System

Abstract

An object of a system according to an embodiment is to quickly and appropriately answer specialized questions related to legal affairs.SOLUTION: A system includes a question reception unit, an answer generation unit, a database reference unit, and a notification unit. The question reception unit receives a question from a user. The answer generation unit generates an answer based on the question received by the question reception unit. The database reference unit checks the answer generated by the answer generation unit by referring to at least one database of all the six laws or the latest legal cases. The notification unit notifies the user of the answer confirmed by the database reference unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has made it difficult to provide prompt and appropriate answers to specialized legal questions, placing a heavy burden on legal departments.

[0005] The system according to the embodiment aims to provide prompt and appropriate answers to specialized legal questions. [Means for solving the problem]

[0006] The system according to the embodiment includes a question receiving unit, an answer generating unit, a database reference unit, and a notification unit. The question receiving unit receives a question from a user. The answer generating unit generates an answer based on the question received by the question receiving unit. The database reference unit verifies the answer generated by the answer generating unit by referencing at least one database of the Six Codes of Law or the latest legal cases. The notification unit notifies the user of the answer confirmed by the database reference unit. [Effects of the Invention]

[0007] The system according to the embodiment can quickly and appropriately answer technical questions related to legal matters. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The LegalBot system, an embodiment of the present invention, is a system designed to enable people and companies to receive prompt and appropriate answers to specialized legal questions. This LegalBot system is an AI chatbot that utilizes generative AI and is based on databases such as the Six Codes and the latest legal cases. This not only reduces the burden on legal departments, but also contributes to improving risk management across the entire company. Furthermore, by collecting specific legal themes and issues for each company, it can also contribute to improving risk management for each employee.

[0029] The LegalBot system according to the embodiment includes a question receiving unit, an answer generating unit, a database reference unit, and a notification unit. The question receiving unit receives a question from a user. For example, when a user inputs a question about legal matters, the question receiving unit receives the question. The question receiving unit can also receive questions using voice input. The answer generating unit generates an answer based on the question received by the question receiving unit. For example, the generation AI generates an appropriate answer to the question using a text generation AI (e.g., LLM). The generation AI can also generate an answer to the question using a multimodal generation AI. The generation AI can also learn past question history and generate an answer optimized for an individual user. The database reference unit verifies the answer generated by the answer generating unit by referencing at least one database of the Roppo Zensho or the latest legal cases. For example, the database reference unit references the Roppo Zensho database to verify whether the generated answer is accurate. The database reference unit references the latest legal cases database to verify whether the generated answer is based on the latest information. The notification unit notifies the user of the answer verified by the database reference unit. For example, the notification unit may send the generated answer to the user by email. The notification unit may also display the generated answer on the user's chat screen. The notification unit may also send a push notification of the generated answer to the user's smartphone. This allows the LegalBot system according to the embodiment to provide prompt and appropriate answers to user questions. For example, even if a user asks a legal question late at night or on a holiday, the LegalBot system can provide an answer immediately. The LegalBot system also reduces the burden on the legal department and improves risk management across the entire company.

[0030] The answer generation unit can learn the user's past question history and generate answers appropriate for each individual user. For example, the answer generation unit uses a generation AI to analyze the user's past question history and generate answers optimized for each individual user. For example, a user who has asked many questions about contracts in the past can be provided with detailed information related to contracts. The answer generation unit also uses the generation AI to learn the user's interests and needs based on the user's past question history and provide more appropriate answers. For example, a user who is interested in a specific legal field can be provided with information specialized in that field. The answer generation unit also uses the generation AI to analyze the user's past question history and generate answers appropriate to the user's level of understanding and knowledge. For example, basic information can be provided to beginners and detailed information to experts. This makes it possible to provide answers optimized based on the user's past question history.

[0031] The answer generation unit can automatically generate follow-up questions to clarify the user's intent in order to understand the intent of the question in more detail. For example, the answer generation unit automatically generates follow-up questions in response to a user's question using a generation AI to clarify the user's intent. For example, in response to the question, "What should I pay attention to when creating a contract?", the answer generation unit asks a follow-up question such as, "What specific type of contract is it?" The answer generation unit also asks follow-up questions in response to a user's question to collect more detailed information. For example, it adds a specific question such as, "Is this question about a labor contract?" The answer generation unit also generates appropriate follow-up questions in response to a user's question to more accurately understand the user's intent. For example, it asks a question such as, "What do you particularly consider important when creating a contract?" This makes it possible to more accurately understand the intent of the user's question and provide an appropriate answer.

[0032] The system can develop a multi-domain AI chatbot that can handle specialized fields other than legal affairs. For example, the system uses generative AI to develop a multi-domain AI chatbot that can handle specialized fields other than legal affairs. For example, it can handle questions about medicine and finance. The system also develops a multi-domain AI chatbot that can handle specialized fields other than legal affairs. For example, it can refer to a medical database for questions about medicine and provide an appropriate answer. The system also uses generative AI to develop a chatbot that can handle specialized fields other than legal affairs. For example, it can provide answers based on a financial database for questions about finance. This makes it possible to provide a multi-domain AI chatbot that can handle specialized fields other than legal affairs.

[0033] The system responds to voice input and can use voice recognition technology to conduct legal question and answer sessions. In the system, for example, a generation AI responds to voice input and uses voice recognition technology to conduct legal question and answer sessions. For example, when a user inputs a question by voice, the generation AI converts the voice to text and generates an appropriate answer. The system also utilizes voice recognition technology so that the generation AI responds to voice input. For example, a user inputs a question by voice using a smartphone, and the generation AI provides an answer to that question. The system also develops a system in which the generation AI responds to voice input and uses voice recognition technology to conduct legal question and answer sessions. For example, a user inputs a question by voice, and the generation AI analyzes the voice and generates an answer. This allows for voice input and legal question and answer sessions to be conducted using voice recognition technology.

[0034] The system can learn the legal department's schedule and send notifications to legal department personnel when important questions arise. For example, the system will add a function where the generation AI learns the legal department's schedule and sends notifications to legal department personnel when important questions arise. For example, if a highly urgent question comes in, the person in charge will be notified by email. The system will also develop a generation AI that learns the legal department's schedule and sends an alert to the person in charge when an important question comes in. For example, if an important question comes in during a specific time period, the person in charge will be notified by SMS. The system will also add a function where the generation AI analyzes the legal department's schedule and sends notifications to the person in charge in real time when an important question comes in. For example, the system will link with the legal department's calendar and send an app notification to the person in charge when an important question comes in. This will allow the legal department personnel to be notified when an important question comes in.

[0035] The system can automatically determine the urgency of a question and prioritize responses to questions with high urgency. For example, the system will build a system in which a generation AI automatically determines the urgency of a question and prioritize responses to questions with high urgency. For example, the system will score the urgency based on the content of the question and prioritize questions with high scores. The system will also develop an algorithm that automatically determines the urgency of a question and respond immediately to questions with high urgency. For example, the system will analyze the keywords and context of the question to determine the urgency. The system will also develop a system in which a generation AI determines the urgency of a question in real time and prioritizes responses to questions with high urgency. For example, the system will determine the urgency based on the content of the question and the time of submission and set a priority. This will allow questions with high urgency to be prioritized.

[0036] The system can expand 24-hour legal support to other company departments. For example, the system can expand 24-hour legal support to other company departments and build a system that can also respond to questions about IT support and human resources. For example, it can provide technical answers to questions about IT support. The system can also use generative AI to expand 24-hour legal support to other company departments. For example, it can provide information on labor law and employee benefits to questions about human resources. The system can also expand 24-hour legal support to other company departments and develop a system that provides answers based on the expertise of each department. For example, it can provide answers based on market research data to questions about marketing. This allows 24-hour legal support to be expanded to other company departments.

[0037] The system utilizes the user's geographic location information to address region-specific legal issues. For example, the system uses the user's geographic location information to build a system that also addresses region-specific legal issues. For example, it provides answers based on the laws and regulations that apply in a specific region. The system also uses the geographic location information to develop a system that uses the generation AI to address region-specific legal issues. For example, if the user is in a specific region, it provides legal information for that region. The system also analyzes the user's geographic location information to develop a system that addresses region-specific legal issues. For example, it generates answers based on the laws and regulations of each region. This makes it possible to address region-specific legal issues.

[0038] The system can automatically collect updated information from legal databases and provide the latest legal information. For example, the system will build a system in which a generating AI automatically collects updated information from legal databases and provides the latest legal information. For example, the database will be automatically updated when new laws or precedents are added. The system will also collect updated information from legal databases in real time and the generating AI will provide the latest legal information. For example, the database will be updated immediately when new laws or precedents are enacted. The system will also develop a system in which a generating AI regularly collects updated information from legal databases and provides the latest legal information. For example, the database will be checked daily and automatically updated if new information is found. This will allow the latest legal information to be provided at all times.

[0039] The system can cross-reference information in a legal database and automatically link related laws and precedents. For example, the system builds a system in which a generating AI cross-references information in a legal database and automatically links related laws and precedents. For example, precedents related to a specific law are automatically displayed. The system also cross-references information in a legal database and the generating AI links related laws and precedents. For example, related precedents are automatically displayed when a user searches for a specific law. The system also develops a system in which a generating AI analyzes information in a legal database and automatically links related laws and precedents. For example, precedents related to legal provisions are automatically linked. This makes it possible to automatically link related laws and precedents.

[0040] The system integrates the legal database with databases in other fields of expertise to respond to complex questions. For example, the system integrates the legal database with databases in other fields of expertise to build a system that can respond to complex questions. For example, it can be integrated with a medical database to respond to questions related to medical-legal matters. The system also uses generative AI to integrate the legal database with databases in other fields of expertise. For example, it can be integrated with a financial database to respond to questions related to financial-legal matters. The system also integrates the legal database with databases in other fields of expertise to develop a system that can respond to complex questions. For example, it can be integrated with an environmental database to respond to questions related to environmental law. This makes it possible to respond to complex questions.

[0041] The system can visualize information in a legal database and display it in graphs or charts. For example, the system builds a system in which a generating AI visualizes information in a legal database and displays it in graphs or charts. For example, it displays the enforcement status of laws and trends in case law in graphs. The system also visualizes information in a legal database and a generating AI displays it in graphs or charts. For example, it displays statistical data on a specific law in a chart. The system also develops a system in which a generating AI analyzes information in a legal database, visualizes it, and displays it in graphs or charts. For example, it displays the history of legal amendments in a graph. This makes it possible to visualize and display information in a legal database.

[0042] The system can automatically classify legal themes for each company and provide answers appropriate for each theme. For example, the system builds a system in which a generating AI automatically classifies legal themes for each company and provides answers customized for each theme. For example, it provides legal information specialized for a specific industry. The system also automatically classifies legal themes for each company and a generating AI provides answers customized for each theme. For example, it provides legal information specialized for the manufacturing industry. The system also develops a system in which a generating AI analyzes legal themes for each company and provides answers customized for each theme. For example, it provides legal information specialized for the IT industry. This makes it possible to provide answers customized according to the legal themes of each company.

[0043] The system can provide preventive legal advice based on a company's legal themes. For example, the system builds a system in which a generative AI provides preventive legal advice based on a company's legal themes. For example, it provides advice on how to avoid specific risks. The system also analyzes a company's legal themes and the generative AI provides preventive legal advice. For example, it provides advice on points to be careful of when drafting contracts. The system also develops a system in which a generative AI provides preventive legal advice based on a company's legal themes. For example, it provides specific advice on compliance with laws and regulations. This makes it possible to provide preventive legal advice based on a company's legal themes.

[0044] The system can collect relevant external resources based on a company's legal themes. For example, the system builds a system in which a generating AI automatically collects relevant external resources based on a company's legal themes. For example, it collects expert opinions and academic papers. The system also analyzes a company's legal themes and the generating AI automatically collects relevant external resources. For example, it collects the latest research results and expert opinions on legal matters. The system also develops a system in which a generating AI automatically collects relevant external resources based on a company's legal themes. For example, it collects the latest legal news and expert opinions. This makes it possible to automatically collect relevant external resources based on a company's legal themes.

[0045] The system can evaluate an employee's legal knowledge level and provide an individualized training plan. For example, the system builds a system in which a generative AI evaluates an employee's legal knowledge level and provides an individualized training plan. For example, it can provide basic training for beginners and specialized training for advanced employees. The system also analyzes an employee's legal knowledge level and a generative AI can provide an individualized training plan. For example, it can provide training specialized in a specific legal field. The system also develops a system in which a generative AI evaluates an employee's legal knowledge level and provides an individualized training plan. For example, it can provide training customized according to the employee's knowledge level. This makes it possible to evaluate an employee's legal knowledge level and provide an individualized training plan.

[0046] The system provides simulation-based training to improve employees' risk management skills. For example, the system builds a system in which a generative AI provides simulation-based training to improve employees' risk management skills. For example, it provides a simulation to solve a hypothetical legal problem. The system also uses simulation to provide training in which the generative AI improves employees' risk management skills. For example, it performs a simulation based on an actual legal case. The system also develops a system in which a generative AI provides simulation-based training to improve employees' risk management skills. For example, it provides training based on a risk scenario. In this way, it is possible to provide simulation-based training to improve employees' risk management skills.

[0047] The system can extend risk management training to other skills. For example, the system extends risk management training to other skills, and builds a system in which generative AI provides training in project management, etc. For example, it provides training on how to manage project risks. The system also uses generative AI to extend risk management training to other skills, and develops a system in which generative AI provides multifaceted training. For example, it provides training on project management and problem-solving skills. This allows risk management training to be extended to other skills.

[0048] The system can evaluate employees' risk management skills and suggest appropriate positions within the company. For example, the system builds a system in which a generative AI evaluates employees' risk management skills and suggests appropriate positions within the company. For example, employees who are good at risk management are placed in the risk management department. The system also analyzes employees' risk management skills and a generative AI suggests appropriate positions. For example, an employee who is suitable as a project leader is placed in a leadership position. The system also develops a system in which a generative AI evaluates employees' risk management skills and suggests appropriate positions within the company. For example, an employee who is good at risk assessment is placed in a risk assessment team. This makes it possible to evaluate employees' risk management skills and suggest appropriate positions within the company.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The question reception unit not only receives user questions, but also analyzes the trends in user questions and presents predicted questions in advance. For example, if a user has asked many questions about contracts in the past, general questions about contracts can be presented in advance. The question reception unit can also analyze the frequency and time of the user's questions and suggest the optimal time to provide answers. For example, if a user asks many questions at night, the unit can suggest increasing resources to respond at night. The question reception unit can also automatically provide related legal information and reference materials based on the content of the user's question. For example, when a question about contracts is received, related laws and precedents can be automatically displayed. This allows for faster and more appropriate answers to the user's questions.

[0051] The answer generator not only learns the user's past question history, but can also customize answers based on the user's job function and position. For example, it can provide detailed legal interpretations to legal department personnel and basic legal knowledge to general employees. The answer generator can also optimize answers based on the user's industry and company characteristics. For example, it can provide legal information specialized for manufacturing to manufacturing companies and IT-related legal information to IT companies. The answer generator can also predict future legal information needs based on the user's past question history and provide it in advance. For example, if a specific legal amendment is scheduled, it can provide information about that amendment in advance. This allows the system to provide the most appropriate legal information to meet the user's needs.

[0052] The answer generation unit not only automatically generates follow-up questions to understand the intent of the question, but can also collect background information about the user's question and provide a more detailed answer. For example, if a user asks a question about a contract, it can ask about the specific content and purpose of the contract. The answer generation unit can also automatically link relevant laws and precedents to the user's question, allowing the user to quickly obtain the information they need. For example, in response to a question about a labor contract, it can automatically display relevant labor laws and precedents. The answer generation unit can also ask appropriate follow-up questions to more accurately understand the user's intent. For example, it can ask about points that are particularly important when drafting a contract. This allows the intent of the user's question to be more accurately understood and an appropriate answer to be provided.

[0053] The system not only develops multi-domain AI chatbots that can handle specialties other than legal matters, but also collaborates with experts in each field to improve the accuracy of responses. For example, for questions in the medical field, the system incorporates the opinions of doctors and medical experts. The system also develops multi-domain AI chatbots that can handle specialties other than legal matters, and can automatically collect the latest information in each field and incorporate it into responses. For example, it can provide responses that reflect the latest regulations and market trends in the financial sector. The system also utilizes generative AI to develop chatbots that can handle specialties other than legal matters, and can optimize the expertise of each field based on the user's question history. For example, it can provide detailed medical information to users who frequently ask questions in the medical field. This allows the system to provide multi-domain AI chatbots that can handle specialties other than legal matters, and collaborates with experts in each field to improve the accuracy of responses.

[0054] The system not only responds to voice input and uses voice recognition technology to answer legal questions, but also provides answers via voice synthesis. For example, when a user voice-inputs a question, the generation AI converts the speech to text, generates an appropriate answer, and provides that answer via voice. The system also utilizes voice recognition technology, allowing the generation AI not only to respond to voice input but also to analyze the voice data and estimate the user's emotional state. For example, it can analyze the tone and speed of the user's voice to determine whether the user is feeling stressed or anxious. The system also responds to voice input and uses voice recognition technology to answer legal questions, but can also more accurately understand the intent of the user's question based on the voice data. For example, it can analyze the intonation and emphasis of the user's voice to identify key points. This allows the system to respond to voice input and provide legal questions using voice recognition and voice synthesis.

[0055] The system learns the legal department's schedule and notifies legal department personnel when important questions arise, and can also make suggestions to optimize the legal department's resources. For example, if a large number of questions arise during a certain time period, the system can suggest increasing resources to handle those times. The system has also developed a generative AI that learns the legal department's schedule and not only alerts legal department personnel when important questions arise, but also prioritizes responses based on the question's urgency. For example, it can respond immediately to urgent questions and later to less urgent questions. The system's generative AI also analyzes the legal department's schedule and not only notifies legal department personnel in real time when important questions arise, but also makes suggestions to improve the legal department's work efficiency. For example, it can suggest automating certain tasks. This not only notifies legal department personnel when important questions arise, but also makes suggestions to optimize the legal department's resources.

[0056] The system automatically determines the urgency of a question and prioritizes those that require urgent attention. It can also automatically assign questions to the appropriate person based on their content. For example, questions about contracts are assigned to contract specialists, and questions about labor law are assigned to labor law specialists. The system has also developed an algorithm to automatically determine the urgency of a question, allowing it to respond immediately to urgent questions and allocate appropriate resources based on their content. For example, multiple staff members can work together to respond to complex questions. The system's generative AI can also determine the urgency of a question in real time, prioritizing urgent questions and suggesting the optimal response method based on the question's content. For example, it provides quick answers to urgent questions and detailed answers to less urgent questions. This allows it to prioritize urgent questions and automatically assign them to the appropriate person based on their content.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The question receiving unit receives a question from a user. For example, if the user inputs a question about legal matters, the question receiving unit receives the question. The question receiving unit can also receive a question using voice input. Step 2: The answer generation unit generates an answer based on the question received by the question reception unit. For example, the generation AI generates an appropriate answer to the question using a text generation AI (e.g., LLM). The generation AI can also generate an answer to the question using a multimodal generation AI. The generation AI can also learn from past question history and generate an answer optimized for each individual user. Step 3: The database reference unit verifies the answer generated by the answer generation unit by referring to at least one database of the Six Codes of Law or the latest legal cases. For example, the database reference unit references the Six Codes of Law database to verify whether the generated answer is accurate. The database reference unit also references the latest legal case database to verify whether the generated answer is based on the latest information. Step 4: The notification unit notifies the user of the answer confirmed by the database reference unit. For example, the notification unit sends the generated answer to the user by email. The notification unit can also display the generated answer on the user's chat screen. The notification unit can also push the generated answer to the user's smartphone.

[0059] (Example 2) The LegalBot system, an embodiment of the present invention, is a system designed to enable people and companies to receive prompt and appropriate answers to specialized legal questions. This LegalBot system is an AI chatbot that utilizes generative AI and is based on databases such as the Six Codes and the latest legal cases. This not only reduces the burden on legal departments, but also contributes to improving risk management across the entire company. Furthermore, by collecting specific legal themes and issues for each company, it can also contribute to improving risk management for each employee.

[0060] The LegalBot system according to the embodiment includes a question receiving unit, an answer generating unit, a database reference unit, and a notification unit. The question receiving unit receives a question from a user. For example, when a user inputs a question about legal matters, the question receiving unit receives the question. The question receiving unit can also receive questions using voice input. The answer generating unit generates an answer based on the question received by the question receiving unit. For example, the generation AI generates an appropriate answer to the question using a text generation AI (e.g., LLM). The generation AI can also generate an answer to the question using a multimodal generation AI. The generation AI can also learn past question history and generate an answer optimized for an individual user. The database reference unit verifies the answer generated by the answer generating unit by referencing at least one database of the Roppo Zensho or the latest legal cases. For example, the database reference unit references the Roppo Zensho database to verify whether the generated answer is accurate. The database reference unit references the latest legal cases database to verify whether the generated answer is based on the latest information. The notification unit notifies the user of the answer verified by the database reference unit. For example, the notification unit may send the generated answer to the user by email. The notification unit may also display the generated answer on the user's chat screen. The notification unit may also send a push notification of the generated answer to the user's smartphone. This allows the LegalBot system according to the embodiment to provide prompt and appropriate answers to user questions. For example, even if a user asks a legal question late at night or on a holiday, the LegalBot system can provide an answer immediately. The LegalBot system also reduces the burden on the legal department and improves risk management across the entire company.

[0061] The answer generation unit can learn the user's past question history and generate answers appropriate for each individual user. For example, the answer generation unit uses a generation AI to analyze the user's past question history and generate answers optimized for each individual user. For example, a user who has asked many questions about contracts in the past can be provided with detailed information related to contracts. The answer generation unit also uses the generation AI to learn the user's interests and needs based on the user's past question history and provide more appropriate answers. For example, a user who is interested in a specific legal field can be provided with information specialized in that field. The answer generation unit also uses the generation AI to analyze the user's past question history and generate answers appropriate to the user's level of understanding and knowledge. For example, basic information can be provided to beginners and detailed information to experts. This makes it possible to provide answers optimized based on the user's past question history.

[0062] The answer generation unit can automatically generate follow-up questions to clarify the user's intent in order to understand the intent of the question in more detail. For example, the answer generation unit automatically generates follow-up questions in response to a user's question using a generation AI to clarify the user's intent. For example, in response to the question, "What should I pay attention to when creating a contract?", the answer generation unit asks a follow-up question such as, "What specific type of contract is it?" The answer generation unit also asks follow-up questions in response to a user's question to collect more detailed information. For example, it adds a specific question such as, "Is this question about a labor contract?" The answer generation unit also generates appropriate follow-up questions in response to a user's question to more accurately understand the user's intent. For example, it asks a question such as, "What do you particularly consider important when creating a contract?" This makes it possible to more accurately understand the intent of the user's question and provide an appropriate answer.

[0063] The answer generation unit uses an emotion estimation function to generate an answer that corresponds to the user's emotional state, thereby reducing stress. In the answer generation unit, for example, a generation AI estimates the user's emotional state and generates an answer that corresponds to the emotion. For example, if the user is feeling stressed, an answer is provided using gentle language. The answer generation unit also uses the emotion estimation function to generate an appropriate answer that corresponds to the user's emotional state. For example, if the user is feeling anxious, an answer that gives a sense of security is provided. In the answer generation unit, the generation AI analyzes the user's emotional state in real time and generates an answer that corresponds to the emotion. For example, if the user is feeling angry, a calm and polite answer is provided. This provides an answer that corresponds to the user's emotional state, thereby reducing stress.

[0064] The system can develop a multi-domain AI chatbot that can handle specialized fields other than legal affairs. For example, the system uses generative AI to develop a multi-domain AI chatbot that can handle specialized fields other than legal affairs. For example, it can handle questions about medicine and finance. The system also develops a multi-domain AI chatbot that can handle specialized fields other than legal affairs. For example, it can refer to a medical database for questions about medicine and provide an appropriate answer. The system also uses generative AI to develop a chatbot that can handle specialized fields other than legal affairs. For example, it can provide answers based on a financial database for questions about finance. This makes it possible to provide a multi-domain AI chatbot that can handle specialized fields other than legal affairs.

[0065] The system responds to voice input and can use voice recognition technology to conduct legal question and answer sessions. In the system, for example, a generation AI responds to voice input and uses voice recognition technology to conduct legal question and answer sessions. For example, when a user inputs a question by voice, the generation AI converts the voice to text and generates an appropriate answer. The system also utilizes voice recognition technology so that the generation AI responds to voice input. For example, a user inputs a question by voice using a smartphone, and the generation AI provides an answer to that question. The system also develops a system in which the generation AI responds to voice input and uses voice recognition technology to conduct legal question and answer sessions. For example, a user inputs a question by voice, and the generation AI analyzes the voice and generates an answer. This allows for voice input and legal question and answer sessions to be conducted using voice recognition technology.

[0066] The system uses the emotion estimation function to analyze the emotions of a user when entering a question in real time and make suggestions to elicit positive emotions. For example, the system uses the emotion estimation function to analyze the emotions of a user when entering a question in real time and make suggestions to elicit positive emotions. For example, if the user is feeling anxious, an encouraging message is displayed. The system also uses a generative AI to analyze the user's emotions in real time and make suggestions to elicit positive emotions. For example, if the user is feeling stressed, advice on how to relax is provided. The system also uses the emotion estimation function to analyze the emotions of a user when entering a question and make suggestions to elicit positive emotions. For example, if the user is feeling angry, a suggestion to stay calm is made. This makes it possible to analyze the user's emotions in real time and make suggestions to elicit positive emotions.

[0067] The system can learn the legal department's schedule and send notifications to legal department personnel when important questions arise. For example, the system will add a function where the generation AI learns the legal department's schedule and sends notifications to legal department personnel when important questions arise. For example, if a highly urgent question comes in, the person in charge will be notified by email. The system will also develop a generation AI that learns the legal department's schedule and sends an alert to the person in charge when an important question comes in. For example, if an important question comes in during a specific time period, the person in charge will be notified by SMS. The system will also add a function where the generation AI analyzes the legal department's schedule and sends notifications to the person in charge in real time when an important question comes in. For example, the system will link with the legal department's calendar and send an app notification to the person in charge when an important question comes in. This will allow the legal department personnel to be notified when an important question comes in.

[0068] The system can automatically determine the urgency of a question and prioritize responses to questions with high urgency. For example, the system will build a system in which a generation AI automatically determines the urgency of a question and prioritize responses to questions with high urgency. For example, the system will score the urgency based on the content of the question and prioritize questions with high scores. The system will also develop an algorithm that automatically determines the urgency of a question and respond immediately to questions with high urgency. For example, the system will analyze the keywords and context of the question to determine the urgency. The system will also develop a system in which a generation AI determines the urgency of a question in real time and prioritizes responses to questions with high urgency. For example, the system will determine the urgency based on the content of the question and the time of submission and set a priority. This will allow questions with high urgency to be prioritized.

[0069] The system can use the emotion estimation function to measure a user's stress level and generate a response to help them relax when stress is high. For example, the system uses the emotion estimation function to measure a user's stress level and generate a response to help them relax when stress is high. For example, if the user is feeling stressed, advice to help them relax is provided. The system also develops a system in which a generation AI analyzes a user's stress level in real time and generates a response to help them relax when stress is high. For example, if the user is feeling anxious, an answer that gives a sense of security is provided. The system also builds a system in which the system uses the emotion estimation function to measure a user's stress level and generate a response to help them relax when stress is high. For example, if the user is feeling angry, an answer to help them stay calm is provided. This makes it possible to provide a relaxing answer according to the user's stress level.

[0070] The system can expand 24-hour legal support to other company departments. For example, the system can expand 24-hour legal support to other company departments and build a system that can also respond to questions about IT support and human resources. For example, it can provide technical answers to questions about IT support. The system can also use generative AI to expand 24-hour legal support to other company departments. For example, it can provide information on labor law and employee benefits to questions about human resources. The system can also expand 24-hour legal support to other company departments and develop a system that provides answers based on the expertise of each department. For example, it can provide answers based on market research data to questions about marketing. This allows 24-hour legal support to be expanded to other company departments.

[0071] The system utilizes the user's geographic location information to address region-specific legal issues. For example, the system uses the user's geographic location information to build a system that also addresses region-specific legal issues. For example, it provides answers based on the laws and regulations that apply in a specific region. The system also uses the geographic location information to develop a system that uses the generation AI to address region-specific legal issues. For example, if the user is in a specific region, it provides legal information for that region. The system also analyzes the user's geographic location information to develop a system that addresses region-specific legal issues. For example, it generates answers based on the laws and regulations of each region. This makes it possible to address region-specific legal issues.

[0072] The system uses the emotion estimation function to provide legal support during times when the user is most relaxed. For example, the system uses the emotion estimation function to build a system that provides legal support during times when the user is most relaxed. For example, the optimal time period is identified based on the user's emotional data. The system also uses a generation AI to analyze the user's emotional state in real time and provide legal support during times when the user is most relaxed. For example, important information is provided during times when the user is relaxed. The system also uses the emotion estimation function to develop a system that provides legal support during times when the user is most relaxed. For example, the optimal time period is identified based on the user's emotional data and legal support is provided during that time period. This makes it possible to provide legal support during times when the user is most relaxed.

[0073] The system can automatically collect updated information from legal databases and provide the latest legal information. For example, the system will build a system in which a generating AI automatically collects updated information from legal databases and provides the latest legal information. For example, the database will be automatically updated when new laws or precedents are added. The system will also collect updated information from legal databases in real time and the generating AI will provide the latest legal information. For example, the database will be updated immediately when new laws or precedents are enacted. The system will also develop a system in which a generating AI regularly collects updated information from legal databases and provides the latest legal information. For example, the database will be checked daily and automatically updated if new information is found. This will allow the latest legal information to be provided at all times.

[0074] The system can cross-reference information in a legal database and automatically link related laws and precedents. For example, the system builds a system in which a generating AI cross-references information in a legal database and automatically links related laws and precedents. For example, precedents related to a specific law are automatically displayed. The system also cross-references information in a legal database and the generating AI links related laws and precedents. For example, related precedents are automatically displayed when a user searches for a specific law. The system also develops a system in which a generating AI analyzes information in a legal database and automatically links related laws and precedents. For example, precedents related to legal provisions are automatically linked. This makes it possible to automatically link related laws and precedents.

[0075] The system uses an emotion estimation function to provide legal information in a format that is easy for users to understand. For example, the system uses the emotion estimation function to build a system that provides legal information in a format that is easy for users to understand. For example, if the user is feeling stressed, the system provides information in a concise and easy-to-understand format. The system also uses a generation AI to analyze the user's emotional state in real time and provide legal information in an easy-to-understand format. For example, if the user is feeling anxious, the system provides information in a format that gives a sense of security. The system also uses the emotion estimation function to develop a system that provides legal information in a format that is easy for users to understand. For example, if the user is feeling angry, the system provides information in a calm and polite format. This makes it possible to provide legal information in a format that is easy for users to understand.

[0076] The system integrates the legal database with databases in other fields of expertise to respond to complex questions. For example, the system integrates the legal database with databases in other fields of expertise to build a system that can respond to complex questions. For example, it can be integrated with a medical database to respond to questions related to medical-legal matters. The system also uses generative AI to integrate the legal database with databases in other fields of expertise. For example, it can be integrated with a financial database to respond to questions related to financial-legal matters. The system also integrates the legal database with databases in other fields of expertise to develop a system that can respond to complex questions. For example, it can be integrated with an environmental database to respond to questions related to environmental law. This makes it possible to respond to complex questions.

[0077] The system can visualize information in a legal database and display it in graphs or charts. For example, the system builds a system in which a generating AI visualizes information in a legal database and displays it in graphs or charts. For example, it displays the enforcement status of laws and trends in case law in graphs. The system also visualizes information in a legal database and a generating AI displays it in graphs or charts. For example, it displays statistical data on a specific law in a chart. The system also develops a system in which a generating AI analyzes information in a legal database, visualizes it, and displays it in graphs or charts. For example, it displays the history of legal amendments in a graph. This makes it possible to visualize and display information in a legal database.

[0078] The system uses an emotion estimation function to prioritize displaying legal information that the user is most interested in. For example, the system uses the emotion estimation function to build a system that prioritizes displaying legal information that the user is most interested in. For example, the system prioritizes displaying legal information that the user is interested in based on the user's emotion data. The system also uses a generation AI to analyze the user's emotional state in real time and prioritizes displaying legal information that the user is most interested in. For example, the system prioritizes displaying information in legal fields that the user is interested in. The system also uses the emotion estimation function to develop a system that prioritizes displaying legal information that the user is most interested in. For example, the system prioritizes displaying legal information that the user is interested in based on the user's emotion data. This allows the system to prioritize displaying legal information that the user is most interested in.

[0079] The system can automatically classify legal themes for each company and provide answers appropriate for each theme. For example, the system builds a system in which a generating AI automatically classifies legal themes for each company and provides answers customized for each theme. For example, it provides legal information specialized for a specific industry. The system also automatically classifies legal themes for each company and a generating AI provides answers customized for each theme. For example, it provides legal information specialized for the manufacturing industry. The system also develops a system in which a generating AI analyzes legal themes for each company and provides answers customized for each theme. For example, it provides legal information specialized for the IT industry. This makes it possible to provide answers customized according to the legal themes of each company.

[0080] The system can provide preventive legal advice based on a company's legal themes. For example, the system builds a system in which a generative AI provides preventive legal advice based on a company's legal themes. For example, it provides advice on how to avoid specific risks. The system also analyzes a company's legal themes and the generative AI provides preventive legal advice. For example, it provides advice on points to be careful of when drafting contracts. The system also develops a system in which a generative AI provides preventive legal advice based on a company's legal themes. For example, it provides specific advice on compliance with laws and regulations. This makes it possible to provide preventive legal advice based on a company's legal themes.

[0081] The system uses the emotion estimation function to analyze employees' emotional reactions to the company's legal topics and reinforce positive themes. For example, the system uses the emotion estimation function to analyze employees' emotional reactions to the company's legal topics and build a system that reinforces positive themes. For example, it prioritizes topics to which employees have positive reactions. The system also uses a generative AI to analyze employees' emotional reactions in real time and reinforces positive themes. For example, it focuses on legal topics that employees are interested in. The system also uses the emotion estimation function to analyze employees' emotional reactions to the company's legal topics and develop a system that reinforces positive themes. For example, it prioritizes topics to which employees have positive reactions. This makes it possible to analyze employees' emotional reactions to the company's legal topics and reinforce positive themes.

[0082] The system can collect relevant external resources based on a company's legal themes. For example, the system builds a system in which a generating AI automatically collects relevant external resources based on a company's legal themes. For example, it collects expert opinions and academic papers. The system also analyzes a company's legal themes and the generating AI automatically collects relevant external resources. For example, it collects the latest research results and expert opinions on legal matters. The system also develops a system in which a generating AI automatically collects relevant external resources based on a company's legal themes. For example, it collects the latest legal news and expert opinions. This makes it possible to automatically collect relevant external resources based on a company's legal themes.

[0083] The system uses an emotion estimation function to monitor employees' emotions regarding a company's legal issues in real time and implement appropriate responses. For example, a system can be constructed that uses the emotion estimation function to monitor employees' emotions regarding a company's legal issues in real time and implement appropriate responses. For example, if an employee is feeling stressed, responses can be made to help them relax. The system also uses a generative AI to analyze employees' emotional states in real time and implement appropriate responses. For example, if an employee is feeling anxious, responses can be made to give them a sense of security. The system can also use the emotion estimation function to develop a system that monitors employees' emotions regarding a company's legal issues in real time and implement appropriate responses. For example, if an employee is feeling angry, responses can be made to help them calm down. This makes it possible to monitor employees' emotions regarding a company's legal issues in real time and implement appropriate responses.

[0084] The system can evaluate an employee's legal knowledge level and provide an individualized training plan. For example, the system builds a system in which a generative AI evaluates an employee's legal knowledge level and provides an individualized training plan. For example, it can provide basic training for beginners and specialized training for advanced employees. The system also analyzes an employee's legal knowledge level and a generative AI can provide an individualized training plan. For example, it can provide training specialized in a specific legal field. The system also develops a system in which a generative AI evaluates an employee's legal knowledge level and provides an individualized training plan. For example, it can provide training customized according to the employee's knowledge level. This makes it possible to evaluate an employee's legal knowledge level and provide an individualized training plan.

[0085] The system provides simulation-based training to improve employees' risk management skills. For example, the system builds a system in which a generative AI provides simulation-based training to improve employees' risk management skills. For example, it provides a simulation to solve a hypothetical legal problem. The system also uses simulation to provide training in which the generative AI improves employees' risk management skills. For example, it performs a simulation based on an actual legal case. The system also develops a system in which a generative AI provides simulation-based training to improve employees' risk management skills. For example, it provides training based on a risk scenario. In this way, it is possible to provide simulation-based training to improve employees' risk management skills.

[0086] The system can use the emotion estimation function to provide motivational measures to increase employees' motivation to learn. For example, the system uses the emotion estimation function to build a system that provides motivational measures to increase employees' motivation to learn. For example, it displays encouraging messages according to learning progress. The system also uses a generative AI to analyze employees' emotional states in real time and provides motivational measures to increase their motivation to learn. For example, it provides rewards or praise according to learning results. The system also uses the emotion estimation function to develop a system that provides motivational measures to increase employees' motivation to learn. For example, it provides positive feedback when learning goals are achieved. This makes it possible to provide motivational measures to increase employees' motivation to learn.

[0087] The system can extend risk management training to other skills. For example, the system extends risk management training to other skills, and builds a system in which generative AI provides training in project management, etc. For example, it provides training on how to manage project risks. The system also uses generative AI to extend risk management training to other skills, and develops a system in which generative AI provides multifaceted training. For example, it provides training on project management and problem-solving skills. This allows risk management training to be extended to other skills.

[0088] The system can evaluate employees' risk management skills and suggest appropriate positions within the company. For example, the system builds a system in which a generative AI evaluates employees' risk management skills and suggests appropriate positions within the company. For example, employees who are good at risk management are placed in the risk management department. The system also analyzes employees' risk management skills and a generative AI suggests appropriate positions. For example, an employee who is suitable as a project leader is placed in a leadership position. The system also develops a system in which a generative AI evaluates employees' risk management skills and suggests appropriate positions within the company. For example, an employee who is good at risk assessment is placed in a risk assessment team. This makes it possible to evaluate employees' risk management skills and suggest appropriate positions within the company.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The question reception unit not only receives user questions, but also analyzes the trends in user questions and presents predicted questions in advance. For example, if a user has asked many questions about contracts in the past, general questions about contracts can be presented in advance. The question reception unit can also analyze the frequency and time of the user's questions and suggest the optimal time to provide answers. For example, if a user asks many questions at night, the unit can suggest increasing resources to respond at night. The question reception unit can also automatically provide related legal information and reference materials based on the content of the user's question. For example, when a question about contracts is received, related laws and precedents can be automatically displayed. This allows for faster and more appropriate answers to the user's questions.

[0091] The answer generator not only learns the user's past question history, but can also customize answers based on the user's job function and position. For example, it can provide detailed legal interpretations to legal department personnel and basic legal knowledge to general employees. The answer generator can also optimize answers based on the user's industry and company characteristics. For example, it can provide legal information specialized for manufacturing to manufacturing companies and IT-related legal information to IT companies. The answer generator can also predict future legal information needs based on the user's past question history and provide it in advance. For example, if a specific legal amendment is scheduled, it can provide information about that amendment in advance. This allows the system to provide the most appropriate legal information to meet the user's needs.

[0092] The answer generation unit not only automatically generates follow-up questions to understand the intent of the question, but can also collect background information about the user's question and provide a more detailed answer. For example, if a user asks a question about a contract, it can ask about the specific content and purpose of the contract. The answer generation unit can also automatically link relevant laws and precedents to the user's question, allowing the user to quickly obtain the information they need. For example, in response to a question about a labor contract, it can automatically display relevant labor laws and precedents. The answer generation unit can also ask appropriate follow-up questions to more accurately understand the user's intent. For example, it can ask about points that are particularly important when drafting a contract. This allows the intent of the user's question to be more accurately understood and an appropriate answer to be provided.

[0093] The answer generation unit can use the emotion estimation function to not only generate answers according to the user's emotional state, but also provide appropriate legal advice based on the user's emotional state. For example, if the user is feeling stressed, advice to minimize risks is provided. The answer generation unit can also use the emotion estimation function to analyze the user's emotional state in real time and provide legal information according to the emotion. For example, if the user is feeling anxious, legal information that gives a sense of security is provided. The answer generation unit can also use the emotion estimation function to provide specific advice to avoid legal risks based on the user's emotional state. For example, if the user is feeling angry, legal advice to help the user stay calm is provided. This allows the user to receive appropriate legal advice according to their emotional state and reduce stress.

[0094] The system not only develops multi-domain AI chatbots that can handle specialties other than legal matters, but also collaborates with experts in each field to improve the accuracy of responses. For example, for questions in the medical field, the system incorporates the opinions of doctors and medical experts. The system also develops multi-domain AI chatbots that can handle specialties other than legal matters, and can automatically collect the latest information in each field and incorporate it into responses. For example, it can provide responses that reflect the latest regulations and market trends in the financial sector. The system also utilizes generative AI to develop chatbots that can handle specialties other than legal matters, and can optimize the expertise of each field based on the user's question history. For example, it can provide detailed medical information to users who frequently ask questions in the medical field. This allows the system to provide multi-domain AI chatbots that can handle specialties other than legal matters, and collaborates with experts in each field to improve the accuracy of responses.

[0095] The system not only responds to voice input and uses voice recognition technology to answer legal questions, but also provides answers via voice synthesis. For example, when a user voice-inputs a question, the generation AI converts the speech to text, generates an appropriate answer, and provides that answer via voice. The system also utilizes voice recognition technology, allowing the generation AI not only to respond to voice input but also to analyze the voice data and estimate the user's emotional state. For example, it can analyze the tone and speed of the user's voice to determine whether the user is feeling stressed or anxious. The system also responds to voice input and uses voice recognition technology to answer legal questions, but can also more accurately understand the intent of the user's question based on the voice data. For example, it can analyze the intonation and emphasis of the user's voice to identify key points. This allows the system to respond to voice input and provide legal questions using voice recognition and voice synthesis.

[0096] The system uses emotion estimation to analyze the emotions of users when they input questions in real time, making suggestions to elicit positive emotions and providing customized legal information tailored to the user's emotional state. For example, if the user is feeling anxious, it can provide legal information that gives a sense of security. The system also uses generative AI to analyze the user's emotions in real time, making suggestions to elicit positive emotions and providing specific advice to avoid legal risks based on the user's emotional state. For example, if the user is feeling stressed, it can provide legal advice to help them relax. The system also uses emotion estimation to analyze the emotions of users when they input questions, making suggestions to elicit positive emotions and providing legal information tailored to the user's emotional state. For example, if the user is feeling angry, it can provide legal information to help them stay calm. This allows the system to analyze the user's emotions in real time and provide suggestions to elicit positive emotions.

[0097] The system learns the legal department's schedule and notifies legal department personnel when important questions arise, and can also make suggestions to optimize the legal department's resources. For example, if a large number of questions arise during a certain time period, the system can suggest increasing resources to handle those times. The system has also developed a generative AI that learns the legal department's schedule and not only alerts legal department personnel when important questions arise, but also prioritizes responses based on the question's urgency. For example, it can respond immediately to urgent questions and later to less urgent questions. The system's generative AI also analyzes the legal department's schedule and not only notifies legal department personnel in real time when important questions arise, but also makes suggestions to improve the legal department's work efficiency. For example, it can suggest automating certain tasks. This not only notifies legal department personnel when important questions arise, but also makes suggestions to optimize the legal department's resources.

[0098] The system automatically determines the urgency of a question and prioritizes those that require urgent attention. It can also automatically assign questions to the appropriate person based on their content. For example, questions about contracts are assigned to contract specialists, and questions about labor law are assigned to labor law specialists. The system has also developed an algorithm to automatically determine the urgency of a question, allowing it to respond immediately to urgent questions and allocate appropriate resources based on their content. For example, multiple staff members can work together to respond to complex questions. The system's generative AI can also determine the urgency of a question in real time, prioritizing urgent questions and suggesting the optimal response method based on the question's content. For example, it provides quick answers to urgent questions and detailed answers to less urgent questions. This allows it to prioritize urgent questions and automatically assign them to the appropriate person based on their content.

[0099] The system uses emotion estimation to measure a user's stress level and, when stress levels are high, not only generates answers to help them relax but also suggests specific actions to reduce their stress. For example, if a user is feeling stressed, it suggests relaxing exercises or taking a break. The system also uses a generation AI to analyze a user's stress level in real time, and when stress levels are high, it not only generates answers to help them relax but also provides resources to help them reduce their stress. For example, it provides expert opinions and resources on stress management. The system also uses emotion estimation to measure a user's stress level and, when stress levels are high, not only generates answers to help them relax but also suggests long-term measures to reduce their stress. For example, it suggests lifestyle improvements or stress management training to reduce stress. This allows the system to not only provide relaxing answers based on the user's stress level but also provide specific actions and resources.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The question receiving unit receives a question from a user. For example, if the user inputs a question about legal matters, the question receiving unit receives the question. The question receiving unit can also receive a question using voice input. Step 2: The answer generation unit generates an answer based on the question received by the question reception unit. For example, the generation AI generates an appropriate answer to the question using a text generation AI (e.g., LLM). The generation AI can also generate an answer to the question using a multimodal generation AI. The generation AI can also learn from past question history and generate an answer optimized for each individual user. Step 3: The database reference unit verifies the answer generated by the answer generation unit by referring to at least one database of the Six Codes of Law or the latest legal cases. For example, the database reference unit references the Six Codes of Law database to verify whether the generated answer is accurate. The database reference unit also references the latest legal case database to verify whether the generated answer is based on the latest information. Step 4: The notification unit notifies the user of the answer confirmed by the database reference unit. For example, the notification unit sends the generated answer to the user by email. The notification unit can also display the generated answer on the user's chat screen. The notification unit can also push the generated answer to the user's smartphone.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0104] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0107] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0108] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0109] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0111] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0112] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0113] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0114] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0115] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0122] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0123] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0124] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0127] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0128] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0129] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0130] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0131] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0132] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0133] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0134] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0142] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0143] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0144] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0145] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0146] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0148] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0149] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0150] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0151] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0152] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0153] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0154] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0155] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0156] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0157] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0158] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0159] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0160] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0161] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0162] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0163] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0164] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0165] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0166] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0167] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0168] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a question receiving unit that receives questions from users; an answer generation unit that generates an answer based on the question received by the question receiving unit; a database reference unit that checks the answer generated by the answer generation unit by referring to at least one database of the Six Codes of Law or the latest legal cases; a notification unit that notifies the user of the answer confirmed by the database reference unit. A system characterized by:

2. The answer generation unit Learns the user's past question history and generates answers suited to each individual user 2. The system of claim 1.

3. The answer generation unit To understand the intent of the question in more detail, additional questions are automatically generated to clarify the user's intent.

2. The system of claim 1.

4. The answer generation unit Generate answers according to the user's emotional state to reduce stress 2. The system of claim 1.

5. The system comprises: Developing a multi-domain AI chatbot that also covers non-legal fields 2. The system of claim 1.

6. The system comprises: Supports voice input and uses voice recognition technology to answer legal questions 2. The system of claim 1.

7. The system comprises: Analyze the emotions of the user when they enter a question in real time and make suggestions to elicit positive emotions.

2. The system of claim 1.

8. The system comprises: Learn the legal department schedule and notify legal personnel when important questions arise 2. The system of claim 1.

Images