Program, method, information processing device and system

Abstract

To address such a problem that it is not easy to generate a suitable prompt to be applied to a patent document.SOLUTION: A program causing a computer including a processor and a storage part to execute processing, the program causes the processor to execute: a task receiving step of receiving task information relating to a task to be executed on a patent document; a query receiving step of receiving query information to be applied to the patent document; a document acquisition step of acquiring a patent document relating to the patent; an extraction step of extracting a prescribed extraction part out of the patent document acquired in the document acquisition step, according to the task received in the task reception step; and a generation step of generating a prompt including the query information received in the query reception step and the extracted part extracted in the extraction step.SELECTED DRAWING: Figure 14

Description

Technical Field

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

Background Art

[0002] Techniques for supporting patent operations are known. Patent Document 1 discloses a technique related to a technique for supporting the understanding of claims, which specifies and presents the constituent elements that are key points in the claims so that the description thereof can be read with emphasis.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a problem that a suitable prompt for applying to a patent document cannot be easily generated. Therefore, the present disclosure has been made to solve the above problems, and an object thereof is to provide a technique for easily generating a suitable prompt for applying to a patent document.

Means for Solving the Problems

[0005] A program for causing a computer including a processor and a storage unit to execute, the program causing the processor to execute a task reception step of receiving task information regarding a task to be executed on a patent document, a query reception step of receiving query information to be applied to the patent document, a document acquisition step of acquiring a patent document related to the patent, an extraction step of extracting a predetermined extraction location according to the task received in the task reception step from among the patent documents acquired in the document acquisition step, and a generation step of generating a prompt including the query information received in the query reception step and the extraction location extracted in the extraction step.

Effect of the Invention

[0006] According to the present disclosure, a suitable prompt to be applied to a patent document can be easily generated.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Embodiments for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all the drawings for describing the embodiments, the same reference numerals are assigned to common components, and repeated descriptions are omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Also, not all of the components shown in the embodiments are essential components of the present disclosure. Further, each figure is a schematic diagram and is not necessarily drawn precisely.

[0009] <Configuration of System 1> The system 1 in the present disclosure is an information processing system that provides a service for assisting in understanding patent documents. The system 1 includes information processing apparatuses of a server 10, a user terminal 20, and an artificial intelligence system 40, which are connected via a network N. FIG. 1 is a block diagram showing the functional configuration of the system 1. FIG. 2 is a block diagram showing the functional configuration of the server 10. FIG. 3 is a block diagram showing the functional configuration of the user terminal 20.

[0010] Each information processing device is configured by a computer including an arithmetic unit and a storage unit. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10, the user terminal 20, and the artificial intelligence system 40, descriptions overlapping with the basic hardware configuration of the computer and the basic functional configuration of the computer described later are omitted.

[0011] <Configuration of Server 10> The server 10 is an information processing device that provides a reading support service for patent documents. The server 10 includes a storage unit 101 and a control unit 104.

[0012] <Configuration of the Storage Unit 101 of Server 10> The storage unit 101 of the server 10 includes an application program 1011, a user table 1012, a document table 1013, a term table 1014, a support table 1015, a task master 1016, and a list table 1017.

[0013] The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit. The application program 1011 includes applications such as a web browser application.

[0014] The user table 1012 is a table that stores and manages information of member users (hereinafter referred to as users) who use the service. By registering for the use of the service, the information of the user is stored in a new record in the user table 1012. Thereby, the user can use the service according to the present disclosure. The user table 1012 is a table having columns of user ID and user name with the user ID as the primary key. FIG. 4 is a diagram showing the data structure of the user table 1012.

[0015] The user ID is an item that stores user identification information for identifying a user. The user identification information is an item for which a unique value is set for each user. The user name is an item that stores the name of the user. The user name may be set to any string such as a nickname, rather than the actual name.

[0016] The document table 1013 is a table for storing and managing information (document information) related to patent documents. The document table 1013 is a table having columns for document ID, user ID, document name, and document content. Figure 5 is a diagram showing the data structure of the document table 1013.

[0017] The document ID is an item that stores document identification information for identifying a patent document. The user ID is an item that stores user identification information for identifying a user. The document name is an item that stores the name of the patent document. Any string can be set as the document name. For example, the document name stores the publication number, registration number, application number, or other sorting numbers of the patent document. The document content is an item that stores the content of the patent document. Specifically, the text information of the patent document is stored. For example, the document content includes some or all of "claims", "abstract", "detailed description of the invention", "embodiments", "modes for carrying out the invention", etc. included in the patent document (specification). Specifically, the text of gazettes such as published gazettes and patent gazettes is stored.

[0018] The term table 1014 is a table for storing and managing information (term information) related to terms. The term table 1014 is a table having columns for document ID and term text. Figure 6 is a diagram showing the data structure of the term table 1014.

[0019] The document ID is an item that stores document identification information for identifying a patent document. The term text is an item that stores the character string of a term. Specifically, the term text stores the character strings of technical terms and the like included in a patent document specified by document identification information.

[0020] The support table 1015 is a table for storing and managing prompts related to inquiry sentences for an artificial intelligence system and the response content (support information) from the artificial intelligence system. The support table 1015 is a table having columns for document ID, prompt, and response content. Figure 7 is a diagram showing the data structure of the support table 1015.

[0021] The document ID is an item that stores document identification information for identifying a patent document. The prompt is an item that stores a prompt related to an inquiry sentence for an artificial intelligence system. A prompt is mainly an inquiry sentence (text) input to the artificial intelligence system. Specifically, a user can input a prompt to the artificial intelligence system so that the artificial intelligence system outputs a desired output result. Note that the prompt does not necessarily have to be a character string, and it may be a prompt by an image, video, voice, etc. For example, gestures, voice instructions, etc. by the user can also be a prompt. The response content is an item that stores the response content from the artificial intelligence system to the prompt. Specifically, text information related to the response content from the artificial intelligence system is stored. In the present disclosure, an artificial intelligence system that gives a response in text is described as an example, but it is not limited thereto. In an artificial intelligence system that gives a response by an image, video, voice, etc., image data, video data, voice data, etc. may be stored as the response content.

[0022] The task master 1016 is a table for storing and managing information (task information) related to tasks executed on patent documents. The task master 1016 is a table having columns of task ID, task type, extraction items, and task data, with the task ID as the primary key. Figure 8 is a diagram showing the data structure of the task master 1016.

[0023] The task ID is an item for storing task identification information for identifying a task. The task identification information is an item for which a unique value is set for each task information. The task type is an item for storing task type information regarding the type of a task. Specifically, the task type stores a character string for specifying the content of a task according to the purpose of a process (task) executed on a patent document. In the present disclosure, information such as "classification assignment", "screening", and "relevance determination" is stored in the task type according to the content of the following tasks. · Classification assignment task: A task for assigning a classification according to the content of each of a plurality of patent documents. · Screening task: A task for determining whether each of a plurality of patent documents is related to a target document. Specifically, the task may be subdivided such as "prior art search", "prior art investigation", "invalidity document search", etc. · Relevance determination task: A task for determining whether each of a plurality of patent documents is related to a target product. For example, it is a task executed in patent operations such as "clearance search", "FTO search", "investigation of infringing products of other companies", etc. The extraction items are items for storing information (extraction item information) indicating extraction items of a patent document when executing a task. Specifically, the extraction items include character strings indicating extraction items of a patent document providing tasks such as "abstract", "specification", "claims", and "drawings". Further, the extraction items include character strings indicating extraction items of a patent document providing tasks such as "title of the invention", "detailed description of the invention", "technical field", "background art", "prior art documents", "problems to be solved by the invention", "means for solving the problems", "effects of the invention", "brief description of the drawings", "modes for carrying out the invention", "examples", "industrial applicability", "explanation of reference numerals", "problems", "solution means", etc. Specifically, the extraction items store the following extraction item information according to the task type. · Classification: Abstract, claims, claim 1, specification, etc. · Screening: Abstract, claims, claim 1, specification, etc. · Validity judgment: Claim 1, claims Task data is an item that stores information (string) related to the task. Specifically, the following strings are stored according to the task type. Note that query data described later is inserted into the <query> item, and in the <extracted document>, the extraction location (extracted content, partial sentence) specified based on the extraction item is inserted into the sentences included in the patent document to generate a prompt. · When the task type is "classification" 『 Define the technical classification as follows. Classify the invention described in the following "target patent" into one of Classification A, B, or C. Calculate the relevance between the target patent and the classification between 0 and 100. Output the reason for such a judgment. # Technical classification: <query> (Classification A "···", Classification B "···", Classification C "···") # Target patent: <extracted document> (the parts (contents) of the abstract and claims in the patent document) 』 · When the task type is "screening" 『 Please examine whether the invention described in the following "target invention" is described in the invention described in the following "target patent". Calculate the relevance between the target invention and the target patent between 0 and 100. Output the reason for such a judgment. # Target invention: <query> (··· means, ··· means, an apparatus comprising ···) # Target patent: <extracted document> (the parts (contents) of the abstract, claims, and specification in the patent document) 』 · When the task type is "validity judgment" 『 Please examine whether the products, services, etc. described in the following "Target Products" are included in the scope of rights of the inventions described in the following "Target Patents". Please calculate the degree of relevance between the target products and the target patents on a scale of 0 to 100. Please output the reasons for such a judgment. # Target Product: <Query> (Device comprising... means, ... means, ...) # Target Patent: <Extracted Document> (Location (content) of Claim 1 in the patent document) 』

[0024] List table 1017 is a table for storing and managing a list (list information) including a plurality of patent documents. List table 1017 is a table having columns of list ID, document list, task ID, and query data, with the list ID as the primary key. Figure 9 is a diagram showing the data structure of list table 1017.

[0025] The list ID is an item for storing list identification information for identifying a list. The list identification information is an item for which a unique value is set for each list information. The document list is an item for storing a list consisting of document IDs of a plurality of patent documents. The document list may be configured to store not only the document ID but also the document name, document content, etc. in association with the document ID. The task ID is an item for storing task identification information indicating a task to be applied to a list including a plurality of patent documents specified by the list identification information. The query data is an item for storing a query to be applied to a list including a plurality of patent documents specified by the list identification information. Specifically, the query data stores the following types of queries according to the type of task. · Classification assignment task: What is exemplified by a sentence (string) defining the classification target and a plurality of exemplary sentences (strings) expressing the classification target is stored. Example) Classification A is "···", Classification B is "···", Classification C is "···" · Screening: The text (string) describing the target invention is memorized. Example) ··· means, ··· means, and a device including ··· · Non-determination: The text (string) representing the target product is memorized. Example) ··· means, ··· means, and a device including ···

[0026] <Configuration of the control unit 104 of the server 10> The control unit 104 of the server 10 includes a user registration control unit 1041, a document display unit 1042, and an inquiry unit 1043. The control unit 104 realizes each functional unit by executing the application program 1011 stored in the storage unit 101.

[0027] The user registration control unit 1041 performs a process of storing information of a user who wishes to use the service according to the present disclosure in the user table 1012. The information stored in the user table 1012 is that the user opens a web page or the like operated by the service provider from an arbitrary information processing terminal, inputs information into a predetermined input form, and transmits it to the server 10. The user registration control unit 1041 stores the received information in a new record of the user table 1012, and the user registration is completed. As a result, the user stored in the user table 1012 can use the service. Prior to the registration of the user information by the user registration control unit 1041 in the user table 1012, the service provider may perform a predetermined review to restrict the use of the service by the user. The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or the user registration control unit 1041 may automatically set any character string or number.

[0028] The document display unit 1042 executes a document display process. Details will be described later.

[0029] The inquiry unit 1043 executes an inquiry process. Details will be described later.

[0030] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user who uses the service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or a tablet, or a stationary PC (Personal Computer) or a laptop PC. It may also be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch-type terminal. The user terminal 20 includes a storage unit 201, a control unit 204, an input device 206, and an output device 208.

[0031] <Configuration of Storage Unit 201 of User Terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012.

[0032] The user ID 2011 is the user's account ID. The user transmits the user ID 2011 from the user terminal 20 to the server 10. The server 10 identifies the user based on the user ID 2011 and provides the service according to the present disclosure to the user. Note that the user ID 2011 includes information such as a session ID temporarily assigned by the server 10 when identifying the user using the user terminal 20.

[0033] The application program 2012 may be pre-stored in the storage unit 201, or may be configured to be downloaded from a web server or the like operated by a service provider via a communication IF. The application program 2012 includes applications such as a web browser application. The application program 2012 includes an interpreter-type programming language such as JavaScript (registered trademark) that is executed on a web browser application stored in the user terminal 20.

[0034] <Configuration of Control Unit 204 of User Terminal 20> The control unit 204 of the user terminal 20 includes an input control unit 2041 and an output control unit 2042. The control unit 204 realizes each functional unit by executing the application program 2012 stored in the storage unit 201.

[0035] <Configuration of the input device 206 of the user terminal 20> The input device 206 of the user terminal 20 includes a camera 2061, a microphone 2062, a position information sensor 2063, a motion sensor 2064, and a touch device 2065.

[0036] <Configuration of the output device 208 of the user terminal 20> The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082.

[0037] <Configuration of the artificial intelligence system 40> The artificial intelligence system 40 is an information processing device that outputs the answer content for a prompt. For example, the artificial intelligence system 40 includes ChatGPT, OpenAI GPT, PerplexityAsk, BingAI, etc. These artificial intelligence systems have the function of interactive response (chat), and the user can give an arbitrary inquiry or command instruction to the artificial intelligence system in text to obtain an answer to the inquiry or an answer to the command instruction. In the present disclosure, the user can obtain an article for assisting in reading a patent document as the answer content by sending the prompt created in the inquiry process to the artificial intelligence system 40. Also, in the present disclosure, the artificial intelligence system is not limited to text-based interactive responses. For example, it may be an image generation AI system such as Midjourney or Stable Diffusion. For example, the user can obtain an image or video for assisting in reading a patent document as the answer content by sending the prompt created in the inquiry process to such an image generation AI system. In addition, the present disclosure is also applicable to an artificial intelligence system that outputs response content by means of video, audio, etc. The artificial intelligence system 40 includes a large language model system (LLM system).

[0038] <Operation of System 1> Hereinafter, each process of System 1 will be described. FIG. 10 is a flowchart showing the operation of the document display process. FIG. 11 is a flowchart showing the operation of the inquiry process. FIG. 12 is an example screen showing the operations of the document display process and the inquiry process. FIG. 13 is a flowchart showing the operation of the list process. FIG. 14 is an example screen showing the operation of the list process.

[0039] <Document Display Process> The document display process is a process of receiving a patent document and terms, and highlighting the patent document based on the terms (highlighting by a display mode with different colors, background colors, boldface, underlining, etc.).

[0040] <Overview of Document Display Process> The document display process is a series of processes that receive a patent document, extract important terms based on the patent document, receive input of terms, execute a highlighting process on the patent document based on the terms, and display the document on which the highlighting process has been performed.

[0041] <Details of Document Display Process> Hereinafter, the details of the document display process will be described.

[0042] In step S101, the document display unit 1042 of the server 10 executes a document reception step of receiving a document related to a patent. Specifically, the user operates the input device 206 of the user terminal 20 to input the URL of a page (document display processing page) for executing document display processing in a web browser or the like, and opens the document display processing page. The control unit 204 of the user terminal 20 transmits a request for opening the document display processing page to the server 10. The control unit 104 of the server 10 generates the document display processing page based on the received request and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 displays the received document display processing page on the display 2081 of the user terminal 20.

[0043] FIG. 12 is an example screen of a document display screen in document display processing. A document display page D1 is displayed on the display 2081 of the user terminal 20. The document display page D1 includes a document display screen D10. The document display screen D10 includes a document input button D100, a document display area D101, a term input area D102, and an inquiry response area D105. The term input area D102 includes term input fields D1021, D1022, D1023 ···, definition explanation buttons D1031, D1032, D1033 ···, and a summary generation button D1041. The inquiry response area D105 includes a prompt input field D1051, a prompt transmission button D1052, prompts D1061, D1062 ···, response contents D1071, D1072 ···, and auxiliary buttons D1081, D1082, D1083 ···. The response content D1071 includes paragraph numbers D1091, D1092 ···.

[0044] The user presses the document input button D100 displayed on the document display screen D10 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 generates a document input dialog screen and displays it on the display 2081 of the user terminal 20. The user inputs a document name and document content on the document input dialog screen. Specifically, the user inputs the publication number of the published gazette or patent gazette into the input field for the document name by operating the input device 206 of the user terminal 20. The user inputs the text information of the specification of the published gazette or patent gazette into the input field for the document content by operating the input device 206 of the user terminal 20. Note that the document content may be configured to be automatically acquired and input by the control unit 204 of the user terminal 20 referring to a gazette database (not shown) or the like based on the publication number input into the document name. The user transmits the information input into the input fields for the document name and document content to the server 10 by pressing the "Send button" displayed on the document input dialog screen. The information transmitted to the server 10 includes the user ID 2011. The document display unit 1042 of the server 10 receives and accepts the user ID 2011, document name, and document content from the user terminal 20. The document display unit 1042 of the server 10 stores the received user ID 2011, document name, and document content in the user ID, document name, and document content items of a new record in the document table 1013, respectively.

[0045] In step S101, the document display unit 1042 of the server 10 executes a document presentation step of presenting the document received in the document reception step to the user. The control unit 204 of the user terminal 20 displays the received document content in the document display area D101 and presents it to the user. The user can confirm the content of the patent document through the document display area D101.

[0046] In step S102, the document display unit 1042 of the server 10 executes a keyword identification step of identifying one or more keywords obtained by analyzing the content of the document received in the document reception step. Specifically, the document display unit 1042 of the server 10 identifies one or more important words by analyzing the document content received in step S101. The document display unit 1042 of the server 10 applies morphological analysis to the sentences included in the document content and splits them into words. The document display unit 1042 of the server 10 calculates the importance (score) of each word by methods such as the TF-IDF method, the text ranking method, and the n-gram method. The TF-IDF method is a method for calculating the importance of each word by combining the word frequency and the inverse document frequency. The n-gram method is a method for extracting consecutive n words and calculating the score of each word based on the frequency of occurrence. The text ranking method is a method for calculating the importance of each word based on the page rank algorithm. In addition, there are methods such as LexRank and LSA (Latent Semantic Analysis). The document display unit 1042 of the server 10 extracts and identifies a predetermined number of words in order of importance or words with an importance equal to or higher than a predetermined value as important words. The document display unit 1042 of the server 10 transmits the identified important words to the user terminal 20. The control unit 204 of the user terminal 20 receives and accepts the important words. Note that the control unit 204 of the user terminal 20 may execute the extraction process of important words.

[0047] In step S103, the control unit 204 of the user terminal 20 executes a term reception step of receiving one or more terms included in the document received in the document reception step. Specifically, the user operates the input device 206 of the user terminal 20 to copy and paste the terms included in the document content displayed in the document display area D101 into the term input fields D1021, D1022, D1023, or perform an input operation using the keyboard to input them. The user can input any character string into the term input fields D1021, D1022, D1023.

[0048] In step S103, the term reception step executes a step of receiving one or more important terms specified in the important term identification step as one or more terms. Specifically, the control unit 204 of the user terminal 20 may present the one or more important terms received from the server 10 to the user with the terms entered in the term input fields D1021, D1022, and D1023. The control unit 204 of the user terminal 20 may receive the one or more important terms received from the server 10 as one or more terms.

[0049] In step S103, the control unit 204 of the user terminal 20 executes an important term presentation step of presenting the one or more important terms specified in the important term identification step to the user. Specifically, the control unit 204 of the user terminal 20 may present the one or more important terms received from the server 10 to the user in a selectable manner on the display 2081 of the user terminal 20. For example, the user may be presented with the one or more important terms in a manner (e.g., a manner associated with a checkbox or a radio box) that allows the user to select the one or more important terms by operating the input device 206 of the user terminal 20.

[0050] In step S103, the term reception step executes a step of receiving at least some of the important terms corresponding to the input operation as one or more terms in response to an input operation on the one or more important terms presented in the important term presentation step from the user. Specifically, the user selects a predetermined one or more important terms from among the one or more important terms presented in a selectable manner on the display 2081 of the user terminal 20 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 enters the selected predetermined one or more important terms in the term input fields D1021, D1022, and D1023. Thereby, the control unit 204 of the user terminal 20 can receive the predetermined one or more important terms selected by the user as one or more terms.

[0051] Note that the control unit 204 of the user terminal 20 presents one or more important terms to the user by presenting a dialog for presenting one or more important terms over the document display screen D10. The user may input the selected one or more important terms into the term input fields D1021, D1022, and D1023 by operating the input device 206 of the user terminal 20 to perform a selection operation on the one or more important terms.

[0052] In step S104, the control unit 204 of the user terminal 20 performs a highlighting process on one or more terms included in the document content displayed in the document display area D101. Specifically, the control unit 204 of the user terminal 20 highlights (highlights) the one or more terms included in the document content with respect to the one or more terms received in step S103 in a display mode with different colors, background colors, bold, underlines, or other decorations. For example, the control unit 204 of the user terminal 20 can highlight one or more terms included in the document content by replacing each of the one or more terms in the document content with the highlighted one or more terms. Note that the document display unit 1042 of the server 10 may perform a highlighting process.

[0053] In step S105, the document presentation step executes a step of presenting to the user one or more terms included in the document in a distinguishable manner based on the one or more terms received in the term reception step. Specifically, the control unit 204 of the user terminal 20 displays the highlighted document content in the document display area D101 and presents it to the user.

[0054] <Inquiry process> The inquiry process is a process of creating a prompt (inquiry sentence, question sentence, question query) regarding the inquiry sentence based on the terms received in the document display process and inquiring an artificial intelligence system for information useful for reading the patent document based on the prompt.

[0055] <Overview of Inquiry Processing> The inquiry processing is a series of processes that accepts the selection of terms, creates a prompt based on the selected terms, accepts the editing of the prompt from the user, sends the prompt to the artificial intelligence system, receives the answer content from the artificial intelligence system, and displays the received answer content.

[0056] <Details of Inquiry Processing> The details of the inquiry processing will be described below.

[0057] In step S301, the user selects one or more of the term input fields D1021, D1022, D1023 included in the term input area D102 by operating the input device 206 of the user terminal 20. Specifically, the user presses any one of the definition explanation buttons D1031, D1032, D1033 by operating the input device 206 of the user terminal 20. As a result, any one of the term input fields D1021, D1022, D1023 corresponding to any one of the pressed definition explanation buttons D1031, D1032, D1033 is selected. The user presses the summary generation button D1041 by operating the input device 206 of the user terminal 20. As a result, all of the term input fields D1021, D1022, D1023 are selected. Note that it is also possible to configure such that a part of the term input fields D1021, D1022, D1023 is selected. For example, by selecting a checkbox or the like associated with each of the term input fields D1021, D1022, D1023, it is also possible to configure such that a predetermined one or more of the term input fields among the plurality of term input fields D1021, D1022, D1023 are selected. In addition, the user can select some or all of the term input fields D1021, D1022, D1023 by operating the input device 206 of the user terminal 20 in the term input area D102.

[0058] In step S302, the control unit 204 of the user terminal 20 executes an inquiry creation step of creating a prompt regarding the inquiry sentence based on the terms received in the term reception step. Specifically, the control unit 204 of the user terminal 20 creates a prompt regarding the inquiry sentence based on the terms selected in step S301.

[0059] In step S302, the inquiry creation step executes a step of creating a prompt including a sentence for inquiring about the definition or meaning of one or more terms. Specifically, when the user operates the input device 206 of the user terminal 20 to press the definition explanation button D1031, the control unit 204 of the user terminal 20 creates a prompt (character string) of 'Please explain the meaning and content of the term "term 1" in this sentence.' based on the term 'term 1' input in the term input field D1021. In step S301, when only one term is selected, the control unit 204 of the user terminal 20 may automatically create a prompt including a sentence for inquiring about the definition or meaning of the term.

[0060] In step S302, the inquiry creation step executes a step of creating a prompt including a sentence for inquiring about the relationship between a plurality of terms. Specifically, when the user operates the input device 206 of the user terminal 20 to press the summary generation button D1041, the control unit 204 of the user terminal 20 creates a prompt (character string) of 'Please explain the relationship between the terms "term 1", "term 2", and "term 3" in this sentence.' based on the terms 'term 1', 'term 2', and 'term 3' input in the term input fields D1021, D1022, and D1023. In step S301, when a plurality of terms are selected, the control unit 204 of the user terminal 20 may automatically create a prompt including a sentence for inquiring about the relationship between the plurality of terms.

[0061] In step S302, the inquiry generation step executes a step of creating a prompt including information related to the technical field specified based on the content of the document received in the document reception step. Specifically, the control unit 204 of the user terminal 20 identifies "Technical Field 1", which is the technical field mentioned in the patent document, by analyzing the text content. The technical field may also be specified based on a character string such as a patent classification included in the patent document. The control unit 204 of the user terminal 20 creates a prompt (character string) of "The following text is a text in the technical field of 'Technical Field 1'." and includes it in the already created prompt. Thereby, for example, the control unit 204 of the user terminal 20 creates a prompt of "The following text is a text in the technical field of 'Technical Field 1'. Please explain the meaning and content of the term 'Term 1' in this text."

[0062] In step S302, the inquiry generation step executes a step of creating a prompt in response to an input operation received from the user. Specifically, the control unit 204 of the user terminal 20 may be configured to create a prompt triggered by an input operation of the input device 206 of the user terminal 20, such as pressing the definition explanation buttons D1031, D1032, D1033 or the summary generation button D1041. In addition, the control unit 204 of the user terminal 20 may automatically create a prompt according to the terms and important words input in the term input fields D1021, D1022, D1023 without receiving an input operation by the user.

[0063] In step S302, the control unit 204 of the user terminal 20 completes the prompt by adding the full text of the document content to the end of the prompt. For example, the control unit 204 of the user terminal 20 creates a prompt of "The following text is a text in the technical field of 'Technical Field 1'. Please explain the meaning and content of the term 'Term 1' in this text. [Document content]"

[0064] In step S302, the control unit 204 of the user terminal 20 may complete the prompt by adding a part of the document content instead of the full text of the document content at the end of the prompt. For example, the control unit 204 of the user terminal 20 creates a prompt such as 'The following article is an article in the technical field of "Technical Field 1". Please explain the meaning and content of the term "Term 1" in this article. [Partial Document 1] [Partial Document 2] [Partial Document 3]'.

[0065] The question creation step executes a step of identifying a partial document that is a part of the document received in the document reception step based on the inquiry sentence or one or more terms, and creating a prompt including the partial document. The question creation step executes a step of identifying a line or paragraph including a word included in the inquiry sentence or one or more terms from the document received in the document reception step, and creating a prompt including a partial document consisting of only the line or paragraph. Specifically, the control unit 204 of the user terminal 20 divides the document content into a plurality of partial documents for each line or paragraph. The control unit 204 of the user terminal 20 calculates the relevance between the input values in the term input fields D1021, D1022, D1023 and the plurality of partial documents. Specifically, the cosine similarity, Euclidean distance, Jaccard coefficient, etc. between each of the plurality of partial documents and the input values in the term input fields D1021, D1022, D1023 can be used as the relevance. The control unit 204 of the user terminal 20 extracts a predetermined number of partial documents in the order of relevance, or one or more partial documents with a relevance equal to or higher than a predetermined value, and adds them to the end of the prompt. Note that the control unit 204 of the user terminal 20 may calculate the relevance between the already created prompt and the plurality of partial documents. In this case, one or more partial documents with a high relevance to the already created prompt are added to the end of the prompt. Note that the partial document does not have to be a line or a paragraph, and a document unit arbitrarily divided from the patent document may be used as the partial document.

[0066] Note that the inquiry unit 1043 of the server 10 may execute the prompt creation process.

[0067] The control unit 204 of the user terminal 20 inputs the created prompt into the prompt input field D1051.

[0068] In step S303, the user can edit the content of the prompt input in the prompt input field D1051 by operating the input device 206 of the user terminal 20. Specifically, the user can modify and edit the prompt input in the prompt input field D1051 by operating the input device 206 of the user terminal 20. The user can press any one of the auxiliary buttons D1081, D1082, and D1083 by operating the input device 206 of the user terminal 20, so as to add any one of the auxiliary strings "Please explain briefly.", "Please explain in a list.", and "Please explain within 300 characters." to the prompt input in the prompt input field D1051. Thereby, it is possible to control so that the content of the answer from the artificial intelligence system 40 becomes as expected.

[0069] In step S304, the inquiry unit 1043 of the server 10 executes an inquiry transmission step of transmitting the prompt created in the inquiry creation step to an artificial intelligence system operated by an external operator for inquiry. Specifically, the user presses the prompt transmission button D1052 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits the character string (prompt) input in the prompt input field D1051 to the server 10. The inquiry unit 1043 of the server 10 transmits the character string (prompt) received from the user terminal 20 to the API (Application Programming Interface) endpoint of the artificial intelligence service provided by the artificial intelligence system 40. Note that the control unit 204 of the user terminal 20 may directly send the character string (prompt) entered in the prompt input field D1051 to the API (Application Programming Interface) endpoint of the artificial intelligence service.

[0070] In step S305, the inquiry unit 1043 of the server 10 receives a response to the sent prompt. The response includes a character string regarding the answer content for the prompt. The inquiry unit 1043 of the server 10 sends the received response to the user terminal 20. Note that the control unit 204 of the user terminal 20 may directly receive a response to the sent prompt from the artificial intelligence system 40.

[0071] In step S306, the inquiry unit 1043 of the server 10 executes an answer presentation step of presenting the answer content for the prompt sent in the inquiry sending step to the user. The answer presentation step executes a step of presenting the answer content to the user together with the document presented in the document presentation step. Specifically, when the control unit 204 of the user terminal 20 receives a response, it displays each of the prompt and the answer content included in the response to the prompt in the prompt D1061 and the answer content D1071. Each of a plurality of prompts and a plurality of answer contents for the plurality of prompts is displayed in the prompts D1061, D1062 ··· and the answer contents D1071, D1072 and presented to the user. The inquiry answer area D105 is displayed together with the document display area D101. Thereby, the user can check the highlighted patent document and the answer content from the artificial intelligence system together, and can efficiently read and understand the patent document.

[0072] In step S306, the answer presentation step executes a step of presenting one or more terms included in the answer content to the user in an identifiable manner based on the one or more terms received in the term reception step. Specifically, the control unit 204 of the user terminal 20 may also perform a highlighting process on the character strings displayed in the prompts D1061 and D1062 and the character strings displayed in the answer contents D1071 and D1072. For example, the control unit 204 of the user terminal 20 can highlight one or more terms included in the character string by replacing each of the one or more terms in the character string of the prompt or the answer content with one or more highlighted terms. Thereby, it is possible to highlight the terms included in the answer content from the artificial intelligence system. The user can view the highlighted patent document and the highlighted answer content together, and can efficiently read and understand the patent document.

[0073] The answer presentation step includes a partial identification step of identifying a partial document that is a part of the document received in the document reception step and is related to the prompt or the answer content, and a step of presenting information indicating the identified partial document together with the answer content. The answer presentation step includes a partial identification step of identifying a line or a paragraph of the document received in the document reception step and related to the prompt or the answer content, and a step of presenting the identified line or paragraph together with the answer content. Specifically, the control unit 204 of the user terminal 20 divides the document content into a plurality of partial documents for each line or paragraph. The control unit 204 of the user terminal 20 calculates the degree of relevance between the input values in the term input fields D1021, D1022, and D1023 and the plurality of partial documents. Specifically, the cosine similarity, Euclidean distance, Jaccard coefficient, etc. between each of the plurality of partial documents and the input values in the term input fields D1021, D1022, and D1023 can be used as the degree of relevance. The control unit 204 of the user terminal 20 displays the line numbers or paragraph numbers of a predetermined number of partial documents in the order of the degree of relevance, or one or more partial documents with a degree of relevance equal to or higher than a predetermined value, in the paragraph numbers D1091 and D1092 of the query answer area D105. Note that the partial document does not necessarily have to be a line or a paragraph, and a document unit obtained by dividing the patent document into any arbitrary document unit may be used as the partial document.

[0074] Note that the document display unit 1042 of the server 10 may execute the answer content presentation process.

[0075] <List processing> The list processing receives a list including a plurality of patent documents from the user and a query sentence (query) to be applied to the list, generates a prompt by applying the query to the plurality of patent documents included in the list, and is a process of querying the artificial intelligence system based on the prompt.

[0076] <Overview of list processing> The list processing receives an input of a query from the user, receives a list including a plurality of patent documents, identifies the patent documents included in the list, generates a prompt based on the query and the patent documents, transmits the generated prompt to the artificial intelligence system, receives the answer content from the artificial intelligence system, and is a series of processes of presenting the received answer content in association with the patent documents.

[0077] <Details of list processing> The details of the list processing will be described below.

[0078] In step S501, the list processing unit 1044 of the server 10 presents a list processing screen for executing list processing to the user. Specifically, the user operates the input device 206 of the user terminal 20, executes a browser application or the like, and opens the list page D3 by inputting the URL or the like of a web page (list page) for executing list processing. The control unit 204 of the user terminal 20 transmits a request including the user ID 2011 for opening the list page to the server 10.

[0079] When the server 10 receives the request, it generates a list page and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the list page on the display 2081 of the user terminal 20. FIG. 14 is an example screen of a list screen in list processing. On the display 2081 of the user terminal 20, a list page D3 is displayed. The list page D3 includes a task selection bar D301, an extraction item selection bar D311, a query input bar D302, a document input bar D303, a prompt display bar D304, a send button D305, and a response result D306.

[0080] In step S501, the control unit 204 of the user terminal 20 executes a task presentation step of presenting a plurality of task information to the user in a selectable manner. Specifically, the list processing unit 1044 of the server 10 refers to the task master 1016 to obtain items of task ID and task type, and transmits them to the user terminal 20. The control unit 204 of the user terminal 20 displays the received plurality of task types in the task selection bar D301 in a selectable manner. For example, the control unit 204 of the user terminal 20 presents each of the plurality of task types displayed in the task selection bar D301 to the user in association with a radio button for selecting the task type.

[0081] In step S501, the list processing unit 1044 of the server 10 executes a task reception step of receiving task information regarding a task to be executed on a patent document. The task reception step executes a step of receiving an input operation of predetermined task information from among the plurality of task information presented in the task presentation step from the user. Specifically, the user operates the input device 206 of the user terminal 20 to select a predetermined task type to be executed on the patent document from among the plurality of task types displayed in the task selection bar D301.

[0082] The task reception step executes a step of receiving task information indicating at least any one of a classification assignment task of assigning a classification to a patent document, a screening task of determining the relevance between a patent document and a target document, and a non-determination task of determining the relevance between a patent document and a target product. Specifically, the user can select a predetermined task type from task types such as the classification assignment task, the screening task, and the non-judgment task. Note that a configuration allowing selection of multiple task types may also be adopted.

[0083] The control unit 204 of the user terminal 20 transmits a task ID corresponding to the task information selected in the task selection field D301 to the server 10. The list processing unit 1044 of the server 10 receives and accepts the task ID.

[0084] In the present disclosure, a configuration in which a plurality of task information is presented so as to be selectable and is selected by the user has been disclosed as an example, but the present disclosure is not limited thereto. For example, the task information may be of one type (any one of the classification assignment task, the screening task, and the non-judgment task), and the task information may be defined in advance as predetermined task information. In this case, the process according to step S501 may be omitted. Also in this case, the list processing unit 1044 of the server 10 can be interpreted as having received the input of the predetermined task information. Further, the task information may not be configured to be received by selection, but may be configured to be specified based on the content of the query received in the query reception step described later. Further, instead of the task selection field D301, a task input field may be provided where the user can input task information, task types, etc. The user inputs information indicating task information such as the classification assignment task, the screening task, and the non-judgment task in the task input field, and a configuration in which the control unit 204 of the user terminal 20 or the list processing unit 1044 of the server 10 receives the task type may be adopted.

[0085] In step S502, the list processing unit 1044 of the server 10 executes a query reception step of receiving query information applied to the patent document. Specifically, the user operates the input device 206 of the user terminal 20 to input a character string related to the query to be applied to the patent document in the query input field D302. For example, the user operates the input device 206 of the user terminal 20 to input the following queries in the query input field D302 according to the task type selected in step S501.

[0086] 〔Query in the case of the classification assignment task〕 Classification A is a classification related to information processing equipment. Classification B is a classification related to agricultural implements. Classification C is a classification related to food products.

[0087] 〔Query in the case of the screening task〕 Query example 1) ··· means, ··· means, and a device comprising ··· Query example 2) ··· steps, ··· steps, and a method comprising ··· Query example 3) ··· steps, ··· steps, and a program that executes ···

[0088] 〔Query in the case of the non-determination task〕 Query example 1) ··· means, ··· means, and a device comprising ··· Query example 2) ··· steps, ··· steps, and a method comprising ··· Query example 3) ··· steps, ··· steps, and a program that executes ···

[0089] The control unit 204 of the user terminal 20 transmits the character string input in the query input field D302 to the server 10. The list processing unit 1044 of the server 10 receives the character string and accepts it as query data.

[0090] In step S503, the list processing unit 1044 of the server 10 executes a document acquisition step of acquiring patent documents related to patents. Specifically, the user operates the input device 206 of the user terminal 20 to input the document ID of the patent document into the document input field D303. Note that the patent document does not necessarily need to be specified by the document ID in the document table 1013. The user may input the patent number such as the published patent gazette, the summary of each patent document, the claims, and the content of the patent document such as the patent specification into the document input field D303. The user may also be configured to directly select, as the upload target, the information of the patent document included in Word, Excel, CSV files, etc., stored in the storage unit 201 of the user terminal 20. Any means may be used as long as the user can transmit a predetermined patent document to the server 10 by any means.

[0091] The document acquisition step executes a step of acquiring patent documents related to a plurality of patents. Note that the user may also be configured to transmit a plurality of patent documents to the server 10 by operating the input device 206 of the user terminal 20. The user may operate the input device 206 of the user terminal 20 to input the document IDs of a plurality of patent documents into the document input field D303. Further, the user may transmit an Excel, CSV file, etc. containing the information of a plurality of patent documents to the server 10.

[0092] The control unit 204 of the user terminal 20 transmits one or more patent documents input or selected by the user to the server 10. The list processing unit 1044 of the server 10 acquires and accepts one or more patent documents by receiving them.

[0093] The list processing unit 1044 of the server 10 stores the task ID, query data, and one or more patent documents received from the user terminal 20 in the task ID, query data, and document list items of a new record in the list table 1017.

[0094] In the present disclosure, as an example, the processing when one patent document is input will be described from step S504 to step S507 below. When a plurality of patent documents are input, the processing from step S504 to step S507 may be executed for each of the respective patent documents included in the plurality of patent documents.

[0095] In step S504, the list processing unit 1044 of the server 10 executes an extraction step of extracting a predetermined extraction location from among the patent documents acquired in the document acquisition step according to the task received in the task reception step. Specifically, the list processing unit 1044 of the server 10 searches the document ID item of the document table 1013 based on the received document ID and acquires the document content item. Note that when the user inputs the document content in the document input field D303 or uploads a file or the like including the document content, this processing may be omitted.

[0096] Alternatively, based on the received document ID and document name, a configuration may be adopted in which a patent database (not shown) or the like is referred to and a patent document including an abstract, claims, specification, etc. is acquired. In this case, based on the acquired extraction items, a patent document may be acquired from the patent database or the like by excluding predetermined extraction items. For example, in the case of the non-judgment task, a patent document may be acquired from the patent database or the like by excluding extraction items such as the abstract and the specification. In this case as well, it corresponds to extracting a predetermined extraction location from the text content.

[0097] The list processing unit 1044 of the server 10 searches the task ID item of the task master 1016 based on the received task ID and acquires the extraction items and task data. The list processing unit 1044 of the server 10 extracts a predetermined extraction location (extraction content, partial text) from the document content based on the acquired extraction items.

[0098] Note that in the extraction step, according to the token number limit such as the number of characters that the artificial intelligence system 40 described later can accept as input, a process of further shortening the character string for the extraction location may be performed. Specifically, the list processing unit 1044 of the server 10 divides the character string included in the extraction location into sentences such as sentences and clauses, and extracts sentences, clauses, etc. with high importance calculated based on methods such as TF-IDF, LexRank, and LSA, and excludes sentences, clauses, etc. with low importance, so as to shorten the character string so that it falls within the number of characters that the artificial intelligence system 40 can accept as input. Also, it is also possible to extract a predetermined length that the artificial intelligence system 40 can accept as input from the beginning of the extraction location as the extraction location, and exclude the character string exceeding the predetermined length as the extraction location. In addition, arbitrary post-processing may be applied to a predetermined extraction location. In this case, the character string after applying the arbitrary post-processing can also be treated as a kind of predetermined extraction location.

[0099] For example, in the extraction step, according to the task information received in the task reception step, when the task information is a classification assignment task, at least one of the abstract, claims, claim 1, and description in the patent document; when the task information is a screening task, at least one of the abstract, claims, claim 1, and description in the patent document; when the task information is the non-determination task, at least one of claim 1 and the claims in the patent document, the step of extracting a predetermined extraction location related thereto is executed. Thereby, the locations necessary for executing the task selected by the user are extracted from the document content of the patent document. In the present disclosure, although the process of extracting a predetermined extraction location from the patent document without depending on the operation by the user is disclosed as an example, it is not limited thereto. For example, according to the task information received in the task reception step, the selectability regarding a predetermined extraction item may be presented by the extraction item selection column D311, and according to the extraction item selected by the user, a process of extracting a predetermined extraction location from the patent document may be performed. For example, when the task information is a classification task, an extraction item selection field D311 that allows the user to select at least one of the abstract, claims, claim 1, and the specification may be presented to the user, and according to the extraction items selected by the user, a process of extracting predetermined extraction locations from the patent document may be performed. Thereby, according to the selection by the user, in the classification task, at least one extraction location among the abstract, claims, claim 1, and the specification can be excluded from the predetermined extraction locations. This disclosure only requires that different extraction locations can be extracted from the same patent document according to the content (task information) of the task executed by the user. For example, for a screening task and a non-judgment task applied to one patent document, it is sufficient that a process of extracting different extraction locations (for example, the specification for the screening task and claim 1 for the non-judgment task) can be executed for each of the screening task and the non-judgment task.

[0100] The extraction step executes an extraction step of extracting a plurality of predetermined extraction locations for each of the plurality of patent documents acquired in the document acquisition step according to the task received in the task reception step. Specifically, when a plurality of patent documents are input, the extraction step is executed for each of the patent documents included in the plurality of patent documents. Also, the extracted extraction locations are stored in association with the document ID.

[0101] In step S505, the list processing unit 1044 of the server 10 executes a generation step of generating a prompt including the query information received in the query reception step and the extraction locations extracted in the extraction step. The generation step executes a step of generating a prompt according to the task information received in the task reception step. The generation step executes a step of generating a prompt including instructions for outputting index values related to the patent document obtained in the document acquisition step and the basis of the index values. The generation step executes a step of generating a prompt including instructions for outputting an index value indicating the execution result of a task according to the task information received in the task reception step.

[0102] Specifically, the list processing unit 1044 of the server 10 generates a prompt by applying the query data obtained in step S502 and the extraction location extracted in step S504 to the task data obtained in step S504. The list processing unit 1044 of the server 10 can generate the following prompt by replacing "<query>" with the query data and "<extracted document>" with the extraction location in the character string of the task data.

[0103] 〔Prompt for classification task〕 Define the technical classification as follows. Classify the invention described in the following "target patent" into any of classifications A, B, and C. Calculate the relevance between the target patent and the classification between 0 and 100. Output the reason for such a judgment. # Technical classification: Classification A is a classification related to information processing equipment. Classification B is a classification related to agricultural implements. Classification C is a classification related to food products. # Target patent: 〔Abstract〕 ··· 〔Claims〕 ···

[0104] 〔Prompt for screening task〕 Please examine whether the invention described in the following "target invention" is described in the invention described in the following "target patent". Calculate the relevance between the target invention and the target patent between 0 and 100. Output the reason for such a judgment. # Target invention: ···means, ···means, and an apparatus comprising ··· #Target Patent: 〔Abstract〕 ··· 〔Claims〕 ··· 〔Specification〕 ···

[0105] 〔Prompt for the case of the non-determination task〕 Please examine whether the products, services, etc. described in the following "Target Product" are included in the scope of rights of the invention described in the following "Target Patent". Calculate the relevance between the target product and the target patent on a scale of 0 to 100. Output the reasons for such a determination. #Target Product: ···means, ···means, and an apparatus comprising ··· #Target Patent: 〔Claim 1〕 ···

[0106] In step S505, the generation step executes a step of generating a plurality of prompts for each of the plurality of patent documents acquired in the document acquisition step based on the query information received in the query reception step and each of the plurality of extraction locations extracted in the extraction step. Specifically, when a plurality of patent documents are input, a generation step of generating prompts is executed based on the extraction locations extracted for each of the patent documents included in the plurality of patent documents. Further, the generated prompts are stored in association with the document IDs.

[0107] In step S506, the list processing unit 1044 of the server 10 transmits the generated prompts to the user terminal 20. The control unit 204 of the user terminal 20 displays the received prompts in the prompt display column D304 of the user terminal 20. The list processing unit 1044 of the server 10 executes a transmission step of transmitting the prompts generated in the generation step to the artificial intelligence system. Specifically, the user presses the send button D305 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 sends a request to the server 10 to send the generated prompt (character string) to the artificial intelligence system 40. The list processing unit 1044 of the server 10 sends the generated prompt (character string) to the API (Application Programming Interface) endpoint of the artificial intelligence service provided by the artificial intelligence system 40. Note that the control unit 204 of the user terminal 20 may directly send the prompt (character string) displayed in the prompt display field D304 to the API (Application Programming Interface) endpoint of the artificial intelligence service.

[0108] In step S507, the list processing unit 1044 of the server 10 executes an answer receiving step of receiving the answer content for the prompt from the artificial intelligence system 40. The list processing unit 1044 of the server 10 executes an answer receiving step of receiving the answer content including the index value and basis for the prompt from the artificial intelligence system 40. Specifically, the list processing unit 1044 of the server 10 receives a response to the sent prompt. The response includes a character string regarding the answer content for the prompt. For example, the answer content includes the following information. In the present disclosure, the following answer content is described as an example, but the answer content is preferably received as structured data such as JSON having fields (keys) regarding "index value" and "basis". For example, in a large language model (LLM) called ChatGPT, by using a function called Function Calling, the answer result can be made into structured (typed) data.

[0109] 〔Answer content in the case of the classification assignment task〕 #Classification: A #Relevance: 80 #Reason: The target patent includes configurations ···, ···. On the other hand, the target patent does not include configurations ···, ···. It conforms to the classification definition of Classification A and does not conform to the classification definitions of Classification B and Classification C. The degree of relevance to Classification A is about 80.

[0110] 〔Answer content in the case of the screening task〕 #Relevance: 40 #Reason: The target invention is consistent with the target patent from the perspective of ··· and different from it from the perspective of ···. The different parts are significant, and the degree of relevance to the target patent is about 40.

[0111] 〔Answer content in the case of the non-judgment task〕 #Relevance: 20 #Reason: The target product is consistent with the target patent from the perspective of ··· and different from it from the perspective of ···. The target product is not included in the scope of rights of the target patent. The degree of relevance to the target patent is about 20.

[0112] At this time, the index value (degree of relevance) is an index value indicating the accuracy regarding the assigned classification when the task information is a classification assignment task, an index value indicating the degree of relevance to the target invention when the task information is a screening task, and an index value indicating the degree of relevance to the target product when the task information is a non-judgment task.

[0113] The list processing unit 1044 of the server 10 stores the document ID received in step S503, the prompt generated in step S505, and the answer content in the document ID, prompt, and answer content items of a new record in the support table 1015.

[0114] In step S508, the list processing unit 1044 of the server 10 executes an answer presentation step of presenting the index value and the basis received in the answer reception step to the user. Specifically, the list processing unit 1044 of the server 10 transmits the received response content to the user terminal 20. The control unit 204 of the user terminal 20 displays the received response content in the response result D306. Note that the user may be able to download information regarding the response result in a file format such as a Word, Excel, or CSV file by operating the input device 206 of the user terminal 20. In addition to the index value and basis, the list processing unit 1044 of the server 10 may present the extraction location of the patent document to the user. Thereby, the user can confirm based on which location of the patent document the index value was calculated and what the basis is.

[0115] When a plurality of patent documents are input, the list processing unit 1044 of the server 10 transmits the response content corresponding to the prompts generated for each of the plurality of patent documents to the user terminal 20. The control unit 204 of the user terminal 20 may display and present the received plurality of response contents in the response result D306. Specifically, the information identifying the documents such as the document ID, publication number, and document name of the plurality of patent documents, the prompts generated for each document, and the response content received from the artificial intelligence system 40 in response to the prompts may be associated and presented respectively. In addition to the index value and basis, the extraction location of the patent document may be presented to the user. Further, the user may be able to download a file such as a Word, Excel, or CSV file in which the information identifying the documents such as the document ID, publication number, and document name of the plurality of patent documents, the prompts generated for each document, and the response content received from the artificial intelligence system 40 in response to the prompts are stored, by operating the input device 206 of the user terminal 20.

[0116] <Basic Hardware Configuration of a Computer> FIG. 15 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 includes at least a processor 901, a main memory device 902, an auxiliary storage device 903, and a communication IF 991 (Interface). These are electrically connected to each other by a communication bus 921.

[0117] The processor 901 is hardware for executing an instruction set described in a program. The processor 901 is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0118] The main memory device 902 is for temporarily storing a program and data processed by the program and the like. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0119] The auxiliary storage device 903 is a storage device for storing data and programs. For example, it includes a flash memory, an HDD (Hard Disc Drive), a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, and the like.

[0120] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard. The network is composed of various mobile communication systems constructed by the Internet, a LAN, a wireless base station, and the like. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), a wireless network (e.g., Wi-Fi (registered trademark)) connectable to the Internet by a predetermined access point, and the like. When connecting wirelessly, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), and the like. When connecting wired, the network includes those directly connected by a USB (Universal Serial Bus) cable or the like.

[0121] Note that all or part of each hardware configuration can be distributed and provided to a plurality of computers 90, and the computers 90 can be virtually realized by connecting them to each other via a network. In this way, the computer 90 is a concept that includes not only a single housing or a computer 90 housed in a case, but also a virtualized computer system.

[0122] <Basic functional configuration of computer 90> The functional configuration of the computer realized by the basic hardware configuration of the computer 90 (FIG. 15) will be described. The computer includes at least functional units of a control unit, a storage unit, and a communication unit.

[0123] Note that the functional units included in the computer 90 can also be realized by distributing all or part of each functional unit to a plurality of computers 90 interconnected by a network. The computer 90 is a concept that includes not only a single computer 90, but also a virtualized computer system.

[0124] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903 and expanding them in the main storage device 902, and executing processing according to the programs. The control unit can realize a functional unit that performs various information processes according to the type of program. Thereby, the computer is realized as an information processing device that performs information processing.

[0125] The storage unit is realized by the main storage device 902 and the auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Also, the processor 901 can secure a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 according to the program. Further, the control unit can cause the processor 901 to execute addition, update, and deletion processing of the data stored in the storage unit according to various programs.

[0126] The database refers to a relational database, which is for managing by associating table - like tables, called masters, that are structurally defined by rows and columns. In a database, tables are called tables, masters, columns of a table are called columns, and rows of a table are called records. In a relational database, relationships between tables and masters can be set and associated with each other. Normally, for each table and each master, a column serving as a primary key for uniquely identifying records is set, but setting a primary key for a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in specific tables and masters stored in the storage unit according to various programs. Also, by storing data, various programs, and various databases in the storage unit, the information processing apparatus and information processing system according to the present disclosure can be regarded as being manufactured.

[0127] Note that the database and master in the present disclosure may include any data structure (such as a list, dictionary, associative array, object, etc.) in which information is structurally defined. The data structure shall also include data that can be regarded as a data structure by combining data with functions, classes, methods, etc. described in an arbitrary programming language.

[0128] The communication unit is realized by the communication IF991. The communication unit realizes the function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 901 to execute information processing on the received information according to various programs. Also, the communication unit can transmit the information output from the control unit to other computers 90.

[0129] <Supplementary Note> The matters described in each of the above embodiments are appended below.

[0130] (Supplementary Note 1) A program for causing a computer including a processor and a memory unit to execute, the program causing the processor to execute: a task reception step (S501) of receiving task information regarding a task to be executed on a patent document; a query reception step (S502) of receiving query information to be applied to the patent document; a document acquisition step (S503) of acquiring a patent document related to a patent; an extraction step (S504) of extracting a predetermined extraction location according to the task received in the task reception step from among the patent documents acquired in the document acquisition step; and a generation step (S505) of generating a prompt including the query information received in the query reception step and the extraction location extracted in the extraction step. Thereby, the user can easily generate a suitable prompt according to the task applied to the patent document.

[0131] (Appendix 2) The task reception step (S501) is a step of receiving task information indicating at least any one of a classification assignment task of assigning a classification to a patent document, a screening task of determining the relevance between a patent document and a target document, and a non-determination task of determining the relevance between a patent document and a target product. The extraction step (S504) is a step capable of extracting different predetermined extraction locations according to the task information received in the task reception step, where when the task information is a classification assignment task, at least any one of an abstract, claims, appendix 1, and the specification of the patent document; when the task information is a screening task, at least any one of an abstract, claims, appendix 1, and the specification of the patent document; and when the task information is the non-determination task, at least any one of appendix 1 and claims of the patent document. The program according to appendix 1. Thereby, the user can easily generate a suitable prompt according to the desired task among the classification assignment, screening, and non-determination tasks applied to the patent document.

[0132] (Appendix 3) The generation step (S505) is a step of generating a prompt including an instruction to output an index value related to the patent document acquired in the document acquisition step and the basis of the index value, which is the program described in Appendix 1. Thereby, the user can execute a task on the patent document and can generate a prompt for obtaining an index value and the basis of the index value.

[0133] (Appendix 4) The generation step (S505) is a step of generating a prompt including an instruction to output an index value indicating the execution result of a task according to the task information received in the task reception step. The index value is, when the task information is a classification assignment task, an index value indicating the accuracy regarding the assigned classification, and when the task information is a screening task, an index value indicating the degree of relevance to the target invention, and when the task information is the non-determination task, an index value indicating the degree of relevance to the target product, which is the program described in Appendix 3. Thereby, when the user executes tasks such as classification assignment, screening, and non-determination on the patent document, the user can generate a prompt for outputting an index value indicating the execution result.

[0134] (Appendix 5) The processor executes a transmission step (S506) of transmitting the prompt generated in the generation step to the artificial intelligence system, a response reception step (S507) of receiving a response content including an index value and a basis for the prompt from the artificial intelligence system, and a response presentation step (S508) of presenting the index value and the basis received in the response reception step to the user, which is the program described in Appendix 3. Thereby, the user can execute a task on the patent document and can confirm a response content including an index value indicating the execution result of the task when the task is executed and the basis of the index value.

[0135] (Appendix 6) The generation step (S505) is the step of generating a prompt according to the task information received in the task reception step, which is the program described in Appendix 1. Thereby, the user can easily generate a suitable prompt according to the task applied to the patent document.

[0136] (Appendix 7) The document acquisition step (S503) is the step of acquiring patent documents related to a plurality of patents. The extraction step (S504) is the extraction step of extracting a plurality of predetermined extraction locations for each of the plurality of patent documents acquired in the document acquisition step according to the task received in the task reception step. The generation step (S505) is the step of generating a plurality of prompts for each of the plurality of patent documents acquired in the document acquisition step based on the query information received in the query reception step and each of the plurality of extraction locations extracted in the extraction step, which is the program described in Appendix 1. Thereby, the user can collectively create prompts for applying a predetermined task and a predetermined query to a plurality of patent documents. The man-hour for creating the prompts can be reduced.

[0137] (Appendix 8) The processor executes a task presentation step (S501) of presenting a plurality of task information to the user in a selectable manner. The task reception step (S501) is the step of receiving an input operation of predetermined task information from among the plurality of task information presented in the task presentation step from the user, which is the program described in Appendix 1. Thereby, the user can easily create a suitable prompt according to the task by selecting the desired task information to be executed from among the plurality of presented task information.

[0138] (Appendix 9) A program according to Appendix 1, wherein the processor executes a transmission step (S506) of transmitting the prompt generated in the generation step to the artificial intelligence system, and a response reception step (S507) of receiving a response to the prompt from the artificial intelligence system. Thereby, the user can obtain a response to a suitable prompt according to the task applied to the patent document.

[0139] (Appendix 10) A program according to Appendix 1, wherein the processor executes an extraction prompt step of presenting to the user a plurality of extraction items in a selectable manner according to the task received in the task reception step, and an item selection step of receiving from the user a selection operation for a predetermined one or more of the plurality of extraction items presented in the extraction prompt step, and the extraction step is a step of extracting a predetermined extraction location from the patent document based on the predetermined one or more extraction items selected in the item selection step. Thereby, the user can edit the extraction location according to the task applied to the patent document. A prompt corresponding to a suitable extraction location can be created according to the content of the task the user wants to execute.

[0140] (Appendix 11) A method executed on a computer including a processor and a memory, wherein the processor executes all steps executed in the invention according to any one of Appendix 1 to Appendix 10. Thereby, the user can easily generate a suitable prompt according to the task applied to the patent document.

[0141] (Appendix 12) An information processing apparatus including a control unit and a storage unit, wherein the control unit executes all steps executed in the invention according to any one of Appendix 1 to Appendix 10. Thereby, the user can easily generate a suitable prompt according to the task applied to the patent document.

[0142] (Appendix 13) A system comprising means for performing all steps executed in the invention according to any one of Appendices 1 to 10. Thereby, the user can easily generate a suitable prompt according to the task applied to the patent document.

Description of Reference Numerals

[0143] 1 System, 10 Server, 101 Storage Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminal, 201 Storage Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 40 Artificial Intelligence System, 401 Storage Unit, 404 Control Unit, 406 Input Device, 408 Output Device

Claims

1. A program for causing a computer including a processor and a storage unit to execute, wherein the processor performs a task reception step of receiving task information regarding a task to be executed on a patent document, a query reception step of receiving query information to be applied to the patent document, a document acquisition step of acquiring a patent document related to a patent, an extraction step of extracting a predetermined extraction location according to the task received in the task reception step from among the patent documents acquired in the document acquisition step, and a generation step of generating a prompt including the query information received in the query reception step and the extraction location extracted in the extraction step, and executes the program.

2. The task reception step is a step of receiving the task information indicating at least any one of a classification assignment task of assigning a classification to a patent document, a screening task of determining the relevance between a patent document and a target document, and a non-determination task of determining the relevance between a patent document and a target product, and the extraction step is a step capable of extracting different predetermined extraction locations according to the task information received in the task reception step, wherein when the task information is a classification assignment task, at least any one of an abstract, claims, claim 1, and the specification among the patent documents, when the task information is a screening task, at least any one of an abstract, claims, claim 1, and the specification among the patent documents, and when the task information is the non-determination task, at least any one of claim 1 and the claims among the patent documents. The program according to claim 1.

3. The generation step is a step of generating the prompt including an instruction to output an index value regarding the patent document acquired in the document acquisition step and the basis of the index value. The program according to claim 1.

4. The generation step is a step of generating the prompt including an instruction for outputting an index value indicating the execution result of the task according to the task information received in the task reception step, wherein the index value is an index value indicating the accuracy regarding the assigned classification when the task information is a classification assignment task, ​ When the task information is a screening task, it is an index value indicating the degree of relevance to the target invention, When the task information is the non-determination task, it is an index value indicating the degree of relevance to the target product, The program according to claim 3.

5. The processor is configured to: A transmission step of transmitting the prompt generated in the generation step to an artificial intelligence system; An answer receiving step of receiving, from the artificial intelligence system, answer content including the index value and the basis for the prompt; An answer presenting step of presenting the index value and the basis received in the answer receiving step to the user; and execute the following steps: The program according to claim 3.

6. The generation step is a step of generating the prompt according to the task information received in the task receiving step. The program according to claim 1.

7. The document acquisition step is a step of acquiring patent documents related to a plurality of patents. The extraction step is an extraction step of extracting a plurality of predetermined extraction locations for each of the plurality of patent documents acquired in the document acquisition step according to the task received in the task receiving step. The generation step is a step of generating a plurality of prompts for each of the plurality of patent documents acquired in the document acquisition step based on the query information received in the query receiving step and each of the plurality of extraction locations extracted in the extraction step. The program according to claim 1.

8. The processor is configured to: A task presenting step of presenting a plurality of task information to the user in a selectable manner; and execute the following steps: The task receiving step is a step of receiving, from the user, an input operation of predetermined task information among the plurality of task information presented in the task presenting step. The program according to claim 1.

9. The processor is configured to: A transmission step of transmitting the prompt generated in the generation step to an artificial intelligence system; An answer receiving step of receiving answer content for the prompt from the artificial intelligence system; and execute the following steps: The program according to claim 1.

10. The processor is configured to: An extraction prompt step of presenting a plurality of extraction items to the user so that they can be selected according to the task received in the task reception step; An item selection step of receiving a selection operation from the user for one or more predetermined extraction items among the plurality of extraction items presented in the extraction prompt step; is executed, The extraction step is a step of extracting the predetermined extraction location from the patent document based on the one or more predetermined extraction items selected in the item selection step. The program according to claim 1. **Claim 11** A method executed by a computer including a processor and a memory, the method comprising the processor executing all steps executed in the invention according to any one of claims 1 to 10. **Claim 12** An information processing apparatus including a control unit and a storage unit, the control unit executing all steps executed in the invention according to any one of claims 1 to 10. **Claim 13** A system comprising means for executing all steps executed in the invention according to any one of claims 1 to 10.

Images