Program, method, information processing apparatus

Abstract

In making legal judgments, there is a need for a technology that can make it even easier to identify the applicable laws and regulations, thereby making it even easier to conduct examinations and draw conclusions from a legal perspective. 【Solution means】The storage unit holds information on a plurality of contents related to laws. The program causes one or more computer processors to execute steps of: receiving an input of a question related to a law from a user; searching for information on a plurality of contents related to the law based on the input question; identifying information on the laws and regulations cited in the retrieved search result contents; and presenting the identified information on the laws and regulations to the user.

Description

Technical Field

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

Background Art

[0002] Various stakeholders, such as ordinary consumers and businesses, are conducting procedures based on laws. Users in various positions, such as experts like lawyers and employees of business companies, are conducting searches to investigate documents and collect judgment materials in order to make decisions based on legal perspectives. Furthermore, judgments are being made based on legal perspectives regarding specific events, such as matters to be specified in the terms of use and the evaluation of the propriety of customer attraction measures implemented along with the provision of services. Therefore, the investigation that is the premise of the judgment is important.

[0003] Patent Document 1 points out regarding document search that "document corpora including legal documents, patent documents, medical journals, etc. are searched using query expressions. ··· In many cases, when a user investigates a specific topic, the user can create multiple search queries. However, it may be difficult for the user to efficiently determine which search query will yield the most relevant search results and how completely that search query searches the specific topic. Therefore, many users may not trust their own document corpus searches and may believe that the generated search results are of low reliability or that the generated search results are not sufficiently complete."

[0004] Patent Document 1 focuses on presenting search results as described above and poses as an issue that "another method is needed to graphically display electronic document searches to improve the electronic document search experience."

[0005] Patent Document 1 describes "generating a Venn diagram including a first circle representing a first document set and a second circle representing a second document set and displaying it on a graphic display device", "the first circle overlapping the second circle in an overlapping area representing common electronic documents existing in the first document set and the second document set", "the sizes of the first circle and the second circle respectively reflecting the number of electronic documents in the first document set and the second document set", "the first circle overlapping the second circle in an overlapping area representing common electronic documents existing in the first document set and the second document set", and "responding to user input to show the separation of the first circle and the second circle on the graphic display device and generating a first visualization chart from the first circle and a second visualization chart from the second circle".

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] On the other hand, even when a responder who answers legal consultations from customers or within a business company tries to answer a question from the consulter, it may not be easy to identify the applicable laws from the content of the question. The provisions of the laws themselves are often defined in abstract language, and for specific cases related to the question, it may not be possible to obtain the provisions of the laws through a search. Therefore, it is necessary to go through the procedure of identifying the applicable laws and provisions after specifying a specific case through investigation, and the burden of investigation is large. In particular, when the responder is unfamiliar with the field, the work burden such as case investigation tends to be required.

[0008] Therefore, in making a judgment based on the law, there is a need for a technology that can make it even easier to identify the applicable laws and regulations, and thus make it even easier to conduct examinations and draw conclusions from a legal perspective.

Means for Solving the Problem

[0009] According to one embodiment shown in the present disclosure, there is provided a program for operating a computer including one or more computer processors. In a storage unit, information on a plurality of contents related to the law is held. The program causes the one or more computer processors to execute steps of: receiving an input of a question related to the law from a user; searching for information on a plurality of contents related to the law based on the input question; identifying information on laws and regulations cited in the searched search result contents; and presenting the identified information on laws and regulations to the user.

Advantages of the Invention

[0010] According to the present disclosure, in making a judgment based on the law, it is possible to make it even easier to identify the applicable laws and regulations, and thus make it even easier to conduct examinations and draw conclusions from a legal perspective.

Brief Description of the Drawings

[0011]

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

Mode for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following description, the same parts are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated.

[0013] <Outline of Embodiment> In the first embodiment, for content related to laws, a method for generating a data structure that defines a reference relationship among these contents based on the text (names of laws and the like) included in statutes, case laws, legal books, and legal guidelines, and a method for generating an answer to a user's question using the graph-type data structure generated thereby will be described.

[0014] <1.1 Overall system configuration diagram> FIG. 1 is a diagram showing the configuration of system 1.

[0015] The system 1 shown in FIG. 1 includes a server 20, a user's terminal 10, a server 91 for case law search service, a server 92 for statute search service, a server 93 for book browsing service, a server 94 for information media service, a server 95 for artificial intelligence (large language model) service (hereinafter sometimes referred to as "server 95 for large language model service"), a server 96 of a business operator, a server 97 of an SNS, and a user's terminal 10A. These devices are communicatively connected via a network 80.

[0016] In the illustrated example, terminals such as terminal 10 and terminal 10A are shown as the terminals used by the users of the services provided by server 20, but each user is operating a terminal.

[0017] In the present embodiment, each device (terminal device, server, etc.) can also be regarded as an information processing device. That is, the aggregate of each device can be regarded as one "information processing device", and the system 1 may be formed as an aggregate of a plurality of devices. The way of distributing the plurality of functions required to implement the system 1 according to the present embodiment for one or a plurality of hardware can be appropriately determined in view of the processing capabilities of each hardware and / or the specifications required for the system 1.

[0018] The terminal 10 is a device operated by the user. In this embodiment, it is assumed that the user who conducts investigations, makes judgments, etc. regarding laws operates the terminal 10. The terminal 10 and the terminal 10A have the same functional configuration. The terminal 10 is realized, for example, as follows. · Handheld mobile terminals such as smartphones and tablets · Desktop PCs (Personal Computers), laptop PCs · Wearable terminals (such as wristwatch type, glasses type, etc.) worn by the user The terminal 10 includes a communication IF (Interface) 12, an input device 13, an output device 14, a memory 15, a storage 16, and a processor 19.

[0019] The communication IF 12 is an interface for inputting and outputting signals so that the terminal 10 can communicate with external devices.

[0020] The input device 13 is a device for receiving input operations from the user (for example, pointing devices such as touch panels, touch pads, mice, keyboards, etc.).

[0021] The output device 14 is a device for presenting information to the user (displays, speakers, etc.).

[0022] The memory 15 is for temporarily storing programs and data processed by programs and the like, and is, for example, a volatile memory such as DRAM (Dynamic Random Access Memory).

[0023] The storage 16 is for storing data, and is, for example, a flash memory or an HDD (Hard Disc Drive).

[0024] The processor 19 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0025] The server 20 is a device for providing a service to a user that receives a legal question, presents a plurality of contents related to the relevant law in response to the question, and answers the question. In the present embodiment, the server 20 receives an input of a legal question in free text in a chat format from the user of the terminal 10, and outputs an answer to the received question content. When generating an answer to the question, the server 20 may cause the server 95 of the artificial intelligence (large language model) service to generate an answer, and provide the service by responding to the user with the generation result.

[0026] In the present embodiment, the server 20 provides a service to the user as follows. · Users who perform legal work, such as the legal department of a business company, etc., and answer legal consultations. · Users who do not necessarily specialize in legal work, such as the business department of a business company, etc. · Users who, like a law firm, etc., provide legal consultations to clients as a professional service. The server 20 may receive a request for a legal consultation from a client to an expert by matching users who perform legal consultation services as professionals, such as a law firm, etc., with users who request legal consultations from professionals such as lawyers, such as business companies or individuals. For example, it may be in a form where the consultation content of the person consulting is reflected on a bulletin board that can be viewed by a third party, and the answer of the expert is also made public, or it may be in a form where the consultation content of the person consulting is not disclosed to a third party and is in a non-public state, and consultations can be conducted with the expert. The server 20 may accumulate such consultation content of the client and the answer content of the expert.

[0027] The server 20 includes a communication IF 22, an input / output IF 23, a memory 25, a storage 26, and a processor 29.

[0028] The communication IF 22 is an interface for inputting and outputting signals for the server 20 to communicate with an external device.

[0029] The input / output IF 23 functions as an interface between an input device for receiving input operations from the user and an output device for presenting information to the user.

[0030] The memory 25 is for temporarily storing programs and data processed by programs, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0031] The storage 26 is for storing data, and is, for example, a flash memory or an HDD (Hard Disc Drive).

[0032] The processor 29 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0033] The server 91 of the case search service has a case database and enables the user to search for judgments made by courts, etc.

[0034] The server 92 of the statute search service has a statute database and enables the user to search for statutes.

[0035] The server 93 of the book viewing service is a service that enables viewing of electronic contents such as magazines and books. For example, by the user paying a fixed fee periodically, electronic books in the legal field, etc. can be viewed.

[0036] The server 94 of the information media service provides a service for providing information, and is a service that, for example, collects and enables viewing of blog posts, Q&A sites, news articles, IR information, etc. The server 94 of the information media service accumulates information on guidelines of government agencies, etc. prepared for publicizing interpretations based on statutes and operation rules.

[0037] The server 95 of the large language model service is a server that executes language processing tasks using a language model constructed by learning processing including artificial intelligence (AI). An LLM (Large Language Model) has pre-learned a large amount of data (such as text data), for example, Web content on the Internet, or data accumulated in a predetermined database, and can execute various language processing tasks by being given a task.

[0038] The server 95 of the large language model service receives input of prompts by text, image, voice, etc., and generates and responds to an answer to the prompt. Examples of LLM include GPT-3 and GPT-4 developed by OpenAI, BERT developed by Google, etc.

[0039] The server 96 of the business operator is for the business operator to conduct business activities and accumulate data generated along with the business. These data have viewing permissions set, and the viewing availability is set according to the data for users belonging to the business operator and external users not belonging to the business operator.

[0040] The server 97 of the SNS provides a service that promotes communication between users, for example, a service where the content posted by each user can be viewed mutually. For example, there are services that can be viewed by Internet search, etc. even without having a user account on the SNS, and services where the posts of each user can be viewed when having a user account.

[0041] <1.2 Functional Configuration of Server 20> FIG. 2 is a diagram showing the configuration of the server 20. As shown in FIG. 2, the server 20 exhibits functions as a communication unit 201, a storage unit 202, and a control unit 203.

[0042] The communication unit 201 performs processing for the server 20 to communicate with an external device.

[0043] The storage unit 202 stores various databases such as a user database 211, a legal content database 212, a content usage history database 213, a graph-type data structure 214, a prompt database 218, and a legal term database 219.

[0044] The user database 211 is a database that manages information of each user. Details will be described later.

[0045] The legal content database 212 is a database that holds information of legal-related content. Details will be described later.

[0046] The content usage history database 213 is a database of the history of users' use of legal-related content. Details will be described later.

[0047] The graph-type data structure 214 illustrates a graph-type data structure in which a reference relationship is defined for a part of each content.

[0048] The prompt database 218 is a database that manages templates of prompts to be sent to the server 95 of the large language model service.

[0049] The legal term database 219 is a database of legal terms. Examples of legal terms include names of each argument shown in laws and regulations ("claim", "debt", "damages", "risk bearing", etc.), terms shown in case laws, and the like.

[0050] The control unit 203 is realized by the processor 29 reading a program stored in the storage unit 202 and executing instructions included in the program. By operating according to the program, the control unit 203 exhibits functions shown as a reception control module 2041, a transmission control module 2042, a user management module 2043, a question processing module 2044, an LLM utilization module 2045, and a data structure definition module 2046.

[0051] The reception control module 2041 controls the process in which the server 20 receives signals from an external device according to a communication protocol.

[0052] The transmission control module 2042 controls the process in which the server 20 transmits signals to an external device according to a communication protocol.

[0053] The user management module 2043 is a module for managing information of each user who uses the system 1. Specifically, the user management module 2043 receives registration of each user's information and updates the user database 211.

[0054] The question processing module 2044 is a program module that generates an answer to a question input by a user while searching for the content managed in the legal content database 212 based on the graph-type data structure 214.

[0055] The LLM utilization module 2045 is a program module that generates a prompt and transmits the generated prompt to the server 95 of the large language model service to generate a response to the prompt.

[0056] The data structure definition module 2046 is a program module that defines the graph-type data structure 214 based on the content managed in the legal content database 212.

[0057] <1.3 Configuration of the Terminal 10> FIG. 3 is a diagram showing the configuration of the terminal 10.

[0058] As shown in FIG. 3, the terminal 10 includes a plurality of antennas (antenna 111, antenna 112), a communication unit corresponding to each antenna (first communication unit 120, second communication unit 121), an input device 130 (including a touch-sensitive device 131), a display 132, an audio processing unit 140, a microphone 141, a speaker 142, a position information sensor 150, a camera 160, a motion sensor 170, a storage unit 180, and a control unit 190. The terminal 10 also has functions and configurations not particularly shown in FIG. 3 (for example, a battery for holding power, a power supply circuit for controlling the supply of power from the battery to each circuit, etc.). As shown in FIG. 3, each block included in the terminal 10 is electrically connected by a bus or the like.

[0059] The antenna 111 radiates the signal emitted by the terminal 10 as a radio wave. Also, the antenna 111 receives a radio wave from space and supplies the received signal to the first communication unit 120.

[0060] The antenna 112 radiates the signal emitted by the terminal 10 as a radio wave. Also, the antenna 112 receives a radio wave from space and supplies the received signal to the second communication unit 121.

[0061] The first communication unit 120 performs modulation / demodulation processing and the like for transmitting and receiving signals via the antenna 111 so that the terminal 10 communicates with other wireless devices. The second communication unit 121 performs modulation / demodulation processing and the like for transmitting and receiving signals via the antenna 112 so that the terminal 10 communicates with other wireless devices. The first communication unit 120 and the second communication unit 121 are communication modules including a tuner, an RSSI (Received Signal Strength Indicator) calculation circuit, a CRC (Cyclic Redundancy Check) calculation circuit, a high-frequency circuit, and the like. The first communication unit 120 and the second communication unit 121 perform modulation / demodulation, frequency conversion, etc. of the wireless signals transmitted and received by the terminal 10, and supply the received signals to the control unit 190.

[0062] The input device 130 has a mechanism for receiving a user's input operation. Specifically, the input device 130 is configured as a touch screen and includes a touch-sensitive device 131. The touch-sensitive device 131 receives the input operation of the user of the terminal 10. The touch-sensitive device 131 detects the contact position of the user on the touch panel, for example, by using a capacitive touch panel. The touch-sensitive device 131 outputs a signal indicating the contact position of the user detected by the touch panel to the control unit 190 as an input operation.

[0063] The display 132 displays data such as images, videos, and texts according to the control of the control unit 190. The display 132 is realized by, for example, an LCD, an organic EL display, or the like.

[0064] The audio processing unit 140 performs modulation and demodulation of audio signals. The audio processing unit 140 modulates the signal given from the microphone 141 and gives the modulated signal to the control unit 190. Also, the audio processing unit 140 gives the audio signal to the speaker 142. The audio processing unit 140 is realized by, for example, a processor for audio processing. The microphone 141 receives an audio input and gives an audio signal corresponding to the audio input to the audio processing unit 140. The speaker 142 converts the audio signal given from the audio processing unit 140 into audio and outputs the audio to the outside of the terminal 10.

[0065] The position information sensor 150 is a sensor that detects the position of the terminal 10 and is, for example, a GPS (Global Positioning System) module. The GPS module is a receiving device used in a satellite positioning system. In the satellite positioning system, signals from at least three or four satellites are received, and based on the received signals, the current position of the terminal 10 equipped with the GPS module is detected.

[0066] The camera 160 is a device that receives light by a light-receiving element and outputs it as a captured image. The camera 160 is, for example, a depth camera that can detect the distance from the camera 160 to the object to be photographed.

[0067] The motion sensor 170 includes an acceleration sensor, an angular velocity sensor, etc., and detects the movement of the terminal 10.

[0068] The storage unit 180 is composed of, for example, a flash memory, etc., and stores data and programs used by the terminal 10. Various information stored in the storage unit 180 will be described later.

[0069] The control unit 190 reads the program stored in the storage unit 180 and executes the instructions included in the program, thereby controlling the operation of the terminal 10. The control unit 190 is, for example, an application processor. The control unit 190 functions as an operation reception unit 191, a transmission / reception unit 192, a data processing unit 193, a notification control unit 194, and a storage control unit 195 by operating according to the program.

[0070] The operation reception unit 191 performs processing to receive a user's input operation on an input device such as the touch-sensitive device 131. Based on the information of the coordinates where the user touches the touch-sensitive device 131 with a finger or the like, the operation reception unit 191 determines the type of operation, such as whether the user's operation is a flick operation, a tap operation, a drag (swipe) operation, etc.

[0071] The transmission / reception unit 192 performs processing for the terminal 10 to transmit and receive data to and from an external device such as the server 20 according to a communication protocol.

[0072] The data processing unit 193 performs processing to perform an operation on the data input by the terminal 10 according to a program and output the operation result to a memory or the like.

[0073] The notification control unit 194 performs processes for causing the display image to be displayed on the display 132, causing sound to be output from the speaker 142, and generating vibration.

[0074] The memory control unit 195 controls the storage of data in the memory unit 180.

[0075] Explanation will be given about various information stored in the memory unit 180. In a certain aspect, the memory unit 180 stores each information such as user information 181.

[0076] The user information 181 is information of a user who uses the service of the server 20.

[0077] <2 Data Structure> FIG. 4 is a diagram showing the data structure of the user database 211. The user database 211 includes an item “user ID”, an item “name”, an item “email address”, an item “business operator ID”, an item “affiliated department”, an item “position”, an item “date of joining the company”, an item “date of leaving the company”, and an item “held qualifications”.

[0078] The item “user ID” is information for identifying each user.

[0079] The item “name” is information indicating the name of the user.

[0080] The item “email address” is information of the email address as the contact information of the user.

[0081] Specifically, the item “email address” includes the email address information as information for identifying the user for accepting the user's login to the service provided by the server 20.

[0082] The item “business operator ID” is information for identifying the organization to which the user belongs.

[0083] Specifically, as information for identifying the organization to which the user belongs, the following organizations may exist for the item “business operator ID”. · Business company · Law firm The item "Department" is information about the department to which the user belongs.

[0084] Specifically, the item "Department" may include the following information as the department to which the user belongs. · Departments such as the legal department, where legal work is expected to be carried out · Departments such as the business department and the sales department, where it is not planned to exclusively carry out legal work The item "Position" is information about the user's position.

[0085] Specifically, the item "Position" may include the following information as the user's position. · Positions with decision-making power (such as the management level) · Positions without decision-making power but indicating expertise, roles assisting management departments, etc. · Not holding a position The item "Date of joining the company" is information about the date when the user became a member of the organization.

[0086] Specifically, the item "Date of joining the company" may include the following information. · Start date when already belonging · Date when not yet belonging but planned to belong (since the date of joining is determined but has not arrived, the viewing permission for organizational information may not be assigned) · Belonging but the date is not determined (it may be in the process of adjusting the date of joining) The item "Date of leaving the company" is information about the date when the user left the organization and resigned.

[0087] Specifically, the item "Date of leaving the company" may include the following information. · Date of leaving (accompanying the departure, the viewing permission for organizational information may be lost) · Currently employed The item "Held qualifications" is information indicating the qualifications held by the user.

[0088] Specifically, the item "held qualification" can be qualifications such as the following as information for identifying the qualifications held by the user. · As qualifications indicating expertise, national qualifications such as lawyers, patent attorneys, and certified public accountants · As qualifications indicating expertise, qualifications recognized by organizations such as businesses and general incorporated associations Figure 5 is a diagram showing the data structure of the legal content database 212.

[0089] The item "content ID" is information for identifying each piece of content related to the law.

[0090] The item "type" is information on the type of each piece of content related to the law.

[0091] The item "type" may include the following as the type of content related to the law. · Statutes · Case law · Books on law · Websites on which legal information is posted The item "information source" is information on the information source from which the content is provided.

[0092] The item "information source" may include the following as the information source. · Server 92 of the statute search service · Server 91 of the case law search service · Server 93 of the book viewing service that provides the ability to view books on law · Server 94 of the information media service that is a website on which legal information is posted The item "title" is information on the name of the content.

[0093] The item "title" may include the following as the name of the content. · In the case of statutes, the name of the statute, the article number, the heading attached to the article, etc. · In the case of case law, the case number, the name of the case, etc. · In the case of books on law, the title of the book, etc. · In the case of guidelines related to laws, the name of the guidelines, etc. The item "content tag" is information on the name of the tag attached to the content.

[0094] The item "content tag" may include the following as information on the tag attached to the content. · A tag representing the content of the content, extracted by having the server 95 of the large language model service summarize the data indicating the content of the content in keywords, within a certain number of characters, etc. · The server 20 holds a list of tags assigned in advance to the entire content, and based on the content of the content, a tag specified by the server 95 of the large language model service, etc. from the tags included in the list. The item "data" is information on the data file of the content.

[0095] The item "tagging location" is information on the location where the tag is set at an arbitrary location in the data constituting the content, using the names of laws, precedents, books on laws, guidelines on laws, etc. as tags.

[0096] The item "tagging location" may include the following as the location where the tag is set. · In the case of laws, the tag may be set in association with the number of a specific article, etc. · In the case of precedents, while dividing the judgment text into multiple blocks by paragraphs, item headings, the claims of both parties, the locations of the court's findings for each argument, etc. constituting the judgment text, the tag may be set at an arbitrary location in the text within the block. · In the case of books on laws, while dividing the book into multiple blocks in units of chapters, item headings, paragraphs, etc., the tag may be set at an arbitrary location in the text within the block. · In the case of guidelines on laws, while dividing the guideline text into multiple blocks in the same manner as above, the tag may be set at an arbitrary location in the text within the block. For example, if the server 20 finds names such as the name of a statute, the name of an article, the number of a judicial precedent, etc. in a book related to law, it may set a tag on the part where the name is described.

[0097] The item "Name Tag" is information about the name of the set tag.

[0098] The item "Name Tag" may include the following as tags attached to names. · Names such as the name of a statute and the number of an article · Names such as the case number of a judicial precedent · The title of a book related to law · The name of a guideline related to law The item "Name Tag Score" is information about the evaluation result of a tag indicating a name.

[0099] More specifically, in the item "Name Tag Score", in various services provided by the server 92 of the statute search service, the server 91 of the judicial precedent search service, the server 93 of the book browsing service, the server 94 of the information media service, etc., the tag and the content are associated, and the tag is evaluated according to the history of content browsing based on the tag.

[0100] The server 20 uses the result of evaluating the tag for the name in this way to determine the priority of the tag corresponding to the search term when the user searches (for example, the higher the evaluation, the higher the priority as the tag corresponding to the user's search), and may search for law-related content based on the tag with the highest priority.

[0101] The item "Name Tag Associated Content ID" is information for identifying content that defines a reference relationship based on the location where the tag is set when the same tag is set in multiple contents for the tag set in the item "Name Tag".

[0102] In the illustrated example, the item "Name Tag - Associated Content ID" indicates the result of defining a reference relationship among contents each containing the name of a specific statute in the contents related to multiple laws.

[0103] The item "Argument Tagging Location" is information on the location where a tag is set at any location in the data constituting the content, using an argument related to the law as the tag.

[0104] The item "Argument Tag" is information on the name of the tag of the set argument.

[0105] The item "Argument Tag Score" is information on the evaluation result for the tag indicating the argument.

[0106] More specifically, in the item "Argument Tag Score", in the server 93 of the book browsing service or the like, books related to the law are classified for each argument, and when an operation to search for books to be browsed based on the argument is received, and the user browses books related to the law according to the search result history or the like, the tag of the argument is evaluated.

[0107] The item "Argument Tag - Associated Content ID" is information for identifying the content that defines a reference relationship based on the location where the tag is set when the same tag is set in multiple contents for the argument tag set in the item "Argument Tag".

[0108] Figure 6 is a diagram showing the data structure of the content usage history database 213.

[0109] The item "Search ID" is information for identifying each search conducted to use the content related to the law.

[0110] The item "Search User ID" is information for identifying the user who searched for the content related to the law.

[0111] The item "Search User ID" may be associated with the item "User ID" in the user database 211.

[0112] The item "Search Term" is information on the search terms used for content search.

[0113] More specifically, the item "Search Term" is a word specified by the user, or a sentence such as a sentence in which the user enters a question in natural language.

[0114] The item "Search Argument Tag" is information on the name of the argument tag set for the search terms entered by the user for search.

[0115] More specifically, the item "Search Argument Tag" is an argument tag extracted by matching the search terms entered by the user with a list of argument tags, or is set with information on legal arguments by a server 95 such as a large language model service.

[0116] The item "Search Date and Time" is information on the timing of the search.

[0117] The item "Information Source" is information on the database that is referred to in response to the user's operation of searching for content.

[0118] The item "Information Source" may include the following as the database referred to by the search: · Server 92 of the statute search service · Server 91 of the case law search service · Server 93 of the book browsing service · Server 94 of the information media service The item "Viewed Content ID" is information for identifying the content viewed by the user.

[0119] The item "Viewed Content ID" may be associated with the item "Content ID" in the legal content database 212.

[0120] The item "Content viewing location" is information on the location where the user viewed the content.

[0121] More specifically, in the case of a book related to law, the item "Content viewing location" is information on the location (page. It may be a page where the viewing time was a certain amount or more) that the user viewed in the book.

[0122] Figure 7 is a diagram showing the data structure of the graph-type data structure 214.

[0123] In the example shown in Figure 7, it shows that information on a coherent text 214A including the location included in Document A (for example, a law book) regarding a specific article of a statute is held in the legal content database 212 in association with Document A. Similarly, it shows that information on a coherent text 214B including the location included in Document B (for example, a guideline) regarding a specific article of a statute is held in the legal content database 212 in association with Document B.

[0124] Here, in the illustrated example, it shows that a reference relationship (edge) is defined between parts (text 214A, text 214B) that include the same article of a statute in Document A and Document B. In this way, the data structure definition module 2046 generates a graph-type data structure 214 by defining nodes as the locations where names such as statutes, case laws, law books, and guidelines are included for a plurality of contents in the legal content database 212, and defining nodes and edges based on the names. The illustrated example shows an example of defining a reference relationship for two documents, Document A and Document B, but it is not limited to two.

[0125] <3 Operations (First Embodiment)> Figure 8 is a diagram showing the flow of a process for creating a graph database using information on a plurality of contents related to law.

[0126] In step S821, the data structure definition module 2046 of the server 20 obtains information on content related to laws and information that can be a tagging candidate by referring to the legal content database 212, the legal term database 219, and the like.

[0127] In this way, the server 20 causes the legal content database 212 of the storage unit 202 to hold information on a plurality of contents related to laws.

[0128] In step S823, the data structure definition module 2046 of the server 20 identifies a part included in the content related to laws that includes information for identifying a statute, information for identifying a precedent, information for identifying a legal book, and information for identifying guidelines related to laws.

[0129] In this way, the data structure definition module 2046 identifies, in each of a plurality of contents related to laws, information for identifying a statute, information for identifying a precedent, information for identifying a legal book, information for identifying guidelines related to laws, at least a part that includes any of them.

[0130] More specifically, the data structure definition module 2046 may identify, as information for identifying a statute, at least any of the name of the statute or the article, as information for identifying a precedent, the number of the precedent, as information for identifying a legal book, the title of the legal book, as information for identifying guidelines related to laws, the name of the guidelines, at least a part that includes any of them.

[0131] More specifically, the data structure definition module 2046 may identify, as information for identifying a statute, at least any of the name of the statute or the article, As information for specifying a precedent, the number of the precedent, As information for specifying a legal book, the title of the legal book, As information for specifying guidelines regarding laws, the name of the guidelines, It may also be to specify, as a part, a certain amount of text including at least any one of them.

[0132] In step S825, the data structure definition module 2046 of the server 20 associates a part specified for the content with the content and stores it in the legal content database 212.

[0133] In this way, the data structure definition module 2046 stores the part specified in step S823 in the storage unit 202 in association with the content related to the specification.

[0134] Here, the data structure definition module 2046 may evaluate a part according to the usage status of search results in a service (such as server 91 of the case search service, server 92 of the statute search service, server 93 of the book browsing service, server 94 of the information media service, etc.) that receives an operation of searching for content based on a part associated with the content. For example, for tags associated with content, the tags may be evaluated according to the performance of searching for the tags in the above book browsing service (such as the degree to which the tags are searched, the degree to which books are browsed based on the search results by the tags, the tags that are frequently searched, and the tags with higher evaluation values for the tags for which books are browsed by the search according to the tags). The data structure definition module 2046 may store the evaluation result obtained by evaluating a part in the legal content database 212 in association with the content (for example, item "name tag score"). For example, when identifying tags corresponding to a user's question in a database with a graph structure, the server 20 may select tags according to the evaluation values (such as giving priority to tags with higher evaluation values as tags corresponding to the user's question), and may search the database with the graph structure using the selected tags. Thereby, while improving the response of the search based on tags with a graph structure compared to the case of searching each content included in the legal content database 212 with keywords, the accuracy of the search results (presentation of legal content suitable for the user) can be further improved.

[0135] Through the processing of steps S823 and S825 above, while identifying the locations where the name is described by the name of the statute, the name of the case, the name of the book, the name of the guideline, etc., tags based on these names can be assigned to the content.

[0136] In step S827, the data structure definition module 2046 of the server 20 extracts parts of the same type specified for a plurality of contents. The data structure definition module 2046 defines a reference relationship for the parts extracted on the assumption that each content includes parts of the same type.

[0137] More specifically, in defining the reference relationship, the data structure definition module 2046 may also define the reference relationship between contents by extracting, for a plurality of contents, those with the same name for a specific part, where a part of the plurality of contents is of the same type.

[0138] For example, when the same case number is described in the first e-book and the second e-book, the location where the case number is described in the first e-book and the location where the case number is described in the second e-book are extracted as parts of the same type. The data structure definition module 2046 defines a reference relationship between the extracted locations where the case number is described for the first e-book and the second e-book.

[0139] In this way, the data structure definition module 2046 constructs a graph-structured database by extracting, for a plurality of contents, parts where a specific part is of the same type, and defining the reference relationship between the extracted contents. For example, the data structure definition module 2046 may also store the reference relationship defined for a plurality of contents in the legal content database 212.

[0140] Here, the data structure definition module 2046 may also define the reference relationship between parts that are a certain amount of text of a plurality of contents.

[0141] As a result, for a plurality of contents, when the names of laws, regulations, case laws, books, and guidelines are the same among these contents, a graph-type data structure defining a reference relationship between the contents can be generated. For example, when a graph-type data structure is generated based on the name of a law, by searching for the name of the law, search results of a plurality of information sources such as the original text of the law, case laws corresponding to the law, books referring to the law, and guidelines referring to the law can be presented. Since the search is performed using the graph-type data structure, the responsiveness of the search can be further improved as compared with the case of sequentially searching these information sources with the above keywords.

[0142] In step S829, the data structure definition module 2046 of the server 20 outputs information on the reference relationship defined for a plurality of contents to the terminal 10. Note that the data structure definition module 2046 may not output to the terminal 10 or the like after performing the process of defining the reference relationship between the contents, or may present the information on the reference relationship defined for the contents in response to a request from the terminal 10 or the like.

[0143] In step S811, the terminal 10 displays information indicating the reference relationship of the contents.

[0144] FIG. 9 is a diagram showing a processing flow using a graph database related to laws.

[0145] In step S921, the question processing module 2044 of the server 20 receives an input of a question related to laws and outputs an operation screen for displaying an answer to the terminal 10.

[0146] As described above, the server 20 holds the data structures of information on content related to laws (the legal content database 212, the graph-type data structure 214). The server 20 causes the storage unit 202 to hold information on a plurality of contents related to laws. The server 20 causes the storage unit 202 to hold, for each of the plurality of contents, the result of defining the reference relationship between contents for at least a part of the same type among the information specifying statutes, the information specifying case laws, the information specifying legal books, and the information specifying guidelines related to laws.

[0147] In step S911, the terminal 10 receives an input of a question related to a law from the user.

[0148] In step S923, the question processing module 2044 of the server 20 assigns a tag representing the content of the question to the question input by the user of the terminal 10 by the server 95 of the large language model service. For example, the question processing module 2044 generates a prompt including at least one of an instruction to summarize the content of the question input by the user together with the content of the question, an instruction to assign a tag by referring to legal terms such as the legal term database 219 for the content of the question, etc. The question processing module 2044 transmits the prompt to the server 95 of the large language model service by the LLM utilization module 2045, and receives an output result corresponding to the prompt from the server 95 of the large language model service, thereby assigning a tag to the question.

[0149] In step S925, the question processing module 2044 of the server 20 uses the tag assigned to the question to refer to the graph-type data structure 214 and searches for the content to which the tag is assigned. As a result, compared with the case of searching the database of table-type content, the processing required to search for the content to which the tag is assigned can be reduced, and the response speed of the search result can be further improved.

[0150] In step S927, the question processing module 2044 of the server 20 obtains the generated answer by instructing the server 95 of the large language model service to generate an answer to the question based on the search results. Specifically, the question processing module 2044 generates a prompt including the search results (legal content searched based on the tags assigned to the question) retrieved by referring to the graph-type data structure 214 and the question input by the user in steps S911 and S923, and transmits the generated prompt to the server 95 of the large language model service, thereby receiving the answer generated by the server 95 of the large language model service.

[0151] Note that the question processing module 2044 may also output the search results of the content searched in step S925 to the user's terminal 10 without further generating an answer to the question by the server 95 of the large language model service using the search results of the content searched in response to the user's input of a legal question. Thereby, in response to the user's question, the legal content retrieved by the graph-type data structure 214 can be responded to the user, and compared with the case of sequentially searching each data in the database of the table-type content, the processing required for the search can be reduced, and the search results can be responded more quickly.

[0152] In this way, in response to a search request for information on a plurality of legal-related contents, the server 20 identifies a part (tag) corresponding to the search request in the database, and has a data structure 214 of information on legal-related contents used for the process of responding to the search request based on the reference relationship between the contents of the identified part.

[0153] Here, as described above, data related to the data structure is used in a process of receiving an input of a question from a user and responding with search results of a plurality of contents to a search request for retrieving a part corresponding to the question among the plurality of contents based on the reference relationship between the contents of the part in order to generate an answer to the question by the server 95 of the large language model service. An answer to the question is generated by the large language model based on the search results of the plurality of contents and the question from the user.

[0154] In step S929, the server 20 outputs an answer to the question to the terminal 10 based on the tag corresponding to the question.

[0155] In step S913, the terminal 10 displays an answer to the question.

[0156] <4 Screen example (First embodiment)> FIG. 10 is an example screen of an operation screen that displays the result of generating an answer to a user's question while referring to the graph-type data structure 214 related to law.

[0157] The operation screen 1000 is an operation screen that displays the result of searching for statutes, case laws, legal books, guidelines, etc. while referring to the graph-type data structure 214 for a question.

[0158] The operation screen 1000 corresponds to each process such as step S921 in FIG. 9, step S1121 in FIG. 11, step S1321 in FIG. 13, etc.

[0159] The question specifying unit 1002 is an operation member that receives a specification of question content from the user.

[0160] More specifically, the question specifying unit 1002 receives an input of a question from the user in natural language.

[0161] The transmission operation unit 1004 is an operation member that receives an operation of generating an answer to a question input by the user.

[0162] In the illustrated example, the transmission operation unit 1004 transmits the question input to the question specifying unit 1002 to the server 20 in response to a user operation.

[0163] The account display area 1006 is an area for displaying information on the accounts of users who use the services provided by the server 20.

[0164] In the illustrated example, the account display area 1006 displays the user's affiliation, but may also display the user's account fee plan so that differences in functions available according to the fee plan (for example, restrictions on the number of questions that can be input, restrictions on the scope of statutes, case laws, legal books, guidelines, etc. that can be referred to) can be easily recognized.

[0165] The answer display area 1008 is an area for displaying the answer generated by the server 20 for the question input by the user.

[0166] The question content display area 1010 is an area for displaying the content of the question input by the user in the question specifying unit 1002.

[0167] In the illustrated example, the question content display area 1010 displays the question for which the server 20 has generated an answer, so that it is easy to recognize what question the answer is for. For example, each time a question is input and when generating an answer, or when scrolling back through past questions, it is possible to easily confirm the question that is the target of the answer.

[0168] The question tag display area 1012 is an area for displaying the tags assigned to the input question.

[0169] The question tag display area 1012 corresponds to processing such as step S923 in FIG. 9.

[0170] The statute display area 1014 is an area that displays statutes retrieved by referring to the graph-type data structure 214 for the input question.

[0171] In the illustrated example, the statute display area 1014 displays the statute name and article numbers, and arranges a "View Details" button. In response to the user's operation on the "View Details" button, the terminal 10 may display the details of the statute (for example, the original text of the article, etc.) within the operation screen 1000 (for example, expand the area of the statute display area 1014), or may open a separate window to allow the user to view the details of the statute.

[0172] The case display area 1016 is an area that displays cases retrieved by referring to the graph-type data structure 214 for the input question.

[0173] In the illustrated example, the case display area 1016 displays the case number and arranges a "View Details" button. In response to the user's operation on the "View Details" button, the terminal 10 may display the details of the retrieved case (as will be described later, such as the summary of the case in the case) within the operation screen 1000 or the like.

[0174] The legal book display area 1018 is an area that displays legal books retrieved by referring to the graph-type data structure 214 for the input question.

[0175] In the illustrated example, the legal book display area 1018 presents the details of the retrieved legal book to the user (for example, having received the user's operation on "View Details" shown in the statute display area 1014 or the like). In the legal book display area 1018, while displaying an overview such as the name of the book, the publisher, and the author's name, an excerpt of the text of the book is displayed in the book detail display area 1020 or the like, which will be described later.

[0176] The book detail display area 1020 is an area that displays a part of a legal book extracted according to the searched tags for the searched legal book.

[0177] In the illustrated example, the book detail display area 1020 displays a part displayed in the basis display area 1022 described later and the descriptions before and after it. For example, in a legal book, the descriptions may be divided into multiple blocks by chapter headings, paragraphs, etc., and blocks including the descriptions shown in items such as "tagged location" in the legal content database 212 may be extracted.

[0178] The basis display area 1022 is an area that displays the location where there is a description corresponding to the tag in the legal book.

[0179] In the illustrated example, the basis display area 1022 emphasizes (for example, by highlighting with a fluorescent pen, making the text bold, etc.) the text shown in the item "tagged location" of the legal content database 212, so that it can be easily determined that it is the location of the description of the text corresponding to the tag.

[0180] The guideline display area 1024 is an area that displays the guidelines searched by referring to the graph-type data structure 214 for the input question.

[0181] In the illustrated example, the guideline display area 1024 displays the name of the guideline and arranges a "View Details" button. The terminal 10 may display the details of the case within the operation screen 1000 or the like so as to allow the user to view the details of the searched guideline in response to the user's operation on the "View Details" button.

[0182] <5 Operations (Second Embodiment)> Next, the second embodiment will be described.

[0183] When there is a consultation regarding laws, it may not be easy to identify the applicable laws and regulations from the consultation content when answering the consultation. This is because the provisions of laws and regulations are often defined in abstract terms, and even if search terms are defined and searched based on the consultation content, they may not correspond to the language of the provisions of laws and regulations. Therefore, usually, while searching for cases corresponding to the consultation content, the procedure of identifying the applicable laws and regulations and articles from such cases is sometimes followed. Even for respondents who answer the consultation content, in the case of unfamiliar fields, they will conduct investigations according to the above procedure, which will take time.

[0184] Therefore, in the second embodiment, a technique for receiving an input of natural language and presenting relevant laws and regulations and articles will be described.

[0185] Specifically, in the second embodiment, receiving a question sentence in natural language from the user, having the server 95 of the large language model service identify what law the question is about (for example, a specific law such as the Company Law), previously tagging legal books related to laws, web articles related to laws, etc. (the tagging of such legal books may also be performed by the server 95 of the large language model service), and searching for contents such as legal books where the content of the question sentence matches the tag (searching by keyword, vectorizing the question sentence and the contents such as legal books and searching for vectors of contents related to laws based on the vectors), obtaining the laws and regulations and articles cited in the text of the searched contents, are performed.

[0186] FIG. 11 is a diagram showing the flow of a process of identifying laws corresponding to a user's question and presenting the identified laws to the user.

[0187] In step S1121, the question processing module 2044 of the server 20 outputs an operation screen that receives an input of a question regarding the law and displays an answer to the terminal 10.

[0188] The server 20 holds, in the storage unit 202, at least any one of information on legal books related to the law, guidelines related to the law, and articles in information media related to the law, as information on a plurality of contents related to the law. In the storage unit 202, information on a plurality of legal books is held, and a tag indicating the content of each of the plurality of legal books is associated and held with each legal book.

[0189] For example, the server 20 may set a tag indicating the content of a legal book by referring to the classification (classification input by a human, such as the service operator, the publisher of the book, etc.) set for each book in the server 93 of the book browsing service, or the server 95 of the large language model service may assign a tag indicating the content of the legal book (for example, sending a prompt to summarize the content of the legal book to the server 95 of the large language model service).

[0190] In step S1111, the terminal 10 receives an input of a question regarding the law from the user.

[0191] In step S1123, the question processing module 2044 of the server 20 assigns a tag corresponding to the question to the question input by the user by the server 95 of the large language model service.

[0192] The question processing module 2044 gives a prompt including an instruction to assign a tag related to the law to the question to the server 95 of the large language model service to assign a tag to the question, obtains information on the result of tag assignment output by the server 95 of the large language model service, and assigns a tag to the question based on the obtained information on the result of tag assignment.

[0193] In addition, the question processing module 2044 may input the question entered by the user in step S1111 to a trained model that has been trained to output tags for questions based on the results of tagging the questions, with the understanding that tags will be assigned to the questions.

[0194] In addition, the question processing module 2044 may hold a list of tags to be assigned to a question for the keywords included in the question text, and may assign tags to the question by comparing the question input in step S1111 with the list.

[0195] In step S1125, the question processing module 2044 of the server 20 uses the tags assigned to the question to refer to the database and search for content with the tags.

[0196] In this way, the question processing module 2044 searches for information on a plurality of legal-related contents based on the input question. Here, the question processing module 2044 searches for at least any one of the information such as legal books, legal-related guidelines, and articles in legal information media. The question processing module 2044 may search for legal books based on the tags assigned to the question and the tags associated with the legal books.

[0197] Also, in a service that enables viewing of a plurality of legal books (server 93 of the book viewing service), the scores of the tags associated with the legal books are determined (legal content database 212, content usage history database 213). The question processing module 2044 may search for legal books based on the scores of the tags associated with the legal books. For example, when searching for the tags corresponding to the tags assigned to the question among the tags associated with each legal book in the database, it may be preferable to prioritize those with higher tag scores in the search results.

[0198] As described above, the server 20 causes the storage unit 202 to hold information on a plurality of contents related to laws. In the storage unit 202, for each of the plurality of contents, at least a part including information specifying a statute, information specifying a precedent, information specifying a legal book, or information specifying guidelines related to laws, which are of the same type, is held as a data structure related to laws (legal content database 212, graph-type data structure 214) that defines a reference relationship between the contents. The question processing module 2044 searches for information on a plurality of contents related to laws for a question by referring to the data structure related to laws.

[0199] In step S1127, the question processing module 2044 of the server 20 specifies information on a statute cited in the content of the search result. For example, the question processing module 2044 may search for content based on the tag given to the question and information associated with the legal book held in the legal content database 212 (items such as "title" and "content tag" in the legal content database 212), and specify information on the statute (for example, items "tagged location" and "name tag" in the legal content database 212) included in the searched content.

[0200] In step S1129, the question processing module 2044 of the server 20 presents the specified information on the statute to the user of the terminal 10.

[0201] In step S1113, the terminal 10 displays information on the statute corresponding to the question.

[0202] <6 Screen example (Second embodiment)> FIG. 12 is a screen example of an operation screen for presenting to the user a statute specified as corresponding to the user's question.

[0203] The legal detail display area 1026 is an area that displays a part of a searched law extracted according to the searched tags for the searched law.

[0204] In the illustrated example, the legal detail display area 1026 displays the articles of the law corresponding to the searched tags. For example, the server 20 may display not all of the articles included in the provisions but the articles corresponding to the question.

[0205] The case detail display area 1028 is an area that displays summaries of a plurality of cases extracted according to the searched tags.

[0206] In the illustrated example, the case detail display area 1028 shows the results generated by the server 95 of the large language model service for the summaries of a plurality of cases retrieved by referring to the graph - type data structure 214 according to the tags corresponding to the question (for example, the results of generating the summary of the case by a prompt that generates an outline of the case - related facts and an outline of the conclusion in a predetermined number of characters).

[0207] <7 Operations (Third Embodiment)> Next, the third embodiment will be described.

[0208] Normally, when conducting an investigation related to law, searching for law - related content by keywords lists the content corresponding to the keywords. However, in areas that are unfamiliar especially to the person in charge of the investigation, it is difficult to determine whether the listed content (for example, legal books) is important, and it is necessary to read the content of each of the retrieved individual contents one by one, which is a heavy burden.

[0209] Therefore, in the third embodiment, it accepts the input of a question in natural language and presents the arguments related to the input question to the user. For each argument, it organizes and presents content such as legal books to the user.

[0210] Specifically, in the third embodiment, Constructing a graph - type data structure for the arguments (for each argument in the legal content, for example, the server 95 of the large - language model service may identify the argument of each content. For the argument, legal content such as statutes, case laws, legal books, guidelines, etc. is associated and constructed as a graph - type data structure), Receiving an input of a question in natural language from a user, Identifying the argument corresponding to the question based on a database constructed to hold information on legal content based on the argument (for example, identifying the argument from the keywords included in the question text, vectorizing the question text, and searching for the argument based on the vectors of the legal content). Responding with statutes, case laws, legal books, guidelines, etc. corresponding to the argument based on the argument corresponding to the question and the graph - type data structure for the argument, Do.

[0211] FIG. 13 is a diagram showing the flow of a process of generating a database in which information on legal arguments is identified for information on a plurality of legal - related contents.

[0212] In step S1321, the data structure definition module 2046 of the server 20 obtains information on legal - related contents by referring to the legal content database 212 or the like.

[0213] In this way, the server 20 holds information on a plurality of legal - related contents in the storage unit 202. The server 20 holds at least any one of information on statutes, information on case laws, information on legal books, and information on legal guidelines as information on a plurality of legal - related contents in the storage unit 202.

[0214] In step S1323, the data structure definition module 2046 of the server 20 generates a prompt including an instruction to identify legal arguments corresponding to the content of the law-related content. Further, the data structure definition module 2046 may generate a prompt including an instruction to extract a part of the content that serves as the basis for identifying the legal arguments corresponding to the content of the content.

[0215] In step S1325, the data structure definition module 2046 of the server 20 provides the generated prompt to the server 95 of the large language model service, and obtains, from the server 95 of the large language model service, the result of identifying the legal arguments regarding the content of the content.

[0216] In this way, the data structure definition module 2046 provides the content related to the generation of the prompt and the prompt generated for the content to the server 95 of the large language model service, and receives the output result of the server 95 of the large language model service, thereby obtaining the result of identifying the legal arguments for each content.

[0217] In step S1327, the data structure definition module 2046 of the server 20 updates the legal content database 212 by associating the content with the identified legal arguments.

[0218] Here, the data structure definition module 2046 may also associate a part extracted from the content with the identified legal arguments and store them in the legal content database 212.

[0219] Further, based on the legal arguments associated with the content, evaluate the arguments according to the usage status of the search results in a service (for example, the server 93 of the book browsing service) that receives an operation to search for the content, and store the evaluation result of evaluating the arguments in the legal content database 212 in association with the content (item "argument tag score").

[0220] In step S1329, the data structure definition module 2046 of the server 20 identifies a part of the content related to the same argument for a plurality of contents, defines a reference relationship for the identified part, and updates the database. The data structure definition module 2046 outputs information on the reference relationship defined for the arguments of the plurality of contents to the terminal 10.

[0221] In this way, the data structure definition module 2046 may identify a part of a plurality of contents related to the same argument, define a reference relationship between the identified parts of the plurality of contents, and define a graph-type data structure 214.

[0222] Note that it is not necessary to output to the terminal 10 that the database with the defined reference relationship has been updated. Instead, in response to a request from the terminal 10, it may be sufficient to respond with the situation where the reference relationship is defined in the database.

[0223] In step S1311, the terminal 10 displays information indicating the reference relationship of the content regarding the argument.

[0224] FIG. 14 is a diagram showing the flow of a process of searching for content of an argument corresponding to a user's question based on an argument related to law.

[0225] In step S1421, the question processing module 2044 of the server 20 receives an input of a question related to law and outputs an operation screen for displaying an answer to the terminal 10.

[0226] The server 20 holds information on a plurality of contents related to law in the law content database 212 and the graph-type data structure 214 of the storage unit 202, and holds information on legal arguments in association with each of the plurality of contents.

[0227] The graph-type data structure 214 is used for the process of receiving an input of a legal question from a user, analyzing the input question to identify the argument corresponding to the question, and based on the identified argument, retrieving content related to the law associated with the argument by referring to the information on legal arguments stored in the graph-type data structure 214.

[0228] In the graph-type data structure 214, for each of a plurality of contents, it is configured to associate and store information on legal arguments associated with the content and a part of the content corresponding to the legal argument. In the graph-type data structure 214, a reference relationship is defined between parts of a plurality of contents related to the same argument. As a process in which the graph-type data structure 214 is used, it is used for the process of retrieving a plurality of contents for which a reference relationship is defined for a specified argument based on the reference relationship.

[0229] In step S1411, the terminal 10 receives an input of a legal question from the user.

[0230] In step S1423, the question processing module 2044 of the server 20 identifies the argument corresponding to the input question by analyzing the input question. More specifically, the question processing module 2044 generates a prompt (for example, the prompt may include an instruction to refer to a list of arguments) including an instruction to identify the legal argument for the input question for the input question, and by providing the generated prompt to the server 95 of the large language model service, receives the output result of the server 95 of the large language model service to identify the legal argument for the question.

[0231] In step S1425, the question processing module 2044 of the server 20 uses the argument identified for the question to refer to the legal content database 212 and the graph-type data structure 214 to retrieve the content tagged with the argument.

[0232] In this way, based on the argument corresponding to the specified question, the question processing module 2044 searches for information on content related to the law associated with the argument by referring to the information on legal arguments stored in the storage unit 202.

[0233] In step S1427, the question processing module 2044 of the server 20 outputs to the terminal 10 the search result of the content using the argument tag, including a part corresponding to the argument for these contents (the item "Argument Tagging Location" in the legal content database 212).

[0234] Here, the question processing module 2044 may provide a prompt including the search result of the content using the argument tag and the user's question received in steps S1411 and S1423 to the server 95 of the large language model service, causing the server 95 of the large language model service to generate an answer to the user's question while referring to the search result of the content using the argument tag, and output the generated answer to the terminal 10.

[0235] In step S1413, the terminal 10 displays the search result of the content related to the law together with the argument corresponding to the question.

[0236] <8 Screen Example (Third Embodiment)> FIG. 15 is an example of a screen of an operation screen that responds with the result of searching various databases based on the corresponding legal argument to the user's question.

[0237] The argument display area 1030 is an area for displaying information on the argument corresponding to the question.

[0238] The argument display area 1030 corresponds to the processing such as step S1427 in FIG. 14.

[0239] The argument summary display area 1032 is an area for displaying an overview of the search result retrieved as the argument corresponding to the question.

[0240] In the illustrated example, the argument summary display area 1032 displays information on the arguments retrieved by referring to the graph-type data structure 214 in response to the question, and the results of generating answers by the server 95 of the large language model service based on the search results and the question.

[0241] The individual argument display area 1034 is an area for displaying the details of one of the plurality of arguments.

[0242] The reference document display area 1036 is an area for displaying documents (legal books in the illustrated example) that serve as the basis for the arguments.

[0243] In the illustrated example, the reference document display area 1036 displays a plurality of legal books retrieved corresponding to the tags of the arguments.

[0244] The basis display area 1038 is an area for displaying the locations where there are descriptions corresponding to the argument tags in the legal books.

[0245] The basis display area 1040 is an area for displaying the locations where there are descriptions corresponding to the argument tags in the legal books.

[0246] <Modification example> Each of the embodiments described above may be combined as appropriate.

[0247] Also, each of the embodiments described above may be as follows.

[0248] (1) Information sources for the basis of answers to questions In the description of the above embodiment, a graph-type data structure is defined for laws, precedents, books on law, and guidelines on law, and an example of performing a search using the graph-type data structure for a user's question and outputting an answer including the search results has been described.

[0249] In addition, similar to the information held in the operator's server 96, information that is not necessarily disclosed to an unspecified large number of people can be used to define a graph-type data structure in the same manner as above. Based on this graph-type data structure, information of the same type as that held in the operator's server 96 can be retrieved in response to a query, and an answer to the query can be output. For example, within the operator's company, when there are accumulated results of judgments made based on legal arguments (e.g., based on arguments of the Premiums and Representations Act, etc.) regarding a specific case, it may be possible to present a summary of the cases within the operator's company in the same way as presenting the case precedents such as FIG. 12 above.

[0250] In addition to the above, similar to the SNS server 97, information that can be disclosed to an unspecified large number of people can be used to define a graph-type data structure in the same manner as above, and it may be referred to when answering a user's query. For example, it may be possible to cite as the basis for answering a query the content posted by a specific person's account.

[0251] The network is composed of various mobile communication systems constructed by the Internet, LAN, wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), wireless networks that can be connected to the Internet by a predetermined access point (e.g., Wi-Fi (registered trademark)), etc. When connecting wirelessly, communication protocols such as Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. are included. When connecting by wire, the network also includes those directly connected by a USB (Universal Serial Bus) cable, etc.

[0252] Note that all or part of each hardware configuration can be distributed and provided to a plurality of computers, and by connecting them to each other via a network, a computer can be virtually realized. In this way, a computer is a concept that includes not only a single housing or a computer housed in a case but also a virtualized computer system.

[0253] A database refers to a relational database, which is for managing a table in a tabular form structurally defined by rows and columns and a data set called a master by associating them with each other. In a database, a table is called a table, a master, a column of a table is called a column, and a row of a table is called a record. In a relational database, the relationship between tables and masters can be set and associated.

[0254] Normally, each table and each master are set with a column serving as a primary key for uniquely identifying a record, but setting a primary key for a column is not essential. The control unit can cause the processor 901 to execute addition, deletion, and update of records in a specific table and master stored in the storage unit according to various programs.

[0255] 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.

[0256] 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 any programming language.

[0257] In addition, each of the above-described configurations, functions, processing units, processing means, etc. may be implemented in hardware by designing part or all of them, for example, using an integrated circuit. Further, the present invention can also be realized by a program code of software that realizes the functions of the embodiments. In this case, a storage medium storing the program code is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the program code itself and the storage medium storing the same constitute the present invention. As a storage medium for supplying such a program code, for example, a flexible disk, CD-ROM, DVD-ROM, hard disk, SSD, optical disk, magneto-optical disk, CD-R, magnetic tape, non-volatile memory card, ROM, etc. are used.

[0258] In addition, the program code for realizing the functions described in this embodiment can be implemented in a wide range of programs or script languages such as assembler, C / C++, perl, Shell, PHP, Java (registered trademark), etc.

[0259] Furthermore, by distributing the program code of the software that realizes the functions of the embodiments via a network, it can be stored in a storage means such as a hard disk or memory of a computer or a storage medium such as a CD-RW or CD-R, and a processor included in the computer reads and executes the program code stored in the storage means or the storage medium.

[0260] The functions realized by the components described in this specification may be implemented in circuitry or processing circuitry including a general-purpose processor, a specific-purpose processor, an integrated circuit, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to realize the described functions. A processor includes transistors and other circuits and is regarded as circuitry or processing circuitry. The processor may be a programmed processor that executes a program stored in a memory.

[0261] In this specification, circuitry, units, and means are hardware programmed to realize the described functions or hardware that executes. The hardware may be any hardware disclosed in this specification or any hardware known as being programmed or executing to realize the described functions.

[0262] When the hardware is a processor regarded as a type of circuitry, the circuitry, means, or unit is a combination of hardware and software used to configure the hardware and / or the processor.

[0263] Some embodiments of the present disclosure have been described above. However, these embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are to be included in the scope and gist of the invention, as well as in the invention described in the claims and the equivalent scope thereof.

[0264] (Supplementary Note) The matters described in each of the above embodiments are appended below.

[0265] (Appendix of the First Embodiment)

[0266] (Appendix 1) A program for operating a computer comprising one or more computer processors, in a storage unit, holding information on a plurality of contents related to laws, the program causes one or more computer processors to, in each of a plurality of contents related to laws, identifying information specifying a statute, identifying information specifying a judicial precedent, identifying information specifying a legal book, identifying information specifying a guideline related to laws, identifying at least a part containing any of them, storing, in the storage unit, the part identified in the identifying step in association with the content to which the identification pertains, extracting, for a plurality of contents, parts where the identified parts are of the same type, and defining a reference relationship between the contents for each of the extracted contents, storing, in the storage unit, the reference relationships defined for a plurality of contents, a program for causing execution.

[0267] (Appendix 2) In the identifying step, as identifying information specifying a statute, at least any of the name or article of the statute, as identifying information specifying a judicial precedent, the number of the judicial precedent, as identifying information specifying a legal book, the title of the legal book, as identifying information specifying a guideline related to laws, the name of the guideline, the program according to Appendix 1, identifying at least a part containing any of them.

[0268] (Appendix 3) ​In the step of defining a reference relationship, for a plurality of contents, by extracting those with a part of the same type and then extracting those with the same name for the identified part, a program according to Appendix 2 that defines the reference relationship between the contents.

[0269] (Appendix 4) In the step of specifying, As information for specifying a statute, at least either the name of the statute or a clause, As information for specifying a precedent, the number of the precedent, As information for specifying a legal book, the title of the legal book, As information for specifying a legal guideline, the name of the guideline, specify at least a certain amount of text containing at least any one of them as a part, In the step of defining a reference relationship, a program according to Appendix 3 that defines the reference relationship between parts that are a certain amount of text of a plurality of contents.

[0270] (Appendix 5) On one or more computer processors, further, In a service that receives an operation of searching for content based on a part associated with the content, a step of evaluating the part according to the usage status of the search results, and A step of storing the evaluation result obtained by evaluating the part in a storage unit in association with the content, a program according to any one of Appendices 1 to 4.

[0271] (Appendix 6) A data structure of information on content related to law, In the storage unit, information on a plurality of contents related to law is held, In the storage unit, for each of the plurality of contents, Information for specifying a statute, Information for specifying a precedent, Information for specifying a legal book, Information for specifying a legal guideline, retaining the result of defining the reference relationship between contents for at least a part of the same kind included in any of them, A data structure of information on legal-related contents, which, in response to a search request for searching information on a plurality of legal-related contents, identifies a part corresponding to the search request and is used in a process of responding to the search request based on the reference relationship between contents for the identified part.

[0272] (Appendix 7) The data related to the data structure, In response to a search request for searching a part corresponding to a question among a plurality of contents in order to receive an input of a question from a user and generate an answer to the question by a large language model, it is used in a process of responding to the search request with search results of the plurality of contents based on the reference relationship between contents for the part, The data structure according to Appendix 6, wherein an answer to the question is generated by a large language model based on the search results of the plurality of contents and the question from the user.

[0273] (Appendix 8) A method for operating a computer including one or more computer processors, storing information on a plurality of legal-related contents in a storage unit, The program causes one or more computer processors to, in each of a plurality of legal-related contents, identifying information on statutes, identifying information on case laws, identifying information on legal books, identifying information on legal guidelines, identifying at least a part including any of them, storing the part identified in the identifying step in the storage unit in association with the content related to the identification, For a plurality of contents, extracting a specific part of the same type and defining a reference relationship between the contents for each of the extracted contents; Causing a storage unit to store the reference relationships defined for a plurality of contents, a method.

[0274] (Appendix 9) A method for operating a computer including one or more computer processors, In a storage unit, retaining information on a plurality of contents related to law, In the storage unit, for each of the plurality of contents, Information identifying a statute, Information identifying a precedent, Information identifying a legal book, Information identifying guidelines related to law, Retaining the result of defining the reference relationship between the contents for at least a part of the same type that includes any of the above, One or more computer processors In response to a search request for searching for information on a plurality of contents related to law, identifying a part corresponding to the search request; Responding to the search request based on the reference relationship between the contents for the identified part, a method.

[0275] (Appendix 10) An information processing apparatus, In a storage unit, retaining information on a plurality of contents related to law, The program causes one or more computer processors For each of the plurality of contents related to law, Information identifying a statute, Information identifying a precedent, Information identifying a legal book, Information identifying guidelines related to law, Identifying at least a part that includes any of the above; A step of storing, in a storage unit, a part specified in a specific step in association with the content related to the specification; A step of extracting, for a plurality of contents, parts in which the specified parts are of the same type, and defining a reference relationship between the contents for each of the extracted contents; An information processing apparatus that executes a step of storing, in a storage unit, the reference relationship defined for a plurality of contents.

[0276] (Appendix 11) An information processing apparatus, In a storage unit, information on a plurality of contents related to law is held, In the storage unit, for each of the plurality of contents, Information specifying a statute, Information specifying a precedent, Information specifying a legal book, Information specifying a guideline related to law, The result of defining a reference relationship between contents for at least any of the parts containing the same type is held, The control unit of the information processing apparatus, In response to a search request for searching for information on a plurality of contents related to law, specifying a part corresponding to the search request; An information processing apparatus that responds to the search request based on the reference relationship between contents for the specified part.

[0277] (Appendix to the Second Embodiment)

[0278] (Appendix 1) A program for operating a computer including one or more computer processors, In a storage unit, information on a plurality of contents related to law is held, The program causes one or more computer processors to Receive an input of a question related to law from a user; Based on the input question, a step of searching for information on a plurality of contents related to the law, a step of identifying information on statutes cited in the retrieved search result contents, a program for causing the steps of presenting the identified statute information to the user to be executed.

[0279] (Appendix 2) In the storage unit, as information on a plurality of contents related to the law, at least any one of information on legal books related to the law, guidelines related to the law, and articles in information media related to the law is held, The program according to Appendix 1, wherein in the step of searching, at least any one of information on legal books related to the law, guidelines related to the law, and articles in information media related to the law is targeted for searching.

[0280] (Appendix 3) In the storage unit, information on a plurality of legal books is held, and for each of the plurality of legal books, a tag indicating the content of the legal book is associated and held, In the step of searching, assigning a tag to the input question, The program according to any one of Appendices 1 to 2, wherein based on the tag assigned to the question and the tag associated with the legal book, the legal book is searched.

[0281] (Appendix 4) In a service that enables viewing of a plurality of legal books, a score of a tag associated with a legal book is determined, The program according to Appendix 3, wherein in the step of searching, based on the score of the tag associated with the legal book, the legal book is searched.

[0282] (Appendix 5) In the step of searching, as for tagging the question, by giving a prompt including an instruction to tag the question with a tag related to law to a large language model, obtaining information on the result of tagging output by the large language model, and tagging the question based on the obtained information on the result of tagging, the data structure according to any one of Appendices 3 to 4.

[0283] (Appendix 6) In the storage unit, information on a plurality of contents related to law is retained. In the storage unit, for each of the plurality of contents, Information identifying a statute, Information identifying a precedent, Information identifying a legal book, Information identifying guidelines related to law, As a data structure related to law, the result of defining the reference relationship between contents for at least any part including any of these is retained. In the step of searching, by referring to the data structure related to law, searching for information on a plurality of contents related to law for the question, the program according to any one of Appendices 1 to 5.

[0284] (Appendix 7) A method of operating a computer including one or more computer processors, In the storage unit, information on a plurality of contents related to law is retained. The method is such that one or more computer processors receive an input of a question related to law from a user, search for information on a plurality of contents related to law based on the input question, identify information on a statute cited in the content of the searched search result, and present the identified information on the statute to the user.

[0285] (Appendix 8) An information processing apparatus, in a storage unit, holds information on a plurality of contents related to laws, a control unit of the information processing apparatus, receives an input of a question related to laws from a user, searches for information on a plurality of contents related to laws based on the input question, identifies information on statutes cited in the retrieved search result contents, and presents the identified statute information to the user. An information processing apparatus that executes these steps.

[0286] (Appendix of the Third Embodiment)

[0287] (Appendix 1) A program for operating a computer including one or more computer processors, in a storage unit, holds information on a plurality of contents related to laws, the program causes one or more computer processors to, generate a prompt including an instruction to identify a legal argument corresponding to the content of each of a plurality of contents related to laws, give the content related to the generation of the prompt and the prompt generated for the content to a large language model, and receive the output result of the large language model to obtain a result of identifying the legal argument for each content, and store the identified legal argument in the storage unit in association with the information on the content to which the identification pertains. A program that executes these steps. Program.

[0288] (Appendix 2) As for holding information on a plurality of contents related to laws in a storage unit, information on statutes, information on case laws, information on legal books, holds at least any one of the information of the guidelines regarding the law, In the generating step, generate a prompt including an instruction to extract a part of the content that serves as a basis for identifying a legal argument corresponding to the content of the content, In the step of storing the argument in the storage unit, the program according to Appendix 1, which stores in the storage unit by associating a part of the content extracted for the content with the identified legal argument.

[0289] (Appendix 3) In the step of storing the argument in the storage unit, the program according to Appendix 2, which identifies parts of a plurality of contents related to the same argument, defines a reference relationship between the identified parts of the plurality of contents, and stores them in the storage unit.

[0290] (Appendix 4) Further, on one or more computer processors, In a service that receives an operation of searching for content based on a legal argument associated with the content, evaluating the argument according to the usage status of the search results, The program according to any one of Appendices 1 to 3, which causes the steps of storing the evaluation result obtained by evaluating the argument in the storage unit in association with the content to be executed.

[0291] (Appendix 5) A data structure of information on content related to the law, In the storage unit, holds information on a plurality of contents related to the law, In the storage unit, holds information on legal arguments in association with each of the plurality of contents, Receives an input of a question regarding the law from a user, analyzes the input question to identify an argument corresponding to the question, and uses the information on legal arguments stored in the storage unit based on the identified argument to search for content related to the law associated with the argument. A data structure of information on content related to the law used for the process.

[0292] (Appendix 6) In the storage unit, for each of a plurality of contents, information on a legal issue associated with the content and a part of the content corresponding to the legal issue are associated and stored. In the storage unit, a reference relationship is defined between parts of a plurality of contents related to the same issue. As a process, the data structure described in Appendix 5, which is used for the process of searching a plurality of contents for which a reference relationship is defined for a specified issue based on the reference relationship.

[0293] (Appendix 7) A program for operating a computer including one or more computer processors, In the storage unit, information on a plurality of contents related to laws is retained. In the storage unit, information on a legal issue is retained in association with each of the plurality of contents. The program causes one or more computer processors to receive an input of a question regarding a law from a user, specify an issue corresponding to the question by analyzing the input question, search for information on contents related to the law associated with the issue by referring to the information on the legal issue stored in the storage unit based on the issue corresponding to the specified question, and present the search result of the content information to the user. The program.

[0294] (Appendix 8) A method executed by a computer including one or more computer processors, In the storage unit, information on a plurality of contents related to laws is retained. The method includes one or more computer processors For each of a plurality of contents related to law, generating a prompt including an instruction to identify a legal argument corresponding to the content of the content; Providing the content related to the generation of the prompt and the prompt generated for the content to a large language model, and receiving the output result of the large language model to obtain a result of identifying a legal argument for each content; Storing, in a storage unit, the identified legal argument in association with information on the content to which the identification relates. A method for executing.

[0295] (Appendix 9) A method executed by a computer including one or more computer processors, In a storage unit, retaining information on a plurality of contents related to law, In a storage unit, retaining information on legal arguments in association with each of the plurality of contents, The method is such that one or more computer processors Receiving an input of a question related to law from a user; Identifying an argument corresponding to the question by analyzing the input question; Based on the argument corresponding to the identified question, retrieving information on the content related to law associated with the argument by referring to the information on legal arguments stored in the storage unit; Presenting the search result of the content information to the user. A method for executing.

[0296] (Appendix 10) An information processing apparatus, In a storage unit, retaining information on a plurality of contents related to law, The control unit of the information processing apparatus For each of a plurality of contents related to law, generating a prompt including an instruction to identify a legal argument corresponding to the content of the content; Providing the content related to the generation of the prompt and the prompt generated for the content to a large language model, and receiving the output result of the large language model, thereby obtaining the result of identifying the legal arguments for each content; An information processing apparatus that executes the step of storing, in a storage unit, information on the identified legal arguments in association with information on the content to which the identification relates.

[0297] (Appendix 11) An information processing apparatus, wherein a storage unit holds information on a plurality of contents related to laws; wherein the storage unit holds information on legal arguments in association with each of the plurality of contents; wherein a control unit of the information processing apparatus executes the steps of receiving an input of a question related to a law from a user; identifying an argument corresponding to the question by analyzing the input question; searching for information on the content related to the law associated with the argument by referring to the information on the legal arguments stored in the storage unit based on the argument corresponding to the identified question; and presenting the search result of the content information to the user.

Claims

1. A program for operating a computer having one or more computer processors, A storage unit stores information on a plurality of legal contents, The program causes the one or more computer processors to: receiving an input of a legal question from a user; searching for information on a plurality of content items related to the law based on the input question; identifying statutory information cited in the search result content; presenting information about the identified law to a user; In the storage unit, information on a plurality of legal books is stored as the information on the plurality of legal contents, and a tag indicating the content of the legal book is associated with each of the plurality of legal books and stored; In the searching step, assigning a tag to the input question; searching the legal book based on the tag assigned to the question and a tag associated with the legal book; In the service that enables browsing of the plurality of legal books, a score of a tag associated with the legal book is determined according to a search result of the tag in the service; The program, in the searching step, searches for the legal book based on a score of the tag associated with the legal book, the score being determined according to a track record of searches of the tag on the service.

2. In the storage unit, as the information on the plurality of legal contents, at least one of information on legal guidelines and articles on legal information media is further stored; 2. The program according to claim 1, wherein in said searching step, at least any one of information in said legal books, guidelines related to said law, and articles in information media related to said law is searched for as a target.

3. The program of claim 1, wherein in the searching step, a tag is assigned to the question by providing a prompt to a large-scale language model including an instruction to assign a legal tag to the question, thereby obtaining information on the result of the tagging output by the large-scale language model, and a tag is assigned to the question based on the obtained information on the result of the tagging.

4. The storage unit stores information on a plurality of legal content items, In the storage unit, for each of the plurality of contents, Information identifying the law; Case-identifying information; Information identifying the law book; Information identifying legal guidelines; The result of defining a reference relationship between contents of the same type that includes at least one of the above is stored as a legal data structure; 2. The program according to claim 1, wherein in the searching step, information related to the law for the query is searched for in the plurality of contents by referring to a data structure related to the law.

5. 1. A method of operating a computer having one or more computer processors, comprising: A storage unit stores information on a plurality of legal contents, The method further comprises the step of: receiving an input of a legal question from a user; searching for information on a plurality of content items related to the law based on the input question; identifying statutory information cited in the search result content; presenting information about the identified law to a user; In the storage unit, information on a plurality of legal books is stored as the information on the plurality of legal contents, and a tag indicating the content of the legal book is associated with each of the plurality of legal books and stored; In the searching step, assigning a tag to the input question; searching the legal book based on the tag assigned to the question and a tag associated with the legal book; In the service that enables browsing of the plurality of legal books, a score of a tag associated with the legal book is determined according to a search result of the tag in the service; A method according to claim 1, wherein in the searching step, the legal book is searched for based on a score of the tag associated with the legal book, the score being determined in response to a performance of searches of the tag on the service.

6. An information processing device, A storage unit stores information on a plurality of legal contents, A control unit of the information processing device receiving an input of a legal question from a user; searching for information on a plurality of content items related to the law based on the input question; identifying statutory information cited in the search result content; presenting information about the identified law to a user; In the storage unit, information on a plurality of legal books is stored as the information on the plurality of legal contents, and a tag indicating the content of the legal book is associated with each of the plurality of legal books and stored; In the searching step, assigning a tag to the input question; searching the legal book based on the tag assigned to the question and a tag associated with the legal book; In the service that enables browsing of the plurality of legal books, a score of a tag associated with the legal book is determined according to a search result of the tag in the service; An information processing device, in the searching step, searches for the legal book based on a score of the tag associated with the legal book and determined according to a track record of searches for the tag in the service.

Images