JP2020009330A - Creation support device and creation support method - Google Patents

Abstract

To provide a creation support device and a creation support method for suppressing variation in quality in the case of creating claims, or for reducing time spent for creating claims.SOLUTION: A creation device comprises: reception means for receiving information; application means for applying the received information to a model generated by mechanically learning information extracted from the past application and claims of the application; provision means for providing the claims obtained as a result of application; and correction means for receiving correction for the provided claims. The provision means provides the claims reflected with the received correction.SELECTED DRAWING: Figure 6

Description

  The present invention relates to a creation support device and a creation support method.

  A patent application basically includes a specification, claims, an abstract, and drawings, although there are some differences between countries. Heretofore, in general, the claims (also referred to as claims) of a patent application have been created by a patent attorney or by a person in the Intellectual Property Department of a company.

  In recent years, the term “artificial intelligence (AI)” has come to be frequently seen (for example, see Non-Patent Document 1). In fact, AI has evolved remarkably, and some, such as the human brain, have a cognitive function of recognizing many images and sounds and finding a specific pattern. For example, Google has succeeded in letting a computer identify a cat image. As the performance of the AI has been improved, its application range has been expanded.

http://www.nri.com/jp/journal/2016/10/161031_4/, searched on April 10, 2018

  In the conventional claim creation method, since the knowledge and experience for creating a claim differ depending on the person in charge, the quality of the created claim often varies. In addition, since it is created manually, it takes a relatively long time.

  The present invention has been made in view of such a problem, and an object of the present invention is to provide a technology capable of suppressing a variation in quality at the time of creating a claim or reducing a time required for creating a claim.

  One embodiment of the present invention relates to a creation device. The creation device includes a reception unit that receives information, and an application unit that applies the received information to a model generated by mechanically learning information extracted from a past application and claims of the application. And providing means for providing the claims obtained as a result of the application.

  Another embodiment of the present invention relates to a creation supporting apparatus. The creation support device includes a display control unit for displaying technical information on a display in a graphic form, a receiving unit for receiving a change to the displayed graphic, and a generating unit for generating a new claim in a text format based on the changed graphic form. And.

  It should be noted that any combination of the above-described constituent elements, and those in which the constituent elements and expressions of the present invention are replaced with each other among apparatuses, methods, systems, computer programs, recording media storing computer programs, and the like, are also included in the present invention. This is effective as an embodiment.

  ADVANTAGE OF THE INVENTION According to this invention, the dispersion | variation in the quality at the time of a claim creation can be suppressed, or the time required for a claim creation can be reduced.

FIG. 7 is a schematic diagram illustrating transition of a screen realized by the creation server according to the first embodiment. 1 is a schematic diagram illustrating a configuration of a claim creation support system according to a first embodiment. FIG. 3 is a hardware configuration diagram of the creation server of FIG. 2. FIG. 3 is a block diagram illustrating functions and configurations of a creation server in FIG. 2. FIG. 5 is a data structure diagram illustrating an example of a patent information holding unit in FIG. 4. 3 is a flowchart illustrating a flow of a series of processes in the creation server in FIG. 2. FIG. 9 is a schematic diagram illustrating an example of a relationship between a free keyword of a document to be learned and a free keyword of a cited document. 15 is a flowchart illustrating a flow of a keyword extraction process according to a first modification. It is a typical screen figure of an extraction result display screen. It is a schematic diagram explaining a claim generation model when designating a model application. It is a schematic diagram which shows the flow of claim generation in the creation server according to the second modification. It is a schematic diagram explaining learning of the AI model in the creation server according to the second modification. It is a schematic diagram which shows the flow of claim generation in the creation server according to the third modification. It is a schematic diagram which shows the flow of claim generation in the creation server according to the third modification. It is a mimetic diagram showing the flow of the claim generation in the creation server concerning the 4th modification. It is a schematic diagram explaining learning of the AI model in the creation server according to the fourth modification. It is a block diagram showing the function and composition of the creation support server concerning a 2nd embodiment. FIG. 17 is a schematic diagram illustrating an outline of transition of a screen displayed on a display of a user terminal by the creation support server of FIG. 16. It is a typical screen figure of a self case list screen. It is a typical screen figure of a new matter creation screen. It is a typical screen figure of a component requirement model screen. It is a schematic diagram for explaining an input support function. It is a typical screen figure of a new claim creation screen. It is a representative screen figure of an in-house case search list screen. It is a typical screen figure of a case detail screen. It is a typical screen figure of a case correction screen. It is a typical screen figure of a claim modification screen. 17 is a flowchart illustrating a flow of a series of processes in the creation support server of FIG. 16. It is a data structure figure showing an example of a case component table with which a creation support server concerning a 5th modification is provided. It is a schematic diagram which shows an example case component model. It is a schematic diagram which shows the principal part of the case component model after clicking the plus button. It is a schematic diagram which shows the principal part of the case component model after clicking the plus button. 30 is a schematic diagram showing a case component model obtained by modifying the case component model of FIG. 29. FIG.

  Hereinafter, the same or equivalent components, members, and processes illustrated in each drawing are denoted by the same reference numerals, and the repeated description will be omitted as appropriate. In each drawing, some of the members that are not important for the description are omitted.

(First Embodiment)
FIG. 1 is a schematic diagram showing screen transitions realized by the creation server according to the first embodiment. The creation server first causes the display 100 of the user's terminal to display a generation condition input screen 102 for accepting input of a condition for generating a claim. The generation condition input screen 102 includes a keyword input area 104, an add button 106, an image upload area 105, a claim number input area 108, an assignment input area 110, a reference application input area 107, an auto box 109, a field It has an input area 112 and a generate button 114.

  As a user of the creation server, for example, a person in the intellectual property department of a company is assumed. The user examines a technical document such as an invention proposal submitted by the research and development department, and extracts the essence (or key points, features, essential parts) of the invention or technical idea contained therein as a keyword. At the same time, if possible, the user extracts issues relating to the invention and the technical idea, and determines the technical field to which the invention and the technical idea belong. The user inputs the extracted keyword to the keyword input area 104 of the generation condition input screen 102. By clicking (pressing) the add button 106, the user can increase the number of keywords that can be input in the keyword input area 104. Each keyword in the keyword input area 104 is displayed in association with the degree of importance 103. The user selects the importance 103 of the input keyword from “H” (high), “M” (medium), and “L” (low). In other embodiments, more levels of importance may be used, or continuous values may be used.

  The user can upload various files (hereinafter, referred to as documents, etc.) such as technical documents, such as invention proposals, technical drawings, still images, such as photographs, and moving images, in addition to keywords. The user inputs the path of the target file into the image upload area 105 by referring to a document or the like in the user's terminal. Alternatively, the user may directly input the path of the target file into the image upload area 105. Alternatively, the user may upload an image file of a technical document such as an invention proposal instead of the document.

  The user determines the number of claims to be made in the claims and inputs the number to the claim number input area 108. If the subject and the technical field of the invention are determined, the user inputs them into the subject input area 110 and the field input area 112, respectively. In the assignment input area 110, the assignment may be input in a free text format. If the user has determined a patent application having a model to be modeled (hereinafter referred to as a model application), the user inputs the patent application number in the reference application input area 107. Alternatively, when the model application is automatically selected, the user checks the auto box 109. If the model application is not used, the reference application input area 107 is left blank, and the check box of the auto box 109 is removed. In the field input area 112, the technical field may be specified by classification such as IPC (International Patent Classification), F-term, FI, CPC, or may be specified by text.

  When the user inputs necessary information and then clicks the generate button 114, the creation server acquires the input information. The creation server is equipped with a claim generation AI engine that is generated and updated by making AI learn information of past patent applications. The creation server automatically generates a claim corresponding to the input keyword by processing the input information by the claim generation AI engine. The creation server causes the display 100 to display a generation result display screen 116 that displays the generated claims. On the generation result display screen 116, the generated claims are displayed in text, and an OK button 118 and a correction button 120 are displayed.

  If the user is satisfied with the generated claims, the user clicks the OK button 118 and ends the processing. If the user wishes to modify the generated claims, he or she clicks on the modify button 120. When the correction button 120 is clicked, the creation server causes the display 100 to display an editing screen 122 for accepting correction of the claims by the user.

  On the edit screen 122, the claims are displayed in an editable manner, and a reflection button 124 is displayed. Modifications to the claims made on the editing screen 122 are displayed in a form that allows the modification history to be understood. When the user clicks the reflection button 124 after making the desired correction, the creation server causes the display 100 to display a correction result display screen 126 that displays the claims reflecting the correction. At the same time, the creation server acquires the claims and the contents of the amendment before the amendment, and updates the claim generation AI engine with the acquired information.

  As described above, according to the claim creation support service provided by the creation server, since the claim generation AI engine is used, personal elements at the time of claim creation can be reduced or eliminated, and the quality can be made uniform. it can. Further, the time required for creating a claim can be reduced.

  FIG. 2 is a schematic diagram illustrating a configuration of the claim creation support system 2 according to the first embodiment. The claim creation support system 2 includes a creation server 4 and a user terminal 8. The creation server 4 and the user terminal 8 are communicably connected via a network 6 such as the Internet. The creation server 4 includes a patent information holding unit 42 that holds information on past patent applications, and has a claim creation AI engine as described above. The user terminal 8 is a terminal used by the user, and may be, for example, a desktop PC, a laptop PC, a mobile terminal, or the like.

  In this embodiment, the user inputs information to the user terminal 8, the user terminal 8 transmits the information to the creation server 4 via the network 6, the creation server 4 processes the information, and sends the processing result to the network. A so-called ASP (Application Service Provider) is assumed, in which the processing is returned to the user terminal 8 via the terminal 6 and the user terminal 8 displays the processing result. However, the technical idea of the present embodiment can be applied to a system other than the ASP, for example, when a claim creation AI engine is mounted on a stand-alone terminal and a user inputs information to the terminal and obtains a processing result. It is.

  FIG. 3 is a hardware configuration diagram of the creation server 4 of FIG. The user terminal 8 may have the same hardware configuration as the hardware configuration illustrated in FIG. The creation server 4 includes a memory 130, a processor 132, a communication interface 134, a display 136, and an input interface 138. These components are each connected to a bus 140 and communicate with each other via the bus 140.

  The memory 130 is a storage area for storing data and programs. The data and the program may be permanently stored in the memory 130 or may be temporarily stored. In particular, the memory 130 has an area allocated as the patent information holding unit 42. The processor 132 implements various functions in the creation server 4 by executing a program stored in the memory 130. The communication interface 134 is an interface for transmitting and receiving data to and from the outside of the creation server 4. For example, the communication interface 134 includes an interface for accessing the network 6. The display 136 is a device for displaying various information, and is, for example, a liquid crystal display or an organic EL (Electroluminescence) display. The input interface 138 is a device for receiving an input from a user. The input interface 138 includes, for example, a mouse, a keyboard, and a touch panel provided on the display 138.

  FIG. 4 is a block diagram showing functions and configurations of the creation server 4 of FIG. Each block shown here can be realized by hardware such as a computer CPU and other elements and mechanical devices, and can be realized by software, such as a computer program. The functional blocks are drawn. Therefore, it will be understood by those skilled in the art referred to in this specification that these functional blocks can be realized in various forms by a combination of hardware and software.

  The creation server 4 includes a patent information holding unit 42, a learning unit 402, a generation condition obtaining unit 404, a claim generation AI engine 406, a result output unit 408, and a correction receiving unit 410.

  FIG. 5 is a data structure diagram showing an example of the patent information holding unit 42. The patent information holding unit 42 holds information on past patent applications. The patent information holding unit 42 includes a patent ID for identifying a patent application, an application number of the patent application, a first IPC assigned to the patent application, a patent strength value of the patent application, and a patent strength value assigned to the patent application. Examiner free word, the free keyword assigned to the patent application, the claims of the patent application, the issues of the patent application, the documents cited in the examination of the patent application, The drawings (not shown) of the patent application and the documents (not shown) of the patent application are held in association with each other. A document of a patent application may be registered only when it is available, such as a document relating to an invention proposal of a prior application of the company.

  The patent strength value is one of the indicators of the quality of a patent application. The patent strength value may be, for example, a Technology Size (TS) value provided by NRI Cyber Patent Co., Ltd. Alternatively, another index may be used.

  The free keyword is a keyword that is set by reading the target patent application by a person, and may be a keyword extracted by the person as a point of the target patent application. The free keyword may be, for example, a PATOLIS keyword provided by NRI Cyber Patent Co., Ltd.

  Referring back to FIG. 4, the learning unit 402 refers to the patent information holding unit 42, and mechanically learns information extracted from a past patent application and the claims of the patent application, thereby generating a claim creation model. Generate. At that time, the learning unit 402 may not refer to the information of the past patent applications that do not satisfy the predetermined quality standard among the information of the past patent applications held in the patent information holding unit 42.

  The learning unit 402 may specify a patent application whose patent strength value is equal to or larger than a threshold value, among the patent applications held in the patent information holding unit 42. In other words, the learning unit 402 may exclude a patent application whose patent strength value is less than the threshold from learning targets. In the present embodiment, the magnitude relationship with the threshold value is used as the predetermined criterion for the quality. However, the present invention is not limited to this. For example, a range of patent strength values may be used instead of the threshold value.

  The learning unit 402 acquires the free keyword, the claims, the problem, the first IPC, the document, etc., and the drawing of the specified patent application from the patent information holding unit 42, and mechanically learns the acquired information. , Generate a claim creation model. The generation of the claim creation model in the learning unit 402 may be realized using a known technique related to machine learning and artificial intelligence. The learning of the task and the learning of the first IPC are both optional and need not be the learning targets.

  The claim creation model is a model in which a keyword or a document or the like is required input, a subject and a technical field are optional inputs, and claims are output as a result of processing. Both issues and technical fields are used to increase the accuracy of output results. When the importance specified for each keyword is used as an input of the claim generation model, the learning unit 402 learns the free keyword together with the importance. The importance of the free keyword may be determined in advance by a person and registered in the patent information holding unit 42, or may be automatically given as realized by a keyword extraction model described later.

  FIG. 10 is a schematic diagram illustrating a claim generation model when a model application is specified. The learning unit 402 first divides the information of the past patent application held in the patent information holding unit 42 according to the structure of the claim. Specifically, the learning unit 402 divides the structure of the claims into several types (for example, claim structures A, B, and C), and determines the type of the structure of the claims of the patent application held in the patent information holding unit 42. It is determined whether it belongs to. The learning unit 402 groups the patent applications held in the patent information holding unit 42 according to the type of the structure (for example, claims structure: a group belonging to A, claims structure: a group belonging to B, belonging to a claim structure: C). group). The learning unit 402 generates a claim creation model for each group (that is, for each type of claim structure). As a result, for example, a claim creation model A corresponding to the claim structure A, a claim creation model B corresponding to the claim structure B, and a claim creation model C corresponding to the claim structure C are generated.

  Referring back to FIG. 4, the learning unit 402 sets the claim generation model generated as described above in the claim generation AI engine 406. The type of the claim creation model generated by the learning unit 402 may be determined according to what input is assumed as a condition for creating a claim, or a plurality of types of claims may be determined according to an assumed input pattern. A creation model may be generated. For example, if a keyword is required as a condition for creating a claim and an assignment is optional, the learning unit 402 acquires the free keyword, the claims, and the assignment of the specified patent application from the patent information holding unit 42. Then, a claim creation model is generated by mechanically learning the acquired information. Alternatively, for example, if the keyword is required as a condition for creating a claim and the importance is optional, the learning unit 402 determines the free keywords of the specified patent application, the claims, and the importance of each free keyword. Is acquired from the patent information holding unit 42, and the acquired information is mechanically learned to generate a claim creation model. Alternatively, if, for example, a document or the like is indispensable as a condition for creating a claim and no optional information is set, the learning unit 402 compares the claims, the document, and the drawing of the specified patent application with the patent information. A claim creation model is generated by mechanically learning the information acquired from the holding unit 42 and the acquired information. Alternatively, if it is possible to specify the model application as a condition for creating a claim, a plurality of claim creation models are prepared according to the structure of the claim as shown in FIG.

  The generation condition acquisition unit 404 generates screen information for displaying the generation condition input screen 102, and transmits the screen information to the user terminal 8 via the network 6. The generation condition acquisition unit 404 receives information input by the user on the generation condition input screen 102 displayed on the display 100 of the user terminal 8 from the user terminal 8 via the network 6. The information input by the user includes a set of keywords or documents, etc., and the number of claims, and optionally includes a degree of importance for each keyword, a problem, an application number of the model application, and a technical field.

  When the auto box 109 is checked, the generation condition acquisition unit 404 performs a search using the received keyword set as a key in the external or internal patent application database, and finds the highest matching score among the search results. Set a high application as a model application.

  The claim generation AI engine 406 applies, to the claim creation model generated by the learning unit 402, the set of keywords or documents received by the generation condition acquisition unit 404 from the user terminal 8 and the number of claims. If the generation condition acquisition unit 404 receives the importance of a keyword from the user terminal 8, the claim generation AI engine 406 also applies it to the claim generation model. If the generation condition acquisition unit 404 receives an assignment from the user terminal 8, the claim generation AI engine 406 also applies the assignment to the claim creation model. If the generation condition acquisition unit 404 receives a technical field from the user terminal 8, the claim generation AI engine 406 also applies the technical field to the claim generation model. If the generation condition obtaining unit 404 has obtained the model application, the claim generation AI engine 406 selects and uses a claim generation model corresponding to the structure of the claim of the sample application. The claim generation AI engine 406 acquires the claims output by the claim creation model as a result of the application.

  The result output unit 408 provides the claims of the claim generation AI engine 406 to the user of the user terminal 8. The result output unit 408 generates screen information for displaying the generated result display screen 116 including the obtained claims, and transmits the screen information to the user terminal 8 via the network 6. The user terminal 8 receives the screen information, and displays the generation result display screen 116 on the display 100 based on the received screen information.

  When the correction button 120 on the generation result display screen 116 is clicked, the user terminal 8 generates correction request information and transmits it to the creation server 4 via the network 6. Upon receiving the correction request information from the user terminal 8, the correction receiving unit 410 generates screen information for displaying the editing screen 122 and transmits the screen information to the user terminal 8 via the network 6. The user terminal 8 receives the screen information, and displays the editing screen 122 on the display 100 based on the received screen information.

  When the reflection button 124 on the edit screen 122 is clicked, the user terminal 8 generates correction completion information including the correction content at that time, and transmits the correction completion information to the creation server 4 via the network 6. Upon receiving the correction completion information from the user terminal 8, the correction receiving unit 410 generates screen information for displaying the correction result display screen 126 and transmits the screen information to the user terminal 8 via the network 6. The user terminal 8 receives the screen information and causes the display 100 to display the correction result display screen 126 based on the received screen information.

  Upon receiving the correction completion information, the correction receiving unit 410 determines (1) a set of keywords input by the user, (2) an input task (if any), 3) learning the input technical field (if any), (4) the claims as they were generated by the claim creation model (ie, before the amendment), and (5) the amended claims. Pass it to the unit 402. The learning unit 402 updates the claim creation model based on the information (1) to (5).

The operation of the creation server 4 having the above configuration will be described.
FIG. 6 is a flowchart showing a flow of a series of processes in the creation server 4 of FIG. In the example of FIG. 6, it is assumed that a keyword and a model application are given as conditions for creating a claim. The creation server 4 displays the generation condition input screen 102 on the display 100 of the user terminal 8 (S602). The creation server 4 receives a set of keywords related to the technical idea and the application number of the sample application from the user via the generation condition input screen 102 (S604). The creation server 4 acquires the claims of the example application from an external or internal patent application database (for example, J-Plat) based on the application number of the example application, and specifies the structure of the acquired claims (S6051). The creation support server 4 selects a claim creation model corresponding to the specified structure (S6052). The creation server 4 receives the set of keywords received in step S604 as input, and executes a claim generation by AI using the claim creation model selected in step S6052 (S606). The creation server 4 displays the generated claims by displaying the generation result display screen 116 on the display 100 of the user terminal 8 (S608). If the user has not corrected the complaint (NO in S610), the process ends. If the user has modified the complaint (YES in S610), the creation server 4 accepts the content of the modification (S612). The creating server 4 displays the corrected claim by displaying the correction result display screen 126 on the display 100 of the user terminal 8 (S614). The creation server 4 updates the claim creation model of the claim generation AI engine 406 based on the claims before the correction and the contents of the correction (S616).

  In the above embodiment, examples of the holding unit are a hard disk and a semiconductor memory. Further, based on the description in this specification, each unit is realized by a CPU (not shown), a module of an installed application program, a module of a system program, and a semiconductor memory that temporarily stores the content of data read from a hard disk. It will be understood by those skilled in the art referred to herein that this can be achieved.

  According to the creation server 4 according to the present embodiment, a claim creation model of the claim creation AI engine is created by mechanically learning information of a relatively high-quality past patent application. Claims are automatically generated by applying the keyword extracted by the user to the claim creation model. In this way, the knowledge and experience of claim creation that previously belonged to a patent attorney or a company's intellectual property department as an individual are transferred to the AI, and the AI is used to create a claim. The quality of the claims can be made uniform, and the time required for making the claims can be reduced.

  The configuration and operation of the claim creation support system 2 according to the first embodiment have been described above. This embodiment is an exemplification, and it is understood by those skilled in the art that various modifications can be made to the combination of each component and each processing, and such modifications are also within the scope of the present invention.

  In the first embodiment, the case where the free keyword of the patent information holding unit 42 is used as the keyword to be learned by the learning unit 402 has been described, but the present invention is not limited to this. For example, an examiner free word may be used.

(First Modification)
Of the patent applications held in the patent information holding unit 42, for a patent application without a free keyword, the AI may be used to set a free keyword. In the first modification, the learning unit 402 specifies, among patent applications held in the patent information holding unit 42, a patent application whose patent strength value is equal to or larger than a threshold value. The learning unit 402 mechanically learns the free keywords of the documents cited in the examination of the patent application in addition to the free keywords of the specified patent application, the claims, and the subject, thereby obtaining the keyword. Generate an extraction model.

  The relationship between the free keyword of the patent application to be learned and the free keyword of the cited document in mechanical learning will be described. FIG. 7 is a schematic diagram illustrating an example of a relationship between a free keyword of a document to be learned and a free keyword of a cited document. In the example of FIG. 7, the first document 752 and the second document 754 are cited at the time of examining the document 750 to be learned. In order to show this citation relationship, in the patent information holding unit 42, the number of the publication of the first reference 752 and the number of the publication of the second And are registered. The learning unit 402 specifies the cited reference of the reference 750 to be learned by referring to the column of the cited reference. In the example of FIG. 7, the free keywords of the first document 752 are "AAA" and "BBB", the free keywords of the second document 754 are "AAA", "CCC", and "DDD". The three free keywords in the document 750 are “AAA”, “BBB”, and “EEE”. All of these free keywords are held in the patent information holding unit 42 and can be referred to by the learning unit 402.

  When learning the document 750 to be learned mechanically, the learning unit 402 refers to the free keywords of the first document 752 and the second document 754 which are cited documents of the document 750 to be learned. The learning unit 402 sets the importance of the free keyword of the document 750 to be learned based on the free keyword of the cited document. In particular, the learning unit 402 sets the importance to be higher as the citation of the cited document with the free keyword is smaller. For example, the free keyword “AAA” of the document 750 to be learned is also the free keyword of both the first document 752 and the second document 754, and thus is assigned the lowest importance. Since the free keyword “EEE” of the learning target document 750 is not any of the free keywords of the first reference 752 and the second reference 754, the highest importance is assigned. The free keyword “BBB” of the document 750 to be learned is a free keyword of the first document 752 but is not a free keyword of the second document 754, and thus is assigned an intermediate importance. The learning unit 402 learns the document 750 to be learned including the importance set in this way, and generates a keyword extraction model.

  FIG. 8 is a flowchart illustrating the flow of a keyword extraction process according to the first modification. The creation server 4 accepts a patent application to which a free keyword is not attached among patent applications held in the patent information holding unit 42 as documents to be subjected to keyword extraction (S702). The creation server 4 executes the extraction of the constituent elements (keywords) by AI using the information of the target document (the body text or the like) received in step S702 as an input (S704). In particular, the creation server 4 applies the information of the target document received in step S702 to the keyword extraction model generated by the learning unit 402, and acquires a keyword output by the keyword extraction model. The creation server 4 displays the extracted keyword on the display 100 of the user terminal 8 (S706). If there is no correction of the keyword by the user (NO in S708), the creation server 4 registers the extracted keyword as a free keyword corresponding to the target document in the patent information holding unit 42, and ends the process.

  When there is a correction of the keyword by the user (YES in S708), the creation server 4 accepts the content of the correction (S710). The creation server 4 updates the keyword extraction model based on the keyword before the correction and the content of the correction (S712). The creation server 4 registers the corrected keyword as a free keyword corresponding to the target document in the patent information holding unit 42, and ends the process.

  In step S706, the creation server 4 causes the display 100 to display an extraction result display screen 902 displaying the extracted keywords. FIG. 9 is a representative screen diagram of the extraction result display screen 902. The extracted keyword is displayed on the extraction result display screen 902, and an OK button 118 and a correction button 120 are displayed. The keywords displayed on the extraction result display screen 902 have ranks of importance “high”, “medium”, and “low”.

  In the first modification, the case where a keyword extraction model is used to extract and register an appropriate keyword for a patent application to which a free keyword is not attached has been described. However, the present invention is not limited to this. For example, the creation server 4 may accept a document uploaded by a user as a document to be extracted by a keyword. In this case, by viewing the extraction result display screen 902 shown in FIG. 9, the user can check the keywords extracted from the documents uploaded by the user together with their ranks.

  In the first modification, the case where the keyword extraction model is generated from the information held in the patent information holding unit 42 has been described. However, the present invention is not limited to this. May be generated. Similar to patent documents, academic papers are associated with issues, manually selected keywords, abstracts corresponding to the claims, and citation / cited relationships between the papers.

(Second Modification)
In the first embodiment, the case where the user is requested to input a keyword or an image file has been described, but the present invention is not limited to this. The creation server 4 according to the second modification acquires a technical document itself such as an invention proposal from a user, and uses a keyword extraction model, a technology classification assignment model, a similar document extraction model, and a claim creation model. Obtain necessary information automatically and generate claims. In this modification, the case of using the technology classification assignment model will be described.However, the present invention is not limited to this case. Information may be used. In this modification, a case where a keyword is extracted and used will be described. However, the present invention is not limited to this, and a sentence including a subject and a verb or a subject and a verb may be extracted and used instead of the keyword.

  FIG. 11 is a schematic diagram showing a flow of claim generation in the creation server 4 according to the second modification. The user 302 uploads the invention proposal 304 from the user terminal 8 to the creation server 4. The creation server 4 applies the keyword automatic extraction AI model 306 and the technology classification automatic assignment AI model 308 to the received invention proposal 304. The keyword automatic extraction AI model 306 outputs a keyword 310 required for a claim, and the technology classification automatic assignment AI model 308 outputs a technology classification. The user 302 confirms the keyword 310 and the technology classification 312 via the display 100 of the user terminal 8 and corrects it via the input means (mouse, keyboard, touch panel, etc.) of the user terminal 8 if necessary. The creation server 4 accepts a correction to the keyword 310 and generates a corrected keyword 314. Note that this modification step may be omitted. At this time, the creation server 4 may cause the user 302 to specify the importance for each keyword and acquire the specified importance. The creation server 4 passes a set of the keyword 310 before correction and the corrected keyword 314 to a learning phase described later for updating the keyword automatic extraction AI model 306. Note that the creation server 4 may pass only the keyword 310 before correction or only the corrected keyword 314 to a learning phase described later for updating the keyword automatic extraction AI model 306. The creation server 4 receives a modification to the technology class 312 and generates a modified technology class 316. At this time, the creation server 4 may cause the user 302 to specify the importance for each technology category, and acquire the specified importance. The creation server 4 passes a set of the technical classification 312 before correction and the corrected technical classification 316 to a learning phase described later for updating the technology classification automatic assignment AI model 308.

  The creation server 4 applies the similar document automatic extraction AI model 318 to the corrected keyword 314 and the corrected technical classification 316. The similar document automatic extraction AI model 318 outputs a similar document 320. The user 302 confirms the similar document 320 through the display 100 of the user terminal 8 and corrects it through the input means of the user terminal 8 if necessary. Note that the step of confirming / correcting this similar document may be omitted. The creation server 4 receives a correction to the similar document 320 and generates a corrected similar document 322. The creation server 4 passes the pair of the similar document 320 before correction and the corrected similar document 322 to a learning phase described later for updating the similar document automatic extraction AI model 318. Note that the creation server 4 may pass only the similar document 320 before correction or only the corrected similar document 322 to a learning phase described later for updating the similar document automatic extraction AI model 318.

  The creation server 4 applies the automatically generated AI model 324 to the corrected keyword 314, the corrected technical classification 316, and the corrected similar document 322. The creation server 4 may apply the automatic claim generation AI model 324 to a keyword before correction, a technical classification before correction, and a similar document before correction. The automatic claim generation AI model 324 outputs a claim 326. The user 302 confirms the claim 326 via the display 100 of the user terminal 8 and corrects it through the input means of the user terminal 8 if necessary. Note that the step of correcting this claim may be omitted. The creation server 4 receives a correction to the claim 326 and generates a corrected claim 328. The creation server 4 passes the set of the uncorrected claim 326 and the corrected claim 328 to a learning phase described later for updating the automatically generated AI model 324.

  FIG. 12 is a schematic diagram illustrating learning of an AI model in the creation server 4 according to the second modification. The creation server 4 includes a keyword automatic extraction learning AI 330, a technology classification automatic assignment learning AI 332, a similar document automatic extraction learning AI 334, and an automatic claim generation learning AI 336.

  The keyword automatic extraction learning AI 330 refers to the patent information holding unit 42 and (1) issues, (2) abstracts, (3) abstracts and keywords of documents cited in the examination process, and (4) claims of past patent applications. (Independent term) is obtained as an input, and (5) keywords and (6) examiner keywords of the past patent application are obtained as outputs. Note that the keyword automatic extraction learning AI 330 is based on (1) issues, (2) abstracts, (3) abstracts and keywords of documents cited in the examination process, and (4) claims (independent terms) of past patent applications. Part or all may be obtained as input. At that time, (2) the abstract and (3) the abstract and the keyword of the document cited in the examination process may be obtained from an external commercial database or the like. Further, the keyword automatic extraction learning AI 330 may obtain as an output either (5) the keyword or (6) the examiner keyword of the past patent application. At this time, (5) the keyword may be obtained from an external commercial database or the like. The keyword automatic extraction learning AI 330 acquires a set of the keyword 310 before correction and the corrected keyword 314 passed from the generation phase of FIG. The keyword automatic extraction learning AI 330 performs learning based on the acquired information, and generates a keyword automatic extraction AI model 306.

  The technology classification automatic assignment learning AI 332 refers to the patent information holding unit 42, acquires (1) the problem, (2) the solution, and (3) the abstract of the past patent application as inputs, and obtains the ( 4) Acquire the assigned technology classification as an output. The technology classification automatic assignment learning AI 332 may acquire, as an input, part or all of (1) the problem, (2) the solution, and (3) the abstract of the past patent application. The technology classification automatic assignment learning AI 332 acquires a pair of the technology class 312 before correction and the corrected technology class 316 passed from the generation phase in FIG. 11. The technology classification automatic assignment learning AI 332 performs learning based on the acquired information, and generates a technology classification automatic assignment AI model 308.

The similar document automatic extraction learning AI 334 refers to the patent information holding unit 42 and acquires (1) the full text, (2) the technology classification, (3) the keyword, and (4) the examiner's keyword of the past patent application as inputs. Obtain as output the documents cited by (5) examiner of the past patent application. The similar document automatic extraction learning AI 334 acquires a set of the similar document 320 before correction and the corrected similar document 322 passed from the generation phase in FIG. The similar document automatic extraction learning AI 334 performs learning based on the acquired information to generate a similar document automatic extraction AI model 318.
Alternatively, instead of the above configuration, similar claims may be input using a well-known search engine technology such as ELASTICSEARCH (https://www.elastic.co/jp/products/elasticsearch) with a claim or part of a claim as input. The similar document automatic extraction learning AI may be configured to output a claim or a part of the claim.

  The claim automatic generation learning AI 336 refers to the patent information holding unit 42, and refers to (1) keywords, (2) examiner keywords, (3) technical classification, (4) documents cited by the examiner, (5) The problem and (6) the solution are acquired as input, and the (7) claim (independent term) of the past patent application is acquired as output. It should be noted that the automatic claim generation learning AI 336 includes (1) keywords, (2) examiner keywords, (3) technical classification, (4) documents cited by examiners, (5) issues, (6) ) Some or all of the solutions may be obtained as input. Further, the claim automatic generation learning AI 336 may acquire (1) a set of a subject and a verb, or a sentence including a subject and a verb, instead of the keyword. The claim automatic generation learning AI 336 acquires a pair of the uncorrected claim 326 and the corrected claim 328 passed from the generation phase of FIG. The automatic claim generation learning AI 336 performs learning based on the acquired information, and generates an automatic claim generation AI model 324.

(Third Modification)
FIGS. 13A and 13B are schematic diagrams showing the flow of claim generation in the creation server 4 according to the third modification. The user 302 may upload the invention proposal 304 and the prior patent publication 338 from the user terminal 8 to the creation server 4. At the same time, the user 302 inputs a claim element (subject) via the user terminal 8. The creation server 4 displays the creation table 340 on the display 100 of the user terminal 8. The creation server 4 first sets the input claim element in the creation table 340 as it is. The creation server 4 automatically replenishes verb candidates for each of the set claim elements.

  The user 302 may check the candidate of the verb by looking at the creation table 340 displayed on the display 100 of the user terminal 8. The user 302 may make modifications via the input means of the user terminal 8 if necessary. After receiving the correction for the verb (correction is optional), the creation server 4 automatically supplements the case component candidates for each of the verbs. The user 302 may confirm the case component candidates by looking at the creation table 340 displayed on the display 100 of the user terminal 8. The user 302 may make modifications via the input means of the user terminal 8 if necessary. The user 302 may also input the division.

  After reflecting the correction for the case component, the creation server 4 sets the input classification as it is. The user 302 may make a final check by looking at the creation table 340. When the user 302 issues a complaint generation instruction, the creation server 4 generates a case component table by automatically connecting the words of the case components. The creation server 4 generates a claim and a case component model (described later in the second embodiment) from the generated case component table. The user 302 checks the generated claims and case component models, and corrects them as necessary.

(Fourth modification)
FIG. 14 is a schematic diagram illustrating a flow of claim generation in the creation server 4 according to the fourth modification. The user 302 uploads the invention proposal 304 from the user terminal 8 to the creation server 4. Invention proposal 304 includes the objects and features of the invention. At the same time, the user 302 inputs the number of the similar document 342 serving as the basic patent and the number of the similar document 344 serving as another similar publication via the user terminal 8.

  The creation server 4 performs a case component analysis of the similar document 342 serving as the basic patent (2-1). The creation server 4 converts the description of the features of the invention extracted from the invention proposal 304 into the “subject to which the verb depends”, the “verb”, and the “case component” (hereinafter referred to as case information) described in the claim. Edit (2-2). The creation server 4 compares the case information edited in (2-2) with the detailed description of the similar document 344, which is a similar publication, and re-edits the case information (2-3). At this time, the creation server 4 re-edits the data so that the similarity becomes low.

  The creation server 4 generates case information of the invention according to the invention proposal 304 from the case information obtained in (2-1) and the case information obtained in (2-3) (2-4). In this generation, the creation server 4 responds to three patterns of (1) external addition, (2) internal addition, and (3) replacement. The creation server 4 generates a claim and a case component model (summary version, detailed version, described later in the second embodiment) from the case information of the invention generated in (2-4) (3). . The user 302 checks the generated claim and case component model, and corrects and evaluates it as necessary (4).

  FIG. 15 is a schematic diagram illustrating learning of an AI model in the creation server 4 according to the fourth modification. The claim creation model used in the creation server 4 according to the fourth modified example includes, at the time of generating a claim, the issues and features of the invention extracted from the invention proposal 304, the issues and the claims of the similar document 342 serving as the basic patent, The subject, claim, and detailed description of similar document 344, which is another similar publication, are input, and the claim is output. In the learning phase, the issues and features of the invention extracted from the past patent application, the main reference issues and claims cited in the examination process of the patent application, and the secondary reference issues, claims and detailed description, Is input and learning is performed using the claims of the patent application as outputs to generate a claim creation model.

(Second embodiment)
In the first embodiment, a case has been described in which once the first information (invention proposal, keyword, etc.) is obtained from a user, a claim is automatically generated basically without user intervention. In the second embodiment, a case will be described in which the generation of a claim by a user is supported. The creation support server according to the second embodiment finds an automatically generated keyword or a similar prior application manually (in the case of an automatically generated keyword, performs a patent search using the keyword as a key, and finds a result with the highest matching degree among the results) , Etc.), the found claim of the earlier application is displayed as a graphic, the user is allowed to operate the graphic, and the changed graphic is returned to the sentence, thereby assisting the user in creating a new claim. In another embodiment, a figure may be created from the beginning for the purpose of claim design from the invention proposal.

The configuration of the claim creation support system including the creation support server 14 according to the second embodiment conforms to the configuration shown in FIG.
FIG. 16 is a block diagram illustrating functions and configurations of the creation support server 14 according to the second embodiment. Each block shown here can be realized by hardware such as a computer CPU and other elements and mechanical devices, and can be realized by software, such as a computer program. The functional blocks are drawn. Therefore, it will be understood by those skilled in the art referred to in this specification that these functional blocks can be realized in various forms by a combination of hardware and software.

  The creation support server 14 automatically generates a keyword from the invention proposal received from the user, searches for a patent document using the automatically generated keyword as a key, and identifies a patent document with the highest matching score among the search results as a preceding document. Then, a UI for creating a new claim based on the specified claim of the prior document is displayed on the display 100 of the user terminal 8, the UI accepts a change to the element of the claim, and writes a new claim reflecting the change. Generated by converting The creation support server 14 includes a patent information holding unit 42, a case information holding unit 16, a keyword generation unit 420, a preceding document acquisition unit 422, a display control unit 424, an input reception unit 426, and a claim generation unit 428. , Is provided. The case information holding unit 16 holds information on a case generated using the creation support server 14. Note that the user may newly input a graphic into the display 100 without using a prior document.

  The user uploads an invention proposal to be created to the creation support server 14 from the user terminal 8. The keyword generation unit 420 acquires the uploaded invention proposal and applies the problems and features of the invention described in the acquired invention proposal to the keyword extraction models according to the first and second modifications. Thus, a keyword is generated.

  The preceding document acquisition unit 422 searches an external or internal patent document database using the keyword generated by the keyword generation unit 420 as a key. The preceding document acquisition unit 422 acquires the patent document with the highest matching score among the search results as the preceding document. Alternatively, the preceding document acquisition unit 422 may specify a plurality of patent documents having a high matching score as the preceding documents. Alternatively, the prior document acquisition unit 422 may directly receive the specification of the prior document (for example, by an application number, a publication number, a patent number, or the like) from the user.

The display control unit 424 causes the claims included in the claims of the prior document identified by the prior document acquisition unit 422 to be graphically displayed on the display 100 of the user terminal 8 via the network 6.
The input receiving unit 426 receives a change to the displayed graphic via the network 6. The input receiving unit 426 may newly receive an input of a graphic.
The claim generation unit 428 generates a new claim in a text format based on the changed graphic.

  Hereinafter, the functions of the display control unit 424, the input receiving unit 426, and the claim generation unit 428 will be described in more detail with reference to screen transitions. The display control unit 424 causes each screen described later to be displayed on the display 100 of the user terminal 8 via the network 6. The input receiving unit 426 receives, from the user terminal 8 via the network 6, correction contents described later and instructions from the user. Receiving an instruction to generate a claim described below, the claim generation unit 428 generates a claim in a text format based on the corrected graphic.

  FIG. 17 is a schematic diagram showing an outline of transition of a screen displayed on the display 100 of the user terminal 8 by the creation support server 14 of FIG. When the user accesses the creation support server 14, a login screen 502 is displayed first. When the user inputs authentication information such as an ID and a password on the login screen 502, the creation support server 14 performs user authentication. When the user authentication is successful, the screen displayed on the display 100 transits from the login screen 502 to the own case list screen 504. The login screen 502 may be realized using a known user authentication technology.

  When the user instructs new creation on the own matter list screen 504, the screen transitions to a new matter creation screen 506, when the user instructs matter search, the screen transitions to the own matter search list screen 508, and when the matter number link is specified, the screen corresponds. The screen transits to the case detail screen 512 of the case to be executed. When the user inputs necessary information on the new case creation screen 506 and instructs generation of a claim, the screen changes to a new claim creation screen 510. When registration is instructed on the new claims creation screen 510, the screen transits to the case detail screen 512.

  When the user specifies a case number link on the in-house case search list screen 508, the screen transits to the case detail screen 512 of the corresponding case, and when the user specifies the IPC field list link, the screen transits to the IPC field list screen 514. As the IPC field list screen 514, for example, a screen of the IPC field list of NRI Cyber Patent Desk 2 provided by NRI Cyber Patent Co., Ltd. may be adopted.

  When the user modifies the matter on the matter detail screen 512, the screen transits to the matter modification screen 516, and when the user designates the matter copy, the screen transits to the matter new creation screen 506. When the user corrects the claims on the case correction screen 516, the screen changes to a claims correction screen 518. If reflection of the correction is instructed on the claims correction screen 518, the screen transits to the case detail screen 512.

  FIG. 18 is a representative screen diagram of the self case list screen 504. The user inputs information in the search key input area 520 of the self case list screen 504, and clicks a search button 522. The input receiving unit 426 obtains the information input to the search key input area 520, searches the case information holding unit 16 using the obtained information as a key, and matches the key among the cases of the company to which the logged-in user belongs. Is generated as a search result. The display control unit 424 displays the search result acquired by the input receiving unit 426 in the own case list display area 524 of the own case list screen 504.

  When the user clicks the case number link 526 of the case displayed in the own case list display area 524, the screen transits to the case detail screen 512 of the case corresponding to the clicked case number link 526. When the user clicks the case search button 528, the screen transits to a company case search list screen 508. When the user clicks a new creation button 530, the screen transits to a new matter creation screen 506.

  FIG. 19 is a representative screen diagram of the new case creation screen 506. The new case creation screen 506 includes a case number display area 532 for displaying an automatically assigned case number, an invention name input area 534, a preceding document input area 536, a proposal upload button 538, and an element model edit. An area 540, a model button 542, a relation expression generation button 544, a claims editing area 546, and a claims generation button 548 are provided.

  The user inputs the title of the invention in the title input area 534 of the invention. The user inputs the number of the prior document (application number, publication number, patent number, etc.) as the basis for generating a claim in the prior document input area 536. Alternatively, when the user wants to automatically select the prior document, the user clicks the proposal upload button 538 to display a dialog (not shown) for uploading a file, and the file of the invention proposal is displayed in the dialog. specify. The user terminal 8 transmits the file of the designated invention proposal to the creation support server 14. The creation support server 14 receives the file of the invention proposal and performs keyword creation, patent document search, and preceding document identification as described above. The display control unit 424 causes the number of the specified prior document to be displayed in the preceding document input area 536.

  When the user clicks the model button 542, a model diagram is output. When the user clicks the element model automatic generation button 541, the input receiving unit 426 acquires a preceding document from an external or internal patent document database using the number of the preceding document input in the preceding document input area 536 as a key. The display control unit 424 causes the claim of the prior document to be graphically displayed in the element model editing area 540 based on the flowchart model.

  The flowchart model displayed in the element model editing area 540 expresses the whole image of the claim by input → processing (component requirement) → output. The input / output element 550, the component requirement 552, and the like A requirement 554. The user generates a new desired model by performing selection, movement, deletion, addition, and the like on the elements of the flowchart model displayed in the element model editing area 540.

  FIG. 20 is a representative screen diagram of the component requirement model screen 556. When the user clicks on component requirement 552 displayed in element model editing area 540, display control unit 424 causes display 100 to display component requirement model screen 556 corresponding to the clicked component requirement 552 as a separate screen pop-up. The user can define each component requirement on the component requirement model screen 556. The component requirement model screen 556 has an illustrated editing area 558, a component requirement detail display area 560, a generated text display area 562, and an OK button 564.

  The illustrated editing area 558 graphically displays the constituent requirements for processing and data. The processing flow is indicated by a solid line, and the relationship between data is indicated by a broken line. In the component requirement detail display area 560, data corresponding to the figure displayed in the graphic editing area 558 is displayed. The component requirement detail display area 560 displays the result of decomposing the component requirement into “subject”, “data”, “processing”, and “parts”. When the user performs desired editing on the elements in the illustrated editing area 558, the result of the editing is reflected in the component requirement detail display area 560. At this time, “relevance” and “processing content” are automatically estimated using a probabilistic language model (Long Short-Term Memory, LSTM) and complemented automatically. Thereafter, the user can make the correction manually. At this time, candidates are presented for other items using the stochastic language model. For the parts, the words specific to the claims may be prepared as a dictionary. The generated text display area 562 displays a claim text (a sentence corresponding to the configuration requirement) automatically generated using the data displayed in the configuration requirement detail display area 560. When the OK button 564 is clicked, the screen returns to the new matter creation screen 506.

  Returning to FIG. 19, when the user performs desired editing in the element model editing area 540 and clicks the relation expression generation button 544, the performed editing is reflected in the claims editing area 546. Specifically, the input receiving unit 426 receives a change to an element of the flowchart model displayed in the element model editing area 540. The claim generation unit 428 generates a new claim skeleton (fixed part) based on the changed flowchart model. The display control unit 424 displays the generated fixed unit in the claims editing area 546 of the new case creation screen 506. The claim generation unit 428 complements assumed candidates for the input unit corresponding to each fixed unit from the past appearance frequency information. Here, a stochastic language model may be used. The user checks the fixed part and the input part displayed in the claims editing area 546, and corrects the input part if necessary using the input support function.

  FIG. 21 is a schematic diagram for explaining the input support function. When the user clicks one cell 566 of the input section displayed in the claims editing area 546, a plurality of autocomplete candidates 568 selected from past learning data are displayed. When the user selects one of the plurality of autocomplete candidates 568, a plurality of further autocomplete candidates 570 corresponding to the selected autocomplete candidate 568 are displayed. Thus, by continuously proposing the auto-complete candidates, the input can be simplified, and the generated claims can be standardized.

  Returning to FIG. 19, when the user clicks the claim generation button 548, the claim generation unit 428 generates a new claim based on the information edited in the claim editing area 546. This claim is the same as the claim generated from the flowchart edited in the element model editing area 540 when the editing is not performed in the claims editing area 546. The display control unit 424 causes the display 100 to display a new claim creation screen 510 including the generated new claim.

  FIG. 22 is a representative screen diagram of the new claims creation screen 510. The new claim creation screen 510 has a comparison area 572, a possibility display area 574, a return button 576, and a registration button 578. The comparison area 572 displays the result of comparing the generated claim with the prior document in units of constituent elements. In the comparison area 572, the degree of similarity and the similarity between the claim and each prior document are displayed for each configuration requirement. The possibility display area 574 displays the possibility of obtaining a patent by a numerical value. When the user clicks the return button 576, the screen returns to the new matter creation screen 506. When the user clicks the registration button 578, the input reception unit 426 registers the case number, the title of the invention, the prior document, and the generated claim in the case information holding unit 16 in association with each other. At the same time, the display control unit 424 causes the display 100 to display a case detail screen 512 indicating the registered contents.

  FIG. 23 is a representative screen diagram of the in-house case search list screen 508. The user inputs information into the search key input area 580 of the company case search list screen 508 and clicks a search button 582. The input receiving unit 426 obtains information input to the search key input area 580, searches the case information holding unit 16 using the obtained information as a key, and generates a search result. The display control unit 424 displays the search result generated by the input receiving unit 426 in the search result list display area 586 of the in-house case search list screen 508. When the user clicks the IPC list button 584, the screen transitions to an IPC field list screen 514.

  When the user clicks the matter number link 588 of the matter displayed in the search result list display area 586, the screen transits to the matter detail screen 512 of the matter corresponding to the clicked matter number link 588.

  FIG. 24 is a representative screen diagram of the case detail screen 512. The display control unit 424 generates the case detail screen 512 with reference to the case information holding unit 16 and causes the display 100 to display it. The case detail screen 512 includes a case number display area 590 for displaying the case number, an invention name display area 592 for displaying the title of the invention, a prior art display area 594 for displaying the number of the prior art, and a claim flowchart model. , A claims display area 598 for displaying a fixed part and an input part of the claim, a case copy button 802, and a case correction button 804. When the user clicks the matter copy button 802, the screen transitions to a matter creation screen 506 in which the matter displayed on the matter detail screen 512 is copied. When the user clicks the case modification button 804, the screen transits to a case modification screen 516 that accepts modification of the case displayed on the case detail screen 512.

  FIG. 25 is a representative screen diagram of the case modification screen 516. The configuration of the case modification screen 516 and the flow of the modification process are the same as the configuration and the flow of the creation process of the new case creation screen 506 described with reference to FIG. In the example of FIG. 25, the user corrects a portion surrounded by a broken-line circle in the element model editing area 806, and clicks a relation expression generation button 808. Then, since the information in the claims editing area 810 is updated, the user adjusts the input section of the claims editing area 810 as necessary while using the input support function. After the adjustment, when the user clicks the claim generation button 812, the claim generation unit 428 corrects the claim based on the information edited in the claim editing area 810. The display control unit 424 causes the display 100 to display a claims correction screen 518 including the corrected claims.

  FIG. 26 is a representative screen diagram of the claims correction screen 518. The configuration of the claims correction screen 518 is the same as the configuration of the new claims creation screen 510 described with reference to FIG. When the user clicks the return button 814, the screen returns to the case modification screen 516. When the user clicks the registration button 816, the input receiving unit 426 registers the case number, the title of the invention, the prior document, and the corrected claim in the case information holding unit 16 in association with each other. At the same time, the display control unit 424 causes the display 100 to display a case detail screen 512 on which the details of the correction are reflected.

The operation of the creation support server 14 having the above configuration will be described.
FIG. 27 is a flowchart showing a flow of a series of processes in the creation support server 14 of FIG. The creation support server 14 receives an invention proposal from the user terminal 8 of the user via the network 6 (S650). The creation support server 14 generates a keyword by applying the keyword extraction model to the received invention proposal (S652). The creation support server 14 searches for a patent document based on the generated keyword (S654). The creation support server 14 specifies the preceding document from the search result (S656). In addition, in addition to or instead of steps S650, S652, and S654, the creation support server 14 may receive the number of the prior document from the user terminal 8 in step S656. The creation support server 14 graphically displays the specified prior document claim on the display 100 of the user terminal 8 (S658). Note that the user may newly draw a figure from scratch. The creation support server 14 accepts a change made by the user to the displayed graphic (S660). The creation support server 14 generates a new claim based on the changed graphic (S662).

  In the above embodiment, examples of the holding unit are a hard disk and a semiconductor memory. Further, based on the description in this specification, each unit is realized by a CPU (not shown), a module of an installed application program, a module of a system program, and a semiconductor memory that temporarily stores the content of data read from a hard disk. It will be understood by those skilled in the art referred to herein that this can be achieved.

  According to the creation support server 14 according to the present embodiment, a user can generate a desired claim by operating a graphic such as a flowchart model. Therefore, an intuitive operation can be performed as compared with a case where a sentence is directly operated, and user convenience is improved.

  Further, the creation support server 14 according to the present embodiment generates a new claim by modifying or changing the claim of the specified prior document. Therefore, the time required to generate a claim can be reduced as compared with the case of generating a claim from scratch. Further, the quality of the claims can be made uniform.

  The configuration and operation of the claim creation support system according to the second embodiment have been described above. This embodiment is an exemplification, and it is understood by those skilled in the art that various modifications can be made to the combination of each component and each processing, and such modifications are also within the scope of the present invention.

(Fifth Modification)
In the second embodiment, the case where the flowchart model is adopted as the graphic display has been described, but the present invention is not limited to this. For example, a case component model may be adopted as the graphic display.
FIG. 28 is a data structure diagram illustrating an example of the case component table 818 provided in the creation support server 14 according to the fifth modification. The case component table 818 is generated by performing a case component analysis on a claim of a prior document or by performing a case component analysis on a new claim. The case component analysis may be realized by using, for example, a technique described in JP-A-2015-072573.

The creation support server 14 classifies the words registered in the case component table 818 into the following three types.
(1) Words required for composing the claim Appear in the claim of the preceding document, and are included in or included in the keyword of the preceding document, and appear in the keyword of the document cited in the examination process of the preceding document. .
(2) Words characterizing the claim Appear in the claim of the prior document and are or are included in the keyword of the prior document, and do not appear in the keyword of the document cited in the examination process of the prior document.
(3) Other

  FIG. 29 is a schematic diagram illustrating an exemplary case component model 820. The display control unit 424 generates the case component model 820 with reference to the case component table 818, and causes the display 100 of the user terminal 8 to display the case component model 820. A case component model 820 may be displayed instead of the element model editing area 540 of the new case creation screen 506 in FIG. In the case component model 820, the subject is displayed as a rectangle with a downward arrow. For example, the subject “moving object” is displayed as a rectangle 822. Verbs are displayed as ellipses receiving a down arrow. For example, the verb “has” is displayed as an ellipse 824. The case component is displayed as a rectangle with a left arrow. For example, the case component “image processing device” is displayed as a rectangle 826.

  In the case component model 820, the display color of the word differs depending on the type to which the word belongs. For example, the word "mobile" is displayed in blue because it belongs to "(1) Words necessary for composing a claim", and the word "board seat" is displayed in red because it belongs to "(2) Words characterizing a claim". The word "has" is displayed in black because it belongs to "(3) Others".

  The state of the case component model 820 shown in FIG. 29 is the most compact state or the most folded state. By clicking the plus button 828, the user can display a portion that has been folded and is no longer visible.

  FIG. 30 is a schematic diagram showing a main part of the case component model 820 after clicking the plus button 828. When the plus button is clicked, the lower hierarchy or connection hidden for the corresponding element is displayed. The “connection” is a connection expressed by a broken line in a portion expressed as “said” in the claim. In the example of FIG. 30, the rectangle 832 corresponding to the case component “image processing device” displays the lower hierarchy hidden in the case component model 820 of FIG. In particular, within the rectangle 832, the subject “image acquisition device” is displayed as a rectangle 834, the verb “acquire” is displayed as an ellipse 836, and the case component “experience image according to the passenger's experience” is a rectangle 838. Is displayed with.

  The plus button 828 in FIG. 29 is replaced with a minus button 830 in FIG. 30, and when the user clicks the minus button 830, the display returns to the state of the case component model 820 in FIG. When the user clicks the plus button 840 displayed in association with the word “passenger”, lower layers and connections related to the word “passenger” are displayed.

  FIG. 31 is a schematic diagram showing a main part of case component model 820 after clicking plus button 840. Clicking on the plus button 840 associated with the word "passenger" connects the words "passenger" "claimed" in the claim with a dashed line 842. The plus button 840 in FIG. 30 is replaced by a minus button 844 in FIG. 30, and when the user clicks the minus button 844, the display returns to the state of the case component model 820 in FIG.

Like the element model editing area 540 of the new case creation screen 506 in FIG. 19, the case component model 820 is configured to be able to accept editing of the displayed element. In particular, the user can perform the following three edits on the case component model 820.
(1) Correct the wording of elements (2) Delete case components (3) Add case components

  FIG. 32 is a schematic diagram showing a case component model 850 obtained by modifying the case component model 820 of FIG. The user corrects the word “stereo image” to the word “handle portion” with respect to the rectangle 846 of the case component “capturing a stereo image to be grasped” displayed on the case component model 820 of FIG. In addition, the user deletes the rectangle 848 of the case component “so that the imaging ranges overlap” displayed on the case component model 820 in FIG. 29. As a result, in the case component model 850 shown in FIG. 30, the rectangle 846 of the case component “Let's capture a stereo image of the gripping target” is replaced with a rectangle 852 of the case component “Let's capture the grip portion of the gripping target”. Accordingly, the rectangle 848 of the case component “so that the imaging ranges overlap” is not displayed.

  The creation support server 14 updates the case component table 818 again according to the corrected case component model 850, and generates a claim (text). It should be noted that the wording can be corrected from both the figure and the generated claims, and synchronization is always maintained.

The technical idea according to the first embodiment and the related modified example may be represented by the following items.
(Item 1)
A receiving means for receiving information;
Applying means for applying the received information to a model generated by mechanically learning information extracted from a past application and the claims of the application,
Providing means for providing the claims obtained as a result of the application.
(Item 2)
A correction unit for receiving a correction to the provided claims,
3. The creation device according to item 1, wherein the providing unit provides a claim in which the received correction is reflected.
(Item 3)
3. The creation device according to item 2, further comprising an updating unit that updates the model based on the received correction.
(Item 4)
The receiving means receives an assignment,
The model is generated by mechanically learning information extracted from a past application, issues of the application, and claims of the application,
The creation device according to any one of items 1 to 3, wherein the application unit applies the received information and the task to the model.
(Item 5)
Holding means for holding information of past applications;
The creation device according to any one of items 1 to 4, further comprising: a learning unit configured to generate the model by referring to the holding unit.
(Item 6)
6. The creating apparatus according to item 5, wherein the learning unit does not refer to information of past applications that do not satisfy a predetermined quality standard among information of past applications held in the holding unit.
(Item 7)
7. The creation device according to any one of items 1 to 6, wherein the information is a keyword or an image.
(Item 8)
Accepting information,
Applying the received information to a model generated by mechanically learning the information extracted from the past application and the claims of the application,
Providing a claim resulting from the application.
(Item 9)
A function to accept information,
A function to provide a claim obtained by applying the received information to a model generated by mechanically learning information extracted from a past application and the claims of the application, , A computer program to make a computer realize.

The technical idea according to the second embodiment and the related modified example may be represented by the following items.
(Item 10)
Display control means for displaying the claims included in the claims of the past application on the display graphically,
Receiving means for receiving a change to the displayed figure;
Generating means for generating a new claim in text format based on the changed graphic.
(Item 11)
The display control means causes the claims to be displayed graphically based on the flowchart model,
11. The creation support device according to item 10, wherein the accepting unit accepts a change to an element of the flowchart.
(Item 12)
The display control means displays the claims graphically based on the case component model,
11. The creation support device according to item 10, wherein the accepting unit accepts a change to a case component.
(Item 13)
Means for receiving information on technical literature;
An application unit that applies information of the received technical literature to a model generated by mechanically learning a keyword extracted from a past application, the problem of the application, and the claims of the application,
13. The creation support apparatus according to any one of items 10 to 12, further comprising: a specifying unit that specifies the past application using a keyword obtained as a result of the application.
(Item 14)
Displaying the claims included in the claims of the past application on the display graphically;
Accept changes to the displayed shape,
Generating a new claim in text format based on the changed graphic.
(Item 15)
A function to graphically display the claims included in the claims of the past application on the display,
A function to accept changes to the displayed shape,
A computer program for causing a computer to implement a function of generating a new claim in a text format based on a changed graphic.

  2 claim creation support system, 4 creation server, 6 network, 8 user terminal.

Claims (3)

A receiving means for receiving information;
Applying means for applying the received information to a model generated by mechanically learning information extracted from a past application and the claims of the application,
Providing means for providing the claims obtained as a result of the application. A correction unit for receiving a correction to the provided claims,
The creation device according to claim 1, wherein the providing unit provides a claim in which the received correction is reflected. Display control means for displaying technical information in a graphic form on a display;
Receiving means for receiving a change to the displayed figure;
Generating means for generating a new claim in text format based on the changed graphic.

Images