WO2021152712A1 - Dispositif d'aide à la création de documents, procédé d'aide à la création de documents et programme de création de documents - Google Patents

Dispositif d'aide à la création de documents, procédé d'aide à la création de documents et programme de création de documents Download PDF

Info

Publication number
WO2021152712A1
WO2021152712A1 PCT/JP2020/003054 JP2020003054W WO2021152712A1 WO 2021152712 A1 WO2021152712 A1 WO 2021152712A1 JP 2020003054 W JP2020003054 W JP 2020003054W WO 2021152712 A1 WO2021152712 A1 WO 2021152712A1
Authority
WO
WIPO (PCT)
Prior art keywords
document
user
sentence
information
similar
Prior art date
Application number
PCT/JP2020/003054
Other languages
English (en)
Japanese (ja)
Inventor
びわ 三浦
崇志 三上
白坂　一
Original Assignee
株式会社 ＡＩ Ｓａｍｕｒａｉ
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社 ＡＩ Ｓａｍｕｒａｉ filed Critical 株式会社 ＡＩ Ｓａｍｕｒａｉ
Priority to PCT/JP2020/003054 priority Critical patent/WO2021152712A1/fr
Priority to JP2021573678A priority patent/JP7161255B2/ja
Publication of WO2021152712A1 publication Critical patent/WO2021152712A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/42—Data-driven translation
    • G06F40/44—Statistical methods, e.g. probability models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/55—Rule-based translation
    • G06F40/56—Natural language generation

Definitions

  • the present invention relates to a document creation support device, a document creation support method, a document creation support program, and a document creation support system, and particularly supports the creation of an invention by a user by assisting the user in creating a document relating to the invention.
  • Document creation support device etc.
  • Patent Document 1 discloses a system for creating a patent specification, which has the highest consistency of constituent requirements and automatically creates a patent specification based on the latest prior application.
  • a prior art search for determining whether or not the substantive requirements for registration such as novelty and inventive step are satisfied, and a clearance search for determining the presence or absence of infringement, etc. It is desirable to do.
  • the inventors provide a service (intellectual property creation support service) for conducting such a prior art literature search and a clearance search without the trouble of a user.
  • the prior art search is performed based on the information regarding the invention by the user transmitted from the terminal of the user, and the determination result of patentability is provided.
  • Patent Document 1 It would be very convenient for the user if the user could create a document about the invention while utilizing the above services.
  • the system described in Patent Document 1 has a high degree of agreement (similarity) with the constituent requirements of the claims input by the user.
  • the prior application having the above is extracted, and a part thereof is replaced with the claims input by the user based on the extracted specification of the prior application. That is, the wording of the specification of the prior application based on the wording was diverted, which was not preferable.
  • the present invention has been made in view of the above, and provides a document creation support device or the like for appropriately creating a document relating to an invention by a user using a document relating to an existing invention.
  • the document creation support device that supports the creation of a document relating to the invention according to one embodiment of the present invention learns the correspondence relationship in which the first sentence is input and the second sentence, which is a paraphrase of the first sentence, is output.
  • a paraphrase generation unit that outputs a paraphrase sentence that paraphrases one input sentence based on the learning model generated in Information on a similarity calculation unit that obtains the similarity between an invention included in a prior document and an invention by a user, and a similar document that is a prior document including an invention having a similarity equal to or higher than a predetermined value among a plurality of prior documents.
  • a similar document output unit that outputs
  • the paraphrase generation unit sets the result sentence as a result of folding back and translating one sentence included in the preceding document as the first sentence, and sets one sentence included in the preceding document as the first sentence.
  • a learning model may be generated by learning a plurality of preceding documents.
  • a correction unit that corrects the paraphrase sentence output by the paraphrase generation unit is provided based on the correspondence between the terms included in the similar document and the terms included in the user invention information. Further, the creating unit may create a document relating to the invention by the user based on the paraphrase sentence corrected by the amending unit and the user invention information.
  • the creating unit uses the plurality of prior documents as similar documents and sets them as a plurality of similar documents.
  • a document relating to the invention by the user may be created based on the user invention information.
  • the creating unit is a document relating to the invention by the user among the plurality of similar documents according to the degree of similarity between the invention included in the plurality of similar documents and the invention by the user. You may set the degree that contributes to the creation of.
  • the similar document output unit outputs display information for displaying information on a plurality of similar documents on a user terminal that can be operated by the user, and the reception unit has a plurality of reception units.
  • the user further accepts the selection of the similar document to be used for creating the document relating to the invention by the user, and the creating unit relates to the invention by the user based on the similar document selected by the user and the user invention information. You may create a document.
  • the document relating to the invention is a document used for a patent application
  • the document relating to an existing invention is a patent document
  • the reception unit receives at least as user invention information. Information about the claims in the document used in the patent application may be accepted.
  • the document creation support method for supporting the creation of a document relating to the invention is a correspondence relationship in which a computer inputs a first sentence and outputs a second sentence which is a paraphrase of the first sentence.
  • a paraphrase generation step that outputs a paraphrase sentence that paraphrases one input sentence based on the learning model generated by learning
  • a document creation support program that supports the creation of a document relating to an invention according to an embodiment of the present invention has a correspondence relationship in which a first sentence is input to a computer and a second sentence, which is a paraphrase of the first sentence, is output.
  • a paraphrase generation function that outputs a paraphrase sentence that paraphrases one input sentence based on a learning model generated by learning
  • a similarity calculation function for obtaining the similarity between an invention included in a prior document, which is a document, and an invention by a user, and a similarity which is a prior document including an invention having a similarity of a predetermined value or more among a plurality of prior documents.
  • a similar document output function that outputs information about a document, a paraphrase sentence obtained by inputting a sentence contained in a similar document into a paraphrase generation function, and a creation function that creates a document related to an invention by a user based on user invention information.
  • a document creation support device or the like that appropriately creates a document related to an invention by a user by using a document related to an existing invention.
  • FIG. 1 It is a schematic diagram of the document creation support system configuration which concerns on one Embodiment of this invention.
  • This is an example of the hardware configuration of the server (document creation support device) according to the embodiment of the present invention.
  • This is an example of a functional block diagram of the document creation support device according to the embodiment of the present invention.
  • This is an example of a functional block diagram of a paraphrase generation unit in the document creation support device according to the embodiment of the present invention.
  • It is a flow chart of the search process which concerns on one Embodiment of this invention.
  • This is an example of a functional block diagram of the document creation support device according to the embodiment of the present invention.
  • This is an example of a display screen of a user terminal in the document creation support system according to the embodiment of the present invention.
  • FIG. 1 is a diagram showing a configuration example of a document creation support system according to an embodiment of the present invention.
  • the document creation support system 500 includes a document creation support device 100, user terminals 400 (400A to 400D), and a preceding document database (DB) 200, which are connected to each other via a network 300.
  • DB preceding document database
  • the number of user terminals 400A to 400D and the preceding document database 200 is not limited to the one shown in the figure.
  • the document creation support device 100 is a device (information processing device) for connecting to user terminals 400A to 400D via a network 300 and providing a document creation support service to the user terminals 400A to 400D.
  • the document creation support device 100 is, for example, a so-called server device or computer (for example, a desktop, a laptop, a tablet, etc.).
  • the document creation support device 100 is not limited to these, and the server device is not limited to a physical server, but is a virtual server or a program that realizes a server function. Note that you can point to it.
  • the user terminals 400A to 400D are user terminals of users who use the document creation support service provided by the document creation support system 500.
  • the user terminals 400A to 400D indicate a notebook computer, a desktop personal computer, and a smartphone, but the user terminals 400A to 400D use the document creation support service by the document creation support system 500 via the network 300. Any type can be used as long as it is possible.
  • the user terminals 400A to 400D are collectively referred to as the user terminal 400.
  • the user terminal 400 is, for example, a mobile phone (feature phone), a handheld computer device (for example, PDA (Personal Digital Assistant), etc.), a wearable terminal (for example, a glasses-type device, a clock-type device, a head-mounted display (HMD: Head-)). Mounted Display, etc.), other types of computers, or communication platforms may be included.
  • a mobile phone feature phone
  • a handheld computer device for example, PDA (Personal Digital Assistant), etc.
  • a wearable terminal for example, a glasses-type device, a clock-type device, a head-mounted display (HMD: Head-)). Mounted Display, etc.
  • HMD Head-mounted display
  • other types of computers, or communication platforms may be included.
  • the user terminal 400 receives an input operation from the user and transmits information about the invention by the user to the document creation support device 100 via the network 300.
  • the "information about the invention by the user” is information about the invention created by the user, and may be, for example, information such as a sentence describing the content of the invention, an idea memo, a keyword (word), a drawing, or the like. ..
  • the text describing the content of the invention may be a text described in the form of claims, a text describing the subject of the invention, the purpose of the invention, or the like.
  • “information on the invention by the user” will be referred to as "user invention information”.
  • the document creation support device 100 creates a document related to the invention by the user based on the user invention information transmitted from the user terminal 400 and the prior document stored in the prior document database 200.
  • the "document relating to the invention” is a document prepared in a predetermined format that describes the content of the invention, and is, for example, a document relating to a patent application (specification, claims, abstract, etc.), It may be a paper, an idea sheet, a book, an invention application document used in a company, an educational institution, or the like. Therefore, the "document relating to the invention by the user” refers to the document relating to the invention created by the user.
  • the "preceding document” is an existing document relating to the above invention, and is data that can be transmitted / received via the network 300.
  • the preceding document database 200 is a database that stores the above preceding documents.
  • the prior document database 200 may be, for example, a database of the Japan Patent Office.
  • the database of patent offices may include one or more offices, for example, by including the databases of five offices of the United States, Europe, Japan, China, and South Korea, it covers about 90% of the world's patents. be able to.
  • the database is not limited to the above-mentioned one, and may be information existing on the Internet.
  • the network 300 may include a wireless network or a wired network.
  • the network 300 includes wireless LAN (wireless LAN: WLAN), wide area network (WAN), ISDNs (integrated service digital networks), wireless LANs, LTE (long term evolution), LTE-Advanced, and so on. 4th generation (4G), 5th generation (5G), CDMA (code division multiple access) and the like.
  • the network 300 is not limited to these examples, and the network 300 is not limited to these examples, for example, a public switched telephone network (PSTN), Bluetooth (Bluetooth (registered trademark)), an optical line, an ADSL (Asymmetric Digital Subscriber LINE) line, and a satellite. It may be a communication network or the like. Further, the network 300 may be a combination of these.
  • FIG. 1 shows a mode in which the document creation support device 100, the preceding document database 200, and the user terminal 400 are connected via the network 300, but the document creation support system 500 is separate from the network 300.
  • a locally secure network may be constructed in part or in whole, thereby transmitting and receiving data between each device and terminal.
  • the information processing device 100 includes a processor 101, a memory 102, a storage 103, an input / output interface (I / F) 104, and a communication I / F 105. And realize the method.
  • the function or method of the present disclosure is realized by the processor 101 executing an instruction included in a program read in the memory 102.
  • the processor 101 executes a function and / or a method realized by a code or an instruction included in a program stored in the storage 103.
  • the processor 101 includes, for example, a central processing unit (CPU), an MPU (MicroProcessingUnit), a GPU (GraphicsProcessingUnit), a microprocessor (microprocessor), a processor core (processorcore), a multiprocessor, and an ASIC (Application-). Specific Integrated Circuit), FPGA (Field Programmable Gate Array), etc. are included, and each implementation is performed by a logic circuit (hardware) or a dedicated circuit formed in an integrated circuit (IC (Integrated Circuit) chip, LSI (Large Scale Integration)), etc. Each process disclosed in the form may be realized.
  • these circuits may be realized by one or a plurality of integrated circuits, and a plurality of processes shown in each embodiment may be realized by one integrated circuit.
  • the LSI may be referred to as a VLSI, a super LSI, an ultra LSI, or the like depending on the degree of integration.
  • the memory 102 temporarily stores the program loaded from the storage 103 and provides a work area to the processor 101. Various data created while the processor 101 is executing the program are also temporarily stored in the memory 102.
  • the memory 102 includes, for example, a RAM (RandomAccessMemory), a ROM (ReadOnlyMemory), and the like.
  • the storage 103 stores the program.
  • the storage 103 includes, for example, an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, and the like.
  • the communication I / F 105 is implemented as hardware such as a network adapter, communication software, and a combination thereof, and transmits and receives various data via the network 300.
  • the communication may be executed by wire or wirelessly, and any communication protocol may be used as long as mutual communication can be executed.
  • the communication I / F 105 executes communication with another information processing device such as a user terminal via the network 300.
  • the communication I / F 105 transmits various data to another information processing device according to an instruction from the processor 101. Further, the communication I / F 105 receives various data transmitted from other information processing devices and transmits the various data to the processor 101.
  • the input / output I / F 104 includes an input device for inputting various operations to the information processing device 100 and an output device for outputting the processing result processed by the information processing device 100.
  • the input / output I / F 104 may be integrated with the input device and the output device, or may be separated into the input device and the output device.
  • the input device is realized by any one of all kinds of devices capable of receiving an input from a user and transmitting information related to the input to the processor 101, or a combination thereof.
  • the input device includes, for example, a hardware key such as a touch panel, a touch display, and a keyboard, a pointing device such as a mouse, a camera (operation input via an image), and a microphone (operation input by voice).
  • the output device outputs the processing result processed by the processor 101.
  • the output device includes, for example, a touch panel, a speaker, and the like.
  • each functional unit shown in FIG. 3 is not essential, and other functional units may be provided. Further, the function or processing of each functional unit may be realized by machine learning or AI (Artificial Intelligence) to the extent feasible.
  • AI Artificial Intelligence
  • the document creation support device 100 is a device that supports the creation of a document relating to an invention, and includes at least a reception unit 110, a similarity calculation unit 120, a similar document output unit 130, a storage unit 140, a paraphrase generation unit 150, and a creation unit 160. Be prepared.
  • documents relating to a patent application (specification, claims, abstract, etc.) will be described as examples of documents relating to an invention, but as described above, documents relating to an invention are not limited thereto. do not have.
  • the reception unit 110 receives user invention information.
  • the user invention information is input by the user terminal 400 and transmitted to the document creation support device 100 via the network 300.
  • the user invention information may be a sentence describing the invention created by the user, for example, a sentence described in the form of claims.
  • the similarity calculation unit 120 obtains the similarity between the invention (prior invention) included in the prior document, which is a document relating to the existing invention, and the invention by the user.
  • the prior document may be a patent document such as a patent publication and a patent publication that has been applied for
  • the prior document database 200 may be a database of the Japan Patent Office. Whether or not the inventions are similar can be determined by, for example, recognizing the meaning (implication) of the invention by the user and searching for a prior invention having similar implications.
  • the similarity calculation unit 120 divides the text included in the user invention information transmitted from the user terminal 400 into predetermined constituent units, and determines the degree of agreement with the text included in the patent document for each segmented constituent unit.
  • the structural unit may be a sentence, a predicate, or a word having a certain length.
  • the similarity calculation unit 120 uses a corpus dictionary of words stored in advance in the storage unit 140 to display a sentence transmitted from the user terminal 400 and a sentence included in the patent document for the word included in the constituent unit.
  • the subordinate concept or the superordinate concept may be determined between them, and the similarity may be calculated. For example, if the word contained in the sentence included in the user invention information is the same as the word contained in the patent document, or if it is a subordinate concept, the patent document is similar to the sentence transmitted from the user terminal 400.
  • the degree may be calculated high.
  • the method of calculating the similarity is not limited to the above-mentioned method, and an existing clustering method can be used.
  • the similar document output unit 130 outputs information on a similar document which is a prior document including an invention having a similarity degree of a predetermined value or more among a plurality of prior documents.
  • the predetermined value regarding the similarity may be preset by the user, or may be set according to the number of similar documents to be output. Further, the similar document output unit 130 transmits information about the similar document to the user terminal 400 in order to display the information about the similar document on the user terminal 400.
  • the paraphrase generation unit 150 paraphrases one input sentence based on a learning model generated by learning a correspondence relationship in which the first sentence is input and the second sentence, which is a paraphrased sentence of the first sentence, is output. Output paraphrase sentences. This will be described in detail with reference to FIG.
  • FIG. 4 is a detailed functional block diagram of the paraphrase generation unit 150.
  • the paraphrase generation unit 150 includes a second language conversion unit 152, a first language conversion unit 153, and a learning unit 151.
  • the second language conversion unit 152 is a converter (translator) that converts an input sentence of the first language (for example, Japanese) into a sentence of the second language (for example, English).
  • the first language conversion unit 153 is a converter (translator) that converts the input second language sentence into the first language.
  • an existing translation system may be used as the second language conversion unit 152 and the first language conversion unit 153.
  • the second language is not limited to English, but may be German, French, Russian, or the like.
  • the paraphrase generation unit 150 learns a plurality of preceding documents by using the result sentence as a result of translating one sentence included in the preceding document as the first sentence and the one sentence included in the preceding document as the second sentence. To generate a learning model. That is, in the paraphrase generation unit 150, the preceding document 10 in the first language included in the preceding document database 200 is input to the second language conversion unit 152, and the second language preceding document 11 converted into the second language is output. NS. The second language preceding document 11 is input to the first language conversion unit 153, and the first language conversion document 30 is output. The learning unit 151 generates a learning model that learns the correspondence relationship in which the first language conversion document 30 is input and the preceding document information 10 is output. The paraphrase generation unit 150 performs the learning process according to the above for the prior art document included in the prior art database 200, and generates a paraphrase sentence in which the expression is changed without changing the meaning and content (sentence meaning) of one sentence.
  • the number of language conversion units is not limited to two, and may be multiple.
  • the first language may be converted to the second language, the second language to the third language, and the third language to the first language.
  • a sentence having a different meaning is generated as a result of the conversion, it is not necessary to train the converted document.
  • almost the same sentence is generated as a result of the conversion, it is not necessary to train the converted document.
  • by learning as a negative example when sentences with different meanings are generated or almost the same sentences are generated, it is possible not to output them as paraphrase sentences.
  • the paraphrase generation unit 150 inputs a sentence included in the similar document output by the similar document output unit 130, and generates a paraphrase sentence in which the sentence is paraphrased by using the learning model generated by the learning process described above.
  • the creation unit 160 creates a document relating to the invention by the user based on the paraphrase sentence and the user invention information. Specifically, the preparation unit 160 replaces the items corresponding to the user invention information (here, the scope of claims, the subject of the invention) with those of the user invention information among the documents relating to the patent application as similar documents. However, a new document is created using similar documents for other items (here, technical field, background technology, form for carrying out the invention, etc.). At this time, the sentence of the similar document becomes a new sentence paraphrased by the paraphrase generation unit 150.
  • the document created by the preparation unit 160 will be described by taking the document related to the patent application as an example.
  • the user invention information 40 input in the user terminal 400 includes the subject of the invention and a sentence described in the form of claims.
  • the similarity calculation unit 120 and the similar document output unit 130 of the document creation support device 100 refer to the prior document database 200 and extract patent documents similar to the invention by the user as the similar document 50.
  • the creation unit 160 creates a new document 20 based on the similar document 50 and the user invention information 40.
  • the user invention information 40 is used to describe the title of the invention, the problem to be solved by the invention, the means for solving the problem, and the scope of claims.
  • a sentence in which the sentence of the similar document 50 is paraphrased is used as a mode for carrying out the invention.
  • the learning unit 151 learns the correspondence relationship in which the first sentence is input and the second sentence, which is a sentence obtained by paraphrasing the first sentence, is output, and a learning model is generated (step S11).
  • the reception unit 110 receives information about the invention by the user (step S12).
  • the similarity calculation unit 120 obtains the similarity between the invention included in the prior document, which is a document relating to the existing invention, and the invention by the user (step S13).
  • the similar document output unit 130 outputs information on a similar document that is a prior document including an invention having a similarity degree of a predetermined value or more among a plurality of prior documents (step S14).
  • the creation unit 160 creates a document regarding the invention by the user based on the paraphrase sentence obtained by inputting the sentence included in the similar document into the paraphrase generation unit and the information about the invention by the user (step S15).
  • the text of the document including the invention similar to the invention by the user is paraphrased, and therefore the document relating to the invention by the user is used. Can be created appropriately.
  • a learning model that learns the correspondence between the sentence resulting from the folded translation of the preceding document and the input sentence included in the preceding document is used, so create a natural sentence. Can be done.
  • FIG. 7 shows an example of a functional block diagram of the document creation support device 100 according to the second embodiment of the present invention.
  • the document creation support device 100 according to the second embodiment the same functional parts as those of the first embodiment are designated by the same reference numerals, and the description thereof will be omitted.
  • the document creation support device 100 according to the second embodiment further includes a correction unit 170.
  • the correction unit 170 corrects the paraphrase sentence output by the paraphrase generation unit 150 based on the correspondence between the terms included in the similar document and the terms included in the user invention information.
  • the correction unit 170 refers to a predetermined dictionary and replaces the terms corresponding to the terms included in the user invention information among the terms included in the similar document with the terms included in the user invention information.
  • the dictionary may be a general-purpose dictionary (ontology or thesaurus in which the meanings of general words and hierarchical relationships of concepts are defined) that are generated in advance as general knowledge, or may be defined by the user. , May be stored in the storage unit 140.
  • the creation unit 160 creates a document relating to the invention by the user based on the paraphrase sentence corrected by the correction unit 170 and the user invention information.
  • the sentence in which the sentence included in the similar document is paraphrased is further corrected by the term included in the user invention information, so that the invention by the user is described more accurately. It becomes possible.
  • the creating unit 160 extracts all the plurality of prior documents as similar documents, and based on the plurality of similar documents and invention information, the user. You may create information about the invention according to. This will be described with reference to FIG. For example, when three similar documents are extracted, the creation unit 160 sets the contents of the new document 20 in the form for carrying out the invention as the first similar document, the second similar document, and the third similar document. They may be used as the first embodiment, the second embodiment, and the third embodiment, respectively. As for the sentences of each similar document, the sentences paraphrased by the paraphrase generation unit 150 are generated.
  • a document relating to a patent application is created using a plurality of similar documents including an invention similar to the invention by the user, so that the content of the patent application is enhanced. be able to. Further, it becomes possible to enhance the patentability of the invention by the user.
  • the similar document output unit 130 may output display information for displaying information on a plurality of similar documents on the user terminal 400.
  • FIG. 9 shows an example of a display screen of information related to a plurality of similar documents on the user terminal 400.
  • the similar document display screen 60 includes a constituent requirement display area 62 included in the user invention information, a prior art and similarity display area 61, and a determination result display area 64 for determining the patentability of the invention by the user.
  • the prior art and the similarity display area 61 include similar documents 61A to 61C.
  • the user can select a similar document to be used for creating the user invention document from the prior art and similarity display area 61.
  • the prior art and the similarity display area 61 may be configured so that the prior art can be viewed according to the user's selection.
  • the reception unit 110 further accepts from the user the selection of a similar document to be used for creating a document relating to the invention by the user among a plurality of similar documents.
  • the creation unit 160 creates a user invention document based on a similar document selected by the user and the user invention information.
  • the information about the similar document is provided to the user, and the user can select the similar document to be used for creating the document related to the patent application. Therefore, it is possible to provide a system with higher usability.
  • FIG. 10 shows an example of a display screen on the user terminal 400 that accepts input of user invention information.
  • the input reception screen 70 includes the title input area 71 of the invention, the claim input area 72, the similar document (cited document) selection area 73, the effect input area 74 of the invention, and the drawing input area 75. Since similar documents are extracted in response to the input of the user invention information, the user invention information may already be entered in the claim input area 72. The user can instruct the creation of the user-created document by correcting the missing information or the information already input on the input reception screen 70.
  • the document creation support device 100 may include a determination unit (not shown) for determining the possibility of acquiring the right.
  • the determination unit (not shown) can search for a similar invention similar to the invention by the user, and execute, for example, a process of determining the possibility of acquiring a right depending on the presence or absence of the similar invention. Similar to the invention, for example, a keyword is extracted from the words included in the invention, and a synonym, etc. for the keyword is searched from a database (not shown) that stores synonyms, synonyms, or derivative words (synonyms, etc.). It can be judged whether or not the meanings and contents of sentences composed of synonyms are similar.
  • the determination unit determines that if the similarity calculated by the similarity calculation unit 120 is small, the possibility of acquiring the right is high, and if the degree of similarity is large, the possibility of acquiring the right is low. You may.
  • the judgment unit is, for example, "S rank (extremely high possibility)", “A rank (high possibility)", and “B rank (possible)” according to the high or low possibility of acquiring the right. Judgment by rank may be made, such as "with sex)" and "C rank (less likely)". Further, the determination is not limited to the display from S rank to C rank. The determination may be, for example, displayed from ⁇ to ⁇ in descending order of probability.
  • the judgment unit can judge the possibility of acquisition of rights based on the examination results of acquisition of rights that have been examined in the past by the patent offices of each country.
  • the examination result of acquisition of rights is the invention related to the application, the cited reference, and the examination result (whether or not it was rejected based on the cited document) in comparison between the two.
  • the judgment unit calculates the similarity between the invention of the application and the text of the cited reference, learns the comparison between the calculated similarity and the examination result, and determines the possibility of acquiring the right. You may.
  • the judgment unit can use the judgments made by the JPO in the past as the judgment criteria by learning the comparison between the calculated similarity and the past examination results. The determination accuracy can be improved.
  • the storage unit 140 may be configured to store the examination result in advance.
  • the examination result can be obtained, for example, from the examination information published by the patent offices of each country.
  • the determination unit (not shown) may determine the possibility of acquiring the right based on the examination result.
  • the judgment unit may machine-learn the past examination results and judge the possibility of acquiring the right.
  • the judgment unit performs machine learning (supervised learning) using the input and output as a data set, inputting the invention related to the application and the cited document as an output, and using the examination result as an output.
  • machine learning supervised learning
  • the determination unit can improve the determination accuracy of the possibility of acquiring the right by using the learning result learned in each modeling.
  • the Judgment Department (not shown) will acquire the right in response to the change in the examination tendency at the JPO by machine learning the new examination result. It is possible to judge the possibility.
  • machine learning a supervised learning technique or an unsupervised learning technique may be used.
  • the learning technique of machine learning for example, a neural network (including deep learning), a support vector machine, clustering (for example, a task, a first embodiment, etc.), a Bayesian network, or the like may be used.
  • each component, each step, etc. can be rearranged so as not to be logically inconsistent, and a plurality of components, steps, etc. can be combined or divided into one. Is.
  • the configurations shown in the above embodiments may be combined as appropriate.
  • each component described as being included in the document creation support device 100 may be physically distributed by a plurality of computers, or may be realized as a single computer.
  • the document creation support device 100 can be applied not only to inventions but also to intellectual property in general.
  • the intellectual property refers to a design, a trademark, a device, etc. in addition to the invention, and the "document related to the intellectual property" may be a document showing the contents of the invention, the design, the trademark, the device, etc.
  • the intellectual property is a "trademark” or a "design”
  • it may be an application document or a description thereof.
  • the program of each embodiment of the present disclosure may be provided in a state of being stored in a storage medium readable by a computer.
  • the storage medium can store the program in a "non-temporary tangible medium".
  • Programs include, for example, software programs and computer programs.
  • the storage medium may be one or more semiconductor-based or other integrated circuits (ICs) (eg, field programmable gate arrays (FPGAs), application-specific ICs (ASICs), etc.), hard disks.
  • the storage medium may be volatile, non-volatile, or a combination of volatile and non-volatile, where appropriate.
  • the program of the present disclosure may be provided to the information processing device via an arbitrary transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program.
  • an arbitrary transmission medium communication network, broadcast wave, etc.
  • each embodiment of the present disclosure can also be realized in the form of a data signal embedded in a carrier wave, in which the program is embodied by electronic transmission.
  • the program of the present disclosure is implemented using, for example, a script language such as JavaScript (registered trademark) or Python, C language, Go language, Swift, Kotlin, Java (registered trademark), or the like.
  • a script language such as JavaScript (registered trademark) or Python
  • C language Go language
  • Swift Swift
  • Kotlin Java (registered trademark)
  • Java registered trademark
  • Document creation support device 101 Processor 102 Memory 103 Storage 110 Reception unit 120 Similarity calculation unit 130 Similar document output unit 140 Storage unit 150 Paraphrase generation unit 151 Learning unit 152 Second language conversion unit 153 First language conversion unit 160 Creation unit 170 Correction unit 200 Preceding document database 300 Network 400 User terminal 500 Document creation support system 60 Similar document display screen 61 Similarity display area 62 Configuration requirement display area 64 Judgment result display area 70 Input reception screen 71 Name input area 72 Claim input area 73 Selection area 74 Effect input area 75 Drawing input area

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Probability & Statistics with Applications (AREA)
  • Document Processing Apparatus (AREA)
  • Machine Translation (AREA)

Abstract

Le but de la présente invention est de créer de manière appropriée un document relatif à une invention d'un utilisateur à l'aide d'un document relatif à une invention existante. L'invention concerne un dispositif d'aide à la création de documents comprenant : une unité de génération de paraphrase, qui produit une phrase paraphrasée obtenue par le paraphrasage d'une phrase d'entrée sur la base d'un modèle d'apprentissage généré par l'apprentissage d'une correspondance entre une première phrase, qui correspond à une entrée, et une seconde phrase, qui est une paraphrase de la première phrase et correspond à une sortie ; une unité de réception, qui reçoit des informations d'invention d'utilisateur constituant des informations relatives à l'invention d'un utilisateur ; une unité de calcul de degré de similarité, qui obtient le degré de similarité entre une invention comprise dans un document antérieur, qui constitue un document relatif à une invention existante, et l'invention de l'utilisateur ; une unité de sortie de document similaire, qui produit des informations relatives à un document similaire constituant l'un d'une pluralité de documents antérieurs et qui comprend une invention présentant au moins un degré prescrit de similarité avec l'invention de l'utilisateur ; et une unité de création, qui crée un document relatif à l'invention de l'utilisateur sur la base des informations d'invention de l'utilisateur et d'une phrase paraphrasée obtenue par l'introduction, dans l'unité de génération de paraphrase, d'une phrase comprise dans le document similaire.
PCT/JP2020/003054 2020-01-28 2020-01-28 Dispositif d'aide à la création de documents, procédé d'aide à la création de documents et programme de création de documents WO2021152712A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2020/003054 WO2021152712A1 (fr) 2020-01-28 2020-01-28 Dispositif d'aide à la création de documents, procédé d'aide à la création de documents et programme de création de documents
JP2021573678A JP7161255B2 (ja) 2020-01-28 2020-01-28 文書作成支援装置、文書作成支援方法、及び、文書作成プログラム

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/003054 WO2021152712A1 (fr) 2020-01-28 2020-01-28 Dispositif d'aide à la création de documents, procédé d'aide à la création de documents et programme de création de documents

Publications (1)

Publication Number Publication Date
WO2021152712A1 true WO2021152712A1 (fr) 2021-08-05

Family

ID=77078725

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/003054 WO2021152712A1 (fr) 2020-01-28 2020-01-28 Dispositif d'aide à la création de documents, procédé d'aide à la création de documents et programme de création de documents

Country Status (2)

Country Link
JP (1) JP7161255B2 (fr)
WO (1) WO2021152712A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003022264A (ja) * 2001-07-06 2003-01-24 Communication Research Laboratory 言語変換処理統一システム
JP2004118768A (ja) * 2002-09-30 2004-04-15 Mitsui Chemicals Inc 特許明細書の作成方法
US20190042663A1 (en) * 2017-08-02 2019-02-07 Yahoo Holdings, Inc. Method and system for generating a conversational agent by automatic paraphrase generation based on machine translation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003022264A (ja) * 2001-07-06 2003-01-24 Communication Research Laboratory 言語変換処理統一システム
JP2004118768A (ja) * 2002-09-30 2004-04-15 Mitsui Chemicals Inc 特許明細書の作成方法
US20190042663A1 (en) * 2017-08-02 2019-02-07 Yahoo Holdings, Inc. Method and system for generating a conversational agent by automatic paraphrase generation based on machine translation

Also Published As

Publication number Publication date
JPWO2021152712A1 (fr) 2021-08-05
JP7161255B2 (ja) 2022-10-26

Similar Documents

Publication Publication Date Title
US20170351663A1 (en) Iterative alternating neural attention for machine reading
US20210168098A1 (en) Providing local service information in automated chatting
CA2758632C (fr) Recherche de paires de phrases dans une ressource non structuree
Nair et al. Machine translation systems for Indian languages
US10083398B2 (en) Framework for annotated-text search using indexed parallel fields
US20220147835A1 (en) Knowledge graph construction system and knowledge graph construction method
WO2014169857A1 (fr) Dispositif de traitement de données, procédé de traitement de données et équipement électronique
WO2021152712A1 (fr) Dispositif d'aide à la création de documents, procédé d'aide à la création de documents et programme de création de documents
JP6978735B2 (ja) 文書検索装置、文書検索方法、及び、文書検索プログラム
US20180189262A1 (en) Enhancing QA System Cognition With Improved Lexical Simplification Using Multilingual Resources
Reddy et al. Indic language machine translation tool: English to Kannada/Telugu
KR20200057824A (ko) 단어 교정 시스템
US20210312144A1 (en) Translation device, translation method, and program
KR20160140527A (ko) 다국어 전자책 시스템 및 방법
Gautam et al. Translation into Pali Language from Brahmi Script
Muthalib et al. Making learning ubiquitous with mobile translator using Optical Character Recognition (OCR)
US20180189261A1 (en) Using Multilingual Lexical Resources to Improve Lexical Simplification
WO2021245814A1 (fr) Dispositif d'évaluation d'informations de documents, procédé d'évaluation d'informations de documents et programme d'évaluation d'informations de documents
Suman et al. Two-way Speech to Sign Language Converter application using Python, OpenCV and NLP
JP7139271B2 (ja) 情報処理装置、情報処理方法、及びプログラム
JP5212725B2 (ja) 電子書籍作成支援装置
Nandish et al. A Novel Implementation of a Cohesive Regional Language Tweet Translator
Saha Text summarization using multiobjective optimization
KR102408479B1 (ko) 영어 교육 제공 방법 및 장치
Ryberg Smidt et al. Keep me PoS-ted: experimenting with Part-of-Speech prediction on Old Babylonian letters

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20917161

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021573678

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20917161

Country of ref document: EP

Kind code of ref document: A1