JP2007220144A - Patent retrieval device, and control method and control program for patent retrieval device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To clearly present reference and referred relationships between a plurality of patent literatures and further extract patent literatures of similar technical contents without any reference relationship. <P>SOLUTION: A retrieval processing part 102 of the patent retrieval system 100 analyzes a retrieval source patent literature and extracts a word or composite word contained in the condition setting patent literature as a retrieval condition word. Retrieving words are compared with the retrieval condition word in reference to a database part 11, and patent literatures having high similarity to the retrieval source patent literature are retrieved as patent literatures highly relevant to the retrieval source patent literature. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a patent search device, a control method for a patent search device, a control program, and a recording medium. In particular, a relationship between a plurality of patent documents or a relationship between claims in a patent document is clarified to a searcher. It relates to the technology to present.

  With the recent development of technology, the number of patent applications has become enormous. Along with this, the amount of patent literature has become enormous, preventing duplicate research, checking for infringement of rights, conducting pre-application investigations, grasping technological development trends of other companies, determining the direction of research and development, etc. In fact, it is not easy to search for patent documents. Conventionally, a patent search system is known as a means for reducing the load in such a patent document search. In the conventional patent search system, one or a plurality of keywords that are considered to be included in the patent documents to be searched are input, the patent documents including the keywords or keyword groups are extracted with reference to the database, and the extracted patent documents It was configured to generate and display or output a list.

  In the above conventional patent search system, although a “leakage” investigation can be performed, there is a problem that if a keyword is selected incorrectly, a large amount of unnecessary information is included. In such a case, there was a problem that the time required for the investigation itself was enormous. In addition, there is a problem in that related patent documents are lost if keywords are unnecessarily increased and narrowed down. Further, even when a plurality of patent documents are extracted, there is a problem that the relationship between each patent document cannot be understood unless the contents of the documents are read in detail. That is, even if a plurality of related patent documents are extracted, it is necessary to refer to some information described in the plurality of documents to determine which patent document is closer to the basic patent. Accordingly, an object of the present invention is to provide a patent search device capable of clearly showing a reference between a plurality of patent documents, a referenced relationship, and extracting a patent document having an approximate technical content even without a reference relationship, It is an object to provide a control method, a control program, and a recording medium for a patent search apparatus.

  In order to solve the above-mentioned problem, the patent search device includes a patent search database unit that stores a word or a compound word included in a patent document to be searched in advance as a search term phrase in association with the patent document, and a search source patent document. Analyzes and compares the search term phrase and the search condition phrase with a phrase extraction unit that extracts a word or compound word included in the condition setting patent document as a search condition phrase, and is similar to the search source patent document And a search unit that searches a highly patentable patent document as a patent document highly relevant to the search source patent document. According to the above configuration, the phrase extraction unit of the patent search device analyzes the search source patent document and extracts a word or compound word included in the condition setting patent document as a search condition word. The search unit refers to a patent search database unit to compare the search term phrase and the search condition phrase, and a patent document having a high similarity to the search source patent document is highly relevant to the search source patent document Search as patent literature.

  In this case, a reference destination extracting unit that extracts a reference relationship between the search source patent document and the highly relevant patent document may be provided based on the description in each patent document. Further, the patent search database unit may include a reference destination database unit that stores information on patent documents having a reference relationship in association with the search source patent document based on the extracted reference relationship. . Furthermore, based on the information in the reference destination database unit, a chart creation unit that creates a chart representing a reference relationship between the search source patent document and the highly relevant patent document, and the chart creation unit A display unit that presents a chart.

  Furthermore, a morpheme analysis unit that performs morphological analysis of the search source patent document and extracts the word or the compound word, and calculates the importance of the extracted word or compound word in the search source patent document. You may make it provide the degree calculation part and the registration part which matches the extracted said word or the said compound word with the said importance, and registers it as the said search term phrase in the said patent search database part. The search unit may search for highly relevant patent documents based on a distance between a vector corresponding to the search term phrase and a vector corresponding to the search condition phrase.

  The patent document further includes a description of a plurality of “claims”, and the search unit includes a claim analysis unit that extracts subordinate relationships between the plurality of “claims” based on the search term phrases. You may make it prepare. Furthermore, the claim analysis unit includes the description of other “claims” included in the “claim” of the search object, and the name of the invention of the “claim” and other “claim” of the search object. The dependency relationship may be extracted based on this. In addition, the claim analysis unit includes the description of the other “claim” in the “claim” of the search object, and the name of the invention of the “claim” of the search object and the other “claim”. When the names of the inventions of the “term” are the same, it may be determined that the dependency exists. Further, the patent document includes a description of “claim”, and the search unit includes a claim analysis unit that extracts a constituent element included in the description of “claim” based on the search term phrase. May be.

  Further, in a method for controlling a patent search apparatus having a patent search database unit that stores a word or a compound word included in a patent document to be searched for in association with the patent document as a search term phrase in advance, the search source patent document is analyzed. The phrase extraction process of extracting a word or compound word included in the condition setting patent document as a search condition phrase and the search term phrase and the search condition phrase are compared, and the similarity to the search source patent document is compared. And a search process for searching for a high patent document as a patent document highly relevant to the search source patent document. In this case, a reference destination extraction process for extracting a reference relationship between the search source patent document and the highly relevant patent document based on the description in each patent document may be provided.

  In addition, the patent search database unit includes a reference destination database unit that stores information on patent documents having a reference relationship in association with the search source patent document based on the extracted reference relationship, and the reference destination database A chart creation process for creating a chart representing a reference relationship between the search source patent document and the highly relevant patent document based on the information of the section, and a display for presenting the chart created by the chart creation section And a process. Further, a morpheme analysis process for extracting the word or the compound word by performing a morphological analysis of the search source patent document, and an importance calculation for calculating the importance of the extracted word or the compound word in the search source patent document A registration process for registering the extracted word or the compound word as the search term phrase in the patent search database unit in association with the importance.

  Furthermore, the search process may search for highly relevant patent documents based on a distance between a vector corresponding to the search term phrase and a vector corresponding to the search condition phrase. In addition, the patent document includes a description of a plurality of “claims”, and the search process extracts a subordinate relationship between the plurality of “claims” based on the search term phrase. You may make it provide. Further, the claim analysis process is based on the description of other “claims” included in the “claim” to be searched and the names of the inventions of the “claim” and other “claims” of the search target. The dependency relationship may be extracted.

  Furthermore, the claim analysis process includes the description of the other “claim” in the “claim” of the search object, and the name of the invention of the “claim” of the search object and the other “claim”. When the names of the inventions of the “claims” are the same, it may be determined that the dependency exists. Further, the patent document includes a description of “claim”, and the search process includes a claim analysis process of extracting a constituent element included in the description of “claim” based on the search term phrase. It may be.

  In addition, a control program that causes a computer having a patent search database unit that stores a word or a compound word included in a patent document to be searched for in advance as a search term phrase in association with the patent document is a search source patent. Analyzing the document, extracting a word or compound word contained in the condition setting patent document as a search condition word, comparing the search term phrase and the search condition word, and having similarity to the search source patent document It is characterized in that a high-patent document is searched as a patent document highly relevant to the search source patent document. In this case, a reference relationship between the search source patent document and the highly related patent document may be extracted based on the description in each patent document. Further, the patent document may include a plurality of “claims”, and a dependency relationship between the plurality of “claims” may be extracted based on the search term phrase. Further, the patent document may include a description of “claim”, and a constituent element included in the description of “claim” may be extracted based on the search term phrase. The control programs may be recorded on a recording medium.

  According to the present invention, when performing a patent search, a “leakage” search can be performed and unnecessary information can be prevented from being included. In addition, it is possible to clearly present a reference and a referenced relationship between a plurality of patent documents, and to extract patent documents having approximate technical contents even without a reference relationship. Furthermore, the dependent relationships of the claims in the same patent document can be clarified and presented.

Next, preferred embodiments of the present invention will be described with reference to the drawings. In the present embodiment, the present invention is applied to a patent search system.
[1] Patent Search Database Registration System First, a patent search database registration system for constructing a patent search database used in the patent search system will be described.
[1-1] Configuration of Patent Search Database Registration System FIG. 1 is a schematic configuration block diagram of a patent search database registration system. The patent search database registration system 10 roughly includes a database unit 11 that stores various data as a database, and a registration processing unit 12 that registers various data in the database unit 11. Here, the patent search database registration system 10 can be realized in a computer system, and the function of the registration processing unit 12 is realized by a program that can be executed by a microprocessor corresponding to each unit constituting the registration processing unit 12. . Such a program may be directly executed from a recording medium such as a semiconductor memory or a CD-ROM. It is also possible to install and execute a program in the external storage device in advance. Further, it may be installed via a network such as the Internet every time it is executed prior to execution of the program or only once at the beginning.

[1.1.1] Configuration of Database Unit First, the configuration of the database unit will be described. The database unit 11 is constructed in an external storage device such as a hard disk. The database unit 11 includes a word database 15, a component requirement (invention specific matter) database 16, a dependency relationship database 17, and a reference document database 18. The word database 15 is a database for storing words or compound words included in the patent document PD in association with a specific classification (field) designated in advance.

  FIG. 2 shows the basic configuration of the word database. The word database 15 roughly includes a page table 21, a keyword table 22, and a word table 23. In FIG. 2, only one system keyword table 22 and word table 23 are shown for one page table 21, but in practice, a plurality of system keyword tables 22 and A word table 23 is configured and has a tree structure (tree structure) as a whole. The page table 21 includes page ID data 31, identification number data 32, title data 33, update date / time data 34, bibliographic data 35 and linked number data 36. Note that this data configuration is an example, and the present invention is not limited to this. For example, data such as the number of pages and technical fields of the corresponding publication may be incorporated.

  The page ID data 31 is uniquely assigned to each patent document (patent document) PD to be registered, and is data for specifying each patent document PD. The identification number data 32 is data having a value assigned to each patent document PD by the Patent Office, such as a publication number. The title data 33 stores a name representing the contents of each patent document PD. For example, when the patent document PD is a patent publication, it is the name of the invention. The update date / time data 34 stores the registration date / time of each patent document PD. When the patent document PD is a patent gazette, the bibliographic data 35 includes the publication country, publication type, publication number, publication date, international patent classification information (FI classification number, etc.), examination request, Number, application form, total number of pages, application number, filing date, application number of priority claim basic application, application number of priority claim basic application, filing date of priority claim basic application, applicant information (identification number, name) Or name, address or residence), inventor information (name, address or residence), agent information (identification number, name, qualification), theme code, F-term, etc. That is, the bibliographic data 35 is data for storing various bibliographic information related to each patent document PD. The number-of-links data 36 is data for storing the number of documents of other patent documents to which each patent document PD is referenced.

  The keyword table 22 is a table for associating the page table 21 and the word table 23. The keyword table 22 includes page ID data 41, word ID data 42, appearance frequency (cost) data 43, importance data 44, and paragraph flag data 45. The page ID data 41 is data stored by data corresponding to the page ID data 31 of the page table 21. That is, if the same data as the page ID data 31 of the page table 21 is stored, the keyword table 22 indicates that data related to the page table 21 having the same page ID data is stored. Yes. The word ID data 42 is data for associating with the word table 23 that stores information about the corresponding word.

  The appearance number (cost) data 43 is data corresponding to the number of appearances in the patent document specified by the page ID data 41 of the word specified by the word ID data 42. That is, it is data representing how many times a certain word is used in the patent document. The importance data 44 stores the TFIDF value calculated by the TFIDF method as the importance of the word specified by the word ID data 42 in the patent document specified by the page ID data 41. This TFIDF value is calculated based on IDF data (IDF value; corresponding to the number of documents in which the corresponding word appears in all patent documents) and the appearance frequency data 43 stored in a word table to be described later. That is, the smaller the number of documents in which a certain word appears and the larger the number of occurrences of the word in each document, the more important the word is recognized.

  The paragraph flag data 45 is data indicating in which paragraph in the patent document specified by the page ID data 41 the word specified by the word ID data 42 is detected. The paragraph in this case includes concepts such as chapters and sections in addition to the meaning of a general paragraph when the patent document is a normal document such as a paper or a book. If the patent document is a patent gazette, etc., the title column of the invention, the claims column, the detailed description column of the invention, the brief description column of the drawings, the summary column, etc. are also included in the paragraph. I handle it.

  The word table 23 includes word data 51, word ID data 52, and IDF data 53. In the word data 51, words after morphological analysis are registered. The word ID data 52 is data for specifying a word registered as the word data 51. In IDF data 53, IDF values corresponding to the number of documents in which words registered as word data 51 appear in all patent documents are registered. The configuration requirement database 16 stores data of configuration requirements (so-called invention specific items) included in the scope of claims from patent publications such as patent publications and patent publications. Specifically, the name of each constituent requirement, a word that characterizes the action of each constituent requirement, and the like are stored. The dependency relationship database 17 stores data related to dependency relationships that are links between claims (claims).

  FIG. 3 shows the data format of the dependency relationship database 17. The dependency relationship database 17 includes page ID data 55, cited request data 56, and cited request data 57. The page ID data 55 is the same data as the page ID data 31 of the page table 21, and the cited claim data 56 and the cited claim data 57 corresponding to the page ID data 55 correspond to the page ID data 55. It represents the dependency of the claims included in the patent document. In the cited claim data 56, the claim number of a claim cited by another claim is registered. In the cited claim data 57, the claim number of a claim that cites another claim is registered.

Specifically, in the description of the claims of the patent document specified by page data = 1, claims 1 and 2 are independent claims, and claim 3 is claims 1 and 2. In the description of the claims of the patent document specified by page data = 2, claim 1 is an independent claim, and claim 2 is cited as claim 1. In the case of a dependent term, data as shown in FIG. 4 is registered in the dependency relationship database 17. That is, as shown in FIG. 4, the following data (1) to (3) are registered.
(1) Page ID data = 1, cited claim data = 1, cited claim data = 3
(2) Page ID data = 1, cited claim data = 2, cited claim data = 3
(3) Page ID data = 2, cited request data = 1, cited request data = 2

  The reference document database 18 stores, for each patent document, data related to a reference document referred to in the document or a reference document referred in examination. Specifically, reference document numbers (patent publication numbers, patent numbers,...), Document names, document reference pages, document issuers, author names, and the like are stored as necessary. As shown in FIG. 8, the reference document database 18 includes reference destination page ID data 81, reference source page ID data 82, title data 83, document type data 84, and document bibliographic information data 85. The reference destination page ID data 81 is page ID data for specifying a reference destination patent document. The reference source page ID data 82 is page ID data for specifying a reference source patent document.

  The title data 83 registers the document title of the reference destination. In the case of the above-mentioned example, “Japanese Patent Laid-Open No. 12345/1990” becomes the document title. The document type data 84 is data representing the type of the referenced patent document. For example, the document type data = 0 when the type of the patent document to be referred to is a domestic patent publication, the document type data = 1 when it is a foreign patent gazette, and the document type data = 2 when it is a paper. Is set. The bibliographic information data 85 stores bibliographic information such as a document name, a document reference page, a document publisher, and an author name in a text data format such as CSV format in a predetermined order. Note that this bibliographic information data 85 is not necessarily provided unless such information is required.

[1.1.2] Configuration of Search Processing Unit Next, the configuration of the search processing unit 12 will be described with reference to FIG. 1 again. The search processing unit 12 is roughly divided into a morpheme analysis unit 61, an importance calculation unit 62, a claim analysis unit 63, a morpheme analysis dictionary unit 64, a reference document extraction unit 65, a standardization unit 66, A stop word processing unit 67. The morpheme analysis unit 61 registers, in the word database 15, nouns, sagittal nouns, other nouns, or words similar to sagittal nouns that frequently appear by analyzing the patent document PD. Prior to registration of words in the word database 15 by the morpheme analysis unit 61, the standardization unit 66 performs standardization (unification) of words. For example, when three types of words “PC”, “personal computer”, and “personal computer” are obtained by morphological analysis, these words have the same meaning. Unify. In addition, the stop word processing unit 67 performs processing so as not to register frequently appearing words in the word database 15 regardless of the type of patent document in the patent field. For example, words such as “claim”, “application”, “patent”, “present invention”, and “utility model” are not registered in the word database 15 as words.

  The importance calculation unit 62 calculates the importance as a TFIDF value using the TFIDF method for a word registered by morphological analysis and registers it in the word database 15. The claim analysis unit 63 roughly includes a dependency relationship analysis unit 63A and a component requirement extraction unit 63B. When the patent document is a patent gazette, a utility model gazette, or the like, the dependency relationship analysis unit 63A analyzes the claims and the scope of the utility model registration request and examines the dependency relationship between the claims. Further, the configuration requirement extraction unit 63B extracts configuration requirements (for example, invention-specific matters) from the scope of claims and the scope of claims for utility model registration. The morpheme analysis dictionary unit 64 stores a morpheme analysis dictionary having a generally known aspect that is used when the morpheme analysis unit 61 performs morpheme analysis. The reference document extraction unit 65 extracts, for each patent document, a reference document referred to in the document or a reference document referred to in examination, and registers it in the reference document database 18.

[1.2] Operation of Patent Search Database Registration System Next, the operation of the patent search database registration system will be described. In the following description, a case where a patent publication is registered as a patent document will be described as an example. FIG. 5 shows a flowchart of the patent search database registration process. First, the patent search database registration system 10 performs morphological analysis (step S1) and registers it in the word database (step S2). Specifically, when performing morphological analysis of patent documents, the morpheme analysis unit 61 assigns a unique number to each patent document as a page ID based on a predetermined condition, and page ID data of the page table and page of the keyword table Register in ID data. Next, the morpheme analysis unit 61 performs morpheme analysis of a patent publication that is a patent document, and registers the publication number as the recognition number data 32.

  Subsequently, the morphological analyzer 61 extracts the name of the invention and registers the name of the invention as the title data 33. And the morphological analysis part 61 registers the registration date in the said database registration system into update date data about the said patent gazette. In addition, the morphological analysis unit 61, from the patent publication, the publication country, publication type, publication number, publication date, international patent classification information, presence or absence of examination request, number of claims, application form, total number of pages, application number, Extract application date, priority claim basic application number, priority claim basic application number, priority claim basic application date, applicant information, inventor information, agent information, theme code, F-term, etc. And registered as bibliographic data 35. Next, the patent search database registration system calculates the importance of each word based on the result of morphological analysis (step S3) and registers it in the keyword table 22 of the word database 15 (step S2).

In this case, the importance level calculation unit 62 calculates the importance level stored as the importance level data based on the appearance count (cost) data 43 of the keyword table and the IDF data 53 of the word table. Specifically, the number of appearances for each word (keyword) included in all registered patent documents is TF, the total number of registered patent documents is N, and the importance calculation target of all registered patent documents is N. When the number of patent documents including a word is n, a TFIDF value is calculated as importance data by the following equation.
IDF = log (N / n)
TFIDF = TF ・ IDF
In this case, the calculated IDF is registered in the word table as IDF data. Next, the patent search database registration system analyzes the dependency relationship between claims, which is a part of claim analysis (step S4), and registers it in the dependency relationship database 17 (step S5).

  In this case, the dependency relationship analyzing unit 63A may include “in the □□ method described in claim XX”, “...” in the scope of claims and utility model registration claims. Based on the description such as “1. Apparatus”, the dependency relationship between the claims is analyzed, and the dependency relationship as shown in FIG. 4 is registered in the dependency relationship database. Next, the patent search database registration system extracts constituent requirements that are part of the analysis of claims (step S6). In this case, the component requirement extraction unit 63B extracts the component requirement (invention specific matter) from the description in the claims and registers it in the component requirement database 16 (step S7). Specifically, a description will be given of the case of extracting the configuration requirements from the following claims.

[Claim 1] A method for associating n documents ordered in time series, the step of calculating a similarity between the n documents, and a similarity matrix using a time constraint from the similarity A document associating method comprising: creating a document; and converting the similarity matrix into an adjacency matrix indicating the document association.

In this case, the following three components are extracted by the keyword “step”.
“Step of calculating similarity between the n documents”
“Creating a similarity matrix using time constraints from the similarity”,
“Transforming the similarity matrix into an adjacency matrix indicating the association of the document”
The extracted configuration requirement is registered in the configuration requirement database 16.
Specifically, the configuration requirement database 16 includes page ID data 71, claim ID data 72, and configuration requirement text data 73, as shown in FIG. The page ID data 71 is the same data as the page ID data 31 of the page table 21, and the claim ID data 72 and the configuration requirement text data 73 corresponding to the page ID data 71 are patent documents corresponding to the page ID data 71. Represents the contents of the claims included in. The complaint ID data 72 is data for specifying the complaint number of the text data stored in the component requirement text data 73.

  The configuration requirement text data 73 is data for storing the configuration requirement as text data. And when the said claim is registered into the component requirement database 16, it will come to show in FIG. That is, the number for specifying the patent document = 231 is stored as the page ID data 71, the number = 1 representing claim 1 is stored as the claim ID data 72, and the text data corresponding to the content of claim 1 = “ The step of calculating the similarity between the n documents is stored as the component requirement text data 73.

  Next, the patent search database registration system 10 extracts reference documents (step S8). In this case, the reference document extraction unit 65 detects in the patent publication (patent document) whether one of the patent documents (patent publications in Japan and abroad, papers, etc.) is cited, and references information (publication number). , Book title, paper title, etc.) are registered in the reference database. In addition, when the referenced patent document is already registered, the value of the linked number data 36 of the page table 21 corresponding to the referenced patent document is updated.

  Specifically, descriptions such as “according to Japanese Patent Application Laid-Open No. △ 12345 ...” and “refer to the document“ Fast Algorithms for Mining Association ”……” are extracted from patent gazettes that are patent documents. Register in the database 18.

[1.3] Configuration of Patent Search System FIG. 9 is a schematic configuration block diagram of the patent search system. 9, parts that are the same as those in the patent search database registration system of FIG. 1 are given the same reference numerals, and detailed descriptions thereof are omitted. The patent search system 100 roughly includes a database unit 11 that stores various data as a database, a search processing unit 102 that performs a patent search using the database unit 11, a display unit 103, and an input unit 104. ing.

  Here, the patent search system 100 can be realized in a computer system, and the function of the search processing unit 102 is realized by a program that can be executed by a microprocessor corresponding to each unit constituting the search processing unit 102. Such a program may be directly executed from a recording medium such as a semiconductor memory or a CD-ROM. It is also possible to install and execute a program in the external storage device in advance. Further, it may be installed via a network such as the Internet every time it is executed prior to execution of the program or only once at the beginning. The search processing unit 102 performs similar search, claim search, or reference destination search, which will be described later, based on the search source patent document (or specifying information for specifying the search source patent document) input via the input unit 104. The display unit 103 displays various data including search results and presents them to the search operator. The input unit 104 includes a keyboard, a mouse, a tablet, a scanner, a removable disk device, a communication interface unit, and the like, and inputs data corresponding to a search source patent document and sets various search conditions.

[1.3.1] Configuration of Search Processing Unit Next, the configuration of the search processing unit will be described. The search processing unit 102 is roughly divided into a syntax analysis / morpheme analysis unit 111, a morpheme analysis dictionary unit 112, a chart creation unit 113, an actual search processing unit 114, a standardization unit 115, and a stop word processing unit 116. And. The syntax analysis / morpheme analysis unit 111 functions as a phrase extraction unit, and includes a morpheme analysis unit 121, a claim analysis unit 122, and a reference document extraction unit 123. The morpheme analysis unit 121 uses the morpheme analysis dictionary 64 to extract nouns, sa-changing nouns, other nouns, or words that are similar to sa-changing nouns by morphologically analyzing patent documents.

  When the morpheme analysis result is output by the morpheme analysis unit 121, the standardization unit 115 standardizes (unifies) words. In addition, the stop word processing unit 116 performs processing so that words that appear frequently regardless of the type of patent document in the patent field are not output as morphological analysis results. When the search source patent document is a patent gazette, a utility model gazette, or the like, the claim analysis unit 122 analyzes a claim range, a utility model registration request range, and the like, and examines a dependency relationship between the claims. Further, constituent requirements (for example, invention-specific matters) are extracted from the scope of claims and the scope of claims for utility model registration. The reference destination extracting unit 123 extracts a reference document referred to in the search source patent document or a reference document referred to in examination or the like for the search source patent document. The morpheme analysis dictionary unit 112 stores a morpheme analysis dictionary used when the morpheme analysis unit 121 performs morpheme analysis.

  The chart creation unit 113 charts the search results and presents them to the search operator. The actual search processing unit 114 functions as a search unit, and roughly includes a similarity search unit 131, a claim search unit 132, and a reference destination search unit 133. The similarity search unit 131 searches for patent documents similar to the search source patent document, extracts patent documents having a similar relationship, and grasps the similar relationship. The claim search unit 132 grasps the dependency relationship of the claims (claims) of the search source patent document. The reference document search unit 133 extracts a patent document referred to in the search source patent document or a patent document referred to in examination.

[1.4] Operation of Patent Search System Next, the operation of the patent search system will be described. In the following description, a case where a patent gazette is used as a search source patent document will be mainly described. FIG. 10 shows a flowchart of the patent search process. In this case, prior to the patent search process, either an operator performs a similar search process for searching for similar patent documents or a claims search process for examining the relationship between claims of the patent documents. It is assumed that the similarity search flag is set when the similar search process is performed, and the claim flag is set when the claim search process is performed. First, the patent search system 100 determines whether or not the search source patent document is unregistered in the database unit 11 (step S11).

  If the search source patent document is already registered in the database in step S11 (step S11; No), it is determined which of the similar search flag and the claim flag is set (step S12). If it is determined in step S12 that the similar search flag is set (step S12; similar flag set), the reference destination search unit 133 of the actual search processing unit 114 searches the reference document database 18 to search the source patent. The patent document referred to by the document is extracted (step S13). Next, the similarity search unit 131 of the actual search processing unit 114 reads the words included in the search source patent document with reference to the word database 15 and performs a similar search for each word (step S14). The distance matching with other patent documents registered in the word database 15 and pattern matching are performed for the constituent elements of the claims.

  More specifically, when the search source patent document is a Japanese patent gazette, for example, each of the words included in the detailed description and summary of the invention is represented by a vector and registered in the word database. A distance calculation process is performed with a vector corresponding to a word included in the patent document. In addition, pattern matching processing is performed between the constituent elements of the claims constituting the scope of claims in the search source patent document and the constituent elements registered in the constituent requirement database to obtain the similarity. Based on the degree of similarity obtained by the distance calculation process and the pattern matching process, patent documents in a predetermined similarity range are specified. The same distance calculation process and pattern matching process are also performed for the patent document referenced by the search source patent document. When the similarity search process is completed, the chart creation unit 113 performs a process for charting the similarity search result (step S15). When the chart creation unit 113 finishes the process for charting the similar search results, the display unit 103 displays a chart corresponding to the similar search results (step S16).

  FIG. 11 shows an example of a chart corresponding to the similar search result. In the following description, the expression “patent gazette” includes not only a patent publication gazette in Japan but also a published patent gazette and other gazettes. In FIG. 11, patent publication X is a search source patent document. A patent document that is directly or indirectly connected to the patent publication X is a patent document that is directly or indirectly referred to. A patent document that is not tied to any patent document is a similar document, but is not a direct reference relationship. In this case, the closer the two-dimensional distance between the patent documents is, the higher the similarity is. Further, a patent document displayed on the left side of the display position of the patent publication X and directly connected to the patent publication X (US Patent Publication S, Patent Publication C, Patent Publication B, Patent Publication D, University Article R) Is a patent document directly referred to by Patent Publication X. That is, US Patent Publication S, Patent Publication C, Patent Publication B, Patent Publication D, and University Paper R are patent documents that are directly described and referenced in Patent Publication X that is a search source patent document.

  Further, the closer the two-dimensional distance between these US patent publication S, patent publication C, patent publication B, patent publication D, university paper R and patent publication X, the higher the similarity. Moreover, the number displayed in the frame representing each patent document is the number of patent documents referring to the patent document. In the case of the example in this figure, since Patent Gazette A and Patent Gazette E have a large number of references, it can be determined that the possibility of a basic patent is high. Therefore, when the patent publication X is a patent publication publication, it is considered that the patent applicant should refer to the inventions described in the patent publications A and E first. Further, since there are also patent publications N, Q, and P similar to the patent publication X, it can be understood that attention is necessary for the inventions described in these patent publications. In this case, if any patent document is selected on the display screen of the display unit 103 and a search type is designated, similarly, a search process using the selected patent document as a search source patent document is performed. With this configuration, the search can be continued hierarchically, and a desired patent document can be searched efficiently.

  In addition, when multiple patent documents are connected by line segments, line segments are color-coded and systematized, or within the frame representing patent documents for each applicant, for each inventor, for each agent (such as patent attorney) It is possible to make it easier to grasp the relationship between patent documents by changing the color of the image or by blinking (blinking). On the other hand, if it is determined in step S12 that the claim flag is set (step S12; claim flag set), the claim search unit 132 of the actual search processing unit 114 searches the configuration requirement database and the dependency relationship database. Then, the dependency relation between claims is extracted (step S17). When the claim search process ends, the chart creation unit 113 performs a process for charting the claim search result (step S15). When the chart creation unit 113 finishes the process for charting the complaint search results, the display unit 103 displays a chart corresponding to the complaint search results (step S16).

FIG. 12 shows an example of a chart corresponding to the complaint search result. In this case, each claim has the following description.
Claim 1: "Knowledge extraction method characterized by comprising ..."
Claim 2: "In the knowledge extracting method according to claim 1, ..."
Claim 3: "In the knowledge extraction method according to claim 2, ..."
Claim 4: "Knowledge extraction device characterized by comprising ..."
Claim 5: “In the knowledge extracting device according to claim 4, ...”
Claim 6: "In the knowledge extracting device according to claim 4, ..."
Claim 7: “In the knowledge extracting device according to claim 4, ...”
Claim 8: "In the knowledge extracting device according to claim 4, ..."
Claim 9: "Knowledge extraction program characterized by comprising ..."

  The claim search unit 132 detects that claims 1, 4 and 9 are independent claims based on the description of each claim. In other words, an independent claim is defined as a claim that does not include a description of another claim in the description of the claim or a claim that includes only a description of another claim with a different title. Further, the claim search unit 132 has the same name as the invention of the claim described before the claim and the description of the other claim (for example, “claim XX”). ) Are determined to be dependent claims dependent on the other claims. That is, it is detected that claim 2 is a dependent claim of claim 1, claim 3 is a dependent claim of claim 2, and claims 5 to 8 are dependent claims of claim 4, respectively. As a result, as shown in FIG. 12, the frame corresponding to claim 1 and the frame corresponding to claim 2 are connected by a line segment, and the frame corresponding to claim 2 and the frame corresponding to claim 3 are lines. Connected and displayed by minutes. The frames corresponding to claim 4 are displayed with the frames corresponding to claims 5 to 8 connected in parallel by line segments. Further, the frame corresponding to claim 9 is displayed independently. With such a display, the searcher can intuitively grasp the independent claims specifying the basic contents in the claim group and easily determine the dependency between the claims. I can grasp.

[1.5] Effects of the Embodiment As described above, according to the present embodiment, when performing a patent search, an operator performs a “leak leak” investigation without inputting a keyword, Inclusion of necessary information can be suppressed. In addition, it is possible to clearly present a reference and a referenced relationship between a plurality of patent documents, and to extract patent documents having approximate technical contents even without a reference relationship. Furthermore, the dependency relationship of the claims in the same patent document can be clarified and presented to the operator in a state that can be easily grasped visually.

[2] Modification of Embodiment [2.1] First Modification In the above description, the database unit 11 is configured integrally with the registration processing unit 12 (or the search processing unit 102). It is also possible to configure as a distributed processing system via In this case, each database 15, 16, 17, 18 and morphological analysis dictionary 64 constituting the database unit 11 is further stored in another database server via the network, and a plurality of registration processing units 12 ( Alternatively, a configuration that can be used from a computer system that functions as the search processing unit 102) is also possible.

[2.2] Second Modification In the above description, the standardization unit 66 (or the standardization unit 115) has been described as an indispensable configuration. However, even if the standardization unit 23 is not necessarily provided, the capacity of the database slightly increases. Although there are disadvantages, it is possible to obtain almost the same effect.

It is a general | schematic block diagram of a patent search database registration system. It is a basic lineblock diagram of a word database. It is explanatory drawing of the data format of a dependency relationship database. It is explanatory drawing of the data registration example of a dependency relationship database. It is a flowchart of a patent search database registration process. It is explanatory drawing of the data format of a component requirement database. It is explanatory drawing of the data registration example of a structure requirement database. It is explanatory drawing of the data format of a reference literature database. It is a general | schematic block diagram of a patent search system. It is a flowchart of a patent search process. It is explanatory drawing of an example of the chart corresponding to a similar search result. It is explanatory drawing of an example of the chart corresponding to a claim search result.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Patent search database registration system, 11 ... Database part, 12 ... Registration process part, 15 ... Word database, 16 ... Configuration requirement (invention specific matter) database, 17 ... Dependency relation database, 18 ... Reference literature database, 21 ... Page Table: 22 ... Keyword table, 31 ... Page ID data, 32 ... Recognition number data, 33 ... Title data, 34 ... Update date / time data, 35 ... Bibliographic data, 36 ... Number of linked data, 100 ... Patent search system, 102 ... search processing unit, 103 ... display unit, 104 ... input unit, 111 ... syntax analysis / morpheme analysis unit, 112 ... dictionary unit for morpheme analysis, 113 ... chart creation unit, 114 ... actual search processing unit, 115 ... standardization unit, 116: Stop word processing unit, 121 ... Morphological analysis unit, 122 ... Claim analysis unit 123 ... reference extraction unit.

Claims (24)

A patent search database unit that stores words or compound words included in a patent document to be searched in advance in association with the patent document as a search term phrase;
Analyzing a search source patent document, and extracting a word or compound word included in the condition setting patent document as a search condition word; and
A search unit that compares the search term phrase and the search condition phrase, and searches for a patent document that is highly similar to the search source patent document as a patent document that is highly relevant to the search source patent document. Patent search device characterized by the above. The patent search device according to claim 1,
A patent search apparatus comprising: a reference destination extraction unit that extracts a reference relationship between the search source patent document and the highly relevant patent document based on description in each patent document. The patent search device according to claim 2,
The patent search database unit includes a reference destination database unit that stores information on patent documents having a reference relationship in association with the search source patent document based on the extracted reference relationship. Search device. The patent search device according to claim 3,
A chart created by the chart creating section for creating a chart representing a reference relationship between the search source patent document and the highly relevant patent document based on the information in the referenced database section, and the chart created by the chart creating section And a display section for presenting a patent search device. In the patent search device according to any one of claims 1 to 4,
A morphological analysis unit that performs morphological analysis of the search source patent document and extracts the word or the compound word; and
An importance calculating unit for calculating the importance of the extracted word or the compound word in the search source patent document;
A patent search apparatus comprising: a registration unit that registers the extracted word or the compound word as the search term phrase in the patent search database unit in association with the importance. In the patent search device according to any one of claims 1 to 5,
The patent search device, wherein the search unit searches for a highly relevant patent document based on a distance between a vector corresponding to the search term phrase and a vector corresponding to the search condition phrase. The patent search device according to any one of claims 1 to 6,
The patent document includes a description of a plurality of “claims”, and the search unit includes a claim analysis unit that extracts a subordinate relationship between the plurality of “claims” based on the search term phrase. Patent search device characterized by that. The patent search device according to claim 7, wherein
The claim analysis unit is configured based on the description of other “claims” included in the “claim” of the search target and the names of the inventions of the “claim” and other “claims” of the search target. A patent search device characterized by extracting dependency relationships. The patent search device according to claim 8,
The claim analysis unit includes the description of the other “claim” in the “claim” of the search target, and the name of the invention of the “claim” of the search target and the other “claim”. When the names of the inventions are the same, it is determined that the dependency exists. The patent search device according to any one of claims 1 to 6,
The patent document includes a description of a “claim”, and the search unit includes a claim analysis unit that extracts a configuration requirement included in the description of the “claim” based on the search term phrase. Patent search device featuring. In a control method of a patent search apparatus having a patent search database unit that stores a word or a compound word included in a patent document to be searched for in association with the patent document as a search term phrase in advance,
Analyzing the search source patent document and extracting a word or compound word included in the condition setting patent document as a search condition phrase;
A search process for comparing the search term phrase and the search condition phrase and searching for a patent document having a high similarity to the search source patent document as a patent document having high relevance to the search source patent document. A method of controlling a patent search apparatus characterized by the above. In the control method of the patent search device according to claim 11,
A method for controlling a patent search apparatus, comprising: a reference destination extraction process for extracting a reference relationship between the search source patent document and the highly relevant patent document based on the description in each patent document . In the control method of the patent search device according to claim 12,
The patent search database unit includes a reference database unit that stores information on patent documents having a reference relationship in association with the search source patent document based on the extracted reference relationship,
A chart creation process for creating a chart representing a reference relationship between the search source patent document and the highly relevant patent document based on the information in the reference destination database unit;
And a display process for presenting the chart created by the chart creating section. In the control method of the patent search device according to any one of claims 11 to 13,
A morphological analysis process of extracting the word or the compound word by performing morphological analysis of the search source patent document;
Importance calculation process for calculating the importance of the extracted word or the compound word in the search source patent document,
And a registration step of registering the extracted word or the compound word as the search term phrase in the patent search database unit in association with the degree of importance. In the control method of the patent search device according to any one of claims 11 to 14,
The method of controlling a patent search apparatus, wherein the search process searches for a highly relevant patent document based on a distance between a vector corresponding to the search term phrase and a vector corresponding to the search condition phrase. In the control method of the patent search device according to any one of claims 11 to 15,
The patent document includes a description of a plurality of “claims”, and the search process includes a claim analysis process for extracting a subordinate relationship between the plurality of “claims” based on the search term phrase. A method for controlling a patent search apparatus, characterized in that: In the control method of the patent search device according to claim 16,
The claim analysis process is based on the description of other “claims” included in the “claim” of the search object and the name of the invention of the “claim” of the search object and the other “claim”. A method for controlling a patent search apparatus, characterized in that a dependency relationship is extracted. In the control method of the patent search device according to claim 17,
In the claim analysis process, there is a description of the other “claim” in the “claim” of the search object, and the name of the invention of the “claim” of the search object and the other “claim”. When the names of the inventions are the same, it is determined that the dependency exists. In the control method of the patent search device according to any one of claims 11 to 15,
The patent document includes a description of “claim”, and the search process includes a claim analysis process for extracting a constituent element included in the description of “claim” based on the search term phrase. A method for controlling a patent search apparatus. A control program that causes a computer having a patent search database unit that stores a word or a compound word included in a patent document to be searched for in association with the patent document as a search term phrase in advance as a patent search device,
Analyzing the search source patent document, extracting a word or compound word contained in the condition setting patent document as a search condition phrase, comparing the search term phrase and the search condition phrase, and for the search source patent document A control program for causing a patent document having high similarity to be searched as a patent document having high relevance to the search source patent document. The control program according to claim 20,
A control program that extracts a reference relationship between the search source patent document and the highly relevant patent document based on the description in each patent document. The control program according to claim 20 or claim 21,
The patent document includes a description of a plurality of “claims” and causes a dependency relationship between the plurality of “claims” to be extracted based on the search term phrase. The control program according to claim 20 or claim 21,
The patent document includes a description of “claim”, and extracts a constituent requirement included in the description of “claim” based on the search term phrase.   24. A recording medium on which the control program according to any one of claims 20 to 23 is recorded.

Images