Programs, methods, information processing devices, systems

Abstract

We provide a program that offers appropriate answers to legal questions from users. [Solution] A program to be executed by a computer having a processor and a memory unit, the program causing the processor to execute a process that includes: a question receiving step of receiving a question from a user; a document search step of searching for one or more documents that describe legal opinions that may be useful when answering the question based on the question received in the question receiving step; and a generation step of generating a prompt based on the question received in the question receiving step and one or more documents found in the document search step.

Description

Technical Field

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

Background Art

[0002] Web services that provide cases related to legal issues on a website are known. Patent Document 1 discloses a legal search system that can search for desired articles and case laws even without knowing search keywords related to laws, can be easily and quickly searched from combinations of verbs and objects, and can obtain a desired conclusion by sequentially selecting from appropriate options.

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 an appropriate answer cannot be given to a legal question from a user. Therefore, the present disclosure has been made to solve the above problems, and an object thereof is to provide an appropriate answer to a legal question from a user.

Means for Solving the Problems

[0005] A program to be executed by a computer having a processor and a memory unit, wherein the processor performs a question receiving step of receiving a question from a user; a document search step of searching for one or more documents containing legal opinions that may be useful in answering the question based on the question received in the question receiving step; and a generation step of generating a prompt based on the question received in the question receiving step and one or more documents found in the document search step. [Effects of the Invention]

[0006] This disclosure allows us to provide appropriate answers to legal questions from users. [Brief explanation of the drawing]

[0007] [Figure 1] This is a block diagram showing the functional configuration of System 1. [Figure 2] This block diagram shows the functional configuration of Server 10. [Figure 3] This is a block diagram showing the functional configuration of user terminal 20. [Figure 4] This diagram shows the data structure of user table 1012. [Figure 5] This diagram shows the data structure of document table 1013. [Figure 6] This diagram shows the data structure of question table 1014. [Figure 7] This is a flowchart showing the operation of the report presentation process. [Figure 8] This is an example of a question screen demonstrating the operation of the report presentation process. [Figure 9] This is an example of the report presentation screen, demonstrating the operation of the report presentation process. [Figure 10] A block diagram showing the basic hardware configuration of Computer 90. [Modes for carrying out the invention]

[0008] The embodiments of this disclosure will be described below with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted. The following embodiments are not intended to unduly limit the content of this disclosure as described in the claims. Not all components shown in the embodiments are necessarily essential components of this disclosure. Also, each drawing is a schematic diagram and is not necessarily a strict illustration.

[0009] <System 1 Configuration> System 1 in this disclosure is an information processing system that outputs answers to legal questions. System 1 comprises a server 10, a user terminal 20, and an information processing device for generating AI 50, all connected via network N. Figure 1 is a block diagram showing the functional configuration of System 1. Figure 2 is a block diagram showing the functional configuration of server 10. Figure 3 is a block diagram showing the functional configuration of the user terminal 20.

[0010] Each information processing device consists of a computer equipped with an arithmetic unit and a memory device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by said hardware configuration will be described later. For each of the server 10, user terminal 20, and generation AI 50, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0011] <Server 10 Configuration> Server 10 is an information processing device that provides an information processing service that outputs answers to legal questions. 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, and a question table 1014.

[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 for storing and managing information of member users (hereinafter referred to as users) who use the service. By registering for use of the service, the information of the user is stored in a new record of 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 for storing 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 for storing the name of the user. The user name may be set to any string such as a nickname instead of the name.

[0016] The document table 1013 is a table for storing and managing information related to documents (document information). The document table 1013 is a table having columns of document ID, document type, document data, related document ID, and importance with the document ID as the primary key. FIG. 5 is a diagram showing the data structure of the document table 1013.

[0017] The document ID is an item for storing document identification information for identifying a document. The document identification information is an item for which a unique value is set for each document information. The document type stores information about the type of document information (document type). Specifically, the document type is an item that stores a string of characters indicating "case law," "commentary on case law," "law book," "collection of papers," "paper," etc. In this disclosure, as an example, document information is managed on a document-by-document basis, such as case law, commentary on case law, and law book. However, in the case of books and collections of papers, document information may be managed on a sub-unit basis, such as chapters and sections contained within the collection of papers. Furthermore, the relationships between these sub-units may be linked based on related document IDs, etc., as described later. Document data is an item that stores the content of document information. Specifically, document data is an item that stores the content of documents in PDF (Portable Document Format), Word, and text format. The related document ID is an item that stores the document IDs of one or more other documents related to the document information. For example, if the document type is "Commentary on Case Law," the document IDs of the documents relating to the "case law" explained in that commentary will be stored. Importance is an item that stores the importance level of document information. Importance may be configured to allow each user to store and refer to their own importance level. Importance may also be configured to allow multiple users to store and refer to one or more common importance levels.

[0018] Question table 1014 is a table for storing and managing information related to questions (question information). Question table 1014 is a table with Question ID as the primary key, and has columns for Question ID, Question Text, Answer Text, Parent Question ID, Search Document Information, Relevant Reason, and Document Summary. Figure 6 shows the data structure of question table 1014.

[0019] The Question ID is an item that stores question identification information to identify a question. The question identification information is an item that has a unique value assigned to each piece of question information. The "Question Text" field stores the string of the question text (query) received from the user. The answer field is an item that stores the string of characters representing the answer to the question. The response should include information from a report containing one or more documentary pieces of information related to the question. The Parent Question ID is an item that stores question identification information to identify the parent question. The search document information is an item that stores the document identification information of one or more documents related to the query. Specifically, the search document information is an item that stores the document identification information of one or more documents retrieved based on the query. The search document information may include the entire document data of one or more documents related to the question. The search document information may also include portions (snippets) of the document data that are relevant to the question. Furthermore, the search document information may include information indicating the portions (snippets) of the document data that are relevant to the question (such as chapter numbers, section numbers, paragraph numbers, identification information such as IDs, starting character counts, ending character counts, etc.). The related reason is an item that stores a string of information about the related reason (related reason information) for one or more document pieces of information related to the question. Specifically, for each of the one or more document pieces of information, the related reason stores the reason related to the question in association with each of the document pieces of information. A document summary is an item that stores a string of information (summary information) that provides an overview of one or more document pieces of information related to the question. Specifically, a document summary includes information about the summary. A document summary may also include summary information based on the portion of the document data of the document piece that is relevant to the question. For example, a document summary may include a summary created based on the portion of the document data of the document piece that is relevant to the question. Specifically, the document summary stores summary information for each of the one or more document pieces of information, associating it with each of the document pieces of information.

[0020] <Configuration of the control unit 104 of server 10> The control unit 104 of the server 10 includes a user registration control unit 1041 and a presentation unit 1042. The control unit 104 realizes each functional unit by executing the application program 1011 stored in the storage unit 101.

[0021] The user registration control unit 1041 processes information of users who wish to use the services related to this disclosure and stores it in the user table 1012. Information stored in the user table 1012 is obtained when a user opens a web page operated by the service provider from any information processing terminal, enters information into a designated input form, and sends it to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, and user registration is completed. As a result, users stored in the user table 1012 can use the service. Prior to the registration of user information in the user table 1012 by the user registration control unit 1041, the service provider may perform a prescribed review and restrict whether or not the user can use the service. The user ID can be any string or number that can identify the user, and may be any string or number desired by the user, or the user registration control unit 1041 may automatically set any string or number.

[0022] The presentation unit 1042 performs the report presentation process. Details will be described later.

[0023] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user of the service. The user terminal 20 may be, for example, a mobile device such as a smartphone or tablet, or a stationary PC (Personal Computer) or laptop PC. It may also be a wearable device such as an HMD (Head Mount Display) or a smartwatch. The user terminal 20 includes a storage unit 201, a control unit 204, an input device 206, and an output device 208.

[0024] <Configuration of the storage unit 201 of the user terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012.

[0025] User ID 2011 is the user's account ID. The user sends User ID 2011 from user terminal 20 to server 10. Server 10 identifies the user based on User ID 2011 and provides the services related to this disclosure to the user. User ID 2011 includes information such as a session ID that is temporarily assigned by server 10 to identify the user using user terminal 20.

[0026] The application program 2012 may be pre-stored in the memory unit 201, or it may be configured to be downloaded from a web server operated by the service provider via a communication interface. Application Program 2012 includes applications such as web browser applications. Application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the user terminal 20.

[0027] <Configuration of the control unit 204 of the user terminal 20> The control unit 204 of the user terminal 20 comprises 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 memory unit 201.

[0028] <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.

[0029] <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.

[0030] <Configuration of Generation AI50> Generative AI50 is a type of artificial intelligence model (deep learning model) that outputs output data such as strings or images based on input data such as strings or images. In this disclosure, a large language model (LLM) that outputs output data related to strings based on input data related to strings will be described as an example. Examples of LLMs include OpenAI ChatGPT, Microsoft Bing Chat, and Google Bard.

[0031] <System 1 operation> The following describes each process in System 1. Figure 7 is a flowchart showing the operation of the report presentation process. Figure 8 shows an example of a question screen illustrating the operation of the report presentation process. Figure 9 shows an example of the report presentation screen, illustrating the operation of the report presentation process.

[0032] <Report presentation process> The report presentation process is a process in which, in response to a user's legal question, a report is presented to the user containing information such as relevant court cases, explanatory articles on those cases, and legal books.

[0033] <Overview of Report Presentation Process> This process involves receiving a question from the user, searching for documents based on the question, presenting the search results to the user, receiving a document selection operation from the user, generating a prompt based on the selected document, obtaining the answer by inputting the prompt into the generating AI, creating a report based on the answer, and presenting the created report.

[0034] <Details of the report submission process> The details of the report submission process are described below.

[0035] In step S101, the presentation unit 1042 of the server 10 performs a question reception step in which it receives questions from the user. The user opens the report presentation page D1 by operating the input device 206 of the user terminal 20, running a browser application or the like, and entering the URL of the web page (report presentation page) for executing the report presentation process. The control unit 204 of the user terminal 20 sends a request to the server 10 that includes the user ID 2011 to open the report presentation page.

[0036] When server 10 receives a request, it generates a report presentation page and sends it to user terminal 20. The control unit 204 of user terminal 20 displays the report presentation page on the user terminal 20's display 2081 and presents it. Figure 8 shows an example of the question screen in the report presentation process. The user terminal 20's display 2081 shows the question page D1. The question page D1 includes a question input field D11, a send button D12, documents related to the search results D131, D132, D133, checkboxes D141, D142, D143 for selecting each document related to the search results, document summaries D151, D152, D153 of the documents included in the document data, reasons for relevance to the entered question D161, D162, D163, and related documents D171, D172, D173 of the document information related to the search results.

[0037] The user operates the input device 206 of the user terminal 20 and enters the question text into the question input field D11. In this disclosure, the user shall ask a question concerning a legal matter. Possible question formats include the following. Users can freely enter their question in the question input field D11. [Question] Are there any precedents that mention whether nail clippers can be considered a weapon under the Minor Offenses Act? Are there any precedents that address the division of property between spouses? Are there any precedents where the termination of a lease agreement due to non-payment of rent was deemed lawful? What are some court precedents that address the improper termination of lease agreements?

[0038] The user presses the send button D12 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 sends the question entered in the question input field D11 to the server 10. The presentation unit 1042 of the server 10 receives and accepts the question. The presentation unit 1042 of the server 10 stores the received question text in the question text field of a new record (target record) in the question table 1014.

[0039] In step S102, the presentation unit 1042 of the server 10 performs a document search step to search for one or more documents that contain legal opinions that may be helpful in answering the question, based on the question received in the question reception step. Specifically, the presentation unit 1042 of the server 10 searches for document data items in the document table 1013 based on the received question text and obtains document information including document ID, document type, document data, related document ID, and importance. Alternatively, the presentation unit 1042 of the server 10 may also search for document data items in the document table 1013 by partial matching based on words extracted by applying morphological analysis processing to the received question text. Furthermore, the presentation unit 1042 of the server 10 can search for document information based on any natural language search technique. In this way, the presentation unit 1042 of the server 10 searches for and identifies multiple documents related to the question text. The presentation unit 1042 of the server 10 stores the identified document information (including document ID, document data, and related document IDs) in the search document information field of the target record in the query table 1014.

[0040] The presentation unit 1042 of the server 10 performs an extraction step to extract the portion of the document relevant to the question from the one or more documents searched in the document search step. The presentation unit 1042 of server 10 extracts from the document data of each document information in the search results the portion containing words related to the question (any part of the document data, such as a paragraph, line, sentence, etc., hereinafter referred to as snippet information). The presentation unit 1042 of server 10 may also calculate the degree of relevance between each document information in the search results and the question. The degree of relevance can be calculated using any algorithm such as TF-IDF or cosine similarity, and can be a score indicating the relationship between the question and the document information. The presentation unit 1042 of server 10 stores the snippet information in the document summary field of the target record in the question table 1014. In this disclosure, a configuration in which snippet information is stored in the document summary field is used as an example, but the invention is not limited to this. For example, the document summary may store documents such as summaries, abstracts, case summaries, and commentaries that are created based on the characteristic points of the document data, rather than the question text. For example, information such as summaries, abstracts, case summaries, and commentaries stored in an unillustrated column of the document table 1013 may be stored in the document summary field of the target record in the question table 1014. Furthermore, the document summary may include information indicating the location of words related to the question, such as paragraph numbers, line numbers, and sentence numbers. Users can refer to the paragraph numbers, line numbers, and sentence numbers that are the source of the snippet information, along with the snippet information itself.

[0041] The presentation unit 1042 of the server 10 creates information indicating why the document data of each document in the search results is related to the question. Specifically, the presentation unit 1042 of the server 10 creates a sentence indicating why the document information in the search results is related to the question, based on the question and the snippet information. For example, the presentation unit 1042 of the server 10 may create a sentence indicating why the document information in the search results is related to the question by transmitting the question and the snippet information of each document to the generating AI 50. Furthermore, the text explaining the relevant reasons can be obtained as an output result by inputting the following prompt (snippet generation) to the generating AI50. The [Question] section is where the question received from the user in step S101 is entered. The [Document Summary of Document Information A] section is where the snippet information of Document Information A is entered. A prompt is created for each of the multiple documents related to the search results (for example, Document Information A, Document Information B, Document Information C). [Prompt (snippet generation)] Document Information A contains information about the document summary of Document Information A. Please explain why [the question] and document information A are related.

[0042] The presentation unit 1042 of the server 10 associates multiple document information related to the search results with information indicating why the document information related to the search results is related to the question (including sentences indicating the reason for the relationship, a score such as the degree of relevance, etc.) and stores this information in the "Relevance Reason" field of the target record in the question table 1014.

[0043] In step S103, the presentation unit 1042 of the server 10 executes a document presentation step in which it presents one or more documents found in the document search step to the user. Specifically, the presentation unit 1042 of the server 10 transmits the document information relating to the search results obtained in step S102 to the user terminal 20. The presentation unit 1042 of the user terminal 20 displays and presents the received document information on documents D131, D132, and D133 on the question page D1.

[0044] The document presentation step includes a step of controlling the presentation order when presenting one or more documents in response to the user's selection operation in the document selection step. Specifically, the control unit 204 of the user terminal 20 may display documents D131, D132, and D133 on question page D1 in order of increasing importance, based on the importance of the received document information. The control unit 204 of the user terminal 20 may also display documents D131, D132, and D133 on question page D1 in order of increasing relevance, based on the degree of relevance calculated for each of the received document information and the question text. The control unit 204 of the user terminal 20 may also display documents D131, D132, and D133 on question page D1 in order of increasing score, based on an arbitrary score calculated based on importance and relevance.

[0045] In step S103, the document presentation step performs the step of presenting to the user information that indicates the relevant section of the question for each of the one or more documents found in the document search step. Specifically, the presentation unit 1042 of the server 10 associates the received document information with documents D131, D132, and D133 on question page D1, and displays and presents document summaries D151, D152, and D153, which are document summaries such as snippet information that contain words related to the question text from the document data.

[0046] In step S103, the document presentation step performs the step of presenting to the user information that indicates the reason related to the question for each of the one or more documents found in the document search step. Specifically, the presentation unit 1042 of the server 10 associates the received document information with documents D131, D132, and D133 on question page D1, and displays and presents the reasons why each document piece of information is related to the question, as related reasons D161, D162, and D163.

[0047] In step S103, the document presentation step performs the step of presenting to the user one or more reference documents related to each of the one or more documents found in the document search step. Specifically, the presentation unit 1042 of server 10 retrieves document information (related document information) by searching for document IDs in document table 1013 based on the related document IDs contained in each document information related to the search results. The received document information is associated with documents D131, D132, and D133 on question page D1, and the related documents corresponding to the related document IDs of each document information are displayed and presented as related reasons D161, D162, and D163.

[0048] In step S103, the document presentation step may include a step of presenting summary information about the search results to the user. The document presentation step may include a step of presenting summary information about the search results to the user together with one or more documents retrieved in the document search step. Specifically, the presentation unit 1042 of the server 10 presents the user with summary information that shows an overview of the search results, including information about each of the one or more documents searched in the document search step. For example, in step S101, in response to the question, "What are the points to be aware of when switching an employee who is currently employed as a full-time employee to a business outsourcing contract?", the presentation unit 1042 of the server 10 presents the user with the summary statement, "The employee's consent and the content of the business outsourcing contract are important. For details, please refer to the following books and case precedents."

[0049] In step S103, the document presentation step may include a step of associating a link to each of the one or more documents found in the document search step and presenting it to the user. Specifically, a link to refer to the contents of each of the one or more documents found in the document search step may be associated with each of the one or more documents and presented to the user. For example, if the content of one or more documents is included in and available through the information processing services related to this disclosure, such as document table 1013, the associated links will be links to access the content of those documents. On the other hand, if the content of one or more documents is not available through the information processing services related to this disclosure, links to external information processing services that guide users on purchasing those documents will be associated. In other words, the presentation unit 1042 of the server 10 can be configured to selectively associate a first link for referencing a first information processing service and a second link for referencing a second information processing service with each of the one or more documents retrieved in the document search step. This allows the information processing service related to this disclosure to provide users with links to directly access the document content for documents for which the document content can be provided, and to provide users with external links that disclose the means to access or refer to the document content for documents for which the information processing service related to this disclosure cannot be provided. Users can conveniently review one or more documents related to the search results.

[0050] In step S104, the presentation unit 1042 of the server 10 executes a document selection step in which it receives a selection from the user for one or more predetermined documents from among the one or more documents presented in the document presentation step. Specifically, the user reviews the document summaries, related reasons, and related documents for documents D131, D132, and D133 related to the search results displayed on question page D1, and confirms their contents. The user then operates the input device 206 of the user terminal 20 to select the checkboxes D141, D142, and D143 that are displayed in association with the appropriate documents D131, D132, and D133 for the question. The user can select multiple checkboxes. The control unit 204 of the user terminal 20 sends the document information (selected document information) for which checkboxes D141, D142, and D143 have been selected to the server 10.

[0051] Alternatively, the system may be configured to accept input from the user for a "relevance score," which is an indicator of whether or not a document is relevant to the question, for document information for which checkboxes D141, D142, and D143 have been selected. In addition, the system may be configured to accept input only for the reference score without requiring the user to select any checkboxes, and document information with a reference score above a predetermined value may be sent to the server 10 as selected document information.

[0052] The presentation unit 1042 of the server 10 stores the received selected document information in the search document information field of the question table 1014. As a result, information indicating that the document was selected by the user is associated and stored with each of the search results document information stored in the search document information field.

[0053] The presentation unit 1042 of server 10 searches the document ID field in document table 1013 based on the document ID included in the selected document information to identify the record of the document information. In response to the user's selection operation, it changes the importance field of the identified record of the selected document information. Specifically, it increases the importance value of the selected document information chosen by the user. This allows for control over the weighting (importance, score) of multiple patent documents presented based on user selections. For example, patent documents selected by a large number of users can be given higher importance and displayed in a more prominent position during document presentation. Conversely, patent documents excluded by a large number of users can be given lower importance and less likely to be presented during document presentation.

[0054] In step S105, the presentation unit 1042 of the server 10 executes a generation step in which it generates a prompt based on the question received in the question reception step and one or more documents retrieved in the document search step. The generation step performs the step of generating a prompt based on the question received in the question receiving step and one or more predetermined documents selected in the document selection step. Specifically, the presentation unit 1042 of the server 10 generates a prompt that will be input data to the generating AI based on the question text of the target record in the question table 1014 and at least one of the following: search document information, related reason, and document summary. Note that the search document information, related reason, and document summary may be generated based only on the search document information, related reason, and document summary related to the document information selected by the user in step S104, excluding the search document information, related reason, and document summary related to the document information not selected by the user. Furthermore, while this disclosure presents an example of generating a prompt based on the document information selected in step S104, the user's step of selecting document information in step S104 may be omitted, and a prompt to be generated as input data for the AI ​​may be generated based on the search document information, related reasons, and document summary related to the search results.

[0055] In step S105, the generation step performs the step of generating a prompt based on the question received in the question receiving step and the documents obtained by excluding one or more documents selected in the document selection step from the one or more documents retrieved in the document search step. Specifically, in step S104, the user may select an appropriate document in response to a question, or it may be configured to select an inappropriate document. In this case, the search document information, related reasons, and document summary related to the document selected in step S104 may be excluded when generating the prompt.

[0056] In step S105, the generation step performs the step of generating a prompt based on the question received in the question receiving step and the relevant sections of the one or more documents extracted in the extraction step. Specifically, the presentation unit 1042 of the server 10 generates prompts, which become input data for the generating AI, based on the question text of the target record in the question table 1014 and the snippet information included in the document summary.

[0057] The generation step includes generating prompts for creating a report that includes a comparison of the similarities or differences between multiple documents found in the document search step. Specifically, the presentation unit 1042 of the server 10 generates the following prompts. The [Question] section is where the question received from the user in step S101 is entered. The [Document Summary of Document Information A], [Document Summary of Document Information B], and [Document Summary of Document Information C] sections are where the respective document summaries (snippet information) of Document Information A to C are entered. [Prompts (Similarities and Differences)] #Document Information A: [Summary of Document Information A] #Document Information B: [Summary of Document Information B] #Document Information C: [Document summary of Document Information C] Regarding the [question], please explain the similarities and differences between Document Information A, Document Information B, and Document Information C by comparing them.

[0058] The generation step includes generating prompts for creating summaries that describe the outlines of multiple documents found in the document search step. Specifically, the presentation unit 1042 of the server 10 generates the following prompts. The [Question] section is where the question received from the user in step S101 is entered. The [Document Summary of Document Information A], [Document Summary of Document Information B], and [Document Summary of Document Information C] sections are where the respective document summaries (snippet information) of Document Information A to C are entered. [Prompts (Similarities and Differences)] #Document Information A: [Summary of Document Information A] #Document Information B: [Summary of Document Information B] #Document Information C: [Document summary of Document Information C] Please create an overall summary of Document Information A, Document Information B, and Document Information C regarding [the question].

[0059] The generation step involves creating a report in response to a question based on one or more reference documents related to each of the multiple documents retrieved in the document search step. Specifically, the presentation unit 1042 of the server 10 generates the following prompt. In this disclosure, document information A to C are court cases. Related documents D to F are articles or commentaries that explain the court cases of document information A to C, respectively. The [Question] field is where the question received from the user in step S101 is entered. The [Document Summary for Document Information A], [Document Summary for Document Information B], and [Document Summary for Document Information C] fields are where the respective document summaries (snippet information) for Document Information A through C are entered. Document Information D, Document Information E, and Document Information F should contain document summaries, such as snippets extracted from related documents D through F that relate to Document Information A through C. Related documents D through F may also be their respective document data. Alternatively, they may contain document summaries, such as snippets extracted from sections related to the question. [Prompt (Related Documents)] #Document Information A: [Summary of Document Information A] #Document Information B: [Summary of Document Information B] #Document Information C: [Document summary of Document Information C] #Related document D for document information A: [Document summary for document information D] #Related document E for document information B: [Document summary for document information E] #Related document F for document information C: [Document summary for document information F] Regarding the [question], please explain the similarities or differences between Document Information A, Document Information B, and Document Information C, referring to the explanations in Related Documents D, E, and F.

[0060] The presentation unit 1042 of the server 10 may generate prompts according to the user's attribute information (user attributes). Specifically, the user's attribute information may include whether or not the user has legal expertise, occupation, educational background, gender, and age. The user's attribute information may be received through an input field provided on the report presentation page D1, or it may be identified based on past questions asked by the user. Alternatively, the server may ask the user questions to inquire about their attribute information and receive the user's attribute information as an answer to those questions. The presentation unit 1042 of the server 10 takes user attributes into consideration and includes instructional phrases in the prompt, such as "Please explain it clearly using the simplest terms possible" or "Please provide a concise explanation for experts using technical terms." Furthermore, by including instructions tailored to user attributes in the prompts (snippet generation), the document summary (snippet information) of the document information can also be made more appropriate according to the user's attributes. Specifically, non-expert users can obtain document summaries and answers using simple language. On the other hand, expert users can obtain concise document summaries and answers using specialized terminology.

[0061] In step S106, the presentation unit 1042 of the server 10 inputs the prompt generated in the generation step to the generation AI, thereby executing a response acquisition step to obtain the response content to the prompt. Specifically, the presentation unit 1042 of the server 10 sends the prompt generated in step S105 to the generation AI 50 as input data. The presentation unit 1042 of the server 10 receives the output data (response content) of the generation AI 50 as a response to the sent prompt. The presentation unit 1042 of the server 10 stores the received response in the response text field of the target record in the question table 1014.

[0062] In step S107, the presentation unit 1042 of the server 10 executes a report creation step, which creates a report on the questions received in the question reception step based on the answers obtained in the answer acquisition step. Specifically, the presentation unit 1042 of the server 10 creates a report based on the response received in step S106. The response itself may also be used as the report; in other words, the report may include the response. For example, the presentation unit 1042 of the server 10 creates a report by combining the question text, answer text, document information selected in step S104, related reasons, and document summary stored in the question table 1014. For example, the report is in the following format: The [Question] section is where the question received from the user in step S101 is entered. The [Document Summary for Document Information A], [Document Summary for Document Information B], and [Document Summary for Document Information C] sections are where the document summaries (snippet information) for Document Information A, Document Information B, and Document Information C are entered. The [Related Reason for Document Information A], [Related Reason for Document Information B], and [Related Reason for Document Information C] sections are where the related reasons for Document Information A, Document Information B, and Document Information C are entered. [Report] Question: [Question] Answer content: [Answer content] Document Information A: [Document Summary of Document Information A] [Relevant Reasons for Document Information A] Document Information B: [Document Summary of Document Information B] [Relevance of Document Information B] Document Information C: [Document Summary of Document Information C] [Relevance of Document Information C]

[0063] In step S107, the report creation step creates a report that includes a review comparing the similarities and differences between multiple documents found in the document search step. Specifically, the presentation unit 1042 of the server 10 sends the prompts (matching points and differences) generated in step S106 to the generation AI 50 as input data. The presentation unit 1042 of the server 10 receives the response content regarding the examination of matching points or differences between multiple documents as output data from the generation AI 50. The presentation unit 1042 of the server 10 creates a report based on the response content received in step S106.

[0064] In step S107, the report creation step performs the step of creating a report on the question based on one or more reference documents related to each of the multiple documents found in the document search step. Specifically, the presentation unit 1042 of the server 10 sends the prompt (related document) generated in step S106 to the generation AI 50 as input data. The presentation unit 1042 of the server 10 receives the response content regarding the examination of the points of agreement or disagreement between multiple documents as output data from the generation AI 50. The presentation unit 1042 of the server 10 creates a report based on the response content received in step S106.

[0065] In step S108, the presentation unit 1042 of the server 10 executes a report presentation step in which it presents the report created in the document creation step to the user. Figure 9 shows an example of the report presentation screen in the report presentation process. The user terminal 20's display 2081 shows the report presentation page D3. The report presentation page D3 includes the report D31, an additional question input field D32, the answer to the additional question D34, a send button D33, document information D351, D352, D353, a document summary of the document information D3511, D3521, D3531, and the reason for the connection to the entered question D3512, D3522, D3532. The control unit 204 of the user terminal 20 sends the created report to the user terminal 20. The control unit 204 of the user terminal 20 displays the received report on report D31 of report display page D3. The control unit 204 of the user terminal 20 displays document information A to C on document information D351, D352, and D353, respectively. The control unit 204 of the user terminal 20 displays the document summaries of document information A to C on document summary D3511, D3521, and D3531, respectively. The control unit 204 of the user terminal 20 displays the related reasons for document information A to C on related reasons D3512, D3522, and D3532, respectively. This allows the system to retrieve the responses to the created prompts from the generating AI, and to create a report based on those responses regarding the questions received from the user. This report can then be presented to the user.

[0066] In step S109, the question reception step includes a step of receiving a second question from the user after the report has been presented to the user in the report presentation step. Specifically, users can ask additional questions (second questions) depending on the content of the report. The user enters the question text (second question text) into the additional question input field D32 by operating the input device 206 of the user terminal 20. For example, depending on the content of the report, the following questions are possible. [Question] Please explain in more detail the application of the Minor Offenses Act to nail clippers. Husband A's assets are..., and wife B's assets are.... Please explain how the assets would be divided in this case. Please explain what actions a landlord can take in case of rent arrears. Please explain the legal risks involved when terminating a lease agreement.

[0067] The user presses the send button D33 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 sends the second question entered in the additional question input field D32 to the server 10. The presentation unit 1042 of the server 10 receives and accepts the second question. The presentation unit 1042 of the server 10 stores the received second question in the question text field of the new record (second record) in the question table 1014. It also stores the question ID of the target record in the parent question ID field of the second record. This indicates that the second question asked in step S109 is a child question of the question asked in step S101.

[0068] In step S109, the generation step includes generating a prompt based on the second question and one or more documents retrieved in the document search step. The presentation unit 1042 of the server 10 performs an extraction step to extract the portion of the one or more documents retrieved in the document search step that is related to the second question. The generation step performs a step to generate a prompt based on the second question received in the question reception step and the portion of the one or more documents extracted in the extraction step that is related to the question. Specifically, the presentation unit 1042 of the server 10 generates the following prompts based on the received second question. The second question is entered in the [Second Question] section. The document summaries (snippet information) or document data for each of the document information A to C are entered in [Document Summary of Document Information A], [Document Summary of Document Information B], and [Document Summary of Document Information C]. Note that the document summaries for document information A to C do not need to be the document summaries such as the snippet information created in step S102, but are preferably document summaries extracted from document data A to C that contain words related to the second question. This allows the AI ​​50 to generate a more appropriate answer based on the parts of document information A to C that are related to the second question. In this disclosure, a prompt is generated based on the second question and the document information selected in step S104. At this time, document information not selected in step S104 is not included in the prompt. This allows additional questions to be asked of the generating AI 50 regarding the selected document information A to C from the search results for the first question received. 〔prompt〕 #Document Information A: [Summary of Document Information A] #Document Information B: [Summary of Document Information B] #Document Information C: [Document summary of Document Information C] Based on Document Information A, Document Information B, and Document Information C, please answer the second question.

[0069] The presentation unit 1042 of the server 10 sends the generated prompt to the generating AI 50 as input data. The presentation unit 1042 of the server 10 receives the output data (second response content) of the generating AI 50 as a response to the sent prompt. The presentation unit 1042 of the server 10 stores the received response in the response text field of the second record in the question table 1014. Furthermore, the presentation unit 1042 of the server 10 may store the relevant reasons and document summary created based on document information A to C and the second question in the relevant reasons and document summary fields of the second record.

[0070] The display unit 1042 of the server 10 transmits the received second response content to the user terminal 20. The control unit 204 of the user terminal 20 displays the second response content on the response content D34 of the report display page D3 and presents it. This allows users to ask additional questions (second questions) based on the content of the report. Users can generate prompts that take the content of these additional questions into consideration, and can also obtain answers to these additional questions from the generating AI. Specifically, users can ask additional questions about multiple documents found through their initial question, and obtain answers to those documents from the generating AI.

[0071] <Basic Computer Hardware Configuration> Figure 10 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 comprises at least a processor 901, main memory 902, auxiliary storage 903, and a communication interface IF991. These are electrically connected to each other by a communication bus 921.

[0072] The processor 901 is hardware for executing the instruction set written in a program. The processor 901 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0073] Main memory 902 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0074] Auxiliary storage device 903 refers to a storage device for saving data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, and semiconductor memory.

[0075] The IF991 communication interface is an interface for inputting and outputting signals for communication with other computers via a network using wired or wireless communication standards. A network consists of various mobile communication systems, such as the internet, LANs, and wireless base stations. For example, a network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the internet via designated access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, and Bluetooth®. When connecting via a wired connection, the network also includes connections made directly via USB (Universal Serial Bus) cables, etc.

[0076] Furthermore, by distributing all or part of each hardware configuration across multiple computers 90 and connecting them to each other via a network, a computer 90 can be virtually realized. Thus, the concept of computer 90 includes not only a computer 90 housed in a single enclosure or case, but also a virtualized computer system.

[0077] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of computer 90 (Figure 10) is described below. The computer comprises at least one functional unit: a control unit, a memory unit, and a communication unit.

[0078] Furthermore, the functional units of computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 interconnected via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

[0079] The control unit is realized when the processor 901 reads various programs stored in the auxiliary storage device 903, loads them into the main memory device 902, and executes processing according to those programs. The control unit can realize various functional units that perform information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0080] The memory unit is implemented by the main memory 902 and the auxiliary memory 903. The memory unit stores data, various programs, and various databases. The processor 901 can also reserve memory areas corresponding to the memory unit in the main memory 902 or the auxiliary memory 903 according to the program. The control unit can also cause the processor 901 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0081] A database, specifically a relational database, is used to manage and link together tabular data sets called masters, which are structurally defined by rows and columns. In a database, tables are called tables, masters are called masters, the columns of tables are called columns, and the rows of tables are called records. In a relational database, relationships can be established and linked between tables and masters. Typically, each table and master has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit can instruct the processor 901 to add, delete, or update records in specific tables and masters stored in the memory unit, according to various programs. Furthermore, by storing data, various programs, and various databases in the memory unit, the information processing device and information processing system related to this disclosure can be considered to have been manufactured.

[0082] Furthermore, the databases and masters in this disclosure may include any data structures (lists, dictionaries, associative arrays, objects, etc.) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc., written in any programming language.

[0083] The communication unit is implemented by the communication IF991. The communication unit provides the functionality to communicate with other computers 90 via the 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 perform information processing on the received information according to various programs. The communication unit can also transmit information output from the control unit to other computers 90.

[0084] <Note> The details described in each of the above embodiments are noted below.

[0085] (Note 1) A program to be executed by a computer having a processor and a memory unit, wherein the processor executes a question reception step (S101) in which it receives a question from a user; a document search step (S102) in which it searches for one or more documents containing legal opinions that may be useful in answering the question based on the question received in the question reception step; and a generation step (S105) in which it generates a prompt based on the question received in the question reception step and one or more documents found in the document search step. This allows the system to generate prompts that prompt the AI ​​to create an appropriate answer to a user's question, based on one or more documents containing legal opinions.

[0086] (Note 2) The program as described in Appendix 1, wherein the processor performs a document presentation step (S103) in which it presents one or more documents found in the document search step to the user, and a document selection step (S104) in which it receives a selection from the user for one or more predetermined documents from among the one or more documents presented in the document presentation step, and the generation step (S105) is a step in which it generates a prompt based on the question received in the question receiving step and the one or more predetermined documents selected in the document selection step. This allows the system to generate prompts for the AI ​​to create more suitable answers based on the user's selections from multiple searched documents.

[0087] (Note 3) The program as described in Appendix 1, wherein the processor performs a document presentation step (S103) in which it presents one or more documents found in the document search step to the user, and a document selection step (S104) in which it receives a selection from the user for one or more predetermined documents from the one or more documents presented in the document presentation step, and the generation step (S105) is a step in which it generates a prompt based on the question received in the question receiving step and the documents obtained by excluding the one or more predetermined documents selected in the document selection step from the one or more documents found in the document search step. This allows the system to generate prompts for the AI ​​to create more suitable answers based on the user's selections from multiple searched documents.

[0088] (Note 4) The program as described in Appendix 1, wherein the processor performs a document presentation step (S103) in which it presents to the user one or more documents found in the document search step, and the document presentation step (S103) is a step in which the processor associates information indicating a section related to the question with each of the one or more documents found in the document search step and presents it to the user. This allows users to view multiple documents related to the search results, along with information indicating relevant sections within those documents, such as paragraphs and line numbers. Users can then select or exclude documents while referring to the relevant sections within the multiple documents in the search results.

[0089] (Note 5) The program as described in Appendix 1, wherein the processor performs a document presentation step (S103) in which it presents to the user one or more documents found in the document search step, and the document presentation step (S103) is a step in which the processor associates information indicating reasons related to the question with each of the one or more documents found in the document search step and presents it to the user. This allows users to view multiple documents related to the search results, along with information indicating the reasons why those documents are relevant to their question. Users can then select or exclude documents from the search results while referring to the relevant reasons.

[0090] (Note 6) The program as described in Appendix 1, wherein the processor performs a document presentation step (S103) in which it presents to the user one or more documents found in the document search step, and the document presentation step (S103) is a step in which the processor presents to the user one or more reference documents related to each of the one or more documents found in the document search step, in association with each of them. This allows users to view multiple documents related to the search results, along with related reference documents. Users can select or exclude documents while referring to the related reference documents for multiple documents related to the search results.

[0091] (Note 7) The program as described in Appendix 1, wherein the processor performs an extraction step (S105) in which it extracts portions related to a question from one or more documents searched in the document search step, and the generation step (S105) is a step in which it generates a prompt based on the question received in the question reception step and the portions related to the question from one or more documents extracted in the extraction step. This allows the system to filter out irrelevant sections of multiple documents in the search results and generate prompts based only on the relevant parts. By filtering out irrelevant sections, the quality of the AI-generated answers can be improved.

[0092] (Note 8) The document is the program described in Appendix 1, which includes at least one of the following: a court case, an explanatory article on a court case, or a legal book. This allows the system to generate prompts for the AI ​​to create appropriate answers to user questions, based on documents such as court precedents, explanatory articles on those precedents, and legal texts.

[0093] (Note 9) The program described in Appendix 1, wherein the processor inputs a prompt generated in the generation step to the generation AI, thereby obtaining the content of the response to the prompt; the report creation step (S107) creates a report on the question received in the question reception step based on the content of the response obtained in the answer acquisition step; and the report presentation step (S108) presents the report created in the report creation step to the user. This allows the system to retrieve the responses to the created prompts from the generating AI, and to create a report based on those responses regarding the questions received from the user. This report can then be presented to the user.

[0094] (Note 10) The report creation step (S107) is a program described in Appendix 9 that creates a report containing a review comparing the similarities or differences between multiple documents found in the document search step. This allows users to compare and review multiple documents, highlighting their similarities and differences.

[0095] (Note 11) The program described in Appendix 9 includes a report creation step (S107), which is a step in creating a report in response to a question based on one or more reference documents related to each of the multiple documents retrieved in the document search step. This allows the AI ​​to generate higher-quality answers that take into account explanations and other information related to multiple documents searched within the reference materials.

[0096] (Note 12) The program as described in Appendix 9, wherein the question receiving step (S109) includes a step of receiving a second question from the user after presenting a report to the user in the report presentation step, and the generation step (S109) includes a step of generating a prompt based on the second question and one or more documents retrieved in the document search step. This allows users to ask additional questions (second questions) based on the content of the report. Users can generate prompts that take the content of these additional questions into consideration, and can also obtain answers to these additional questions from the generating AI. Specifically, users can ask additional questions about multiple documents found through their initial question, and obtain answers to those documents from the generating AI.

[0097] (Note 13) The program as described in Appendix 12, wherein the processor performs an extraction step (S102) in which it extracts portions related to the second question from one or more documents searched in the document search step, and the generation step (S109) is a step in which it generates a prompt based on the second question received in the question reception step and the portions related to the question from one or more documents extracted in the extraction step. This allows the system to filter out irrelevant sections of multiple documents in the search results and generate prompts based only on the relevant sections. By filtering out irrelevant sections, the quality of the AI-generated answers can be improved.

[0098] (Note 14) The document presentation step (S103) is a program according to Appendix 2 or 3, which includes a step of controlling the presentation order when presenting one or more documents in response to a selection operation by the user in the document selection step. This allows for control over the weighting (importance, score) of multiple patent documents presented based on user selections. For example, patent documents selected by a large number of users can be given higher importance and displayed in a more prominent position during document presentation. Conversely, patent documents excluded by a large number of users can be given lower importance and less likely to be presented during document presentation.

[0099] (Note 15) A method to be performed on a computer comprising a processor and memory, wherein the processor performs all steps performed in any of the inventions described in Appendix 1 to Appendix 13. This allows the system to generate prompts that prompt the AI ​​to create an appropriate answer to a user's question, based on one or more documents containing legal opinions.

[0100] (Note 16) An information processing apparatus comprising a control unit and a storage unit, wherein the control unit performs all steps performed in the invention according to any of the appendices 1 to 13. This allows the system to generate prompts that prompt the AI ​​to create an appropriate answer to a user's question, based on one or more documents containing legal opinions.

[0101] (Note 17) A system comprising means for performing all steps performed in any of the inventions described in Appendix 1 to Appendix 13. This allows the system to generate prompts that prompt the AI ​​to create an appropriate answer to a user's question, based on one or more documents containing legal opinions. [Explanation of symbols]

[0102] 1 System, 10 Servers, 101 Memory Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminals, 201 Memory Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 50 Generating AI, 501 Memory Unit, 504 Control Unit, 506 Input Device, 508 Output Device

Claims

1. A program to be executed by a computer having a processor and a memory unit, The aforementioned processor, A question reception step for receiving questions from users, A document search step, based on the question received in the question reception step, searches for one or more documents that contain legal opinions that may be helpful in answering the question; A generation step that generates a prompt based on the question received in the question receiving step and one or more documents retrieved in the document search step, A program that executes this task.

2. The aforementioned processor, A document presentation step in which one or more documents found in the document search step are presented to the user, A document selection step in which the user selects one or more documents from the one or more documents presented in the document presentation step, Execute, The generation step is a step of generating the prompt based on the question received in the question receiving step and the predetermined one or more documents selected in the document selection step. The program according to claim 1.

3. The aforementioned processor, A document presentation step in which one or more documents found in the document search step are presented to the user, A document selection step in which the user selects one or more documents from the one or more documents presented in the document presentation step, Execute, The generation step is a step of generating the prompt based on the question received in the question receiving step and the documents obtained by excluding the predetermined one or more documents selected in the document selection step from the one or more documents retrieved in the document search step. The program according to claim 1.

4. The aforementioned processor, A document presentation step in which one or more documents found in the document search step are presented to the user, Execute, The document presentation step is a step of presenting to the user information indicating the section related to the question for each of the one or more documents found in the document search step. The program according to claim 1.

5. The aforementioned processor, A document presentation step in which one or more documents found in the document search step are presented to the user, Execute, The document presentation step is a step of presenting to the user information relating to the reason for the question, associated with each of the one or more documents found in the document search step. The program according to claim 1.

6. The aforementioned processor, A document presentation step in which one or more documents found in the document search step are presented to the user, Execute, The document presentation step is a step of presenting to the user one or more reference documents related to each of the one or more documents found in the document search step, in association with each of them. The program according to claim 1.

7. The aforementioned processor, An extraction step is performed to extract portions related to the question from one or more documents found in the document search step, Execute, The generation step is a step of generating the prompt based on the question received in the question receiving step and the portion of the one or more documents extracted in the extraction step that is related to the question. The program according to claim 1.

8. The aforementioned document includes at least one of the following: a court case, an explanatory article on a court case, and a legal book. The program according to claim 1.

9. The aforementioned processor, The response acquisition step involves inputting the prompt generated in the generation step into the generating AI to obtain the response content to the prompt, A report creation step, which creates a report on the questions received in the question reception step, based on the answers obtained in the answer acquisition step, A report presentation step in which the report created in the report creation step is presented to the user, Execute The program according to claim 1.

10. The report creation step involves creating a report that includes an analysis comparing the similarities or differences between the multiple documents found in the document search step. The program according to claim 9.

11. The report preparation step is to prepare the report in response to the question based on one or more reference documents related to each of the multiple documents retrieved in the document search step. The program according to claim 9.

12. The aforementioned question reception step includes a step of receiving a second question from the user after presenting the report to the user in the report presentation step, The generation step includes generating the prompt based on the second question and one or more documents retrieved in the document search step. The program according to claim 9.

13. The aforementioned processor, An extraction step is performed to extract portions of the one or more documents found in the document search step that are relevant to the second question, Execute, The generation step is a step of generating the prompt based on the second question received in the question receiving step and the portion of the one or more documents extracted in the extraction step that is related to the question. The program according to claim 12.

14. The document presentation step includes a step of controlling the presentation order when presenting one or more documents in response to the selection operation by the user in the document selection step. The program according to claim 2 or 3.

15. A method to be performed on a computer comprising a processor and memory, wherein the processor performs all steps performed in any of the inventions according to claims 1 to 13.

16. An information processing apparatus comprising a control unit and a storage unit, wherein the control unit performs all steps performed in the invention according to any one of claims 1 to 13.

17. A system comprising means for performing all steps performed in the invention according to any one of claims 1 to 13.

Images