each of the words, the display control information related to the key words indicates the display color to be added to the key words, and the display control information for each of the multiple key words having mutually different character strings constituting the key words in the claim information. The display control information is for controlling each of the plurality of key words and phrases to be displayed in a display mode in which a different display color is added for each key word, and constitutes the key words and phrases in the complaint information. The display control information related to the important phrase in the claim information, which is composed of the same character string as any one of the plurality of important phrases whose character strings are different from each other, It is for controlling to display in a display mode in which the same display color as one important phrase is added, and for each of a plurality of important phrases in the specification information, the relevant important phrase is the above-mentioned If it is the same as any one key phrase out of a plurality of key phrases, the display control information related to the key phrase in the specification information changes the key phrase to the one key phrase in the claim information. It is for controlling to display in a display mode to which the same display color as the display color added as a display mode is added, and the claim translation information and the specification translation information are important words and phrases in the claim information. For key phrases that are the same as each of the plurality of key phrases whose character strings are different from each other, as information to be added to the display element of the result of machine translation with the key phrase as the object of machine translation, the result of the machine translation Controlling the display mode of the result of the machine translation so that the display color of at least part of the display mode is the same as the display color of at least part of the display mode of the important phrase in the claim information and the specification information may include display control information for

As a result, a translator or the like can browse the patent application-related information as a display document, which is an HTML document, using a PC, smartphone, or other computer equipped with an HTML-compatible browser. Translators, etc., who view the patent application-related information as a display document displayed by a browser, etc., identify important words and phrases in the patent application-related information, and the display colors added to the translation results of the important words and phrases. As a result, it becomes possible to identify whether or not a certain key phrase is the key phrase described in the claim, and it is possible to quickly grasp whether multiple key phrases are the same or different. It is possible to quickly grasp which important phrase corresponds to.

Further, for example, the display control information relating to each of a plurality of important phrases having different character strings constituting the important phrases in the complaint information displays each of the plurality of important phrases in a different display color for each of the important phrases. It is for controlling to display in a display mode in which a left border line having a predetermined width is added. , the display control information related to the key phrase in the specification information controls the key phrase to display the one key phrase in the claim information. Control to display in a display mode to which the left border line having the predetermined width is added in the same display color as the display color of the left border line according to the mode, and the important phrase in the description information is displayed in the claim information , the display control information related to the key phrase in the specification information is such that the key phrase is displayed in a display mode in which the left border line is not added. The display control information related to the key phrase in the claim information is for controlling to display the key phrase in a display mode with the left boundary line having the predetermined width added. The display control information relating to the result of machine translation of the key words in the claim translation information and the specification translation information, which targets the key words and phrases of the It may be for controlling to display in a display mode to which the left boundary line having the predetermined width is added in the same display color as the display color of the left boundary line related to the display mode of the important phrase.

As a result, translators, etc., who view the patent application-related information as a display document displayed by a browser, etc., can add different key phrases included in the claim information in the patent application-related information to each key phrase. can be quickly distinguished by identifying the display color of the left border line. It should be noted that the method of expressing different key phrases by using different display colors for the left boundary line added to the key phrases is more important than the method of expressing key phrases by using different character colors or character background colors. There is an advantage that the readability of the important phrase itself is not degraded regardless of whether the background color of the region is dark (eg black) or bright (eg white). In addition, the left border line that can be added to some display elements in HTML documents is not a character, so it is ignored when copying and pasting the text of the display content that includes important phrases. It does not get in the way when copying and pasting into a text editor etc. and editing descriptions including important phrases. In addition, translators, etc., who have browsed the patent application-related information, can identify a certain claim by identifying the important words in the patent application-related information and the display color of the left border line added to the translation results of the important words and phrases. It is possible to quickly grasp which key words and phrases described in the claim correspond to the translation result of the key words and phrases.

Further, for example, the claim translation information includes each line of the claim information, and for each line or item of the included claim information, immediately after the content of the line or item, the content of the line or item A fully translated line or a partially translated line representing the result of machine translation corresponding to the machine translation target is inserted, and the specification translation information includes each line of the specification information, and the included specification For each line of the document information, a complete translation line or a partial translation line representing the result of machine translation corresponding to the machine translation target of the line is inserted immediately after the line, and the claim translation information and the The description translation information includes the display mode of at least a part of the machine translation target in the claim translation information and the description translation information, and the display element of at least a part of the machine translation result corresponding to the machine translation target. Display control information may be added to each of the display elements in order to control the display mode to be at least partially different.

As a result, translators, etc., who view the patent application-related information as a display document displayed by a browser, etc., can distinguish between the lines to be machine-translated and the lines resulting from machine translation in the claim translation information and the specification translation information. quickly identifiable.

In addition, while visually confirming the line to be machine-translated in the claim translation information or the description translation information, the translator, etc., can read the contents of the line of the machine translation result located after the line to be machine-translated. It may be possible to make appropriate corrections to efficiently create more appropriate translations.

Further, for example, the claim translation information and the specification translation information include a display mode of at least a part of a display element to be machine-translated in the claim translation information and the specification translation information, and a machine corresponding to the machine-translation target. To control the display mode of display elements of at least a part of the translation result to be different in at least one of character background color, character color, character decoration, font size, font style, and font weight , display control information may be added to each display element.

As a result, translators, etc., who view the patent application-related information as a display document displayed by a browser, etc., can distinguish between the lines to be machine-translated and the lines resulting from machine translation in the claim translation information and the specification translation information. , character background color, character color, character decoration, font size, font style, and font weight.

In addition, for example, in the display element of the result of machine translation for which key words in the claim translation information and the specification translation information are to be machine-translated, the Display control information including translation word candidate information is added for the display element to have a GUI function for displaying a set of translation word candidates different from the result, and the display control information is the result of the operation. When an operation to select one element from the set of candidate translation words is performed on the GUI displaying the set of candidate translation words displayed as , the content of the display element of the result of machine translation is selected by the selection operation It may be determined to change to the one element that has been specified.

As a result, translators, etc., who view the patent application-related information as a display document displayed by a browser, etc., can select the results of machine translation of important terms in the claim translation information and the specification translation information as necessary. It can be changed easily by operation.

Further, for example, the document acquisition unit acquires a plurality of invention documents, and the corresponding translated words in the partially translated lines of the claim translation information and the specification translation information are learning models for machine translation of important words. Generated as a result of machine translation using a learning model for translation of key words, the invention document analysis system acquires invention document standard specifications for translation that define a plurality of conditions to be satisfied by invention documents to be translated. an invention document standard specification acquisition unit; and for each of the plurality of invention documents acquired by the document acquisition unit, the invention document satisfies at least a part of the plurality of conditions stipulated by the invention document standard specification for translation. a document evaluation unit that determines whether or not each condition is satisfied, and selects, from among the plurality of invention documents, invention documents for which the degree of the condition for which the determination is made exceeds a predetermined degree; , and a machine learning unit, wherein the machine learning unit generates a document for display by the invention document analysis system based on the invention document selected by the document evaluation unit and converts it into a translation word candidate set for important words. As a result of displaying the GUI, a set of the key phrase and one element selected from the translation candidate set is accumulated as teacher data for machine learning for generating the learning model for the translation of the key phrase. , a function of generating a learning model for machine translation of important phrases by machine learning using a plurality of teacher data accumulated in the past.

As a result, an invention document having a relatively high conformity to the invention document standard specification for translation is selected, and the key words in the invention document and the elements selected from the corresponding translation candidate set are combined into a learning model for translation of key words. , and inappropriate invention documents that are difficult to translate are excluded from the materials for generating the learning model for important phrase translation, so that the learning model for important phrase translation can be appropriately generated. In addition, by using the generated learning model for translation of important phrases later in the analysis of the invention document, more appropriate machine translation of the important phrases in the invention document can be realized. By referring to the results of more appropriate machine translation, the translator may be able to efficiently or properly determine translated words and phrases for the important words and phrases in the invention document.

Further, for example, the complete translation line in the claim translation information and the specification translation information is generated as a result of machine translation using a translation learning model, which is a learning model for machine translation, and the document acquisition unit , a plurality of invention documents and a plurality of translation result documents, which are translation results of each of the plurality of invention documents, are acquired, and the invention document analysis system defines a plurality of conditions to be satisfied by the invention documents to be translated. and an acquisition unit for standard specifications for invention documents for translation that acquires the standard specifications for invention documents for translation, and for each of the plurality of invention documents acquired by the document acquisition unit, the invention documents are specified by the standard specifications for invention documents for translation. A determination is made as to whether or not each of at least some of the conditions among the plurality of conditions is satisfied, and among the plurality of invention documents, the extent to which the conditions for which the determination is made satisfies a predetermined degree. and a machine learning unit, wherein the machine learning unit selects the invention document selected by the document evaluation unit and the translation result based on the invention document It may include a function of generating the learning model for translation by machine learning using a plurality of sets of translation result documents as teacher data.

As a result, invention documents are selected based on the standard rules for invention documents for translation. Pairs with inconsistent translation result documents are less likely to be used as teacher data, and the invention document analysis system can generate an appropriate learning model for translation. In addition, in the invention document analysis system, it becomes possible to machine-translate the invention document by arithmetic processing using the appropriate learning model for translation. By referring to the complete translation lines in the claim translation information and the specification translation information as a result of machine translation of this invention document and correcting them accordingly, the translator can translate the invention document efficiently or properly. can be.

Further, for example, the analysis unit generates warning information under certain conditions based on the invention document acquired by the document acquisition unit, the patent application related information includes the warning information, and the warning information is indication information that inspects whether or not the invention document acquired by the document acquisition unit satisfies a plurality of conditions stipulated in the invention document standard specification for translation and points out if the conditions are not met; Predetermined calculation based on the result of checking whether or not the invention document acquired by the document acquisition unit satisfies at least some of the plurality of conditions defined in the invention document standard specification for translation and invention document evaluation information indicating the evaluation value of conformity of the invention document to the invention document standard specification for translation calculated by the invention document evaluation information.

Accordingly, by referring to the patent application-related information output by the invention document analysis system, the inventor or the like or the patent attorney who prepared the invention document can correct the invention document if necessary. In addition, the translator, for example, receives invention documents to be translated and patent application-related information from the inventors, etc. or patent attorneys, so that even if the warning information in the patent application-related information remains pointed out, Since it can be presumed that the inventor, etc. or the patent attorney determined that there is no particular need to deal with the indication, it is possible to obtain an appropriate invention document to be translated, and as a result, the translation of the invention document can be done efficiently or properly.

Further, by referring to the invention document evaluation information included in the patent application-related information output by the invention document analysis system, the inventor or patent attorney may be able to appropriately correct the invention document. Further, by checking the invention document evaluation information, the translator can recognize whether or not the invention document is suitable for translation. Invention documents that include inappropriate descriptions, for example, are likely to cause translation errors, and it is possible that a translator may revise and translate the invention document in order to obtain appropriate rights (for example, to obtain patent rights). . Therefore, if the warning information in the patent application-related information generated based on the invention document includes invention document evaluation information indicating relatively low conformity with the standard provisions for invention documents for translation, It can be judged that there is a high possibility that there may be discrepancies in content between the invention document and the translation result document, which is the result of translation based on the invention document, other than the language being different. It may be possible to determine that it is not useful to use the combination of the invention document and the translation result document as teacher data for machine learning in order to generate the translation learning model to be used.

Further, for example, the standard specification of invention documents for translation includes version information indicating the version of the standard specification of invention documents for translation, and whether the invention document conforms to each of a plurality of conditions stipulated in the standard specification of invention documents for translation. and an inspection program for processing for determining whether or not there is an invention document standard specification for translation, and the acquisition unit accesses the invention document standard specification for translation as a resource on the network and has already acquired If it is possible to acquire a newer version of the invention document standard specification for translation than the version indicated by the version information of the invention document standard specification for translation, the new version of the invention document standard specification for translation is acquired, and the analysis unit Whether the invention document acquired by the document acquisition unit by executing the inspection program included in the standard specification of invention documents for translation conforms to each of the plurality of conditions stipulated in the standard specification of invention documents for translation The warning information may be generated by determining whether or not, and using the result of the determination.

Standard provisions for invention documents for translation are, for example, provisions established by a specific organization or a specific person, such as an organization aiming to standardize invention documents for translation, and are provided on a network such as the Internet (for example, public, etc.) In that case, over time, the specific organization or person who enacted the invention document standard specification for translation may be upgraded to make it more appropriate, but this invention document analysis system According to this, when necessary, a new version of the invention document standard specification for translation is acquired from the network and used for analysis of the invention document (that is, generation of warning information, etc.), so appropriate analysis (that is, warning information , etc.) can be performed.

Further, for example, the complete translation line in the claim translation information and the specification translation information is generated as a result of machine translation using a translation learning model, which is a learning model for machine translation, and the invention document analysis system includes an invention document standard specification acquisition unit for acquiring an invention document standard specification for translation that defines a plurality of conditions to be satisfied by an invention document to be translated, and the invention document standard specification for translation is to be translated. Inappropriate character string pattern information indicating an inappropriate character string pattern representing a character string pattern of a possibly inappropriate description part that does not satisfy the conditions, as information that defines the conditions to be satisfied by the invention document; The invention document analysis system includes correction information related to a method of correcting the description portion in association with the invention document analysis system, and the machine learning unit stores the translation information in the invention document acquired by the document acquisition unit. If there is a character string corresponding to the inappropriate character string pattern indicated by the inappropriate character string pattern information related to the conditions stipulated in the standard provisions of the invention document, the contents of the invention document and the inappropriate character string A modified invention document generated by modifying the contents of the invention document so as to meet the conditions based on the modification information associated with the pattern information, and a translation result document corresponding to the invention document. It is also possible to include a function of generating the learning model for translation, which is a learning model for machine translation, by machine learning using a set of as teacher data.

As a result, there is a possibility that the modified invention document and the translation result document used as training data for machine learning will have reduced discrepancies in their contents, so that the invention document analysis system can A learning model may be generated. In addition, in the invention document analysis system, it becomes possible to machine-translate the invention document by arithmetic processing using the appropriate learning model for translation. The translator can translate the invention document efficiently or properly by referring to the complete translation line in the claim translation information and the description translation information as a result of the machine translation of the invention document and correcting them accordingly. can be.

In addition, for example, the invention document analysis system, based on the correlation between key phrase groups extracted from each of a plurality of invention documents by the key phrase extraction unit, or based on a user's designation, groups invention documents. Classification is performed, and for each group, a learning model for machine translation of important phrases is created by machine learning using multiple pairs of key phrases extracted from invention documents and corresponding translated words as training data. A learning model for word translation is generated, and the corresponding translated word in the partial translation line of the claim translation information and the specification translation information generated based on one invention document acquired by the document acquisition unit is the one It may be generated as a result of machine translation using the important phrase translation learning model of the group to which the invention document belongs. In this grouping, for example, it can be assumed that the correlation between key phrase groups extracted from each of a plurality of invention documents to which the invention belongs is high to a certain extent or higher, so that the technical field to which the invention pertaining to the invention document belongs can be a classification based on the user's designation, and can be a classification such that sections of the IPC in the case of classification by IPC, or sections and classes that are different are grouped differently from each other. In order to distinguish the department to which the inventor who created the invention indicated in one invention document belongs from other departments based on Although it is possible, it is assumed that the inventors, etc., patent attorneys, or translators will operate so as to make useful group classifications.

As a result, it is possible to machine-translate each of the important phrases in the invention document by arithmetic processing using the important phrase translation learning model adapted to the group to which the invention document belongs. Also, by referring to the partial translation lines of the claim translation information and the description translation information, the translator may be able to efficiently or properly translate the key words of the invention document.

Further, for example, the invention document analysis system may extract a plurality of invention documents based on the correlation between key phrase groups extracted by the key phrase extraction unit from each of the plurality of invention documents, or based on a user's designation. For each group, a learning model for translation, which is a learning model for machine translation, is generated by machine learning using multiple sets of invention documents and corresponding translation result documents as training data, The complete translation line in the claim translation information and the specification translation information generated based on the one invention document acquired by the document acquisition unit uses the learning model for translation of the group to which the one invention document belongs. It may be generated as a result of machine translation.

As a result, it may be possible to machine-translate each key phrase in the invention document by arithmetic processing using a translation learning model suitable for the group to which the invention document belongs. Also, by referring to the complete translation lines of the claim translation information and the specification translation information, the translator may be able to translate the invention document efficiently or properly.

Further, for example, the grouping of the invention documents is performed based on the correlation between the key phrase groups extracted from each of the plurality of invention documents by the key phrase extraction unit, and The correlation between key phrase groups is determined based on the importance of each key phrase of the key phrase group extracted from each of the plurality of invention documents, based on the attribute information of the key phrase. The attribute information of the key words and phrases calculated and extracted from the invention document after performing corresponding weighting is information identifying whether or not the key words and phrases are used in the claims of the invention document, the invention Information identifying whether or not there is a code corresponding to the key phrase in the document, information identifying whether the key phrase is used as a subject in the invention document, and information identifying whether the key phrase is used as a subject It may also include information identifying whether or not it has a predetermined technical term-specific ending string.

As a result, the degree of importance of each key phrase is reflected in the correlation between key phrase groups, so group classification can be more appropriate for generation of a learning model for translation of key phrases or a learning model for translation. By referring to the result of machine translation of the invention document by the invention document analysis system using the key phrase translation learning model or the translation learning model generated as a result of the group classification, the translator can further improve the invention document. It may be possible to translate efficiently.

Further, for example, the importance determined based on the attribute information for each key phrase extracted from the invention document is based on the structural inclusion relationship between each element represented by each key phrase in the invention document. , the importance of the important phrases related to the containing element is the degree of importance of each important phrase related to all the included elements contained in the element represented by the important phrase related to the containing element After being updated to a value equal to or greater than the highest importance value, it may be used for calculating the correlation between the important phrase groups.

As a result, the importance of the important phrase whose importance is once determined to be the highest based on the attribute information among the important phrases related to the contained element group between the elements having the structural inclusion relationship is finally changed to is propagated to the importance of the important phrases related to the element on the inclusion side, so the result of grouping based on the correlation between the above-mentioned important phrase groups calculated based on the compositional inclusion relation related to the important phrases is , for the generation of learning models for key phrase translation or learning models for translation.

Further, for example, the display control information related to key phrases in the display document related to the patent application-related information generated for the invention document acquired by the document acquisition unit is configured to display elements of the key phrases in the display. A process for displaying the attribute information for the key phrase in response to the operation of the element, and the claim information based on the invention document, the description information, or the key phrase from an invention document other than the invention document. Important phrase inclusion description listing process for listing and displaying lines containing It functions as a GUI for executing a process of retrieving related images or a process of translating the relevant key words on a translation site on the network. are listed and displayed from the claim information, the specification information, or the separate invention document, and the key phrase in each listed and displayed line is highlighted, and in the displayed line , display control information for causing the line to function as a GUI for displaying links to multiple lines including the line in the claim information, the specification information, or the another invention document in response to an operation on the line. It may be a process of adding.

As a result, a translator, etc. who browses the patent application-related information related to the display document displayed by a browser or the like can operate the key words in the displayed patent application-related information to search results (e.g. web pages containing key words, definitions of key words, synonyms, related images), translation results of key words, etc., so that important words in invention documents can be efficiently Or it may be possible to understand properly. This may allow the translator to efficiently or properly determine translation terms for key terms.

In addition, by including the manipulated important phrase, the important phrase in the line listed by the important phrase inclusion description enumeration process is highlighted, so that the translator can accurately identify the important phrase. In addition, the translator or the like further operates one of the lines listed by the important phrase inclusion description enumeration process by including the operated important phrase, so that it is further displayed. Multiple lines of claim information, specification information, or other invention documents that precede or follow a single line can be readily identified.

Further, for example, the display control information included in the additional information related to the important phrases extracted from the invention document is translated as a result of execution of the decision processing by executing the script for executing the decision processing. A script for executing processing for generating and outputting translation assistance information, which is information in which each key phrase for which a word has been determined is associated with the key phrase and the corresponding translated word, wherein the document acquisition unit When the translation word information included in the additional information related to one key phrase of the acquired invention document is the translation word candidate set, the elements of the translation word candidate set are: In the past, for each of one or more invention documents, the display document related to the patent application related information generated based on the analysis result of the invention document by the analysis unit was output to the output unit for display. of the invention document, which is specified based on the translation assistance information generated for each key phrase in each of the one or more invention documents as a result of the use of the invention document acquired by the document acquisition unit When the translated word information included in the additional information related to one important phrase is a corresponding translated word, the corresponding translated word is determined by using the translation assistance information for the one important phrase. It may be a thing.

As a result, the results of the selection operation performed by the translator on the GUI elements related to the translation word candidate set of the document for display are then used by the invention document analysis system to determine the corresponding translation words corresponding to the important words and phrases via the translation auxiliary information. or the validity of identifying a translation word candidate set for key phrases.

Further, for example, when the translation word information included in the additional information related to one key phrase of the invention document acquired by the document acquisition unit is the translation word candidate set, the translation word candidate set Elements are important words and phrases in each of the plurality of translation assistance information generated as a result of displaying each of the display documents output based on each of the plurality of invention documents in the past by the invention document analysis system. , a set of corresponding translation words as training data for machine learning for translation of key phrases, and results of machine translation using a learning model for translation of key phrases, which is a learning model generated by machine learning. , and when the translation word information included in the additional information related to one key phrase of the invention document acquired by the document acquisition unit is the corresponding translation word, the corresponding translation The word may be determined as a result of machine translation of the one key phrase using the learning model for key phrase translation generated based on the translation auxiliary information.

As a result, the important word translation learning model generated based on the translation assistance information generated as a result of the translator's selection operation on the GUI elements related to the translation word candidate set of the display document is later applied to the invention document analysis system. By using it, the validity of determining the corresponding translation word corresponding to the key word or specifying the translation word candidate set for the key word by the invention document analysis system can be improved.

Further, for example, the document acquisition unit acquires a plurality of invention documents, and the output unit displays each of the display documents output for each of the plurality of invention documents acquired by the document acquisition unit. generated by machine learning using pairs of key phrases and corresponding translation words in each of the plurality of translation auxiliary information generated as a result as training data for machine learning for translation of key phrases A learning model output unit for outputting a learning model for translation of important phrases, which is a learning model, may be included.

As a result, in a machine translation system or the like for performing machine translation of invention documents, by executing arithmetic processing with key phrases as input using the learning model for translation of key phrases, machine translation of key phrases in invention documents can be performed. A translation can be realized.

By referring to the results of this machine translation, the translator may be able to efficiently or properly determine the translated words and phrases for the key words and phrases in the invention document.

Further, for example, in the display document related to the patent application-related information generated for the invention document acquired by the document acquisition unit, the display related to the key phrase extracted from the invention document by the key phrase extraction unit The control information includes processing for displaying the display element of the key phrase, attribute information of the key phrase in response to the operation of the display element, and processing of the key phrase from the claim information and the specification information based on the invention document. Important phrase inclusion description enumeration process for listing and displaying lines containing , web pages containing the relevant important phrases on a network search site, definitions of the relevant important phrases, synonyms of the relevant important phrases, or relationships of the relevant important phrases It functions as a GUI for executing a process of searching for an image or a process of translating the key phrase on a translation site on the network, and the attribute information of the key phrase extracted from the invention document is used for the invention. If the key phrase is used in the claims of the document, information indicating the paragraph number of the claim that includes the key phrase, and the description in the invention document with the key phrase added with a code. It is also possible to include information indicating the code when doing so.

As a result, translators, etc., who have browsed the patent application-related information related to the display document displayed by a browser, etc., can operate the key words in the displayed patent application-related information, and the important words as attribute information of the key words. Information such as the claim number in which the phrase is stated, the code corresponding to the key phrase, the search results of the key phrase (e.g. web pages containing the key phrase, the definition of the key phrase, synonyms, related images), the translation results of the key phrase, etc. Because it may be possible to know the key terms in the invention document, it may be possible to efficiently or properly understand the key terms. This may allow the translator to efficiently or properly determine translation terms for key terms.

In addition, the invention document analysis processing program in the present disclosure analyzes an invention document, which is a document describing a claim or specification for a patent application expressing a technical idea in Japanese, in a device equipped with a microprocessor. An invention document analysis processing program for performing invention document analysis processing, wherein the invention document analysis processing includes a setting information acquisition step of acquiring setting information including condition information indicating conditions for extracting key words; a document acquisition step of acquiring a document; an analysis step of analyzing the invention document acquired by the document acquisition step based on the setting information; and an analysis by the analysis step of the invention document acquired by the document acquisition step. an output step of outputting information generated based on the result, and the analysis step includes an important phrase extraction step of extracting important phrases from the invention document acquired by the document acquisition step based on the setting information. and the output step outputs information generated based on each of the plurality of important phrases extracted by the important phrase extraction step from the invention document acquired by the document acquisition step.
By installing this invention document analysis processing program in a device or the like having a microprocessor, the device or the like can implement the invention document analysis processing. By referring to the information output by the invention document analysis processing realized by this invention document analysis processing program, there is a possibility that translators and the like will be able to facilitate understanding of the invention document. Facilitating the understanding of the invention document is useful for translators to translate the invention document appropriately or efficiently.

In addition, the display document in the present disclosure is data output by the invention document analysis system described above, which may include a script as a computer program, and is data including a document written in a markup language. Documents for display in the present disclosure include documents written in a markup language, are subject to interpretation by a browser in a device equipped with a microprocessor, and display the above-mentioned patent application-related information generated by the above-described invention document analysis system. , as content to be displayed.
The patent application-related information is displayed by causing the browser in the device having the microprocessor to interpret this display document. By referring to this patent application-related information, there is a possibility that the understanding of the invention document will be promoted for translators and the like.

The invention document analysis system and invention document analysis processing program according to the present disclosure can be used to analyze invention documents, and the display document according to the present disclosure can be used to promote understanding of invention documents.

10, 20 invention document analysis system 10a, 10c, 10d, 10e, 10g, 10h terminal device 10b, 10f, 10i server device 101, 201 setting information acquisition unit 102, 202 document acquisition unit 103, 203 important phrase setting dictionary acquisition unit 104 , 204 invention document standard definition acquisition unit for translation 105, 205 analysis unit 106, 2071 document evaluation unit 107, 207 machine learning unit 108, 208 output unit 1051, 2051 key phrase extraction unit 10511 first extraction unit 10512 second extraction unit 10513 Third extraction unit 10514 Fourth extraction unit 1052, 20541 Translation word candidate set identification unit 1053, 2053 Classification unit 10531, 20531 Technical field identification unit 1054, 2054 Translation unit 1081, 2081 Learning model output unit 2021 Invention document acquisition unit 2022 Drawing document Acquisition unit 2023 Translation result document acquisition unit 2055 Importance determination unit 2056 Attribute identification unit 2057 Claim citation relation detection unit 2058 Inter-element relation determination unit 2059 Warning information generation unit 205a Claim information generation unit 205b Description information generation unit 205c Claim tree generation unit 2072 Teacher data accumulation unit 2073 Learning model management unit 2082 Patent application related information output unit 2083 Display document generation unit 2084 Display unit 20841 Operation reception unit

Claims (35)

An invention document analysis system for analyzing an invention document, which is a document describing claims and specifications for a patent application, in which a technical idea is expressed in Japanese,
a setting information acquisition unit for acquiring setting information including condition information indicating conditions for extracting key words;
a document acquisition unit that acquires an invention document;
an analysis unit that analyzes the invention document acquired by the document acquisition unit based on the setting information;
an output unit that outputs information generated based on the analysis result of the analysis unit for the invention document acquired by the document acquisition unit;
The analysis unit includes an important phrase extraction unit that extracts important phrases based on the setting information from the invention document acquired by the document acquisition unit,
The invention document analysis system, wherein the output unit outputs information generated based on each of the plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit. The output unit outputs patent application related information generated based on the analysis result of the analysis unit for the invention document acquired by the document acquisition unit,
The patent application-related information is output as a display document containing, as contents to be displayed, each of a plurality of important phrases extracted by the important phrase extraction unit from the invention document acquired by the document acquisition unit. ,
The patent application related information includes claim information representing the content of the claim of the invention document acquired by the document acquisition unit, which is to be displayed in the display document,
The claim information representing the content of the claim of the invention document acquired by the document acquisition unit is a display of the key phrase for each of a plurality of key phrases in the claim extracted from the invention document by the key phrase extraction unit. including display control information for controlling aspects,
The patent application related information includes specification information representing the content of the specification of the invention document acquired by the document acquisition unit, which should be displayed in the display document,
The description information representing the content of the specification of the invention document acquired by the document acquisition unit is for each of a plurality of key words in the specification extracted by the key word extraction unit from the invention document, including display control information for controlling the display mode of words,
The display control information for controlling the display mode of each of the plurality of important phrases extracted by the important phrase extraction unit in the claim information and the specification information corresponds to the display control information. including highlighting information for making the display mode of the key words and phrases to be different from the display mode of words and phrases other than the multiple key words and phrases in the claim information and the specification information,
Each of the display control information for controlling a display mode corresponding to each of a plurality of important phrases having different character strings constituting the important phrase among the important phrases represented in the claim information is Including different identification information for controlling each word to be displayed in a different display mode,
A mode of displaying key words and phrases that are the same as any one of the plurality of key words and phrases in which the character strings constituting the key words and phrases in the claim information are different from each other, among the key words and phrases represented in the specification information. The display control information for controlling the display element of the key phrase is controlled to be displayed in a display mode that is at least partially similar to the display mode of the display element of the one key phrase in the claim information. contains information for
The invention document analysis system according to claim 1. For each of a plurality of key words in the claim extracted by the key word extracting part, the display related to the key word/phrase included in the claim information representing the content of the claim of the invention document acquired by the document acquiring part. The control information includes information indicating a display color to be added to the important phrase,
For each of a plurality of key phrases in the specification extracted by the key phrase extraction unit, the key phrase is included in the specification information representing the content of the specification of the invention document acquired by the document acquisition unit. The display control information includes information indicating a display color to be added to the important phrase,
The display control information related to each of a plurality of key phrases having different character strings constituting the key phrase among the key phrases represented in the claim information controls the display element of each of the plurality of key phrases for each key phrase. Including information for controlling to display in a display mode with a different display color added, corresponding to the identification information of
the display for controlling the display mode of key words and phrases represented in the specification information that differ from any of the plurality of key words and phrases in which the character strings constituting the key words and phrases in the claim information are different from each other; The control information includes information for controlling the display element of the key phrase to be displayed in a display mode different from any of the display elements of the plurality of key phrases in the claim information,
of the key phrases represented in the specification information, the key phrases that are the same as any one of the plurality of key phrases in which the character strings constituting the key phrases in the claim information are different from each other; The display control information controls to display the display element of the important phrase in a display mode to which the same display color as the display mode of the display element of the one important phrase in the complaint information is added. 3. The invention document analysis system according to claim 2, wherein the information for analyzing the invention document is included. The display document is an HTML document containing an HTML file written in HTML (Hypertext Markup Language) containing the patent application-related information as content to be displayed,
Display control for an important phrase in the complaint information, which is composed of the same character string as any one of the plurality of important phrases in which the character strings constituting the important phrase are different from each other in the complaint information. The information is for controlling to display the key phrase in a display mode to which the same display color as the display mode of the one key phrase is added,
In the claim information, the display control information for each of the plurality of key phrases having different character strings constituting the key phrase has a predetermined width in which each of the plurality of key phrases is displayed in a different display color for each key phrase. It is for controlling to display in a display mode with a left border added,
For each of the plurality of key phrases in the specification information, if the key phrase is the same as any one of the plurality of key phrases in the claim information, the key phrase in the specification information In the display control information relating to the claim information, a left boundary line having the predetermined width is added to the important phrase in the same display color as the left border line according to the display mode of the one important phrase in the claim information. If the key phrase in the description information is different from any of the plurality of key phrases in the claim information, the key phrase in the description information 4. The invention document analysis system according to claim 3, wherein the display control information pertaining to is for controlling to display the important phrase in a display mode in which the left boundary line having the predetermined width is not added. The predetermined width is a width for one character,
In the claim information, for each of the plurality of key phrases having different character strings constituting the key phrase, the display control information related to the key phrase controls the key phrase as a right boundary line, an upper boundary line, and a lower boundary line. It is for controlling to display in a display mode without lines added,
The different display colors for each of the important phrases are display colors having different hue components for each of the important phrases, or display colors having different components of RGB values representing display colors for each of the important phrases.
The invention document analysis system according to claim 4 . The patent application related information includes at least part of the attribute information of each of the key phrases extracted from the invention document by the key phrase extraction unit, or at least one of the attribute information of the key phrases. Contains information based on
The invention document analysis system according to any one of claims 3 to 5. The analysis unit discriminates the relationship between the elements represented by the key words extracted by the key word extraction unit from the claims written in the invention document acquired by the document acquisition unit, including an inter-element relationship determination unit that generates word relationship information;
The patent application related information includes the important phrase related information,
The inter-element relation determining unit stores, in the important phrase relation information , part of the attribute information of the relevant important phrase for each of the plurality of important phrases extracted by the important phrase extraction unit from the claims written in the invention document. 7. The invention document analysis system according to claim 6 , wherein the inclusion relationship information expressing the compositional inclusion relationship between the element represented by the key phrase and the element represented by another key phrase is included . The setting information acquired by the setting information acquisition unit includes comment specifying information that is information specifying a comment line or a comment,
The analysis unit includes a claim tree generation unit that generates a claim tree that expresses the citation relationship of each item of the claim represented in the claim information in the patent application related information in a tree structure format,
The patent application related information includes the claim tree,
The claim tree generator,
For each claim clause in the above claim information, in ascending order of the clause number, on a new line, the claim that indicates the information indicating the clause number of the clause cited by the said clause by the symbol for expressing the citation relationship and the clause number generate a tree,
For each term in each row of such claim tree:
If the line immediately preceding the relevant paragraph in the claim information is a comment line in a prescribed format identified based on the aforementioned comment identifying information, the content of the comment line shall be the number of the relevant paragraph in the claim tree. Append to the line to be described,
If the line immediately preceding the relevant section in the claim information is not the comment line, and a comment is written in a predetermined format specified based on the comment specifying information on the same line as the heading of the relevant section, Append the content of the comment to the line that describes the item number of the item in the claim tree,
If the line immediately preceding the paragraph in the claim information is not the comment line and the comment is not stated on the same line as the heading of the paragraph, the When there are one or more key phrases extracted by the phrase extraction unit, at least one of the one or more key phrases is added to the line describing the item number of the claim tree. ,
The claim tree generation unit generates a configuration claim tree that expresses, in a tree structure format, the citation relationship of each item of the claim represented in the claim information in the patent application related information,
The patent application related information includes the configuration claim tree,
The claim tree generating unit, for each claim clause in the claim information, replaces the line in ascending order of the clause number, and converts information indicating the clause numbers of the clauses cited by the clauses into symbols for expressing citation relationships. and an item number, and for each item related to each line of the configuration claim tree, one or more important phrases described in the relevant item in the claim information and extracted by the important phrase extraction unit are If there is, each key phrase is added to the line that describes the paragraph number of the paragraph, and there are multiple key phrases to be added to the paragraph, and there is a structural gap between the elements represented by each of the multiple key phrases. If there is an inclusion relationship, add a description to the line that shows the relationship between key words
The invention document analysis system according to claim 7 . The patent application-related information includes claim-based specification information representing the content of the specification of the invention document acquired by the document acquisition unit, which should be displayed in the display document,
The claim-based specification information is each of a plurality of key phrases extracted by the key phrase extraction unit from the claims described in the invention document as part of the description content following the heading of the mode for carrying out the invention. , as part of the attribute information of the key phrase, inclusion based on inclusion relationship information that expresses the structural inclusion relationship between the element represented by the key phrase and the element represented by another key phrase Contains a description of a string with an incomplete message for description support to be used with appropriate modification, which represents but does not necessarily indicate inclusion
The invention document analysis system according to any one of claims 6 to 8. The invention document analysis system extracts from the claims written in the invention document acquired by the document acquisition unit the key phrase extraction unit, among the plurality of key phrases extracted by the key phrase extraction unit, key phrases whose codes do not correspond in the invention document. For words and phrases, the important words and phrases are identified based on the inclusion relationship information that expresses the structural inclusion relationship between the elements that the important words and phrases express and the elements that other important words and phrases express, as part of the attribute information of the relevant important words and phrases. determine the sign as part of the attribute information of
The patent application related information includes, for each of a plurality of important phrases extracted by the important phrase extraction unit from the claims described in the invention document, a code as a part of the attribute information of the relevant important phrase as the important phrase. containing an associated code list,
The patent application related information includes claim-based drawing information,
The claim-based drawing information is a configuration diagram based on a code as part of the attribute information of each of a plurality of key words and phrases extracted by the key word extraction unit from the claims described in the invention document. including
The invention document analysis system according to any one of claims 6 to 9. The patent application-related information includes an important phrase list listing important phrases and at least a part of attribute information of the important phrases extracted from the invention document by the important phrase extracting unit.
Each line of the list of important words and phrases is arranged in a predetermined order. The order according to the result of sorting in order, the descending order of the number of usage in the invention document for the key words for each line, or the descending order of the number of uses in the claims of the invention document for the key words for each line . 11. The invention document analysis system according to any one of -10 . In the claim information, the display control information for each of the plurality of key phrases having different character strings constituting the key phrase has a predetermined width in which each of the plurality of key phrases is displayed in a different display color for each key phrase. It is for controlling to display in a display mode with a left border added,
For each key phrase in the key phrase list, if the key phrase is the same as any one of the plurality of key phrases in the claim information, the key phrase in the key phrase list includes: The key phrase is displayed in a display mode to which a left border line having the predetermined width is added in the same display color as the display color of the left border line according to the display mode of the one key phrase in the claim information. 12. The invention document analysis system according to claim 11 , wherein control display control information is added. The analysis unit is configured to, for one or more key phrases extracted by the key phrase extraction unit from the invention document acquired by the document acquisition unit, translate word candidates that are a set of corresponding translation word candidates for the key phrases. including a translation word candidate set identification unit for identifying a set,
13. The invention document analysis system according to claim 11 or 12, wherein each line of said important phrase list includes one important phrase and a corresponding translation word or translation word candidate set corresponding to said important phrase. The display control information related to key phrases extracted from the invention document by the key phrase extraction unit in the display document relating to the patent application related information generated for the invention document acquired by the document acquisition unit, The display element of the key phrase functions as a graphical user interface for displaying at least part of the attribute information of the key phrase according to the operation.
The invention document analysis system according to any one of claims 6 to 13 . The display control information related to the important phrase extracted from the invention document by the important phrase extraction unit in the display document related to the patent application related information generated for the invention document acquired by the document acquisition unit, To display the number of the claim section that defines the relevant key term and the claim number that refers to the relevant key term in accordance with the mouseover operation on the display element of the relevant key term It functions as a graphical user interface for
The invention document analysis system according to claim 14. The display control information related to key phrases extracted from the invention document by the key phrase extraction unit in the display document relating to the patent application related information generated for the invention document acquired by the document acquisition unit, Using the display elements of the relevant important phrases to search for web pages containing the relevant important phrases, definitions of the relevant important phrases, synonyms of the relevant important phrases, or images related to the relevant important phrases on a search site on the network according to the operation. 16. The invention document analysis system according to any one of claims 6 to 15, wherein the invention document analysis system functions as a graphical user interface that executes a process of translating the relevant key words on a translation site on a network. The display control information related to key phrases extracted from the invention document by the key phrase extraction unit in the display document relating to the patent application related information generated for the invention document acquired by the document acquisition unit, Functioning as a graphical user interface for executing an important phrase inclusion description listing process for listing and displaying lines containing the relevant important phrase from the claim information and the specification information in accordance with the operation of the display element of the relevant important phrase. is what makes
The invention document analysis system according to any one of claims 6 to 16 . In the invention document analysis system, of the important phrases extracted from the invention document by the important phrase extraction unit, for important phrases corresponding to codes, the code and the important phrase are included as a part of the attribute information of the important phrases . Generate a code list that is a list in which words and phrases are associated and include it in the patent application related information,
The invention document analysis system is
Listing the codes described after the important words and phrases extracted by the important word extracting unit from the invention document, and representing the codes and the corresponding important words in association with each other,
If there is no description in the invention document in which a sign is added after the key phrase extracted by the key phrase extraction unit, the element represented by the key phrase is structurally different from the element represented by another key phrase. or when it is structurally contained in an element represented by another key phrase, a code is determined based on the structural inclusion relationship between the key phrase and the other key phrase, and the determined code and the By associating with key words and phrases,
The invention document analysis system according to any one of claims 6 to 17, wherein the code list is generated. The patent application related information includes a description heading list in which lines containing descriptions of headings representing paragraph numbers in the description of the invention document acquired by the document acquisition unit are listed in the order of description in the description,
In the specification heading list, for the line containing the description of the heading representing the paragraph number in the specification of the invention document, within the paragraph range related to the paragraph number in the specification, from the claim of the invention document to the above If there is a key phrase that is the same as the key phrase extracted by the key phrase extraction unit, the key phrase is added to the line of the specification heading list.
The invention document analysis system according to any one of claims 3 to 18 . The analysis unit generates warning information based on the invention document acquired by the document acquisition unit, and generates warning information including one or more pieces of indication information indicating inappropriate statements contained in the invention document. including the part
The patent application related information includes the warning information,
The warning information generation unit
If it is detected that the invention document acquired by the document acquisition unit contains a description that does not satisfy the condition that the same element name is described immediately before the same code, the same The warning information includes indication information indicating the code of and the element names of a plurality of different expressions to which the code is added ,
If a word or phrase is described following a reference character string in any of the claims of the invention document acquired by the document acquisition unit, the referenced word or phrase that is the same as that word or phrase is the reference character of the relevant paragraph. Including descriptions of reference strings that do not meet the requirement that they must appear in the part preceding the column or must appear within the paragraph to which the paragraph is cited given the chain of citations. If it is detected that there is no preceding referenced word, the section number of the section containing the description related to the detected reference character string, and the description related to the reference character string The warning information includes indication information indicating the contents of
The invention document analysis system according to any one of claims 3 to 19 . The warning information generation unit adds the claim information or the specification corresponding to the indication of the indication information to at least one display element of the indication information in the warning information included in the patent application related information as the display document. 21. The invention document analysis system according to claim 20 , further comprising adding display control information for causing the display element to function as a graphical user interface for displaying a link to the description location in the book information. In the claim information, the display control information for each of the plurality of key phrases having different character strings constituting the key phrase has a predetermined width in which each of the plurality of key phrases is displayed in a different display color for each key phrase. It is for controlling to display in a display mode with a left border added,
The patent application-related information includes each line of the claim information, and for each line or item of the included claim information, immediately after the contents of the line or item, Include claim translation information in which a translation line containing the result of replacing the included key phrase with a corresponding translated word corresponding to the key phrase is inserted,
The patent application related information includes each line of the specification information, and for each line of the included specification information, immediately after the content of the line, the important phrase contained in the line corresponds to the important phrase. Including the description translation information in which the translation line containing the result of replacement with the corresponding translated word is inserted,
The claim translation information and the description translation information are arranged so that corresponding translated words corresponding to the same key words as each of the plurality of key words having different character strings constituting the key words in the claim information are translated into the key words and phrases. including display control information for controlling the display mode of the corresponding corresponding translated word,
The display control information related to the corresponding translated word corresponding to the important phrase in the claim translation information and the specification translation information displays the corresponding translated word in the same color as the display color added to the relevant important phrase and in the predetermined width. The invention document analysis system according to any one of claims 3 to 21, which is for controlling display in a display mode in which a left boundary line having The condition information is
key phrase candidate character string pattern information indicating key phrase candidate character string patterns representing patterns of character strings that are key phrase candidates;
Reference character string pattern information indicating a reference character string pattern representing a reference character string pattern used for referencing the previously described character string;
coded string pattern information indicating a coded string pattern representing a pattern of a coded string appended after a string representing an element name;
and specific particle character string pattern information indicating a specific particle character string pattern representing a pattern of a character string that is a predetermined particle,
The key phrase candidate character string pattern information is defined so that at least a predetermined character string whose first character is Kanji and a predetermined character string whose first character is Katakana correspond to the important phrase candidate character string pattern. and
The reference character string pattern information is defined so that at least the character string "said" corresponds to the reference character string pattern,
The coded character string pattern information is defined so that at least a predetermined character string whose first character is a number corresponds to the coded character string pattern,
In the specific particle character string pattern information, at least any one of the characters "wo", "ni", "ga", "to", "kara", "he" and "ha" corresponds to the specific particle character string It is determined to correspond to the pattern,
The important phrase extraction unit
If the invention document acquired by the document acquisition unit contains a second character string corresponding to the key word candidate character string pattern subsequent to the first character string corresponding to the reference character string pattern, the second character string corresponding to the key phrase candidate character string pattern exists. a first extraction unit that extracts a character string that is the same as the two character strings as an important phrase;
In the claim of the invention document acquired by the document acquisition unit, when there is a period character following the third character string corresponding to the important phrase candidate character string pattern, the same character string as the third character string as an important phrase; and
If the invention document acquired by the document acquisition unit contains a fifth character string corresponding to the code character string pattern following the fourth character string corresponding to the important phrase candidate character string pattern, the fourth character string corresponding to the code character string pattern a third extraction unit that extracts the same character string as the four character strings as an important phrase;
If the invention document acquired by the document acquisition unit contains a seventh character string corresponding to the specific particle character string pattern following the sixth character string corresponding to the important phrase candidate character string pattern, a fourth extraction unit that extracts the same character string as the sixth character string as an important phrase,
In the extraction of important phrases, the important phrase extracting unit, when a plurality of character strings correspond to the important phrase candidate character string pattern, replaces one of the plurality of character strings with another character string. is included in the description of the invention document, select and extract the important words and phrases from the remaining character strings excluding the one character string among the plurality of character strings.
The invention document analysis system according to any one of claims 1 to 22 . The document acquisition unit acquires a plurality of invention documents and a plurality of translation result documents, which are translation results of each of the plurality of invention documents,
The invention document analysis system is
an invention document standard specification acquisition unit for acquiring an invention document standard specification for translation that defines a plurality of conditions to be satisfied by an invention document to be translated;
Regarding each of the plurality of invention documents acquired by the document acquisition unit, whether or not the invention document satisfies at least some of the plurality of conditions defined in the standard specification of invention documents for translation and a document evaluation unit that selects, from among the plurality of invention documents, invention documents for which the extent to which the conditions for which the judgment has been made exceeds a predetermined extent;
A machine that generates a learning model for translation, which is a learning model for machine translation, by machine learning using a combination of an invention document selected by the document evaluation unit and a translation result document corresponding to the invention document as teacher data. a learning part;
The invention document analysis system according to any one of claims 1 to 23, wherein the output unit includes a learning model output unit that outputs the learning model for translation generated by the machine learning unit. A device equipped with a microprocessor analyzes an invention document, which is a document describing claims and specifications for a patent application in which technical ideas are expressed in Japanese, and performs invention document analysis processing to generate a document for display. An invention document analysis method,
The invention document analysis process includes:
a document obtaining step of obtaining an invention document;
an analysis step of analyzing the invention document obtained by the document obtaining step by extracting important phrases based on predetermined conditions for extracting important phrases;
an output step of generating and outputting the display document for displaying the patent application-related information generated based on the analysis result of the analysis step for the invention document acquired by the document acquisition step;
The display document includes a document written in a markup language, is subject to interpretation by a browser in a device equipped with a microprocessor, and contains claims in an invention document for a patent application in which technical ideas are expressed in Japanese. and patent application related information including claim information representing the content of the specification of the invention document and the content to be displayed ,
The complaint information representing the contents of the complaint includes, for each key phrase extracted based on the predetermined conditions for extracting key phrases among the terms of the complaint, the display mode of the display element of the key phrase. contains display control information for controlling the
Each of the display control information relating to each of a plurality of key phrases having different character strings constituting the key phrase among the key phrases represented in the claim information controls display elements of the plurality of key phrases to be different from each other. Including information for controlling to display in a display mode with the display color added,
related to an important phrase composed of the same character string as any one of the plurality of important phrases in which the character strings constituting the important phrase are different from each other among the important phrases represented in the claim information The display control information is for controlling to display the display element of the key phrase in a display mode to which the same display color as the display mode of the display element of the one key phrase is added. contains information,
The specification information representing the content of the specification includes, for each key phrase extracted based on the conditions for extraction of key phrases among the terms in the specification, the display mode of the display element of the key phrase. contains display control information for controlling the
of the key phrases represented in the specification information, the key phrases that are the same as any one of the plurality of key phrases in which the character strings constituting the key phrases in the claim information are different from each other; The display control information controls to display the display element of the important phrase in a display mode to which the same display color as the display mode of the display element of the one important phrase in the complaint information is added. contains information for
Invention document analysis method. The display document is an HTML document containing an HTML file written in HTML (Hypertext Markup Language) as content for displaying the patent application-related information,
In the claim information, the display control information related to each of the plurality of key phrases having different character strings constituting the key phrase may display the display element of each of the plurality of key phrases in a different display color for each key phrase. is for controlling to display in a display mode with a left border line having a predetermined width added,
For each key phrase in the specification information, if the key phrase is the same as any one of the plurality of key phrases in the claim information, the key phrase related to the key phrase in the specification information The display control information sets the display element of the important phrase to a left boundary line having the predetermined width in the same display color as the display color of the left boundary line according to the display mode of the display element of the one important phrase in the claim information. is added, and if the key phrase in the description information is different from any of the multiple key phrases in the claim information, the key phrase in the description information 26. The invention document analysis method according to claim 25 , wherein said display control information is for controlling the display element of said important phrase to be displayed in a display mode in which said left boundary line having said predetermined width is not added. . The predetermined width is a width for one character,
The patent application-related information includes an important phrase list in which each of a plurality of important phrases in which the character strings constituting the important phrases in the claim information are different from each other are listed on a new line for each important phrase,
Each key phrase in the key phrase list is added with display control information for controlling the display mode of the display element of the key phrase,
The display control information related to the important phrase in the important phrase list is such that the important phrase is any one of the plurality of important phrases in the claim information, the character strings of which are different from each other. If it is the same as the phrase, the display element of the important phrase is displayed in the same display color as the display color of the left boundary line according to the display mode of the display element of the one important phrase in the claim information, and has the predetermined width. 27. The invention document analysis method according to claim 26 , wherein the invention document analysis method is for controlling display in a display mode in which a boundary line is added. Each row of the important phrase list includes one important phrase and a corresponding translated word corresponding to the important phrase, or a translation word candidate set that is a set of candidates for the corresponding translated word for the important phrase,
The display control information related to the important phrases in the important phrase list,
for controlling the display elements of the set of candidate translation words for the key phrase so as to function as a graphical user interface that enables selection of any element of the set of candidate translation words in response to an operation and
An element of the set of candidate translation words selected in response to an operation on the display element of the set of candidate translation words while functioning as the graphical user interface is used as a corresponding translation word corresponding to the key phrase. 28. The invention document analysis method according to claim 27 , further comprising a script for executing a process of determining, replacing the content of the display element of the set of candidate translation words with the determined corresponding translation word, and displaying the result. The display control information related to the key phrase in the patent application related information is such that the display element of the key phrase is displayed on a search site on the network according to the operation, the web page including the key phrase, the definition of the key phrase , a process of searching for synonyms of the relevant key words or related images of the relevant key words, or a process of translating the key words on a translation site on the network. The invention document analysis method according to any one of 25 to 28 . The display control information related to the key phrase in the patent application related information causes the display element of the key phrase to display at least a part of the attribute information of the key phrase, or the attribute of the key phrase, according to the operation. serves as a graphical user interface for displaying the importance of the relevant key phrases as determined based on information;
The attribute information of the important phrase is
information indicating the item number of a claim that defines the key phrase in the claim represented by the claim information, if there is one;
information indicating, if there is a claim section referring to the key phrase in the claim represented by the claim information, the number of the claim;
The invention document analysis method according to any one of claims 25 to 29, including information indicating the code when there is a description with a code added to the key phrase in the specification represented by the description information. . The display control information related to the key phrase in the patent application related information is a key phrase that lists the lines containing the key phrase from the claim information and the specification information according to the operation of the display element of the key phrase. It functions as a graphical user interface for executing inclusion description enumeration processing,
The key phrase inclusion description listing process lists and displays lines containing key phrases to be operated from the claim information and the specification information, and highlights the key phrases in each of the listed and displayed lines. and for the displayed line to function as a graphical user interface for displaying links to multiple lines including the line in the claim information or the description information according to the operation on the line. The invention document analysis method according to any one of claims 25 to 30, which is a process of adding display control information. The patent application related information includes claim translation information representing the results of machine translation of the claims represented in the claim information, and specification translation information representing the results of machine translation of the specification represented in the specification information. and
In the claim translation information, one line or one item representing the result of machine translation of one line or one item of the claim information is a complete translation of the entire line or item of the claim information in the target language. A partially translated line that is the result of replacing a key phrase contained in a line or a line or paragraph of the claim information with a corresponding translated word corresponding to the key phrase or a translation word candidate set for the key phrase can be,
In the description translation information, one line representing the result of machine translation for one line of the description information is a complete translation line that represents the entire line of the description information in the target language, or the A partially translated line that is the result of replacing key words contained in a line of specification information with a corresponding translated word corresponding to the key word or a translation word candidate set for the key word,
The claim translation information and the description translation information are arranged so that, for the same important phrase as any one of the plurality of important phrases in which the character strings constituting the important phrases in the claim information are different from each other, the important Including display control information for controlling the display mode of the display element of the result of machine translation of words and phrases as the object of machine translation, the display control information related to the display element of the result of the machine translation is the display mode of the display element for controlling the display mode of the display element so that at least a part of The invention document analysis method according to any one of claims 25 to 31 . The claim translation information includes each line of the claim information, and for each line or item of the included claim information, immediately after the content of the line or item, a machine translation of the content of the line or item The fully translated line or the partially translated line representing the result of machine translation corresponding to the target is inserted,
The description translation information includes each line of the description information, and for each line of the included description information, immediately after the line, the machine translation result corresponding to the machine translation target that is the line A fully translated line or the partially translated line is inserted,
In the claim translation information and the specification translation information, the display mode of at least a part of the display element to be machine-translated in the claim translation information and the specification translation information, and the result of machine translation corresponding to the machine-translation target In order to control the display mode of at least a part of the display elements to be different in at least one of character background color, character color, character decoration, font size, font style, and font weight, each display 33. The invention document analysis method according to claim 32 , wherein display control information is added to the element. The patent application related information includes warning information,
The warning information is
Pointing out whether or not the claim or the specification of the invention document satisfies a plurality of conditions set forth in the predefined Standard Rules for Invention Documents for Translation, and points out when the conditions are not met. information and
Predetermined based on the result of an examination as to whether or not the claim or the specification of the invention document satisfies at least some of a plurality of conditions stipulated in the invention document standard rules for translation Invention document evaluation information indicating the evaluation value of conformity of the invention document to the invention document standard provisions for translation calculated by the calculation;
provisional access information for accessing said invention document standard provision for translation;
The invention document analysis method according to any one of claims 25 to 33, further comprising: version information indicating a version of said invention document standard specification for translation. A device equipped with a microprocessor analyzes an invention document, which is a document describing claims and specifications for a patent application in which technical ideas are expressed in Japanese, and performs invention document analysis processing to generate a document for display. An invention document analysis processing program for realizing the invention document analysis method according to any one of claims 25 to 34 .