Analysis program, information processing device, and analysis method

Abstract

To provide a novel technique using a large-scale language model for comparing input information representing a technical idea with other information.SOLUTION: An analysis program causes a computer to execute the steps of: acquiring input information representing a technical idea; acquiring comparative information of an object to be compared with the technical idea; dividing the technical idea for every component; generating a first instruction sentence including an instruction to compare each of the plurality of divided components with the comparative information; and outputting an evaluation result representing a relevance of each of the plurality of components to the comparative information, based on a result obtained from the large-scale language model by inputting the first instruction into the large-scale language model.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to an analysis program, an information processing apparatus, and an analysis method.

Background Art

[0002] In recent years, various large language models have been developed. A large language model is a language model that has learned an enormous amount of text data and is trained to be able to process various natural languages.

[0003] Non-Patent Document 1 discloses a method for improving the output accuracy of ChatGPT, which is an example of a large language model. Specifically, Non-Patent Document 1 discloses that by inputting an instruction sentence "Let's think step by step" into ChatGPT, the accuracy of the output is improved.

Prior Art Documents

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Although large language models can be applied to various services, there are still few examples realized as specific services. In this regard, a new technology that uses a large language model to compare input information indicating a technical idea with other information is desired.

Means for Solving the Problems

[0006] In one example of this disclosure, an analysis program is provided. The analysis program causes a computer to perform the following steps: acquire input information representing a technical idea; acquire comparison information to be compared with the technical idea; divide the technical idea into constituent elements; generate a first instruction statement that includes instructions to compare each of the divided constituent elements with the comparison information; and input the first instruction statement into a large-scale language model and output an evaluation result showing the relationship between each of the constituent elements and the comparison information based on the results obtained from the large-scale language model.

[0007] In one example of this disclosure, the division step includes generating a second directive for dividing the technical idea into constituent elements, and inputting the second directive into the large-scale language model.

[0008] In one example of this disclosure, the above division step includes dividing the above technical idea into constituent elements according to predetermined rules.

[0009] In one example of this disclosure, the first instruction includes an instruction to cause the large-scale language model to output the locations of the multiple constituent elements within the comparison information.

[0010] In one example of this disclosure, the comparative information includes patent documents. The above description includes at least one of the paragraph number in the patent document, the figure number in the patent document, and the claim number in the patent document.

[0011] In one example of this disclosure, the first instruction includes an instruction to cause the large-scale language model to output the reason for extracting the location described above.

[0012] In one example of this disclosure, the first instruction includes instructions to cause the large-scale language model to output the degree of association between each of the multiple constituent elements and the comparison information.

[0013] In one example of this disclosure, the analysis program causes the computer to perform the steps of generating a third instruction that summarizes the comparative information from a predetermined perspective, and inputting the third instruction into the large-scale language model and outputting a summary of the comparative information based on the results obtained from the large-scale language model.

[0014] In another example of this disclosure, an information processing device is provided. The information processing device comprises a control unit for controlling the information processing device. The control unit performs the following processes: acquiring input information representing a technical idea; acquiring comparison information to be compared with the technical idea; dividing the technical idea into constituent elements; generating a first instruction statement that includes an instruction to compare each of the divided constituent elements with the comparison information; and inputting the first instruction statement into a large-scale language model and outputting an evaluation result showing the relationship between each of the constituent elements and the comparison information based on the results obtained from the large-scale language model.

[0015] Other examples of this disclosure provide a computer-based analysis method. This analysis method comprises the steps of: obtaining input information representing a technical idea; obtaining comparison information to be compared with the technical idea; dividing the technical idea into constituent elements; generating a first instruction statement that includes instructions to compare each of the divided constituent elements with the comparison information; and inputting the first instruction statement into a large-scale language model and outputting an evaluation result showing the relationship between each of the constituent elements and the comparison information based on the results obtained from the large-scale language model.

[0016] The above and other objects, features, aspects and advantages of the present invention will become apparent from the following detailed description relating to the invention, which will be understood in conjunction with the accompanying drawings. [Brief explanation of the drawing]

[0017] [Figure 1] This figure shows an example of the device configuration of an information processing system. [Figure 2] This is a diagram for explaining the relevance evaluation function. [Figure 3] This is a schematic diagram showing an example of the hardware configuration of an information processing device. [Figure 4] This is a schematic diagram showing an example of the hardware configuration of a user terminal. [Figure 5] This is a diagram showing an example of the data flow among an information processing device, a user terminal, and a server. [Figure 6] This is a diagram showing an example of the setting screen displayed in step S110 shown in FIG. 5. [Figure 7] This is a diagram showing an example of the setting screen displayed in step S112 shown in FIG. 5. [Figure 8] This is a diagram showing an example of the setting screen displayed in steps S114 and S118 shown in FIG. 5. [Figure 9] This is a diagram showing an example of an instruction text. [Figure 10] This is a diagram showing an example of an instruction text. [Figure 11] This is a diagram showing an example of answer information generated by a large language model. [Figure 12] This is a diagram showing an example of an instruction text. [Figure 13] This is a diagram showing an example of the evaluation result screen displayed in step S150 shown in FIG. 5. [Figure 14] This is a diagram for explaining an example of generating input information from an image. [Figure 15] This is a diagram schematically showing the relevance evaluation process according to other examples. [Figure 16] This is a diagram showing an example of an instruction text.

Embodiments for Carrying Out the Invention

[0018] Hereinafter, each embodiment according to the present invention will be described while referring to the drawings. In the following description, the same parts and components are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated. Note that each embodiment and each modification described below may be selectively combined as appropriate.

[0019] <A. Information Processing System 10> First, referring to FIG. 1, the device configuration of the information processing system 10 will be described. FIG. 1 is a diagram showing an example of the device configuration of the information processing system 10.

[0020] As shown in FIG. 1, the information processing system 10 includes an information processing device 100, a user terminal 200, and a server 300. The information processing device 100, the user terminal 200, and the server 300 are configured to be communicable with each other through a network NW (for example, the Internet).

[0021] The information processing device 100 is a notebook or desktop PC (Personal Computer), a tablet terminal, a smartphone, or other computer equipped with a communication function. The number of information processing devices 100 constituting the information processing system 10 may be one or two or more. The information processing device 100 is, for example, operated by company "A".

[0022] The user terminal 200 is, for example, a notebook or desktop PC, a tablet terminal, a smartphone, or other computer equipped with a communication function. The number of user terminals 200 constituting the information processing system 10 may be one or two or more. The information processing device 100 is, for example, owned by user "A" who is an ordinary user.

[0023] Server 300 is a notebook or desktop PC (Personal Computer), a tablet device, a smartphone, or another computer with communication capabilities. The number of servers 300 constituting the information processing system 10 may be one or two or more. Server 300 is operated, for example, by company "B".

[0024] Server 300 stores the Large Language Model 324. The Large Language Model 324 is a language model that has been trained on a massive amount of text data, exceeding several billion entries, and is trained to process various natural languages. The Large Language Model 324 is also known as an LLM (Large Language Model). The Large Language Model 324 is trained to receive an instruction as input and generate an output corresponding to that instruction.

[0025] Examples of large-scale language models 324 include the GPT series such as GPT-3 (Generative Pretrained Transformer) and GPT-4, PaLM (Scaling Language Modeling with Pathways), LLaMA (Large Language Model Meta AI), and known LLMs. In addition to the GPT series, various other large-scale language models may be used, such as Transformer-based large-scale language models like BERT (Bidirectional Encoder Representations from Transformers), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), and LSTM (Long Short-Term Memory).

[0026] Company "B", for example, has published an API (Application Programming Interface) for utilizing the functions of the large language model 324. As a result, designers and general users of Company "A" can utilize the functions of the large language model 324 through this API.

[0027] In addition, various processes described in this specification may be implemented in the information processing apparatus 100, may be implemented in the user terminal 200, may be implemented in the server 300, or may be implemented in other computers.

[0028] Also, in the above description, an example where the information processing system 10 includes the server 300 has been explained, but the information processing system 10 may not include the server 300. In this case, the information processing system 10 is composed of one or more information processing apparatuses 100 and one or more user terminals 200.

[0029] <B. Processing Overview> The information processing apparatus 100 provides a function for user "A" to evaluate the relevance between input information indicating a technical idea and comparison information.

[0030] The "technical idea" is a technical means for solving a technical problem. The technical idea is defined by a combination of elements (hereinafter, also referred to as "constituent elements") that constitute an invention. Examples of input information indicating a technical idea include, for example, the claims described in the claims of a patent, the constituent elements obtained by summarizing technical materials with a large language model, and the constituent elements obtained by summarizing an image with a large language model.

[0031] The "comparison information" is information to be compared with the above input information. The comparison information may be publicly known information that can be publicly known to unspecified persons, or may be non-public information that is secretly managed within the company.

[0032] Publicly available information includes publicly available patent documents and publicly available non-patent documents. Confidential information includes, for example, information kept confidential within a company (such as patent documents or technical documents that have not yet been made public).

[0033] Examples of patent documents include published patent gazettes, patent gazettes, publicly released patent gazettes, republished patents, and utility model gazettes. For example, a patent document includes bibliographic information, a specification, claims, drawings, and an abstract. Examples of bibliographic information include the application number, publication number, patent registration number, application date, publication date, registration date, applicant, patent holder, title of invention, agent, and country of application. Examples of non-patent documents include academic papers, newspaper articles, books, and web pages.

[0034] In the following explanation, "publicly available information" will be used as an example of "comparative information," but comparative information is not limited to publicly available information.

[0035] Referring to Figure 2, we will now describe the overview of the function that evaluates the relationship between input information 123 and publicly available information 125. Figure 2 is a diagram illustrating the relationship evaluation function.

[0036] The information processing device 100 acquires input information 123 that represents a technical concept. The source from which the input information 123 is acquired is arbitrary. For example, the input information 123 is acquired from the user terminal 200 mentioned above.

[0037] Furthermore, the information processing device 100 obtains public information 125 to be compared with the input information 123. The source from which the public information 125 is obtained is arbitrary. For example, the public information 125 is obtained from the patent database 124 (see Figure 3), which is stored in the storage device of the information processing device 100. As another example, the public information 125 is obtained from a patent database on a server managed by the Japan Patent Office. As yet another example, the public information 125 is obtained from a patent database managed on another server.

[0038] The relationship evaluation between input information 123 and public information 125 is achieved by utilizing a large-scale language model 324. More specifically, first, the information processing device 100 divides the technical concept shown in input information 123 into constituent elements. Then, the information processing device 100 generates an instruction statement 126 (first instruction statement) which includes instructions to compare each of the divided constituent elements with the public information 125.

[0039] The instruction statement 126 is pre-registered in the information processing device 100, for example, as a template. The information processing device 100 generates the instruction statement 126 by specifying various information in the argument sections 127 to 129 within the instruction statement 126.

[0040] More specifically, the argument part 127 is specified as the acquired input information 123. The argument part 129 is specified as the acquired public information 125.

[0041] The argument section 128 is used to specify each of the divided constituent elements in order. For example, if the technical idea shown in the input information 123 is divided into N constituent elements (where N is an integer greater than or equal to 2), the information processing device 100 specifies each of the N constituent elements in the argument section 128. As a result, the information processing device 100 generates instruction statements 126 corresponding to the number of divided constituent elements. In the example in Figure 2, N instruction statements 126 are generated.

[0042] The generated instruction sentence 126 is input to the large-scale language model 324. Upon receiving the instruction sentence 126, the large-scale language model 324 generates a response corresponding to the instruction sentence 126.

[0043] The information processing device 100 inputs the instruction statement 126 into the large-scale language model 324 and, based on the results obtained from the large-scale language model 324, outputs an evaluation result 130 showing the relationship between each of the divided constituent elements and the publicly available information 125. This relationship may be expressed as a numerical value indicating the degree of relationship, or as an explanatory text. In the example in Figure 2, the relationship is expressed as a numerical value.

[0044] The output destination of the evaluation result 130 by the information processing apparatus 100 is arbitrary. As an example, the output destination is the user terminal 200. The evaluation result 130 output to the user terminal 200 is displayed, for example, on the display of the user terminal 200.

[0045] The above evaluation function is effective, for example, when conducting an invalidation search. More specifically, the user designates a patent invention to be invalidated as the input information 123. Thereafter, the information processing apparatus 100 decomposes the patent invention into constituent elements and compares each constituent element with the public information 125. Then, the information processing apparatus 100 outputs an evaluation result 130 indicating the degree to which each constituent element is disclosed in the public information 125. Thereby, the user can significantly shorten the time required for literature screening and literature review.

[0046] Note that the application of the above evaluation function is not limited to invalidation searches. As another example, the above evaluation function may be used for prior art searches. In this case, the user designates an invention to be the subject of a prior art search as the input information 123. Thereafter, the information processing apparatus 100 decomposes the invention into constituent elements and compares each constituent element with the public information 125. Then, the information processing apparatus 100 outputs an evaluation result 130 indicating the degree to which each constituent element is disclosed with the public information 125. Thereby, the user can easily determine whether the invention under investigation has novelty or inventive step. As a result, the user can significantly shorten the time required for literature screening and literature review.

[0047] As described above, the information processing apparatus 100 uses the large language model 324 for the comparison between the input information 123 indicating a technical idea and the public information 125, and provides new value to the user.

[0048] <C. Hardware Configuration> Next, referring to FIGS. 3 and 4, the hardware configurations of the information processing apparatus 100 and the user terminal 200 shown in FIG. 1 above will be described in order.

[0049] The hardware configuration of the server 300 shown in Figure 1 is the same as that of the information processing device 100, so its explanation will not be repeated.

[0050] (C1. Information processing device 100) First, with reference to Figure 3, the hardware configuration of the information processing device 100 shown in Figure 1 will be explained. Figure 3 is a schematic diagram showing an example of the hardware configuration of the information processing device 100.

[0051] The information processing device 100 includes a control device 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a communication interface 104, a display interface 105, an input interface 107, and an auxiliary storage device 120. These components are connected to a bus 110.

[0052] The control device 101 is comprised of, for example, at least one integrated circuit. The integrated circuit may consist of, for example, at least one CPU (Central Processing Unit), at least one GPU (Graphics Processing Unit), at least one ASIC (Application Specific Integrated Circuit), at least one FPGA (Field Programmable Gate Array), or a combination thereof.

[0053] The control device 101 controls the operation of the information processing device 100 by executing various programs such as the analysis program 122 and the operating system. Based on the receipt of execution commands for various programs, the control device 101 reads the program from the auxiliary storage device 120 or ROM 102 into the RAM 103. The RAM 103 functions as working memory and temporarily stores various data necessary for the execution of various programs.

[0054] The communication interface 104 is connected to a LAN (Local Area Network), an antenna, and other devices. The information processing device 100 exchanges data with external devices via the communication interface 104. These external devices include, for example, a user terminal 200, a server 300, and other communication devices.

[0055] A display 106 is connected to the display interface 105. The display interface 105 sends image signals to the display 106 for displaying images, in accordance with commands from the control device 101 or the like. The display 106 is, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, or other display device. The display 106 may be configured integrally with the information processing device 100, or it may be configured separately from the information processing device 100.

[0056] An input device 108 is connected to the input interface 107. The input device 108 is, for example, a mouse, keyboard, touch panel, or other device capable of receiving user input. The input device 108 may be configured integrally with the information processing device 100, or it may be configured separately from the information processing device 100.

[0057] The auxiliary storage device 120 is, for example, a hard disk, flash memory, SSD (Solid State Drive), or other storage medium. The auxiliary storage device 120 stores the analysis program 122, the patent database 124, and the instruction statements 126 described above. The patent database 124 includes multiple publicly available information 125. The storage location of the analysis program 122, the patent database 124, and the instruction statements 126 is not limited to the auxiliary storage device 120, but may also be stored in the storage area of ​​the control device 101 (for example, cache memory), ROM 102, RAM 103, external devices, etc.

[0058] Furthermore, the analysis program 122 may be provided not as a standalone program, but incorporated as part of any other program. In this case, the various processes defined in the analysis program 122 are realized in cooperation with any other program, such as the analysis program 222 described later. Even a program that does not include such modules does not deviate from the intent of the analysis program 122 according to this embodiment. Moreover, some or all of the functions provided by the analysis program 122 may be realized by dedicated hardware. Furthermore, the information processing device 100 may be configured in a form similar to a so-called cloud service, in which at least one server executes a portion of the processing of the analysis program 122.

[0059] (C2. User terminal 200) Next, with reference to Figure 4, the hardware configuration of the user terminal 200 shown in Figure 1 will be described. Figure 4 is a schematic diagram showing an example of the hardware configuration of the user terminal 200.

[0060] The user terminal 200 includes a control unit 201, a ROM 202, a RAM 203, a communication interface 204, a display interface 205, an input interface 207, and an auxiliary storage device 220. These components are connected to a bus 210.

[0061] The control device 201 is comprised of, for example, at least one integrated circuit. The integrated circuit may consist of, for example, at least one CPU, at least one GPU, at least one ASIC, at least one FPGA, or a combination thereof.

[0062] The control device 201 controls the operation of the user terminal 200 by executing various programs such as the analysis program 222 and the operating system. Based on the receipt of execution commands for various programs, the control device 201 reads the program from the auxiliary storage device 220 or ROM 202 into the RAM 203. The RAM 203 functions as working memory and temporarily stores various data necessary for the execution of the program.

[0063] The communication interface 204 is connected to a LAN, an antenna, and the like. The user terminal 200 exchanges data with external devices via the communication interface 204. These external devices include, for example, an information processing device 100, a server 300, and other communication devices. The user terminal 200 may be configured to download an analysis program 222 from the information processing device 100.

[0064] A display 206 is connected to the display interface 205. The display interface 205 sends image signals to the display 206 for displaying images, in accordance with commands from the control device 201 or the like. The display 206 is, for example, a liquid crystal display, an organic EL display, or other display device. The display 206 may be configured integrally with the user terminal 200, or it may be configured separately from the user terminal 200.

[0065] An input device 208 is connected to the input interface 207. The input device 208 may be, for example, a mouse, keyboard, touch panel, or other device capable of receiving user input. The input device 208 may be configured integrally with the user terminal 200 or separately from the user terminal 200.

[0066] The auxiliary storage device 220 is, for example, a hard disk, flash memory, SSD (Solid State Drive), or other storage medium. The auxiliary storage device 220 stores the analysis program 222, etc. The storage location of the analysis program 222 is not limited to the auxiliary storage device 220, but may also be stored in the storage area of ​​the control device 201 (for example, cache memory), ROM 202, RAM 203, external devices (for example, a server), etc.

[0067] Furthermore, the analysis program 222 may be provided not as a standalone program, but incorporated as part of any other program. In this case, the various processes defined in the analysis program 222 are realized in cooperation with any other program, such as the analysis program 122 mentioned above. Even a program that does not include such modules does not deviate from the intent of the analysis program 222 according to this embodiment. Moreover, some or all of the functions provided by the analysis program 222 may be realized by dedicated hardware. Furthermore, the user terminal 200 may be configured in a form similar to a so-called cloud service, where at least one server executes some of the processing of the analysis program 222.

[0068] <D.データフロー> Next, referring to Figures 5 to 13, the operation of the information processing system 10 related to the evaluation of the relationship between input information 123 and public information 125 will be described. Figure 5 is a diagram showing an example of data flow between the information processing device 100, the user terminal 200, and the server 300.

[0069] In the following explanation, we will assume that the aforementioned relevance evaluation function provided by the information processing device 100 is applied to the peer review of publicly available information 125. However, the application of the relevance evaluation function is not limited to the peer review of publicly available information 125.

[0070] (D1. Step S110) First, with reference to Figure 6, the process of step S110 shown in Figure 5 will be explained. Figure 6 is a diagram showing an example of the setting screen 400A displayed in step S110.

[0071] The settings screen 400A accepts the setting of search conditions for searching for publicly available information 125 from the aforementioned patent database 124 (see Figure 3). By setting these search conditions, the user can specify one or more publicly available information 125 to be compared with the input information 123. The settings screen 400A includes, for example, a selection field 410 and a setting field 412.

[0072] The selection field 410 accepts input for the search type. For example, the search types that can be specified in the selection field 410 include "full-text search," "field search," "command search," "semantic search," and "number search."

[0073] The settings field 412 accepts input of various search criteria. Examples of search criteria that can be entered in the settings field 412 include the patent document number, the type of the number (e.g., application number or publication number), and the country in which the application was published.

[0074] In the above explanation, we described an example where the search criteria are entered by the user, but the search criteria may also be automatically generated based on the input information 123.

[0075] (D2. Step S112) Next, with reference to Figure 7, the process of step S112 shown in Figure 5 will be explained. Figure 7 is a diagram showing an example of the settings screen 400B displayed in step S112.

[0076] The settings screen 400B is displayed, for example, by scrolling through the settings screen 400A described above. The settings screen 400B accepts the setting of review conditions. For example, the settings screen 400B includes a settings field 420, a selection field 422, and a settings field 424. The settings field 424 includes an editing field 425.

[0077] The settings field 420 accepts the setting of the items to be reviewed. For example, the settings field 420 accepts input for the maximum number of publicly available documents 125 to be reviewed and the sections within the publicly available documents 125 to be reviewed. Examples of sections that can be specified for review include the abstract, the title of the invention, the top claim in the claims (i.e., claim 1), the technical field, the background art, the problem the invention aims to solve, the effects of the invention, the means for solving the problem, and the specification.

[0078] Selection field 422 accepts the selection of the peer review type. Selectable peer review types include, for example, "Investigation Perspective / Comparative Invention," "Claim Relevance Assessment," "User Instructions such as Abstract / Information Extraction," and "User Tags / Evaluation." By selecting "Claim Relevance Assessment," the user can utilize the relevance assessment function.

[0079] The settings field 424 accepts input information 123 that indicates the technical concept. Input information 123 can be set in various ways.

[0080] Suppose, in a certain scenario, the user selects the "Claim Text" button in the settings field 424. In this case, the user can manually enter the claims in the editing field 425. The user can, for example, copy and paste claims from some document or draft claims they have created into the editing field 425. Alternatively, the user may directly enter the claims into the editing field 425.

[0081] In another scenario, suppose the user selects the "Publication Number" button in the settings field 424. In this case, the user enters a publication number, such as a patent number or publication number, into the settings field 424 and presses the "Get Claim Text" button. Based on this, the information processing device 100 refers to the aforementioned patent database 124 and searches for a patent document corresponding to the entered publication number. The information processing device 100 then reflects the claims described in the searched patent document in the editing field 425.

[0082] In another scenario, suppose the user selects the "Technical Text" button in the settings section 424. In this case, the user specifies a document that illustrates a technical idea. Examples of such documents include technical papers, newspaper articles, and invention documents. The user then presses the "Get Claim Text" button. Based on this, the information processing device 100 extracts the constituent elements from the specified document by having the large-scale language model 324 summarize it.

[0083] More specifically, the information processing device 100 generates an instruction statement for extracting technical features from the input document and inputs this instruction statement into the large-scale language model 324. For example, the instruction statement includes the instruction, "Identify technical features based on [Target Document] and generate claims for a patent claim in Japanese." [Target Document] is an argument part, which specifies the document to be summarized. As a result, the large-scale language model 324 extracts constituent elements from the input document. The extracted constituent elements are reflected in the editing field 425.

[0084] (D3. Steps S114, S116, S118) Next, referring to Figures 8 and 9, the processes of steps S114, S116, and S118 shown in Figure 5 will be explained. Figure 8 is a diagram showing an example of the setting screen 400C displayed in steps S114 and S118.

[0085] The settings screen 400C is displayed, for example, by scrolling the settings screen 400B described above. For example, the settings screen 400C includes a selection field 430, an editing field 432, a selection field 436, a selection field 438, and a start button 440. The editing field 432 includes a display field 434 for configuration requirements.

[0086] The selection field 430 accepts the selection of a method for dividing the input information 123, which was set in the editing field 425 (see Figure 7) described above, into constituent elements. As an example, the selection field 430 includes a "Newline" button, an "Automatic Splitting by AI" button, and a "Manual Input" button.

[0087] Suppose that in a certain situation, the user selects the "Newline" button in the selection field 430. In this case, the information processing device 100 divides the technical idea contained in the input information 123 into constituent elements according to predetermined division rules (step S116). In the example in Figure 8, a claim, which is an example of input information 123, is divided. The above division rules include dividing according to predetermined keywords. Examples of such predetermined keywords include newline characters, "~is", "~and", and "~consist of".

[0088] In another scenario, suppose the user selects the "Automatically divide by AI" button in the selection field 430. In this case, the information processing device 100 uses the large-scale language model 324 to divide the claims into constituent elements (step S116).

[0089] More specifically, the information processing device 100 generates instruction statements (second instruction statements) for dividing the technical idea, which is the input information 123, into constituent elements. Figure 9 shows an example of the generated instruction statement 156. The instruction statement 156 is pre-stored in the auxiliary storage device 120 of the information processing device 100, for example, as a template.

[0090] Instruction 156 specifies that the input information 123 specified in the argument section 157 should be divided according to its constituent elements. The argument section 157 specifies, for example, a claim which is an example of the input information 123.

[0091] Subsequently, the information processing device 100 inputs an instruction statement 156 specifying the input information 123 to the large-scale language model 324. Upon receiving the instruction statement 156, the large-scale language model 324 generates a response corresponding to the instruction statement 156. The generated response is output to the information processing device 100. In the generated response, the input information 123 is shown for each configuration requirement.

[0092] In another scenario, suppose the user selects the "Manual Input" button in the selection field 430. In this case, the information processing device 100 can freely edit the constituent elements of the claim in the editing field 432.

[0093] The input information 123, divided according to the method selected in the selection field 430, is displayed in the display field 434 of the editing field 432, according to the constituent requirements. The display field 434 is displayed in the editing field 432 according to the number of divided constituent requirements.

[0094] For example, if a claim entered as input information 123 is divided into constituent elements #1 to #4, four display fields 434 will be displayed in the editing field 432. In the example in Figure 8, constituent element #1 is displayed in display field 434A, constituent element #2 is displayed in display field 434B, constituent element #3 is displayed in display field 434C, and constituent element #4 is displayed in display field 434D.

[0095] Users can freely edit each configuration requirement displayed in display field 434.

[0096] Furthermore, users can increase or decrease the number of display fields 434 shown in the editing field 432. For example, a user can increase the number of empty display fields 434 by clicking the "Add Configuration Requirement" button. A user can also delete a display field 434 corresponding to a button by clicking the "Delete Configuration Requirement" button. Additionally, a user can delete all display fields 434 currently displayed in the editing field 432 by clicking the "Delete All Configuration Requirements" button.

[0097] The selection field 436 accepts the selection of items to be summarized regarding the publicly available information 125. The information processing device 100 generates a summary of the publicly available information 125 according to the items to be summarized selected in the selection field 436. The method of generation will be described later.

[0098] The selection field 438 accepts the selection of the large-scale language model 324 to be used. The large-scale language model 324 selected in the selection field 438 will be used for evaluating the relationship between the input information 123 and the publicly available information 125, etc.

[0099] Based on the user pressing the start review button 440, the user terminal 200 transmits the information entered on the setting screens 400A to 400C (see Figures 6 to 8) to the information processing device 100.

[0100] In the above description, we explained an example in which the processes in steps S112, S114, S116, and S118 are executed after the process in step S110. However, the processes in steps S112, S114, S116, and S118 may be executed before the process in step S110. In this case, the search conditions in step S110 may be automatically set using the divided constituent elements #1 to #4 as the conditions for similarity search. If the search conditions are set automatically, the process in step S110 does not necessarily have to be executed.

[0101] (D3. Step S120) Next, in step S120, the information processing device 100 searches for publicly available information 125 from among the publicly available information 125 registered in the aforementioned patent database 124 that matches the search conditions set on the setting screen 400A (see Figure 6). The information processing device 100 uses the publicly available information 125 that matches the search conditions as the population to be compared with the input information 123.

[0102] (D4. Step S122) Next, in step S122, the information processing device 100 generates the above-mentioned instruction statement 126 (see Figure 2) for input into the large-scale language model 324.

[0103] Figure 10 shows an example of instruction statement 126. Preferably, instruction statement 126 includes a plurality of instructions 131A to 131D.

[0104] The information processing device 100 specifies input information 123 for each argument portion 127 of instructions 131A to 131D. The information processing device 100 also specifies public information 125 for each argument portion 129 of instructions 131A to 131D.

[0105] Furthermore, the information processing device 100 sequentially specifies each of the configuration requirements divided in the above-mentioned setting screen 400C to each of the argument parts 128 of instructions 131A to 131D.

[0106] As an example, suppose the technical idea contained in the input information 123 is divided into the above constituent elements #1 to #4. In this case, the information processing device 100 specifies constituent element #1 to the argument part 128 for each argument part 128 of instructions 131A to 131D, and generates the first instruction statement 126. Next, the information processing device 100 specifies constituent element #2 to the argument part 128 for each argument part 128 of instructions 131A to 131D, and generates the second instruction statement 126. Next, the information processing device 100 specifies constituent element #3 to the argument part 128 for each argument part 128 of instructions 131A to 131D, and generates the third instruction statement 126. Next, the information processing device 100 specifies constituent element #4 to the argument part 128 for each argument part 128 of instructions 131A to 131D, and generates the fourth instruction statement 126. In this manner, the information processing device 100 repeatedly generates the instruction statement 126 according to the number of divided constituent elements #1 to #4.

[0107] Instruction 131A provides instructions for extracting the relevant information from Public Information 125 for each of the constituent elements #1 to #4. This allows users to easily determine whether each of the constituent elements #1 to #4 is disclosed in Public Information 125.

[0108] Instruction 131B specifies instructions for causing the large-scale language model 324 to extract the locations of constituent elements #1 to #4 in the publicly available information 125. These locations may be indicated by paragraph numbers in the patent document, claim numbers in the patent document, or by the number of characters or lines from a predetermined reference position in the patent document. This allows the user to easily determine the locations of constituent elements #1 to #4 in the publicly available information 125.

[0109] Instruction 131C specifies instructions for causing the large-scale language model 324 to output the reasons for extracting the locations of constituent elements #1 to #4 in the public information 125. In other words, instruction 131C specifies instructions for causing the model to output the reasons for determining that each of constituent elements #1 to #4 is described at its respective location. This provides the user with information to determine whether each of constituent elements #1 to #4 is disclosed in the public information 125.

[0110] Instruction 131D specifies instructions for causing the large-scale language model 324 to output the degree of relevance between each of the constituent elements #1 to #4 and the public information 125. This allows the user to easily understand the degree to which each of the constituent elements #1 to #4 is related to the public information 125.

[0111] The information processing device 100 sends the instruction statement 126 generated in step S122 to the server 300.

[0112] In the above explanation, we described an example in which all four instructions 131A to 131D are specified in instruction 126. However, it is not necessary for all of instructions 131A to 131D to be specified in instruction 126. For example, at least one of instructions 131A to 131D may be specified in instruction 126.

[0113] Furthermore, although the above explanation assumed that the entire text of the public information 125 was specified in the argument section 129, if the amount of text in the public information 125 is large, the information processing device 100 may divide the public information 125 and then compare the public information 125 with constituent requirements #1 to #4. This allows users to use the API without restriction, even if the amount of data that can be input is limited in the terms of use for the API for using the large-scale language model 324. It also helps to suppress the omission of comparison results.

[0114] (D5. Step S124) Next, in step S124, the server 300 inputs the instruction 126 to the large-scale language model 324 based on the fact that it has received the instruction 126 from the information processing device 100. As a result, the large-scale language model 324 generates a response corresponding to the instruction 126.

[0115] Figure 11 shows an example of response information 326 generated by the large-scale language model 324. In the example in Figure 11, the response information 326 is shown in tabular format, but the format of the response information 326 is arbitrary. The output format of the large-scale language model 324 is predetermined, for example, in instruction 126, and the large-scale language model 324 outputs the response information 326 according to the output format specified in instruction 126.

[0116] The response information 326 includes an evaluation result 327 for each of the public information 125 retrieved in step S120. In the example in Figure 11, each evaluation result 327 is associated with a specific identifier of the public information 125. The identifier of the public information 125 is defined, for example, by the application number, publication number, or registration publication number.

[0117] Furthermore, the evaluation result 327 includes, in addition to the configuration requirements #1 to #4 (see Figure 8) set on the settings screen 400C, "Description Text," "Location of Description," "Reason for Extraction," and "Relevance Score." "Description Text" is the result output from the large-scale language model 324 according to the above instruction 131A (see Figure 10). "Location of Description" is the result output from the large-scale language model 324 according to the above instruction 131B (see Figure 10). "Reason for Extraction" is the result output from the large-scale language model 324 according to the above instruction 131C (see Figure 10). "Relevance Score" is the result output from the large-scale language model 324 according to the above instruction 131D (see Figure 10).

[0118] The server 300 transmits the response information 326 generated in step S124 to the information processing device 100.

[0119] (D6. Step S126) Next, in step S126, the information processing device 100 generates the instruction statement 166 shown in Figure 12. Figure 12 is a diagram showing an example of the instruction statement 166.

[0120] Instruction 166 is pre-stored, for example, as a template in the auxiliary storage device 120 of the information processing device 100. Instruction 166 (third instruction) specifies instructions for summarizing the public information 125 from a predetermined perspective.

[0121] For example, instruction 166 includes at least one of the following: instruction 167A which summarizes the published information 125 with respect to the technical field; instruction 167B which summarizes the published information 125 with respect to the problem that the invention aims to solve; instruction 167C which summarizes the published information 125 with respect to the effects of the invention; and instruction 167D which summarizes the published information 125 with respect to the operation and function.

[0122] More specifically, each of instructions 167A to 167D includes an argument section 168. The information processing device 100 specifies the public information 125 to be summarized for each of the argument sections 168.

[0123] The information processing device 100 sends the instruction statement 166 generated in step S126 to the server 300.

[0124] (D7. Step S128) Next, in step S128, the server 300 inputs the instruction 166 to the large-scale language model 324 based on the fact that it has received the instruction 166 from the information processing device 100. As a result, the large-scale language model 324 outputs a summary of the public information 125 in accordance with the instruction 126.

[0125] The summaries output from the large-scale language model 324 include summaries of the publicly available information 125 relating to the technical field, summaries of the publicly available information 125 relating to the problems the invention aims to solve, summaries of the publicly available information 125 relating to the effects of the invention, and summaries of the publicly available information 125 relating to the operation and function.

[0126] The server 300 transmits the response information generated in step S128 to the information processing device 100. In this way, the information processing device 100 inputs the instruction sentence 166 into the large-scale language model 324 and outputs a summary of the public information 125 based on the results obtained from the large-scale language model 324.

[0127] (D8. Steps S140, S150) Next, in step S140, the information processing device 100 generates an evaluation result screen based on the response information 326 received from the server 300. This evaluation result screen is written in a language such as HTML (HyperText Markup Language).

[0128] Next, in step S150, the user terminal 200 displays the evaluation result screen generated by the information processing device 100. Figure 13 shows an example of the evaluation result screen 400D. The evaluation result screen 400D is displayed, for example, on the display 206 of the user terminal 200.

[0129] The evaluation results screen 400D includes a display area 450 that displays information related to the input information 123, a display area 452 that displays information related to the publicly available information 125, a display area 454 that displays the evaluation results of the relationship between the input information 123 and the publicly available information 125, and a display area 456 that displays information related to the summary of the publicly available information 125.

[0130] Display field 450 displays information entered in the settings screens 400A and 400B (see Figures 6 and 7) mentioned above. For example, display field 450 displays "ID" (Identification), "Review Type", "Model", "Number of Items Retrieved", "Status", "Retrieval Time", "Review Subject", and "Configuration Requirements".

[0131] "ID" is an identifier used to uniquely identify the peer review evaluation result. "Peer Review Type" corresponds to the item set in the selection field 422 (see Figure 7) above. "Model" indicates the type of large-scale language model 324 used during the relevance evaluation and corresponds to the information set in the selection field 438 (see Figure 8) above. "Number of Items Retrieved" corresponds to the number of publicly available items 125 compared with the input information 123. "Status" indicates whether the relevance evaluation process was completed successfully or not. "Retrieval Time" indicates the time taken from the start to the end of the relevance evaluation process. "Review Subject" corresponds to the information selected in the setting field 420 (see Figure 7) above. "Configuration Requirements" displays the configuration requirements set in the editing field 432 (see Figure 8) above.

[0132] Display field 452 displays information relating to the publicly available information 125 that was subject to relevance evaluation. Display field 452 displays, for example, the "Title of Invention," "Solution," "Selected Figure," "Application Number," "Publication Number," "Legal Status," and "Applicant."

[0133] Display area 454 displays the evaluation results generated from the response information 326 (see Figure 11) of the large-scale language model 324. As an example, the evaluation results display the relevance score of each of the constituent elements #1 to #4 with the public information 125, the location of constituent elements #1 to #4 in the public information 125, the content of the public information 125 regarding constituent elements #1 to #4, and the reason for determining the above relevance score. The evaluation results also include the total score of the relevance of each constituent element #1 to #4 with the public information 125.

[0134] The display field 456 displays a summary of the publicly available information 125. This summary is the result of inputting the above-mentioned instruction 166 (see Figure 12) into the large-scale language model 324. This summary includes a summary of the publicly available information 125 relating to the technical field, a summary of the publicly available information 125 relating to the problem the invention aims to solve, a summary of the publicly available information 125 relating to the effects of the invention, and a summary of the publicly available information 125 relating to the operation and function.

[0135] As described above, by extracting the comparison results between the input information 123 and the published information 125 separately for the components #1 to #4, the user can significantly reduce the time spent reading the published information 125 with a large amount of text. As a result, the user can significantly shorten the time spent on invalidity searches and prior art searches.

[0136] In the example of FIG. 13, the comparison results of one piece of published information 125 are shown in the display columns 452, 454, and 456. However, in reality, the display columns 452, 454, and 456 are displayed on the evaluation result screen 400D for the number of pieces of published information 125 for which the relevance has been evaluated. The evaluation results of the published information 125 are arranged, for example, in the order of the total scores of the relevance evaluations.

[0137] <E1. Others> Next, another example of the above-described embodiment will be described.

[0138] In the above-described setting screens 400B and 400C, an example in which the input information 123 is generated by splitting the claims input in text into constituent elements has been described. However, the input information 123 indicating the technical idea does not necessarily have to be generated from text. As an example, the input information 123 indicating the technical idea may be generated from an image.

[0139] FIG. 14 is a diagram for explaining an example of generating the input information 123 from the image IM. In the example of FIG. 14, an image IM showing a PET bottle is shown.

[0140] The large language model 324 according to this example is learned to be able to interpret the content of the image. As a large language model capable of interpreting the content of an image, for example, CLIP (Contrastive Language-Image Pretraining), BLIP (Bootstrapping Language Image Pre-training for unified vision-language understanding and generation), ViLBERT (Vision-and-Language BERT), etc. can be used.

[0141] For such a large language model 324, the information processing apparatus 100 inputs the image IM and the instruction text 176. The instruction text 176 is defined to interpret the objects shown in the image IM according to the constituent elements. Thereby, the large language model 324 divides the objects shown in the image IM into constituent elements and outputs the input information 123 indicating the technical idea.

[0142] Note that the input information 123 shown in FIG. 14 is the actual output result of ChatGPT. In the output result, the plastic bottle shown in the image IM is divided into constituent elements of "bottle cap", "neck part", "body part", and "bottom part".

[0143] In this way, by extracting the technical idea from the image, even a designer who is not familiar with creating claims can easily generate the input information 123.

[0144] <E2. Others> Next, another example of the above embodiment will be described.

[0145] In the example of FIG. 10 described above, based on receiving the input of the instruction text 126, the large language model 324 outputs, as an example of the evaluation result, the positions where each constituent element is described in the public information 125. In the above example, the paragraph numbers in the public information 125 are output as the described positions. In contrast, in this example, the drawing numbers in the public information 125 are output as the described positions.

[0146] FIG. 15 is a diagram schematically showing the process of relevance evaluation in this example. As shown in FIG. 15, the public information 125 includes one or more drawings 125F. The drawing 125F is, for example, image data. The format of the image is not particularly limited.

[0147] The information processing apparatus 100 according to this example uses the large language model 324 to compare the input information 123 with the public information 125 including the drawing 125F in the public information 125.

[0148] More specifically, the large language model 324 according to this example is learned to be able to interpret the content of images. For such a large language model 324, the information processing apparatus 100 inputs the drawing 125F and a predetermined instruction text. The instruction text is defined to describe the object shown in the drawing 125F. When receiving the input of the instruction text, the large language model 324 outputs a description text of the object shown in the drawing 125F.

[0149] Thereafter, the information processing apparatus 100 instructs the large language model 324 to compare the input information 123 with the description text of the drawing 125F. Thereby, the information processing apparatus 100 evaluates the relevance between the input information 123 and the drawing 125F included in the public information 125. In addition, the information processing apparatus 100 also evaluates the relevance between the input information 123 and a document (for example, a specification, etc.) included in the public information 125. Since the evaluation is as described above, the description thereof will not be repeated.

[0150] As a result, an evaluation result 130 is output. The evaluation result 130 includes not only the relevance score of each constituent element with the public information 125 but also the description position of each constituent element in the public information 125. The description position may be indicated by the paragraph number of the specification in the public information 125 or may be indicated by the figure number in the public information 125.

[0151] <E3. Others> Next, still another example of the above embodiment will be described.

[0152] In the above, the logical combination of each of the public information 125 has not been particularly evaluated. In contrast, the information processing apparatus 100 according to this example evaluates whether the logical combination of each of the public information 125 is possible.

[0153] Figure 16 shows an example of an instruction statement 186 used for logic evaluation. The instruction statement 186 is pre-stored, for example, as a template in the auxiliary storage device 120 of the information processing device 100. The instruction statement 186 includes argument sections 187, 188, 189A, and 189B.

[0154] Instruction 186 specifies that, with respect to the input information 123 specified in the argument section 187, it is necessary to determine whether inventive step can be denied by the combination of patent documents specified in the argument sections 189A and 189B. The input information 123 set in the argument section 187 is, for example, a claim.

[0155] The argument section 189A specifies a candidate for the main reference. As an example, the information processing device 100 specifies one of the public information 125 defined in the above-mentioned response information 326 (see Figure 11) to the argument section 189A. Preferably, the information processing device 100 specifies to the argument section 189A the public information 125 that has the highest relevance score with the input information 123 among the public information 125 defined in the response information 326. In this case, the information processing device 100 may specify the entire text of the public information 125 to the argument section 189A, or it may specify a part of the public information 125 (for example, an abstract or specification) to the argument section 189A.

[0156] The argument section 189A specifies a candidate for a secondary reference. As an example, the information processing device 100 specifies one of the public information 125 defined in the above-mentioned answer information 326 (see Figure 11) in the argument section 189B. The document specified in the argument section 189B is different from the document specified in the argument section 189A. Preferably, with respect to a constituent element whose relevance score with the primary reference is less than or equal to a predetermined value (for example, 2 or less), the information processing device 100 specifies another public information 125 whose relevance score is greater than or equal to a predetermined value (for example, 4 or more) as a secondary reference in the argument section 189B. In this case, the information processing device 100 may specify the entire text of the public information 125 in the argument section 189B, or it may specify a part of the public information 125 (for example, an abstract) in the argument section 189B.

[0157] Preferably, the information processing device 100 specifies the content of the examination criteria "Part III, Chapter 2, Section 2: Inventive Step" to the argument section 188. This allows the large-scale language model 324 to understand the content of the examination criteria and determine whether it is possible to construct a logical argument by combining the publicly available information 125 specified in the argument sections 189A and 189B.

[0158] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims rather than by the foregoing description, and all modifications within the meaning and scope equivalent to the claims are intended to be included. [Explanation of Symbols]

[0159] 10 Information processing system, 100 Information processing device, 101 Control device, 102 ROM, 103 RAM, 104 Communication interface, 105 Display interface, 106 Display, 107 Input interface, 108 Input device, 110 Bus, 120 Auxiliary storage device, 122 Analysis program, 123 Input information, 124 Patent database, 125 Public information, 125F Drawing, 126 Instructions, 127 Argument section, 128 Argument section, 129 Argument section, 130 Evaluation results, 131A Instructions, 131B Instructions, 131C Instructions, 131D Instructions, 156 Instructions, 157 Argument section, 166 Instructions, 167A Instructions, 167B Instructions, 167C Instructions, 167D Instructions, 168 Argument section, 176 Instructions, 186 Instructions, 187 Argument section, 188 Argument section, 189A Argument section, 189B Argument section, 200 User terminal, 201 Control unit, 202 ROM, 203 RAM, 204 Communication interface, 205 Display interface, 206 Display, 207 Input interface, 208 Input device, 210 Bus, 220 Auxiliary storage device, 222 Analysis program, 300 Server, 324 Large-scale language model, 326 Response information, 327 Evaluation results, 400A Settings screen, 400B Settings screen, 400C Settings screen, 400D Evaluation results screen, 410 Selection field, 412 Settings field, 420 Settings field, 422 Selection field, 424 Settings field, 425 Editing field, 430 Selection field, 432 Editing field, 434 Display field, 434A Display field, 434B Display field, 434D Display field, 436 Selection field, 438 Selection field, 440 Start button, 450 Display field, 452 Display field, 454 Display field, 456 Display field, IM Image, NW Network.

Claims

1. It is an analysis program, The aforementioned analysis program is programmed into a computer. Steps include obtaining input information that represents the technical concept, The steps include obtaining patent documents to be compared with the aforementioned technical idea, The steps include dividing the aforementioned technical concept into constituent elements, A step of generating an instruction statement by including the multiple constituent elements divided in the dividing step and the patent document in a pre-registered template which includes instructions that specify how to evaluate the relationship between constituent elements and predetermined information, An analysis program that inputs the instruction sentences generated in the above generation step into a large-scale language model, and then, based on the results obtained from the large-scale language model, outputs an evaluation result showing the relationship between each of the multiple constituent elements and the patent document.

2. The analysis program according to claim 1, wherein the evaluation results include the location of each of the plurality of constituent elements described in the patent document.

3. The analysis program according to claim 2, wherein the location of the description includes at least one of the paragraph number in the patent document, the figure number in the patent document, and the claim number in the patent document.

4. The analysis program according to claim 2 or 3, wherein the evaluation result includes the reason for extracting the described location.

5. The analysis program according to any one of claims 1 to 3, wherein the division step includes a step of dividing the technical idea into constituent elements by inputting instruction statements that specify how to divide the technical idea into constituent elements into the large-scale language model.

6. The analysis program according to any one of claims 1 to 3, wherein the division step includes a step of dividing the technical idea into constituent elements according to predetermined rules.

7. The analysis program according to any one of claims 1 to 3, wherein in the output step, the abstract of the patent document is output alongside the evaluation result.

8. The analysis program according to any one of claims 1 to 3, wherein the evaluation results include the degree of relevance of each of the plurality of constituent elements to the patent document.

9. The analysis program according to claim 8, wherein in the output step, a plurality of correlations and a plurality of constituent elements are output side by side.

10. The analysis program according to claim 8, wherein the evaluation result further includes a total score of multiple correlations.

11. The analysis program according to claim 10, wherein in the output step, the relationship between the plurality of patent documents and the plurality of constituent elements is evaluated, and the evaluation results for each of the plurality of patent documents are output in order of the total score.

12. The evaluation results mentioned above are: The degree of relevance of each of the divided constituent elements to the aforementioned patent document, Including the location of each of the multiple constituent elements described in the aforementioned patent document, The analysis program according to claim 1, wherein in the output step, a plurality of the described positions and a plurality of the correlation degrees are output side by side.

13. The evaluation results further include the reasons for extracting multiple locations, The analysis program according to claim 12, wherein in the output step, a plurality of the described locations, a plurality of the relevance degrees, and a plurality of the extraction reasons are output side by side.

14. The analysis program according to claim 12 or 13, wherein in the output step, the identifier of the patent document is output alongside the evaluation result.

15. The analysis program according to claim 14, wherein the identifier includes at least one of the application number of the patent document, the publication number of the patent document, and the registered publication number of the patent document.

16. The analysis program according to any one of claims 1 to 3, wherein in the output step, the relationship between the plurality of patent documents and the plurality of constituent elements is evaluated, and the evaluation result for each of the plurality of patent documents is output.

17. It is an analysis program, The aforementioned analysis program is programmed into a computer. Steps include obtaining input information that represents the technical concept, The steps include obtaining patent documents to be compared with the aforementioned technical idea, The steps include dividing the aforementioned technical concept into constituent elements, The process involves inputting instructions into a large-scale language model that specify comparing each of the divided constituent elements with the patent document, and then outputting an evaluation result showing the relationship between each of the divided constituent elements and the patent document based on the results obtained from the large-scale language model. The aforementioned input information includes an image, The analysis program includes a step of dividing an object into constituent elements by inputting instructions into the large-scale language model that specify how to interpret the object in the image according to its constituent elements.

18. An information processing device, Equipped with a control unit, The control unit, A process for obtaining input information that represents the technical concept, A process for obtaining patent documents to be compared with the aforementioned technical idea, The process of dividing the aforementioned technical concept into constituent elements, A process to generate instruction statements by including the multiple constituent elements divided in the division process and the patent documents in a pre-registered template that includes instructions for evaluating the relationship between constituent elements and specified information, An information processing device that inputs the instruction sentences generated in the above-mentioned generation process into a large-scale language model, and then performs a process to output an evaluation result showing the relationship between each of the multiple constituent elements and the patent document, based on the results obtained from the large-scale language model.

19. A computer-based analysis method, Steps include obtaining input information that represents the technical concept, The steps include obtaining patent documents to be compared with the aforementioned technical idea, The steps include dividing the aforementioned technical concept into constituent elements, A step of generating an instruction statement by including the multiple constituent elements divided in the dividing step and the patent document in a pre-registered template which includes instructions that specify how to evaluate the relationship between constituent elements and predetermined information, An analysis method comprising the steps of inputting the instruction sentences generated in the above generation step into a large-scale language model, and outputting an evaluation result showing the relationship between each of the plurality of constituent elements and the patent document based on the results obtained from the large-scale language model.

20. It is an analysis program, The aforementioned analysis program is programmed into a computer. Steps include obtaining input information that represents the technical concept, Steps include obtaining patent documents that include drawings, The steps include dividing the aforementioned technical concept into constituent elements, The steps include obtaining a description of the drawing by inputting instructions, which are defined to interpret the contents of the drawing, into a large-scale language model, An analysis program that performs the steps of inputting instructional statements, which specify that each of the divided plurality of constituent elements be compared with the explanatory statement, into the large-scale language model, and outputting an evaluation result showing the relationship between each of the plurality of constituent elements and the drawing, based on the results obtained from the large-scale language model.

21. An information processing device, Equipped with a control unit, The control unit, A process for obtaining input information that represents the technical concept, The process of obtaining patent documents including drawings, The process of dividing the aforementioned technical concept into constituent elements, A process to obtain a descriptive text for the drawing by inputting instructions that define how to interpret the contents of the drawing into a large-scale language model, An information processing device that inputs instructional statements, which specify that each of the divided plurality of constituent elements be compared with the explanatory statement, into the large-scale language model, and then performs a process of outputting an evaluation result showing the relationship between each of the plurality of constituent elements and the drawing based on the results obtained from the large-scale language model.

22. A computer-based analysis method, Steps include obtaining input information that represents the technical concept, Steps include obtaining patent documents that include drawings, The steps include dividing the aforementioned technical concept into constituent elements, The steps include obtaining a description of the drawing by inputting instructions, which are defined to interpret the contents of the drawing, into a large-scale language model, An analysis method comprising the steps of inputting instructional statements, which specify that each of the divided plurality of constituent elements be compared with the explanatory statement, into the large-scale language model, and outputting an evaluation result showing the relationship between each of the plurality of constituent elements and the drawing, based on the results obtained from the large-scale language model.

Images