system

Abstract

Provide a system. 【Solution means】 Means for a user to input legal consultation content via a terminal, Means for the terminal to transmit the input data to the server, Means for the server to analyze the received data and extract main keywords, Means for the server to search for relevant information from the internal database and the Internet based on the extracted keywords, Means for the server to form a legal judgment suitable for the user's situation based on the collected information, Means for the server to formulate the legal judgment and convert it into a visually easy-to-understand form, Means for the server to transmit the formulated result to the terminal, Means for the terminal to display the received result to the user, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In current systems that provide legal consultations and advice, it is difficult to obtain specific judgments based on the interpretation of laws and past cases. Also, in order for users to quickly obtain accurate legal advice according to their own situations, in-depth knowledge by experts is required. As a result, corporations and individuals lack a quick and reliable solution to legal problems. Especially in complex tax laws and inheritance issues, quick and accurate information is required, but it is difficult for current systems to meet this requirement.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides the following means: a means for the user to input legal consultation details via a terminal, and a means for transmitting the data entered from the terminal to a server. The server has means for analyzing the received data and extracting key keywords. Furthermore, the server has means for searching for relevant information from an internal database and the internet based on the extracted keywords. The server provides means for forming a legal judgment appropriate to the user's situation based on the collected information, and has means for diagramming this and converting it into a visually easy-to-understand form. By providing means for transmitting the diagrammed result to the terminal and means for displaying the received result to the user, a system is realized in which the user can obtain quick and accurate legal advice.

[0006] A "user" refers to an individual or legal entity that uses the system to input legal consultation details and receive legal advice.

[0007] A "terminal" is an electronic device used by a user to input legal consultation details and send data to a server.

[0008] A "server" is a computer system that receives, analyzes, searches, and provides advice on data sent by users.

[0009] "Data analysis" refers to the process of extracting key keywords from data received by a server and making legal judgments based on these keywords.

[0010] "Keyword extraction" is a technique for identifying key concepts and topics from data entered by a user and extracting related information.

[0011] An "internal database" refers to a collection of information accessible to the server, including laws, past precedents, and regulatory documents.

[0012] "Internet search" refers to the process of obtaining relevant information from publicly available online resources.

[0013] "Legal judgment" is the process of forming legal advice that is most appropriate to the user's situation based on the information collected by the server.

[0014] "Diagramming" refers to the act of converting legal judgments into flowcharts or tabular formats to make them visually easier to understand.

[0015] An "HTTP request" refers to a request that uses the Internet protocol to send data from a terminal to a server.

[0016] Based on the above definitions, the present invention is a system designed to enable users to respond quickly and accurately to legal issues. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map on which a plurality of emotions are mapped. [Figure 10] It shows an emotion map on which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0019] First, the terms used in the following description will be described.

[0020] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units 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), and the like.

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the 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.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention is a system for providing legal consultation and advice, which analyzes the consultation content entered by the user and provides appropriate legal judgments quickly and accurately. This system is realized through the following main components and functions.

[0039] User input

[0040] The user uses their device to enter specific legal questions. For example, if they are asking a question about inheritance tax, they might enter, "My father has passed away, and I have inherited some assets. I would like to know the necessary procedures and the amount of tax."

[0041] Sending and receiving data

[0042] The terminal sends the entered information to the server. This transmission is done using an HTTP request, and the data is encoded in JSON format. The server receives this request and proceeds to the next step.

[0043] Data Analysis

[0044] The server decodes the received data to obtain text data. Then, it uses a natural language processing engine to extract key keywords. For example, "inheritance," "property," and "tax amount" might be extracted.

[0045] Searching for and collecting related information

[0046] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved quickly using SQL queries and Elasticsearch®. Meanwhile, web scraping techniques are used to collect information from the internet, utilizing libraries such as Beautiful Soup and Selenium.

[0047] Formation of legal judgments

[0048] Based on the collected information, the server forms specific legal judgments tailored to the user's situation. For example, it may indicate how to calculate inheritance tax and the necessary procedures. This process executes pre-programmed legal logic.

[0049] Diagramming of results

[0050] The server performs a diagramming process to make legal decisions easier to understand. It uses libraries such as FlowChart.js and D3.js to convert the information into flowcharts and tables. Specifically, it is illustrated in the form of "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0051] Sending and displaying results

[0052] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal parses the received data and displays it in a user-friendly format. This allows the user to quickly obtain specific legal advice.

[0053] Specific example

[0054] For example, if a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be paid," the following process will be performed:

[0055] 1. The user enters the details of their inquiry into the terminal.

[0056] 2. The device sends data to the server.

[0057] 3. The server analyzes the data and extracts keywords such as "inheritance," "assets," and "tax amount."

[0058] 4. The server collects relevant information from its internal database and the internet.

[0059] 5. The server will form specific legal judgments tailored to the user's situation (for example, how to calculate inheritance tax and the necessary procedures).

[0060] 6. The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0061] 7. The server sends the diagrammed results to the terminal.

[0062] 8. The device displays the results to the user.

[0063] This allows users to obtain information to respond quickly and accurately, enabling them to make swift decisions regarding legal issues.

[0064] The following describes the processing flow.

[0065] Step 1:

[0066] The user enters specific legal questions into the device. For example, they might enter, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be owed."

[0067] Step 2:

[0068] The terminal receives the input text data and encodes it into JSON format. Then, it sends the data to the server using an HTTP POST request.

[0069] Step 3:

[0070] The server receives an HTTP request, decodes the received JSON data, and obtains text data.

[0071] Step 4:

[0072] The server uses a natural language processing (NLP) engine to analyze the text data. Specifically, it uses NLP libraries such as SpaCy and NLTK to extract key keywords (e.g., "inheritance," "property," "tax amount").

[0073] Step 5:

[0074] The server searches for relevant information from its internal database and the internet based on the extracted keywords. It retrieves legal texts and past case precedents from the internal database using SQL queries, and collects relevant information from the internet using web scraping techniques. For example, it might use Beautiful Soup or the Selenium library.

[0075] Step 6:

[0076] The server analyzes the collected information and forms legal judgments based on the user's specific situation. Using pre-programmed legal logic, it derives the method for calculating inheritance tax and the necessary procedural steps.

[0077] Step 7:

[0078] The server visualizes the resulting legal judgment in a way that is easy for the user to understand. It uses libraries such as FlowChart.js and D3.js to convert it into flowcharts or tables. For example, it could be structured as follows: "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," "Step 4: Document preparation."

[0079] Step 8:

[0080] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response.

[0081] Step 9:

[0082] The device decodes the received JSON data, parses the results, and displays them on the screen. This allows users to obtain specific legal advice in a visually easy-to-understand format.

[0083] Specific example

[0084] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be paid":

[0085] 1. The user enters the details of their legal consultation into the terminal.

[0086] 2. The device sends data to the server.

[0087] 3. The server receives the data and retrieves the text data.

[0088] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0089] 5. The server searches for and retrieves correlation information from its internal database and the internet.

[0090] 6. The server uses legal logic to derive the inheritance tax calculation method and necessary procedures.

[0091] 7. The server visualizes legal judgments and converts them into a visually easy-to-understand format for the user.

[0092] 8. The server sends the diagrammed results to the terminal.

[0093] 9. The device analyzes the results and displays them on the screen for the user to review.

[0094] This allows users to receive prompt and accurate legal advice.

[0095] (Example 1)

[0096] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] Conventional legal consultation systems struggled to quickly and accurately analyze user-entered consultation content and provide appropriate legal advice. Furthermore, they lacked the technology to efficiently collect relevant information and display results in a visually easy-to-understand format. As a result, it was difficult for users to obtain appropriate legal judgments in a short amount of time. Additionally, natural language processing and information generation based on prompts were not fully utilized.

[0098] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0099] In this invention, the server includes means for analyzing received data and extracting key keywords, means for searching for relevant information from an internal database and the internet based on the extracted keywords, and means for forming a legal judgment appropriate to the user's situation based on the collected information. This enables the user to obtain appropriate legal advice quickly, accurately, and effectively.

[0100] A "user" is an entity that inputs questions or inquiries into the system to receive legal advice and information.

[0101] A "terminal" is an electronic device used by a user to input consultation details into the system, and it is a device that communicates data with the server.

[0102] A "server" is a central processing unit that analyzes data received from users, collects relevant information, forms legal judgments, and transmits them to terminals.

[0103] "Entered data" refers to information about legal consultations provided by the user to the system via their device.

[0104] A "natural language processing engine" is software or an algorithm used to analyze text data and extract key keywords.

[0105] "Keywords" are terms that are considered important in legal judgments and are extracted from the input data by a natural language processing engine.

[0106] An "internal database" is a database containing legal information such as legal texts, past court precedents, and regulatory documents, and is used as storage for servers to quickly retrieve information.

[0107] "Searching for relevant information on the internet" refers to the process of collecting necessary data from publicly available information on the internet using techniques such as web scraping.

[0108] "Legal judgment" refers to specific legal advice or opinions formed based on the user's situation, using information collected by the server.

[0109] "Diagramming in flowchart or tabular format" refers to a method of visually organizing formed legal judgments using libraries such as FlowChart.js or D3.js, making them easy for users to understand.

[0110] A "generative AI model" is a machine learning model that automatically generates relevant information and advice based on specific prompt sentences.

[0111] A "prompt statement" is an instruction given to a generative AI model, a text intended to guide the generation or processing of specific information.

[0112] This invention is a system for providing legal consultations and advice. It analyzes the legal consultation content entered by the user and provides prompt, accurate, and appropriate legal judgments. This system is implemented using the following hardware and software.

[0113] User input

[0114] Users enter specific legal questions using their devices. For example, they might ask, "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax." The devices used can include PCs, smartphones, and tablets. The entered data is retrieved through web forms or text boxes in applications.

[0115] Sending data

[0116] The terminal sends the entered data to the server. This transmission uses an HTTP POST request, and the data is encoded in JSON format. This enables efficient data transmission and reception.

[0117] Data reception and analysis

[0118] The server receives an HTTP request and decodes the JSON data to obtain text data. The server is a high-performance server machine used to execute computer programs. This text data is analyzed using a natural language processing engine, and key keywords are extracted. Libraries such as NLTK (Natural Language Toolkit) and spaCy are used for natural language processing. Furthermore, a generative AI model can be used to generate relevant information based on specific prompt statements.

[0119] Information retrieval and collection

[0120] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved using SQL queries and Elasticsearch. Web scraping techniques using Beautiful Soup and Selenium are utilized to collect information from the internet.

[0121] Formation of legal judgments

[0122] Based on the collected information, the server forms specific legal judgments appropriate to the user's situation. This involves applying pre-programmed legal logic. For example, it may show how to calculate inheritance tax and the necessary procedures. This process may also utilize an artificial intelligence inference engine, and information may be generated based on prompts using a generative AI model.

[0123] Diagramming of results

[0124] The server performs a diagramming process to make legal decisions easier to understand visually. For this purpose, libraries such as FlowChart.js and D3.js are used to convert the information into flowcharts and tables. For example, it may be visually presented as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0125] Sending and displaying results

[0126] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal parses the received data and displays it in a user-friendly format. This display may use a web page or application interface. The user can then obtain quick and accurate legal advice.

[0127] Specific example

[0128] For example, if a user inputs "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax," the following prompt could be input into the AI ​​model:

[0129] "Could you please explain the laws regarding inheritance? My father has passed away, and I have inherited some assets. I would like to know the necessary procedures and the amount of tax involved."

[0130] This allows users to obtain the necessary legal information on the spot and quickly begin taking concrete actions to resolve the problem.

[0131] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0132] Step 1:

[0133] The user enters their legal consultation details using a terminal. The text entered by the user is in the format of, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax." Once the user has finished entering the information, they click the "Submit" button. The input is done through a text box, and the output is a text file of the legal consultation.

[0134] Step 2:

[0135] The terminal sends the legal consultation details entered by the user to the server. This transmission uses an HTTP POST request, and the data is encoded in JSON format. For example, it is sent with the following JSON structure: "{"query": "My father has passed away, and I have inherited property. I would like to know the necessary procedures and tax amount"}". The input is text data, and the output is sent as JSON data.

[0136] Step 3:

[0137] The server receives an HTTP request and decodes the JSON data to obtain text data. The received data is parsed by an internal component. The input is JSON data, and the output is the parsed text data. The text data is stored in a variable within the server.

[0138] Step 4:

[0139] The server uses a natural language processing engine to extract key keywords from text data. For example, it might use NLTK or spaCy to extract keywords such as "inheritance," "property," and "tax amount." The natural language processing engine analyzes the text and identifies important words using a specific algorithm. The input is text data, and the output is a list of keywords.

[0140] Step 5:

[0141] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database contains legal texts, past case precedents, and regulatory documents, and data is quickly retrieved using SQL queries and Elasticsearch. Web scraping using Beautiful Soup and Selenium is used to collect information from the internet. The input is a list of keywords, and the output is data of relevant information.

[0142] Step 6:

[0143] The server uses the collected information to form specific legal judgments tailored to the user's situation. Calculations and reasoning are performed according to programmed legal logic, generating information such as "how to calculate inheritance tax" and "necessary procedures." Using a generative AI model, customized information based on prompts can also be generated for the user's situation. The input is relevant data, and the output is a legal judgment.

[0144] Step 7:

[0145] The server visualizes legal judgments in an easily understandable format. Libraries such as FlowChart.js and D3.js are used to convert the information into flowcharts and tables. For example, it might visually represent steps such as "Step 1: Inheritance Commencement," "Step 2: Property Valuation," "Step 3: Tax Calculation," and "Step 4: Document Preparation." The input is legal judgment data, and the output is generated as diagrammatic data.

[0146] Step 8:

[0147] The server re-encodes the diagrammed results into JSON format and sends them to the terminal. The terminal decodes the received data and displays it on the screen. The user visually reviews the results and understands the specific procedures and necessary actions. The input is diagrammed data, and the output provides the user with visually organized information.

[0148] This allows users to receive legal advice in a specific and easy-to-understand format.

[0149] (Application Example 1)

[0150] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0151] Conventional legal consultation systems struggle to quickly and accurately analyze user-submitted legal consultations and provide appropriate legal judgments. Furthermore, the lack of systems that present legal judgments in a visually clear and easy-to-understand format makes them difficult for users to comprehend. In particular, a system with adaptability to effectively respond to legal consultations attempted by users in virtual spaces is necessary.

[0152] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0153] In this invention, the server includes means for the user to input legal consultation details via a terminal, means for the terminal to transmit the input data to the server, means for the server to analyze the received data and extract key keywords, means for searching for relevant information from databases and networks, means for forming a legal judgment appropriate to the user's situation based on the collected information, means for diagramming the legal judgment and converting it into a visually easy-to-understand form, means for transmitting the diagrammed results to the terminal, and means for the terminal to display the received results to the user and make them visible in a virtual space. This enables rapid and accurate analysis of legal consultation details, provision of appropriate legal judgments, and display of results in a visually easy-to-understand format.

[0154] A "user" is a person who enters details of their legal consultation into a terminal and receives the information.

[0155] A "terminal" refers to a device used by a user to input details of their legal consultation, such as a smartphone, smart glasses, or head-mounted display.

[0156] A "server" is a computer system that analyzes received data, extracts keywords, and forms legal judgments.

[0157] "Data analysis" is the process by which a server receives data sent from a user, understands its content, and extracts key keywords.

[0158] "Key keywords" are important terms extracted when analyzing the legal consultation content entered by the user.

[0159] A "database" is an internal source of information that stores relevant legal information.

[0160] "Network" refers to the internet and other means of obtaining information, providing external sources for collecting legal information.

[0161] "Legal judgment" refers to the conclusions and advice that the server forms regarding the user's legal consultation based on extracted keywords and collected information.

[0162] "Diagramming" is the process of converting legal judgments into a visually easy-to-understand format.

[0163] "Visually easy-to-understand format" refers to information that has been converted into formats such as flowcharts and tables so that users can easily understand legal decisions.

[0164] A "virtual space" is a virtual information environment provided to users through devices such as smart glasses or head-mounted displays.

[0165] To implement this invention, a terminal such as a smartphone, smart glasses, or head-mounted display is used. First, the user inputs the details of their legal consultation via the terminal. For example, they might input, using voice or text input, "My father has passed away, and I have inherited property. I would like to know the necessary procedures and the amount of tax." The terminal then sends the input data to the server.

[0166] The server analyzes the received data and extracts key keywords. For this purpose, the server uses a natural language processing engine (e.g., SpaCy). Based on the extracted keywords, the server searches for relevant information from its internal database and network. The internal database contains legal texts and past case precedents, while external sources include legal information on the network. SQL queries, Elasticsearch, and web scraping techniques (e.g., Beautiful Soup, Selenium) are used for information retrieval.

[0167] Based on the collected information, the server forms a legal judgment appropriate to the user's situation. This legal judgment includes specific advice and procedural instructions. For example, information on how to calculate inheritance tax and the necessary procedures is provided. This legal judgment is then converted into a visually easy-to-understand format. Specifically, it is diagrammed into flowcharts and tables using FlowChart.js or D3.js.

[0168] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal receives this and displays it in a format that is easy for the user to understand. The displayed information is provided in a visually clear manner within the virtual space. For example, when using smart glasses, a flowchart of legal decisions is displayed in front of the user's eyes, allowing them to examine each step in detail.

[0169] As a concrete example, if a user enters the prompt, "My father has passed away, and I will inherit the land and house. How much inheritance tax will I have to pay?", the server will process it in the following steps: First, it will use a natural language processing engine to extract key keywords and collect relevant information from the database and network. Then, it will form a legal judgment appropriate to the user's situation, diagram it in flowchart format, and send it to the terminal. Finally, the user's smart glasses will display "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0170] This allows users to quickly and accurately receive specific advice regarding their legal concerns.

[0171] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0172] Step 1:

[0173] The user enters the details of their legal consultation into their device.

[0174] Users use smartphones, smart glasses, or head-mounted displays to input data via voice or text. For example, they might input, "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax." The input data is in text format.

[0175] Step 2:

[0176] The terminal sends the entered data to the server.

[0177] The terminal encodes the input into JSON format and sends it to the server as an HTTP request. The input data is text data, and the encoded data is in JSON format. The server receives this.

[0178] Step 3:

[0179] The server analyzes the received data and extracts key keywords.

[0180] The server uses a natural language processing engine (e.g., SpaCy) to parse the data. The input is text data in JSON format, and the output after parsing is a list of key keywords (e.g., "inheritance," "property," "tax amount"). Specifically, the text is tokenized and specific parts of speech are extracted.

[0181] Step 4:

[0182] The server searches for relevant information from the database and network based on the extracted keywords.

[0183] The server searches its internal database using SQL queries and Elasticsearch, and gathers necessary information from the internet using Beautiful Soup and Selenium. The input is a list of key keywords, and the output is a set of related information (e.g., legal texts and past court precedents). Specifically, it converts keywords into queries and crawls databases and websites.

[0184] Step 5:

[0185] Based on the information collected by the server, legal judgments appropriate to the user's situation are formed.

[0186] The collected information is integrated, and legal judgments are made based on specific logic. The input is a set of relevant information, and the output is the text of the legal judgment conclusion or advice. In concrete terms, a rule-based algorithm is executed to derive the conclusion.

[0187] Step 6:

[0188] The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0189] The server uses FlowChart.js and D3.js to convert legal judgments into flowcharts and tabular formats. The input is the text of the legal judgment, and the output is visual flowchart or tabular image data. Specifically, it converts each step into a diagram and adds visual elements.

[0190] Step 7:

[0191] The server sends the diagrammed result to the terminal.

[0192] The server re-encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. The input is visual flowchart or tabular data, and the output is JSON data.

[0193] Step 8:

[0194] The results received by the device are displayed to the user and made visible within the virtual space.

[0195] The device decodes the received data and displays it on a smartphone, smart glasses, or head-mounted display. The input is data in JSON format, and the output is information displayed in a visually easy-to-understand format (e.g., "Step 1: Inheritance Commencement", "Step 2: Property Valuation", "Step 3: Tax Amount Calculation", "Step 4: Document Preparation"). Specifically, it analyzes the data and renders it on the screen.

[0196] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0197] This invention combines an emotion recognition engine with a system that provides legal consultation and advice, thereby offering legal judgments that take the user's emotions into consideration. This system includes the following elements and functions.

[0198] User input

[0199] The user uses a terminal to enter details of their legal consultation. For example, in an inquiry regarding inheritance issues, they might enter, "My father has passed away. There are assets to inherit, and I would like to know about the procedures and the amount of tax involved."

[0200] Sending and receiving data

[0201] The terminal encodes the input data into JSON format and sends it to the server as an HTTP POST request. The server receives this request and begins processing the data.

[0202] Data Analysis

[0203] The server decodes the received data and obtains text data. Next, it uses a natural language processing (NLP) engine to extract key keywords. For example, keywords such as "inheritance," "property," and "tax amount" are extracted.

[0204] emotion recognition

[0205] The server uses an emotion recognition engine to analyze emotions (joy, sadness, surprise, etc.) from the user's input data. The emotion recognition engine uses machine learning algorithms to evaluate the emotional state of the input text.

[0206] Searching for and collecting related information

[0207] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved using SQL queries and Elasticsearch. Web scraping techniques are used to collect information from the internet.

[0208] Formation of legal judgments

[0209] The server analyzes the collected information and forms the most appropriate legal judgment based on the user's specific situation and emotional state. For example, if the user is feeling anxious, it will provide legal advice that explains the process in a more careful and detailed manner.

[0210] Diagramming of results

[0211] The server visualizes legal decisions and converts them into a user-friendly format. It uses libraries such as FlowChart.js and D3.js to convert them into flowcharts and tables. For example, steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation" are included.

[0212] Sending and displaying results

[0213] The server encodes the diagrammed results into JSON format and sends them to the terminal. The terminal parses the received data and displays the results on the screen. This allows the user to receive legal advice in a specific and emotionally sensitive manner.

[0214] Specific example

[0215] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and tax amount," and if the user's feelings of grief are recognized,

[0216] 1. The user enters the details of their legal consultation into the terminal.

[0217] 2. The device sends data to the server.

[0218] 3. The server receives the data and retrieves the text data.

[0219] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0220] 5. The server analyzes the user's emotions using an emotion recognition engine and recognizes them as "sadness."

[0221] 6. The server collects relevant information from its internal database and the internet based on keywords and sentiment data.

[0222] 7. The server analyzes the collected information and forms specific legal judgments (e.g., detailed procedural explanations and reassuring advice) that are appropriate to the user's situation and feelings.

[0223] 8. The server diagrams legal judgments to make them visually easy to understand.

[0224] 9. The server sends the diagrammed results to the terminal.

[0225] 10. The terminal displays the results to the user.

[0226] This allows users to receive prompt and emotionally sensitive legal advice.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] The user enters specific legal questions into the device. For example, they might enter, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be owed."

[0230] Step 2:

[0231] The terminal encodes the input data into JSON format and sends it to the server using an HTTP POST request. The server's URL and endpoint are configured, and the data is sent to this endpoint.

[0232] Step 3:

[0233] The server decodes the JSON data from the received HTTP request to obtain text data. This makes the user's input available to the server.

[0234] Step 4:

[0235] The server uses a natural language processing (NLP) engine to analyze the text data. Specifically, it uses NLP libraries such as SpaCy and NLTK to extract key keywords (e.g., "inheritance," "property," "tax amount").

[0236] Step 5:

[0237] The server uses an emotion recognition engine to analyze emotions from the user's input text. Possible algorithms used include emotion classifiers and emotion analysis models (e.g., BERT or Sentiment140). Based on the user's text content, it identifies emotions such as "joy," "sadness," and "anxiety."

[0238] Step 6:

[0239] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database contains legal texts, past case precedents, and regulatory documents, from which necessary information is retrieved using SQL queries and Elasticsearch. Web scraping techniques are used to collect data from the internet. Specifically, libraries such as Beautiful Soup and Selenium are utilized.

[0240] Step 7:

[0241] The server uses the collected information to form legal judgments based on the user's specific situation and emotions. In certain cases, it will show how to calculate inheritance tax and the necessary procedures. If the emotional state is "sadness," a more careful and reassuring explanation will be provided.

[0242] Step 8:

[0243] The server visualizes the formed legal judgment and converts it into a format that is easy for the user to understand. It uses libraries such as FlowChart.js and D3.js to convert it into flowcharts and tables. For example, steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation" are visualized.

[0244] Step 9:

[0245] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. This data includes detailed instructions along with emotionally sensitive explanations.

[0246] Step 10:

[0247] The device decodes the received JSON data, analyzes the results, and displays them on the screen in a user-friendly format. The user can then review these results and obtain specific instructions and advice.

[0248] Specific example

[0249] If a user enters "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax," and the emotion recognition engine recognizes the emotion of "sadness":

[0250] 1. The user enters the details of their legal consultation into the terminal.

[0251] 2. The device sends data to the server.

[0252] 3. The server receives the data and retrieves the text data.

[0253] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0254] 5. The server recognizes the emotion of "sadness" using its emotion recognition engine.

[0255] 6. The server collects relevant information from its internal database and the internet based on keywords and sentiment data.

[0256] 7. Based on the collected information, the server forms the most appropriate legal judgment for the user's situation and feelings (e.g., providing clear procedural explanations and reassurance).

[0257] 8. The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0258] 9. The server sends the diagrammed results to the terminal.

[0259] 10. The device analyzes the results and displays them on the screen for the user to review.

[0260] This process allows users to receive prompt and emotionally sensitive legal advice.

[0261] (Example 2)

[0262] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0263] Conventional legal consultation systems rarely provide legal judgments that take into account the user's emotional state, relying solely on entered text data. Therefore, even when a user requires emotional support, this need is often not met. Users facing legal problems often experience stress and anxiety, making emotionally sensitive responses essential. Consequently, a system is needed that provides legal judgments while considering the user's emotions.

[0264] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing received data and extracting key keywords, means for analyzing emotions from user input data using an emotion recognition engine, and means for searching for relevant information from an internal database and the internet based on the extracted keywords and emotion data. This makes it possible to make legal judgments that take into account the user's emotional state.

[0265] A "user" is an individual or legal entity that uses the system to seek legal advice.

[0266] A "terminal" is a device used by a user to input data and send and receive data with a server. Specifically, this refers to computers, smartphones, tablets, and other similar devices.

[0267] A "server" is a device that receives and analyzes data transmitted from a terminal, and searches for and visualizes related information.

[0268] "Legal consultation content" refers to legal questions or issues entered by the user via their device. For example, it could be content related to specific cases such as inheritance, property division, or tax calculations.

[0269] "Data" refers to the text information entered by the user, the results of its analysis, and related information.

[0270] An "NLP engine" is software used for natural language processing and has the function of extracting key keywords from text data.

[0271] An "emotion recognition engine" is software that implements machine learning algorithms to analyze emotions from user input data.

[0272] "Keywords" are important terms in the user's legal consultation, extracted by the NLP engine. Examples include "inheritance," "property," and "tax amount."

[0273] "Emotional data" refers to information that indicates the emotional state contained in the user's input data, as analyzed by the emotion recognition engine.

[0274] "Related information" refers to information obtained from internal databases and the internet based on extracted keywords and sentiment data. This includes legal texts, past case precedents, and regulatory documents.

[0275] An "internal database" is a database that stores legal information, past court precedents, etc., and is used by the server to retrieve information using SQL queries and Elasticsearch.

[0276] "Information gathering from the internet" refers to the method of collecting relevant information from the internet using web scraping techniques.

[0277] "Legal judgment" refers to providing legal advice or judgments that are appropriate to the user's situation and emotional state, based on the information collected by the server.

[0278] "Diagramming" is the process of converting legal judgments into visually easy-to-understand forms such as flowcharts and tables.

[0279] A flowchart is a diagram that visually represents a series of procedures or processes, making it easier for users to understand the flow of those procedures.

[0280] This invention combines an emotion recognition engine with a system that provides legal consultation and advice, thereby offering legal judgments that take the user's emotions into consideration. This system includes the following elements and functions.

[0281] User input

[0282] The user inputs legal consultation content using a terminal. For example, the user inputs "My father has passed away. There is property to be inherited, and I want to know the procedures and tax amounts." The terminal accepts the input and prepares the text data.

[0283] Data transmission and reception

[0284] The terminal encodes the input text data in JSON format and sends it to the server as an HTTP POST request. The server receives the HTTP request, decodes it, and obtains the data.

[0285] Data analysis (keyword extraction)

[0286] The server decodes the received data to obtain the text data. Next, it uses a natural language processing (NLP) engine to extract the main keywords. Specifically, it utilizes libraries such as SpaCy and NLTK to extract important keywords such as "inheritance", "property", and "tax amount".

[0287] Sentiment recognition

[0288] The server inputs the received text data into a sentiment recognition engine to analyze the user's sentiment. This sentiment recognition engine is a model trained using machine learning frameworks such as TENSORFLOW (registered trademark) and PyTorch. Specifically, it classifies sentiments such as "joy", "sadness", and "anxiety" from the input text.

[0289] Search and collection of related information

[0290] Based on the extracted keywords and sentiment data, the server collects related information from an internal database (SQL query or ElasticSearch) and the Internet (web scraping). The internal database stores legal texts, past cases, regulatory documents, etc.

[0291] Formation of legal judgments

[0292] The server analyzes the collected information and forms the most appropriate legal judgment based on the user's specific situation and emotional state. For example, if the user is experiencing sadness, it will provide a more considerate and reassuring explanation of the procedure.

[0293] Diagramming of results

[0294] The server visualizes legal decisions and converts them into a user-friendly format. This involves using visual libraries such as FlowChart.js and D3.js to convert them into flowcharts and tables. Specific examples include steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0295] Sending and displaying results

[0296] The server encodes the diagrammed results into JSON format and sends them to the terminal. The terminal parses the received data and displays it on the screen in a visually easy-to-understand format. Specifically, a flowchart and step-by-step explanations are displayed.

[0297] Specific example

[0298] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and tax amount," and if feelings of grief are recognized, the following steps will be taken.

[0299] 1. The user enters the details of their legal consultation into their device.

[0300] 2. The terminal sends the input data to the server.

[0301] 3. The server receives the data and retrieves the text data.

[0302] 4. The server uses the NLP engine to analyze the data and extracts keywords such as "inheritance", "property", and "tax amount".

[0303] 5. The server uses the emotion recognition engine to analyze the user's emotion and recognizes it as "sadness".

[0304] 6. Based on the keywords and emotion data, the server collects relevant information from the internal database and the Internet.

[0305] 7. The server analyzes the collected information and forms a specific legal judgment suitable for the user's situation and emotion (e.g., a detailed procedure explanation and advice that gives a sense of reassurance).

[0306] 8. The server formulates the legal judgment into a diagram to make it visually understandable.

[0307] 9. The server sends the diagrammed result to the terminal.

[0308] 10. The terminal displays the result to the user.

[0309] Specific example of the prompt text for the generative AI model

[0310] "My father has passed away and there is property to be inherited. I would like a detailed explanation of the necessary procedures and tax amounts. Also, perform an emotion analysis and please explain particularly carefully if the user is anxious."

[0311] The flow of the specific process in Example 2 will be described using FIG. 13.

[0312] Step 1:

[0313] The user inputs the legal consultation content via the terminal. The input includes specific consultation content such as "My father has passed away. There is property to be inherited, but I want to know the procedures and tax amounts." The terminal saves the text data input by the user in the internal memory. The output at this stage is the input text data.

[0314] Step 2:

[0315] The terminal encodes the input data into JSON format and sends it to the server as an HTTP POST request. Specifically, it uses an encoder that converts text data into JSON format. The input is text data from the user, and the output is JSON data sent to the server.

[0316] Step 3:

[0317] The server receives an HTTP request, decodes the received JSON data, and retrieves text data. The input is JSON data sent from the terminal, and the output is the decoded text data. Specifically, the decoding process uses a JSON decoding library.

[0318] Step 4:

[0319] The server passes the decoded text data to a natural language processing (NLP) engine to extract key keywords. The input is text data, which the NLP engine (e.g., spaCy or NLTK) analyzes to extract key keywords (e.g., "inheritance," "property," "tax amount"). The output is a list of the extracted keywords.

[0320] Step 5:

[0321] The server inputs text data into an emotion recognition engine to analyze the user's emotions. The input is text data, and the emotion recognition engine uses machine learning algorithms to classify emotions such as "joy," "sadness," and "anxiety." The output is emotion data, and "sadness" is detected as an example.

[0322] Step 6:

[0323] The server collects relevant information from its internal database and the internet based on extracted keywords and sentiment data. The input consists of keywords and sentiment data, and the server executes SQL queries on the internal database or retrieves information from the internet using web scraping techniques. The output is a set of collected relevant information.

[0324] Step 7:

[0325] The server analyzes the collected information and forms the optimal legal judgment based on the user's specific situation and emotional state. The input consists of relevant information and the user's emotional data, and the server uses an analytical algorithm to make a legal judgment. The output is the formed legal judgment. For example, if the user is experiencing sadness, a more polite and reassuring explanation of the procedure will be generated.

[0326] Step 8:

[0327] The server visualizes legal judgments and converts them into a user-friendly format. The input is text data of legal judgments, which are converted into flowcharts and tables using visual libraries such as FlowChart.js and D3.js. The output is the visualized information.

[0328] Step 9:

[0329] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. The input is the diagrammed information, which is encoded using a JSON encoder. The output is the JSON data sent to the terminal.

[0330] Step 10:

[0331] The terminal decodes the JSON data received from the server and displays it on the screen in a visually easy-to-understand format. The input is JSON data sent from the server, which is decoded and then re-diagrammed. The specific output is a flowchart and step-by-step explanation visually displayed on the browser screen.

[0332] (Application Example 2)

[0333] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0334] Traditional legal consultation systems tended to provide only mechanical answers, failing to consider the user's emotional state. This made it difficult to offer appropriate legal advice tailored to the situation, resulting in a lack of support for users experiencing anxiety and stress. Furthermore, in the rapidly evolving security landscape, there was a growing need for a system that could provide legal judgments that took emotions into account.

[0335] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input legal consultation content via a terminal, means for the terminal to transmit the input data to the server, means for the server to analyze the received data and extract key keywords, means for the server to search for relevant information from an internal database and the internet based on the extracted keywords, means for the server to form a legal judgment appropriate to the user's situation based on the information collected, means for the server to diagram the legal judgment and convert it into a visually easy-to-understand form, means for the server to transmit the diagrammed result to the terminal, means for the terminal to display the received result to the user, and means for analyzing the user's emotions using an emotion recognition engine and providing a legal judgment that takes the emotion data into consideration. This makes it possible to provide legal advice that takes the user's emotions into consideration, and can support quick and appropriate legal judgments that respond to emotions, especially in security settings.

[0336] A "user" is a person who uses a terminal to seek legal advice.

[0337] A "terminal" is a device used by users to input legal consultation details and to send and receive data with the server.

[0338] A "server" is a central processing unit that analyzes received data, searches for and collects necessary information, and forms and diagrams legal judgments.

[0339] "Data" refers to information such as legal consultation details and emotion recognition results entered by the user via their device.

[0340] "Keywords" are words and phrases that are important for understanding the legal consultation content, extracted through natural language processing.

[0341] An "internal database" is an electronic database that holds legal information such as legal texts, past court precedents, and regulatory documents.

[0342] The "Internet" is a network used to obtain additional relevant information from external sources.

[0343] "Related information" refers to laws, precedents, and regulatory documents that are searched based on the content of the legal consultation.

[0344] A "legal judgment" is a decision that provides appropriate advice or instructions regarding legal matters.

[0345] "Diagramming" refers to the process of converting legal judgments into flowcharts or tables to make them visually easier to understand.

[0346] An "emotion recognition engine" is a system that uses a machine learning algorithm to analyze emotions from user input data and evaluate their content.

[0347] "Emotional data" refers to information that indicates the user's emotional state as analyzed by an emotion recognition engine.

[0348] This invention is a system in which a user inputs legal consultation details via a terminal, and a server analyzes, searches, judges, and diagrams the input content, finally sending the visualized results to the terminal for display. Furthermore, by incorporating an emotion recognition engine, it also provides legal advice that takes into account the user's emotional state.

[0349] Hardware and software to use

[0350] Hardware:

[0351] Devices (e.g., smart glasses, smartphones, head-mounted displays)

[0352] Server (cloud server)

[0353] software:

[0354] Natural language processing engine (e.g., Google® NLP API)

[0355] Emotion recognition engine (e.g., Microsoft® Azure® Emotion API)

[0356] Databases (e.g., MySQL®, Elasticsearch)

[0357] Visualization libraries (e.g., FlowChart.js)

[0358] Detailed explanation of data processing and data calculations.

[0359] Users input their legal consultation details using devices such as smart glasses or smartphones. The entered data is sent from the device to the server in JSON format. As a specific example, consider a case where a user inputs, "An intruder has entered the facility. How should I respond?"

[0360] The server decodes the received data to obtain text data. A natural language processing (NLP) engine is then used to extract key keywords from this text data. For example, keywords such as "intruder," "facility," and "response" might be extracted.

[0361] Next, the server uses an emotion recognition engine to analyze the user's input data to determine their emotions. For example, in the case of this prompt, emotions such as "tension" and "anxiety" are recognized.

[0362] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database includes laws, past cases, and regulatory documents, and is searched and retrieved using SQL queries and Elasticsearch.

[0363] Next, the server analyzes the retrieved and collected information to form the most appropriate legal judgment for the user's situation and emotional state. For example, if the user is anxious, it first advises them to calm down and then provides a step-by-step response plan in flowchart format.

[0364] Finally, the server visualizes the legal judgment it has formed and converts it into a flowchart or table using the FlowChart.js library. The visualized result is sent back to the terminal in JSON format, which the terminal parses and displays visually to the user. This allows the user to receive legal advice quickly and in an emotionally sensitive manner.

[0365] Specific example

[0366] Example of a prompt:

[0367] "An intruder has entered the facility. How should we respond?"

[0368] In this specific example, the user's input is analyzed along with their emotions such as "tension" and "anxiety," and appropriate legal response procedures (for example, advice on how to calm down or specific ways to deal with an intruder) are provided in flowchart format.

[0369] In this way, this system allows users to receive not only prompt on-site support but also emotional care, enabling them to deal with situations with greater peace of mind.

[0370] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0371] Step 1:

[0372] The user enters their legal consultation details into a device. The user enters their legal consultation details in text format using a device such as smart glasses or a smartphone. The user's input is captured by the device and stored as a prompt. For example, the prompt might read, "An intruder has entered the facility. How should I respond?"

[0373] Step 2:

[0374] The terminal sends the entered data to the server. The terminal encodes the entered text data into JSON format and sends it to the server as an HTTP POST request. The specific actions of this step are encoding and sending the HTTP request. The input is the legal consultation content entered by the user, and the output is the JSON data sent to the server.

[0375] Step 3:

[0376] The server analyzes the received data and extracts key keywords. The server decodes the received JSON data to obtain text data. Next, it uses a natural language processing engine (NLP engine) to extract key keywords. For example, keywords such as "intruder," "facility," and "response" may be extracted. In this step, the input is the JSON data sent to the server, and the output is the extracted keywords.

[0377] Step 4:

[0378] The server uses an emotion recognition engine to analyze emotions from the user's input data. The server inputs the extracted text data into the emotion recognition engine and analyzes emotions such as "tension" and "anxiety." In this step, the input is the text data sent to the server, and the output is the analyzed emotion data.

[0379] Step 5:

[0380] The server searches for relevant information from its internal database and the internet based on the extracted keywords and sentiment data. The server uses SQL queries and Elasticsearch to search for relevant laws and precedents in its internal database. It also collects additional information from the internet as needed. In this step, the input is keywords and sentiment data, and the output is a set of relevant information.

[0381] Step 6:

[0382] Based on the information collected by the server, it forms a legal judgment appropriate to the user's situation and emotional state. The server combines the collected legal information with the user's emotional state to make the optimal legal judgment. For example, if the user is anxious, it first provides calming advice and then carefully explains how to deal with the situation. In this step, the input is relevant information and emotional data, and the output is the formed legal judgment.

[0383] Step 7:

[0384] The server diagrams legal judgments and converts them into a visually easy-to-understand format. The server then uses the FlowChart.js library to convert the formed legal judgments into flowcharts and tables. By visually showing specific procedures and steps, it makes it easier for users to understand. In this step, the input is the legal judgment, and the output is a diagrammed flowchart or table.

[0385] Step 8:

[0386] The server sends the diagrammed result to the terminal. The server re-encodes the diagrammed data into JSON format and sends it to the terminal as an HTTP response. In this step, the input is the diagrammed legal judgment, and the output is the JSON data sent to the terminal.

[0387] Step 9:

[0388] The terminal displays the results it receives to the user. The terminal decodes the JSON data received from the server and displays the visual judgment result. The user can view the flowchart or tabular legal advice through smart glasses or a smartphone display. In this step, the input is the JSON data sent from the server, and the output is the visual result displayed to the user.

[0389] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0390] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0391] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0392] [Second Embodiment]

[0393] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0394] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0395] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0396] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0397] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0398] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0399] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0400] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0401] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0402] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0403] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0404] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0405] This invention is a system for providing legal consultation and advice, which analyzes the consultation content entered by the user and provides appropriate legal judgments quickly and accurately. This system is realized through the following main components and functions.

[0406] User input

[0407] The user uses their device to enter specific legal questions. For example, if they are asking a question about inheritance tax, they might enter, "My father has passed away, and I have inherited some assets. I would like to know the necessary procedures and the amount of tax."

[0408] Sending and receiving data

[0409] The terminal sends the entered information to the server. This transmission is done using an HTTP request, and the data is encoded in JSON format. The server receives this request and proceeds to the next step.

[0410] Data Analysis

[0411] The server decodes the received data to obtain text data. Then, it uses a natural language processing engine to extract key keywords. For example, "inheritance," "property," and "tax amount" might be extracted.

[0412] Searching for and collecting related information

[0413] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved quickly using SQL queries and Elasticsearch. Meanwhile, web scraping techniques are used to collect information from the internet, utilizing libraries such as Beautiful Soup and Selenium.

[0414] Formation of legal judgments

[0415] Based on the collected information, the server forms specific legal judgments tailored to the user's situation. For example, it may indicate how to calculate inheritance tax and the necessary procedures. This process executes pre-programmed legal logic.

[0416] Diagramming of results

[0417] The server performs a diagramming process to make legal decisions easier to understand. It uses libraries such as FlowChart.js and D3.js to convert the information into flowcharts and tables. Specifically, it is illustrated in the form of "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0418] Sending and displaying results

[0419] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal parses the received data and displays it in a user-friendly format. This allows the user to quickly obtain specific legal advice.

[0420] Specific example

[0421] For example, if a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be paid," the following process will be performed:

[0422] 1. The user enters the details of their inquiry into the terminal.

[0423] 2. The device sends data to the server.

[0424] 3. The server analyzes the data and extracts keywords such as "inheritance," "assets," and "tax amount."

[0425] 4. The server collects relevant information from its internal database and the internet.

[0426] 5. The server will form specific legal judgments tailored to the user's situation (for example, how to calculate inheritance tax and the necessary procedures).

[0427] 6. The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0428] 7. The server sends the diagrammed results to the terminal.

[0429] 8. The device displays the results to the user.

[0430] This allows users to obtain information to respond quickly and accurately, enabling them to make swift decisions regarding legal issues.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] The user enters specific legal questions into the device. For example, they might enter, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be owed."

[0434] Step 2:

[0435] The terminal receives the input text data and encodes it into JSON format. Then, it sends the data to the server using an HTTP POST request.

[0436] Step 3:

[0437] The server receives an HTTP request, decodes the received JSON data, and obtains text data.

[0438] Step 4:

[0439] The server uses a natural language processing (NLP) engine to analyze the text data. Specifically, it uses NLP libraries such as SpaCy and NLTK to extract key keywords (e.g., "inheritance," "property," "tax amount").

[0440] Step 5:

[0441] The server searches for relevant information from its internal database and the internet based on the extracted keywords. It retrieves legal texts and past case precedents from the internal database using SQL queries, and collects relevant information from the internet using web scraping techniques. For example, it might use Beautiful Soup or the Selenium library.

[0442] Step 6:

[0443] The server analyzes the collected information and forms legal judgments based on the user's specific situation. Using pre-programmed legal logic, it derives the method for calculating inheritance tax and the necessary procedural steps.

[0444] Step 7:

[0445] The server visualizes the resulting legal judgment in a way that is easy for the user to understand. It uses libraries such as FlowChart.js and D3.js to convert it into flowcharts or tables. For example, it could be structured as follows: "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," "Step 4: Document preparation."

[0446] Step 8:

[0447] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response.

[0448] Step 9:

[0449] The device decodes the received JSON data, parses the results, and displays them on the screen. This allows users to obtain specific legal advice in a visually easy-to-understand format.

[0450] Specific example

[0451] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be paid":

[0452] 1. The user enters the details of their legal consultation into the terminal.

[0453] 2. The device sends data to the server.

[0454] 3. The server receives the data and retrieves the text data.

[0455] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0456] 5. The server searches for and retrieves correlation information from its internal database and the internet.

[0457] 6. The server uses legal logic to derive the inheritance tax calculation method and necessary procedures.

[0458] 7. The server visualizes legal judgments and converts them into a visually easy-to-understand format for the user.

[0459] 8. The server sends the diagrammed results to the terminal.

[0460] 9. The device analyzes the results and displays them on the screen for the user to review.

[0461] This allows users to receive prompt and accurate legal advice.

[0462] (Example 1)

[0463] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0464] Conventional legal consultation systems struggled to quickly and accurately analyze user-entered consultation content and provide appropriate legal advice. Furthermore, they lacked the technology to efficiently collect relevant information and display results in a visually easy-to-understand format. As a result, it was difficult for users to obtain appropriate legal judgments in a short amount of time. Additionally, natural language processing and information generation based on prompts were not fully utilized.

[0465] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0466] In this invention, the server includes means for analyzing received data and extracting key keywords, means for searching for relevant information from an internal database and the internet based on the extracted keywords, and means for forming a legal judgment appropriate to the user's situation based on the collected information. This enables the user to obtain appropriate legal advice quickly, accurately, and effectively.

[0467] A "user" is an entity that inputs questions or inquiries into the system to receive legal advice and information.

[0468] A "terminal" is an electronic device used by a user to input consultation details into the system, and it is a device that communicates data with the server.

[0469] A "server" is a central processing unit that analyzes data received from users, collects relevant information, forms legal judgments, and transmits them to terminals.

[0470] "Entered data" refers to information about legal consultations provided by the user to the system via their device.

[0471] A "natural language processing engine" is software or an algorithm used to analyze text data and extract key keywords.

[0472] "Keywords" are terms that are considered important in legal judgments and are extracted from the input data by a natural language processing engine.

[0473] An "internal database" is a database containing legal information such as legal texts, past court precedents, and regulatory documents, and is used as storage for servers to quickly retrieve information.

[0474] "Searching for relevant information on the internet" refers to the process of collecting necessary data from publicly available information on the internet using techniques such as web scraping.

[0475] "Legal judgment" refers to specific legal advice or opinions formed based on the user's situation, using information collected by the server.

[0476] "Diagramming in flowchart or tabular format" refers to a method of visually organizing formed legal judgments using libraries such as FlowChart.js or D3.js, making them easy for users to understand.

[0477] A "generative AI model" is a machine learning model that automatically generates relevant information and advice based on specific prompt sentences.

[0478] A "prompt statement" is an instruction given to a generative AI model, a text intended to guide the generation or processing of specific information.

[0479] This invention is a system for providing legal consultations and advice. It analyzes the legal consultation content entered by the user and provides prompt, accurate, and appropriate legal judgments. This system is implemented using the following hardware and software.

[0480] User input

[0481] Users enter specific legal questions using their devices. For example, they might ask, "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax." The devices used can include PCs, smartphones, and tablets. The entered data is retrieved through web forms or text boxes in applications.

[0482] Sending data

[0483] The terminal sends the entered data to the server. This transmission uses an HTTP POST request, and the data is encoded in JSON format. This enables efficient data transmission and reception.

[0484] Data reception and analysis

[0485] The server receives an HTTP request and decodes the JSON data to obtain text data. The server is a high-performance server machine used to execute computer programs. This text data is analyzed using a natural language processing engine, and key keywords are extracted. Libraries such as NLTK (Natural Language Toolkit) and spaCy are used for natural language processing. Furthermore, a generative AI model can be used to generate relevant information based on specific prompt statements.

[0486] Information retrieval and collection

[0487] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved using SQL queries and Elasticsearch. Web scraping techniques using Beautiful Soup and Selenium are utilized to collect information from the internet.

[0488] Formation of legal judgments

[0489] Based on the collected information, the server forms specific legal judgments appropriate to the user's situation. This involves applying pre-programmed legal logic. For example, it may show how to calculate inheritance tax and the necessary procedures. This process may also utilize an artificial intelligence inference engine, and information may be generated based on prompts using a generative AI model.

[0490] Diagramming of results

[0491] The server performs a diagramming process to make legal decisions easier to understand visually. For this purpose, libraries such as FlowChart.js and D3.js are used to convert the information into flowcharts and tables. For example, it may be visually presented as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0492] Sending and displaying results

[0493] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal parses the received data and displays it in a user-friendly format. This display may use a web page or application interface. The user can then obtain quick and accurate legal advice.

[0494] Specific example

[0495] For example, if a user inputs "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax," the following prompt could be input into the AI ​​model:

[0496] "Could you please explain the laws regarding inheritance? My father has passed away, and I have inherited some assets. I would like to know the necessary procedures and the amount of tax involved."

[0497] This allows users to obtain the necessary legal information on the spot and quickly begin taking concrete actions to resolve the problem.

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] The user enters their legal consultation details using a terminal. The text entered by the user is in the format of, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax." Once the user has finished entering the information, they click the "Submit" button. The input is done through a text box, and the output is a text file of the legal consultation.

[0501] Step 2:

[0502] The terminal sends the legal consultation details entered by the user to the server. This transmission uses an HTTP POST request, and the data is encoded in JSON format. For example, it is sent with the following JSON structure: "{"query": "My father has passed away, and I have inherited property. I would like to know the necessary procedures and tax amount"}". The input is text data, and the output is sent as JSON data.

[0503] Step 3:

[0504] The server receives an HTTP request and decodes the JSON data to obtain text data. The received data is parsed by an internal component. The input is JSON data, and the output is the parsed text data. The text data is stored in a variable within the server.

[0505] Step 4:

[0506] The server uses a natural language processing engine to extract key keywords from text data. For example, it might use NLTK or spaCy to extract keywords such as "inheritance," "property," and "tax amount." The natural language processing engine analyzes the text and identifies important words using a specific algorithm. The input is text data, and the output is a list of keywords.

[0507] Step 5:

[0508] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database contains legal texts, past case precedents, and regulatory documents, and data is quickly retrieved using SQL queries and Elasticsearch. Web scraping using Beautiful Soup and Selenium is used to collect information from the internet. The input is a list of keywords, and the output is data of relevant information.

[0509] Step 6:

[0510] The server uses the collected information to form specific legal judgments tailored to the user's situation. Calculations and reasoning are performed according to programmed legal logic, generating information such as "how to calculate inheritance tax" and "necessary procedures." Using a generative AI model, customized information based on prompts can also be generated for the user's situation. The input is relevant data, and the output is a legal judgment.

[0511] Step 7:

[0512] The server visualizes legal judgments in an easily understandable format. Libraries such as FlowChart.js and D3.js are used to convert the information into flowcharts and tables. For example, it might visually represent steps such as "Step 1: Inheritance Commencement," "Step 2: Property Valuation," "Step 3: Tax Calculation," and "Step 4: Document Preparation." The input is legal judgment data, and the output is generated as diagrammatic data.

[0513] Step 8:

[0514] The server re-encodes the diagrammed results into JSON format and sends them to the terminal. The terminal decodes the received data and displays it on the screen. The user visually reviews the results and understands the specific procedures and necessary actions. The input is diagrammed data, and the output provides the user with visually organized information.

[0515] This allows users to receive legal advice in a specific and easy-to-understand format.

[0516] (Application Example 1)

[0517] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0518] Conventional legal consultation systems struggle to quickly and accurately analyze user-submitted legal consultations and provide appropriate legal judgments. Furthermore, the lack of systems that present legal judgments in a visually clear and easy-to-understand format makes them difficult for users to comprehend. In particular, a system with adaptability to effectively respond to legal consultations attempted by users in virtual spaces is necessary.

[0519] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0520] In this invention, the server includes means for the user to input legal consultation details via a terminal, means for the terminal to transmit the input data to the server, means for the server to analyze the received data and extract key keywords, means for searching for relevant information from databases and networks, means for forming a legal judgment appropriate to the user's situation based on the collected information, means for diagramming the legal judgment and converting it into a visually easy-to-understand form, means for transmitting the diagrammed results to the terminal, and means for the terminal to display the received results to the user and make them visible in a virtual space. This enables rapid and accurate analysis of legal consultation details, provision of appropriate legal judgments, and display of results in a visually easy-to-understand format.

[0521] A "user" is a person who enters details of their legal consultation into a terminal and receives the information.

[0522] A "terminal" refers to a device used by a user to input details of their legal consultation, such as a smartphone, smart glasses, or head-mounted display.

[0523] A "server" is a computer system that analyzes received data, extracts keywords, and forms legal judgments.

[0524] "Data analysis" is the process by which a server receives data sent from a user, understands its content, and extracts key keywords.

[0525] "Key keywords" are important terms extracted when analyzing the legal consultation content entered by the user.

[0526] A "database" is an internal source of information that stores relevant legal information.

[0527] "Network" refers to the internet and other means of obtaining information, providing external sources for collecting legal information.

[0528] "Legal judgment" refers to the conclusions and advice that the server forms regarding the user's legal consultation based on extracted keywords and collected information.

[0529] "Diagramming" is the process of converting legal judgments into a visually easy-to-understand format.

[0530] "Visually easy-to-understand format" refers to information that has been converted into formats such as flowcharts and tables so that users can easily understand legal decisions.

[0531] A "virtual space" is a virtual information environment provided to users through devices such as smart glasses or head-mounted displays.

[0532] To implement this invention, a terminal such as a smartphone, smart glasses, or head-mounted display is used. First, the user inputs the details of their legal consultation via the terminal. For example, they might input, using voice or text input, "My father has passed away, and I have inherited property. I would like to know the necessary procedures and the amount of tax." The terminal then sends the input data to the server.

[0533] The server analyzes the received data and extracts key keywords. For this purpose, the server uses a natural language processing engine (e.g., SpaCy). Based on the extracted keywords, the server searches for relevant information from its internal database and network. The internal database contains legal texts and past case precedents, while external sources include legal information on the network. SQL queries, Elasticsearch, and web scraping techniques (e.g., Beautiful Soup, Selenium) are used for information retrieval.

[0534] Based on the collected information, the server forms a legal judgment appropriate to the user's situation. This legal judgment includes specific advice and procedural instructions. For example, information on how to calculate inheritance tax and the necessary procedures is provided. This legal judgment is then converted into a visually easy-to-understand format. Specifically, it is diagrammed into flowcharts and tables using FlowChart.js or D3.js.

[0535] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal receives this and displays it in a format that is easy for the user to understand. The displayed information is provided in a visually clear manner within the virtual space. For example, when using smart glasses, a flowchart of legal decisions is displayed in front of the user's eyes, allowing them to examine each step in detail.

[0536] As a concrete example, if a user enters the prompt, "My father has passed away, and I will inherit the land and house. How much inheritance tax will I have to pay?", the server will process it in the following steps: First, it will use a natural language processing engine to extract key keywords and collect relevant information from the database and network. Then, it will form a legal judgment appropriate to the user's situation, diagram it in flowchart format, and send it to the terminal. Finally, the user's smart glasses will display "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0537] This allows users to quickly and accurately receive specific advice regarding their legal concerns.

[0538] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0539] Step 1:

[0540] The user enters the details of their legal consultation into their device.

[0541] Users use smartphones, smart glasses, or head-mounted displays to input data via voice or text. For example, they might input, "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax." The input data is in text format.

[0542] Step 2:

[0543] The terminal sends the entered data to the server.

[0544] The terminal encodes the input into JSON format and sends it to the server as an HTTP request. The input data is text data, and the encoded data is in JSON format. The server receives this.

[0545] Step 3:

[0546] The server analyzes the received data and extracts key keywords.

[0547] The server uses a natural language processing engine (e.g., SpaCy) to parse the data. The input is text data in JSON format, and the output after parsing is a list of key keywords (e.g., "inheritance," "property," "tax amount"). Specifically, the text is tokenized and specific parts of speech are extracted.

[0548] Step 4:

[0549] The server searches for relevant information from the database and network based on the extracted keywords.

[0550] The server searches its internal database using SQL queries and Elasticsearch, and gathers necessary information from the internet using Beautiful Soup and Selenium. The input is a list of key keywords, and the output is a set of related information (e.g., legal texts and past court precedents). Specifically, it converts keywords into queries and crawls databases and websites.

[0551] Step 5:

[0552] Based on the information collected by the server, legal judgments appropriate to the user's situation are formed.

[0553] The collected information is integrated, and legal judgments are made based on specific logic. The input is a set of relevant information, and the output is the text of the legal judgment conclusion or advice. In concrete terms, a rule-based algorithm is executed to derive the conclusion.

[0554] Step 6:

[0555] The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0556] The server uses FlowChart.js and D3.js to convert legal judgments into flowcharts and tabular formats. The input is the text of the legal judgment, and the output is visual flowchart or tabular image data. Specifically, it converts each step into a diagram and adds visual elements.

[0557] Step 7:

[0558] The server sends the diagrammed result to the terminal.

[0559] The server re-encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. The input is visual flowchart or tabular data, and the output is JSON data.

[0560] Step 8:

[0561] The results received by the device are displayed to the user and made visible within the virtual space.

[0562] The device decodes the received data and displays it on a smartphone, smart glasses, or head-mounted display. The input is data in JSON format, and the output is information displayed in a visually easy-to-understand format (e.g., "Step 1: Inheritance Commencement", "Step 2: Property Valuation", "Step 3: Tax Amount Calculation", "Step 4: Document Preparation"). Specifically, it analyzes the data and renders it on the screen.

[0563] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0564] This invention combines an emotion recognition engine with a system that provides legal consultation and advice, thereby offering legal judgments that take the user's emotions into consideration. This system includes the following elements and functions.

[0565] User input

[0566] The user uses a terminal to enter details of their legal consultation. For example, in an inquiry regarding inheritance issues, they might enter, "My father has passed away. There are assets to inherit, and I would like to know about the procedures and the amount of tax involved."

[0567] Sending and receiving data

[0568] The terminal encodes the input data into JSON format and sends it to the server as an HTTP POST request. The server receives this request and begins processing the data.

[0569] Data Analysis

[0570] The server decodes the received data and obtains text data. Next, it uses a natural language processing (NLP) engine to extract key keywords. For example, keywords such as "inheritance," "property," and "tax amount" are extracted.

[0571] emotion recognition

[0572] The server uses an emotion recognition engine to analyze emotions (joy, sadness, surprise, etc.) from the user's input data. The emotion recognition engine uses machine learning algorithms to evaluate the emotional state of the input text.

[0573] Searching for and collecting related information

[0574] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved using SQL queries and Elasticsearch. Web scraping techniques are used to collect information from the internet.

[0575] Formation of legal judgments

[0576] The server analyzes the collected information and forms the most appropriate legal judgment based on the user's specific situation and emotional state. For example, if the user is feeling anxious, it will provide legal advice that explains the process in a more careful and detailed manner.

[0577] Diagramming of results

[0578] The server visualizes legal decisions and converts them into a user-friendly format. It uses libraries such as FlowChart.js and D3.js to convert them into flowcharts and tables. For example, steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation" are included.

[0579] Sending and displaying results

[0580] The server encodes the diagrammed results into JSON format and sends them to the terminal. The terminal parses the received data and displays the results on the screen. This allows the user to receive legal advice in a specific and emotionally sensitive manner.

[0581] Specific example

[0582] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and tax amount," and if the user's feelings of grief are recognized,

[0583] 1. The user enters the details of their legal consultation into the terminal.

[0584] 2. The device sends data to the server.

[0585] 3. The server receives the data and retrieves the text data.

[0586] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0587] 5. The server analyzes the user's emotions using an emotion recognition engine and recognizes them as "sadness."

[0588] 6. The server collects relevant information from its internal database and the internet based on keywords and sentiment data.

[0589] 7. The server analyzes the collected information and forms specific legal judgments (e.g., detailed procedural explanations and reassuring advice) that are appropriate to the user's situation and feelings.

[0590] 8. The server diagrams legal judgments to make them visually easy to understand.

[0591] 9. The server sends the diagrammed results to the terminal.

[0592] 10. The terminal displays the results to the user.

[0593] This allows users to receive prompt and emotionally sensitive legal advice.

[0594] The following describes the processing flow.

[0595] Step 1:

[0596] The user enters specific legal questions into the device. For example, they might enter, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be owed."

[0597] Step 2:

[0598] The terminal encodes the input data into JSON format and sends it to the server using an HTTP POST request. The server's URL and endpoint are configured, and the data is sent to this endpoint.

[0599] Step 3:

[0600] The server decodes the JSON data from the received HTTP request to obtain text data. This makes the user's input available to the server.

[0601] Step 4:

[0602] The server uses a natural language processing (NLP) engine to analyze the text data. Specifically, it uses NLP libraries such as SpaCy and NLTK to extract key keywords (e.g., "inheritance," "property," "tax amount").

[0603] Step 5:

[0604] The server uses an emotion recognition engine to analyze emotions from the user's input text. Possible algorithms used include emotion classifiers and emotion analysis models (e.g., BERT or Sentiment140). Based on the user's text content, it identifies emotions such as "joy," "sadness," and "anxiety."

[0605] Step 6:

[0606] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database contains legal texts, past case precedents, and regulatory documents, from which necessary information is retrieved using SQL queries and Elasticsearch. Web scraping techniques are used to collect data from the internet. Specifically, libraries such as Beautiful Soup and Selenium are utilized.

[0607] Step 7:

[0608] The server uses the collected information to form legal judgments based on the user's specific situation and emotions. In certain cases, it will show how to calculate inheritance tax and the necessary procedures. If the emotional state is "sadness," a more careful and reassuring explanation will be provided.

[0609] Step 8:

[0610] The server visualizes the formed legal judgment and converts it into a format that is easy for the user to understand. It uses libraries such as FlowChart.js and D3.js to convert it into flowcharts and tables. For example, steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation" are visualized.

[0611] Step 9:

[0612] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. This data includes detailed instructions along with emotionally sensitive explanations.

[0613] Step 10:

[0614] The device decodes the received JSON data, analyzes the results, and displays them on the screen in a user-friendly format. The user can then review these results and obtain specific instructions and advice.

[0615] Specific example

[0616] If a user enters "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax," and the emotion recognition engine recognizes the emotion of "sadness":

[0617] 1. The user enters the details of their legal consultation into the terminal.

[0618] 2. The device sends data to the server.

[0619] 3. The server receives the data and retrieves the text data.

[0620] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0621] 5. The server recognizes the emotion of "sadness" using its emotion recognition engine.

[0622] 6. The server collects relevant information from its internal database and the internet based on keywords and sentiment data.

[0623] 7. Based on the collected information, the server forms the most appropriate legal judgment for the user's situation and feelings (e.g., providing clear procedural explanations and reassurance).

[0624] 8. The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0625] 9. The server sends the diagrammed results to the terminal.

[0626] 10. The device analyzes the results and displays them on the screen for the user to review.

[0627] This process allows users to receive prompt and emotionally sensitive legal advice.

[0628] (Example 2)

[0629] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0630] Conventional legal consultation systems rarely provide legal judgments that take into account the user's emotional state, relying solely on entered text data. Therefore, even when a user requires emotional support, this need is often not met. Users facing legal problems often experience stress and anxiety, making emotionally sensitive responses essential. Consequently, a system is needed that provides legal judgments while considering the user's emotions.

[0631] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing received data and extracting key keywords, means for analyzing emotions from user input data using an emotion recognition engine, and means for searching for relevant information from an internal database and the internet based on the extracted keywords and emotion data. This makes it possible to make legal judgments that take into account the user's emotional state.

[0632] A "user" is an individual or legal entity that uses the system to seek legal advice.

[0633] A "terminal" is a device used by a user to input data and send and receive data with a server. Specifically, this refers to computers, smartphones, tablets, and other similar devices.

[0634] A "server" is a device that receives and analyzes data transmitted from a terminal, and searches for and visualizes related information.

[0635] "Legal consultation content" refers to legal questions or issues entered by the user via their device. For example, it could be content related to specific cases such as inheritance, property division, or tax calculations.

[0636] "Data" refers to the text information entered by the user, the results of its analysis, and related information.

[0637] An "NLP engine" is software used for natural language processing and has the function of extracting key keywords from text data.

[0638] An "emotion recognition engine" is software that implements machine learning algorithms to analyze emotions from user input data.

[0639] "Keywords" are important terms in the user's legal consultation, extracted by the NLP engine. Examples include "inheritance," "property," and "tax amount."

[0640] "Emotional data" refers to information that indicates the emotional state contained in the user's input data, as analyzed by the emotion recognition engine.

[0641] "Related information" refers to information obtained from internal databases and the internet based on extracted keywords and sentiment data. This includes legal texts, past case precedents, and regulatory documents.

[0642] An "internal database" is a database that stores legal information, past court precedents, etc., and is used by the server to retrieve information using SQL queries and Elasticsearch.

[0643] "Information gathering from the internet" refers to the method of collecting relevant information from the internet using web scraping techniques.

[0644] "Legal judgment" refers to providing legal advice or judgments that are appropriate to the user's situation and emotional state, based on the information collected by the server.

[0645] "Diagramming" is the process of converting legal judgments into visually easy-to-understand forms such as flowcharts and tables.

[0646] A flowchart is a diagram that visually represents a series of procedures or processes, making it easier for users to understand the flow of those procedures.

[0647] This invention combines an emotion recognition engine with a system that provides legal consultation and advice, thereby offering legal judgments that take the user's emotions into consideration. This system includes the following elements and functions.

[0648] User input

[0649] The user uses a terminal to input details of their legal inquiry. For example, they might input, "My father has passed away. I have inherited assets, and I would like to know about the procedures and tax implications." The terminal accepts the input and prepares the text data.

[0650] Sending and receiving data

[0651] The terminal encodes the entered text data into JSON format and sends it to the server as an HTTP POST request. The server receives the HTTP request, decodes it, and retrieves the data.

[0652] Data analysis (keyword extraction)

[0653] The server decodes the received data to obtain text data. Next, it uses a natural language processing (NLP) engine to extract key keywords. Specifically, it utilizes libraries such as SpaCy and NLTK to extract important keywords such as "inheritance," "property," and "tax amount."

[0654] emotion recognition

[0655] The server inputs the received text data into an emotion recognition engine to analyze the user's emotions. This emotion recognition engine is a model trained using machine learning frameworks such as TensorFlow or PyTorch. Specifically, it classifies emotions such as "joy," "sadness," and "anxiety" from the input text.

[0656] Searching for and collecting related information

[0657] Based on extracted keywords and sentiment data, the server collects relevant information from its internal database (SQL queries and Elasticsearch) and the internet (web scraping). The internal database contains legal texts, past case precedents, and regulatory documents.

[0658] Formation of legal judgments

[0659] The server analyzes the collected information and forms the most appropriate legal judgment based on the user's specific situation and emotional state. For example, if the user is experiencing sadness, it will provide a more considerate and reassuring explanation of the procedure.

[0660] Diagramming of results

[0661] The server visualizes legal decisions and converts them into a user-friendly format. This involves using visual libraries such as FlowChart.js and D3.js to convert them into flowcharts and tables. Specific examples include steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0662] Sending and displaying results

[0663] The server encodes the diagrammed results into JSON format and sends them to the terminal. The terminal parses the received data and displays it on the screen in a visually easy-to-understand format. Specifically, a flowchart and step-by-step explanations are displayed.

[0664] Specific example

[0665] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and tax amount," and if feelings of grief are recognized, the following steps will be taken.

[0666] 1. The user enters the details of their legal consultation into their device.

[0667] 2. The terminal sends the input data to the server.

[0668] 3. The server receives the data and retrieves the text data.

[0669] 4. The server uses an NLP engine to analyze the data and extract keywords such as "inheritance," "assets," and "tax amount."

[0670] 5. The server uses an emotion recognition engine to analyze the user's emotions and recognizes them as "sadness."

[0671] 6. The server collects relevant information from internal databases and the internet based on keywords and sentiment data.

[0672] 7. The server analyzes the collected information and forms specific legal judgments (e.g., detailed procedural explanations and reassuring advice) that are appropriate to the user's situation and feelings.

[0673] 8. The server visualizes legal judgments in a diagrammatic format, making them easy to understand visually.

[0674] 9. The server sends the diagrammed result to the terminal.

[0675] 10. The device displays the results to the user.

[0676] Concrete examples of prompt sentences for generative AI models

[0677] "My father has passed away, and I have inherited assets. I would like a detailed explanation of the necessary procedures and tax amounts. Please also perform sentiment analysis and provide particularly thorough explanations if the user is anxious."

[0678] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0679] Step 1:

[0680] The user enters their legal consultation details via the terminal. The input might include specific questions such as, "My father has passed away. I have inherited assets, and I would like to know about the procedures and tax implications." The terminal saves the text data entered by the user to its internal memory. At this stage, the output is the entered text data.

[0681] Step 2:

[0682] The terminal encodes the input data into JSON format and sends it to the server as an HTTP POST request. Specifically, it uses an encoder that converts text data into JSON format. The input is text data from the user, and the output is JSON data sent to the server.

[0683] Step 3:

[0684] The server receives an HTTP request, decodes the received JSON data, and retrieves text data. The input is JSON data sent from the terminal, and the output is the decoded text data. Specifically, the decoding process uses a JSON decoding library.

[0685] Step 4:

[0686] The server passes the decoded text data to a natural language processing (NLP) engine to extract key keywords. The input is text data, which the NLP engine (e.g., spaCy or NLTK) analyzes to extract key keywords (e.g., "inheritance," "property," "tax amount"). The output is a list of the extracted keywords.

[0687] Step 5:

[0688] The server inputs text data into an emotion recognition engine to analyze the user's emotions. The input is text data, and the emotion recognition engine uses machine learning algorithms to classify emotions such as "joy," "sadness," and "anxiety." The output is emotion data, and "sadness" is detected as an example.

[0689] Step 6:

[0690] The server collects relevant information from its internal database and the internet based on extracted keywords and sentiment data. The input consists of keywords and sentiment data, and the server executes SQL queries on the internal database or retrieves information from the internet using web scraping techniques. The output is a set of collected relevant information.

[0691] Step 7:

[0692] The server analyzes the collected information and forms the optimal legal judgment based on the user's specific situation and emotional state. The input consists of relevant information and the user's emotional data, and the server uses an analytical algorithm to make a legal judgment. The output is the formed legal judgment. For example, if the user is experiencing sadness, a more polite and reassuring explanation of the procedure will be generated.

[0693] Step 8:

[0694] The server visualizes legal judgments and converts them into a user-friendly format. The input is text data of legal judgments, which are converted into flowcharts and tables using visual libraries such as FlowChart.js and D3.js. The output is the visualized information.

[0695] Step 9:

[0696] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. The input is the diagrammed information, which is encoded using a JSON encoder. The output is the JSON data sent to the terminal.

[0697] Step 10:

[0698] The terminal decodes the JSON data received from the server and displays it on the screen in a visually easy-to-understand format. The input is JSON data sent from the server, which is decoded and then re-diagrammed. The specific output is a flowchart and step-by-step explanation visually displayed on the browser screen.

[0699] (Application Example 2)

[0700] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0701] Traditional legal consultation systems tended to provide only mechanical answers, failing to consider the user's emotional state. This made it difficult to offer appropriate legal advice tailored to the situation, resulting in a lack of support for users experiencing anxiety and stress. Furthermore, in the rapidly evolving security landscape, there was a growing need for a system that could provide legal judgments that took emotions into account.

[0702] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input legal consultation content via a terminal, means for the terminal to transmit the input data to the server, means for the server to analyze the received data and extract key keywords, means for the server to search for relevant information from an internal database and the internet based on the extracted keywords, means for the server to form a legal judgment appropriate to the user's situation based on the information collected, means for the server to diagram the legal judgment and convert it into a visually easy-to-understand form, means for the server to transmit the diagrammed result to the terminal, means for the terminal to display the received result to the user, and means for analyzing the user's emotions using an emotion recognition engine and providing a legal judgment that takes the emotion data into consideration. This makes it possible to provide legal advice that takes the user's emotions into consideration, and can support quick and appropriate legal judgments that respond to emotions, especially in security settings.

[0703] A "user" is a person who uses a terminal to seek legal advice.

[0704] A "terminal" is a device used by users to input legal consultation details and to send and receive data with the server.

[0705] A "server" is a central processing unit that analyzes received data, searches for and collects necessary information, and forms and diagrams legal judgments.

[0706] "Data" refers to information such as legal consultation details and emotion recognition results entered by the user via their device.

[0707] "Keywords" are words and phrases that are important for understanding the legal consultation content, extracted through natural language processing.

[0708] An "internal database" is an electronic database that holds legal information such as legal texts, past court precedents, and regulatory documents.

[0709] The "Internet" is a network used to obtain additional relevant information from external sources.

[0710] "Related information" refers to laws, precedents, and regulatory documents that are searched based on the content of the legal consultation.

[0711] A "legal judgment" is a decision that provides appropriate advice or instructions regarding legal matters.

[0712] "Diagramming" refers to the process of converting legal judgments into flowcharts or tables to make them visually easier to understand.

[0713] An "emotion recognition engine" is a system that uses a machine learning algorithm to analyze emotions from user input data and evaluate their content.

[0714] "Emotional data" refers to information that indicates the user's emotional state as analyzed by an emotion recognition engine.

[0715] This invention is a system in which a user inputs legal consultation details via a terminal, and a server analyzes, searches, judges, and diagrams the input content, finally sending the visualized results to the terminal for display. Furthermore, by incorporating an emotion recognition engine, it also provides legal advice that takes into account the user's emotional state.

[0716] Hardware and software to use

[0717] Hardware:

[0718] Devices (e.g., smart glasses, smartphones, head-mounted displays)

[0719] Server (cloud server)

[0720] software:

[0721] Natural language processing engine (e.g., Google NLP API)

[0722] Emotion recognition engine (e.g., Microsoft Azure Emotion API)

[0723] Databases (e.g., MySQL, Elasticsearch)

[0724] Visualization libraries (e.g., FlowChart.js)

[0725] Detailed explanation of data processing and data calculations.

[0726] Users input their legal consultation details using devices such as smart glasses or smartphones. The entered data is sent from the device to the server in JSON format. As a specific example, consider a case where a user inputs, "An intruder has entered the facility. How should I respond?"

[0727] The server decodes the received data to obtain text data. A natural language processing (NLP) engine is then used to extract key keywords from this text data. For example, keywords such as "intruder," "facility," and "response" might be extracted.

[0728] Next, the server uses an emotion recognition engine to analyze the user's input data to determine their emotions. For example, in the case of this prompt, emotions such as "tension" and "anxiety" are recognized.

[0729] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database includes laws, past cases, and regulatory documents, and is searched and retrieved using SQL queries and Elasticsearch.

[0730] Next, the server analyzes the retrieved and collected information to form the most appropriate legal judgment for the user's situation and emotional state. For example, if the user is anxious, it first advises them to calm down and then provides a step-by-step response plan in flowchart format.

[0731] Finally, the server visualizes the legal judgment it has formed and converts it into a flowchart or table using the FlowChart.js library. The visualized result is sent back to the terminal in JSON format, which the terminal parses and displays visually to the user. This allows the user to receive legal advice quickly and in an emotionally sensitive manner.

[0732] Specific example

[0733] Example of a prompt:

[0734] "An intruder has entered the facility. How should we respond?"

[0735] In this specific example, the user's input is analyzed along with their emotions such as "tension" and "anxiety," and appropriate legal response procedures (for example, advice on how to calm down or specific ways to deal with an intruder) are provided in flowchart format.

[0736] In this way, this system allows users to receive not only prompt on-site support but also emotional care, enabling them to deal with situations with greater peace of mind.

[0737] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0738] Step 1:

[0739] The user enters their legal consultation details into a device. The user enters their legal consultation details in text format using a device such as smart glasses or a smartphone. The user's input is captured by the device and stored as a prompt. For example, the prompt might read, "An intruder has entered the facility. How should I respond?"

[0740] Step 2:

[0741] The terminal sends the entered data to the server. The terminal encodes the entered text data into JSON format and sends it to the server as an HTTP POST request. The specific actions of this step are encoding and sending the HTTP request. The input is the legal consultation content entered by the user, and the output is the JSON data sent to the server.

[0742] Step 3:

[0743] The server analyzes the received data and extracts key keywords. The server decodes the received JSON data to obtain text data. Next, it uses a natural language processing engine (NLP engine) to extract key keywords. For example, keywords such as "intruder," "facility," and "response" may be extracted. In this step, the input is the JSON data sent to the server, and the output is the extracted keywords.

[0744] Step 4:

[0745] The server uses an emotion recognition engine to analyze emotions from the user's input data. The server inputs the extracted text data into the emotion recognition engine and analyzes emotions such as "tension" and "anxiety." In this step, the input is the text data sent to the server, and the output is the analyzed emotion data.

[0746] Step 5:

[0747] The server searches for relevant information from its internal database and the internet based on the extracted keywords and sentiment data. The server uses SQL queries and Elasticsearch to search for relevant laws and precedents in its internal database. It also collects additional information from the internet as needed. In this step, the input is keywords and sentiment data, and the output is a set of relevant information.

[0748] Step 6:

[0749] Based on the information collected by the server, it forms a legal judgment appropriate to the user's situation and emotional state. The server combines the collected legal information with the user's emotional state to make the optimal legal judgment. For example, if the user is anxious, it first provides calming advice and then carefully explains how to deal with the situation. In this step, the input is relevant information and emotional data, and the output is the formed legal judgment.

[0750] Step 7:

[0751] The server diagrams legal judgments and converts them into a visually easy-to-understand format. The server then uses the FlowChart.js library to convert the formed legal judgments into flowcharts and tables. By visually showing specific procedures and steps, it makes it easier for users to understand. In this step, the input is the legal judgment, and the output is a diagrammed flowchart or table.

[0752] Step 8:

[0753] The server sends the diagrammed result to the terminal. The server re-encodes the diagrammed data into JSON format and sends it to the terminal as an HTTP response. In this step, the input is the diagrammed legal judgment, and the output is the JSON data sent to the terminal.

[0754] Step 9:

[0755] The terminal displays the results it receives to the user. The terminal decodes the JSON data received from the server and displays the visual judgment result. The user can view the flowchart or tabular legal advice through smart glasses or a smartphone display. In this step, the input is the JSON data sent from the server, and the output is the visual result displayed to the user.

[0756] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0757] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0758] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0759] [Third Embodiment]

[0760] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0761] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0762] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0763] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0764] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0765] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0766] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0767] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0768] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0769] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0770] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0771] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0772] This invention is a system for providing legal consultation and advice, which analyzes the consultation content entered by the user and provides appropriate legal judgments quickly and accurately. This system is realized through the following main components and functions.

[0773] User input

[0774] The user uses their device to enter specific legal questions. For example, if they are asking a question about inheritance tax, they might enter, "My father has passed away, and I have inherited some assets. I would like to know the necessary procedures and the amount of tax."

[0775] Sending and receiving data

[0776] The terminal sends the entered information to the server. This transmission is done using an HTTP request, and the data is encoded in JSON format. The server receives this request and proceeds to the next step.

[0777] Data Analysis

[0778] The server decodes the received data to obtain text data. Then, it uses a natural language processing engine to extract key keywords. For example, "inheritance," "property," and "tax amount" might be extracted.

[0779] Searching for and collecting related information

[0780] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved quickly using SQL queries and Elasticsearch. Meanwhile, web scraping techniques are used to collect information from the internet, utilizing libraries such as Beautiful Soup and Selenium.

[0781] Formation of legal judgments

[0782] Based on the collected information, the server forms specific legal judgments tailored to the user's situation. For example, it may indicate how to calculate inheritance tax and the necessary procedures. This process executes pre-programmed legal logic.

[0783] Diagramming of results

[0784] The server performs a diagramming process to make legal decisions easier to understand. It uses libraries such as FlowChart.js and D3.js to convert the information into flowcharts and tables. Specifically, it is illustrated in the form of "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0785] Sending and displaying results

[0786] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal parses the received data and displays it in a user-friendly format. This allows the user to quickly obtain specific legal advice.

[0787] Specific example

[0788] For example, if a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be paid," the following process will be performed:

[0789] 1. The user enters the details of their inquiry into the terminal.

[0790] 2. The device sends data to the server.

[0791] 3. The server analyzes the data and extracts keywords such as "inheritance," "assets," and "tax amount."

[0792] 4. The server collects relevant information from its internal database and the internet.

[0793] 5. The server will form specific legal judgments tailored to the user's situation (for example, how to calculate inheritance tax and the necessary procedures).

[0794] 6. The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0795] 7. The server sends the diagrammed results to the terminal.

[0796] 8. The device displays the results to the user.

[0797] This allows users to obtain information to respond quickly and accurately, enabling them to make swift decisions regarding legal issues.

[0798] The following describes the processing flow.

[0799] Step 1:

[0800] The user enters specific legal questions into the device. For example, they might enter, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be owed."

[0801] Step 2:

[0802] The terminal receives the input text data and encodes it into JSON format. Then, it sends the data to the server using an HTTP POST request.

[0803] Step 3:

[0804] The server receives an HTTP request, decodes the received JSON data, and obtains text data.

[0805] Step 4:

[0806] The server uses a natural language processing (NLP) engine to analyze the text data. Specifically, it uses NLP libraries such as SpaCy and NLTK to extract key keywords (e.g., "inheritance," "property," "tax amount").

[0807] Step 5:

[0808] The server searches for relevant information from its internal database and the internet based on the extracted keywords. It retrieves legal texts and past case precedents from the internal database using SQL queries, and collects relevant information from the internet using web scraping techniques. For example, it might use Beautiful Soup or the Selenium library.

[0809] Step 6:

[0810] The server analyzes the collected information and forms legal judgments based on the user's specific situation. Using pre-programmed legal logic, it derives the method for calculating inheritance tax and the necessary procedural steps.

[0811] Step 7:

[0812] The server visualizes the resulting legal judgment in a way that is easy for the user to understand. It uses libraries such as FlowChart.js and D3.js to convert it into flowcharts or tables. For example, it could be structured as follows: "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," "Step 4: Document preparation."

[0813] Step 8:

[0814] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response.

[0815] Step 9:

[0816] The device decodes the received JSON data, parses the results, and displays them on the screen. This allows users to obtain specific legal advice in a visually easy-to-understand format.

[0817] Specific example

[0818] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be paid":

[0819] 1. The user enters the details of their legal consultation into the terminal.

[0820] 2. The device sends data to the server.

[0821] 3. The server receives the data and retrieves the text data.

[0822] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0823] 5. The server searches for and retrieves correlation information from its internal database and the internet.

[0824] 6. The server uses legal logic to derive the inheritance tax calculation method and necessary procedures.

[0825] 7. The server visualizes legal judgments and converts them into a visually easy-to-understand format for the user.

[0826] 8. The server sends the diagrammed results to the terminal.

[0827] 9. The device analyzes the results and displays them on the screen for the user to review.

[0828] This allows users to receive prompt and accurate legal advice.

[0829] (Example 1)

[0830] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0831] Conventional legal consultation systems struggled to quickly and accurately analyze user-entered consultation content and provide appropriate legal advice. Furthermore, they lacked the technology to efficiently collect relevant information and display results in a visually easy-to-understand format. As a result, it was difficult for users to obtain appropriate legal judgments in a short amount of time. Additionally, natural language processing and information generation based on prompts were not fully utilized.

[0832] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0833] In this invention, the server includes means for analyzing received data and extracting key keywords, means for searching for relevant information from an internal database and the internet based on the extracted keywords, and means for forming a legal judgment appropriate to the user's situation based on the collected information. This enables the user to obtain appropriate legal advice quickly, accurately, and effectively.

[0834] A "user" is an entity that inputs questions or inquiries into the system to receive legal advice and information.

[0835] A "terminal" is an electronic device used by a user to input consultation details into the system, and it is a device that communicates data with the server.

[0836] A "server" is a central processing unit that analyzes data received from users, collects relevant information, forms legal judgments, and transmits them to terminals.

[0837] "Entered data" refers to information about legal consultations provided by the user to the system via their device.

[0838] A "natural language processing engine" is software or an algorithm used to analyze text data and extract key keywords.

[0839] "Keywords" are terms that are considered important in legal judgments and are extracted from the input data by a natural language processing engine.

[0840] An "internal database" is a database containing legal information such as legal texts, past court precedents, and regulatory documents, and is used as storage for servers to quickly retrieve information.

[0841] "Searching for relevant information on the internet" refers to the process of collecting necessary data from publicly available information on the internet using techniques such as web scraping.

[0842] "Legal judgment" refers to specific legal advice or opinions formed based on the user's situation, using information collected by the server.

[0843] "Diagramming in flowchart or tabular format" refers to a method of visually organizing formed legal judgments using libraries such as FlowChart.js or D3.js, making them easy for users to understand.

[0844] A "generative AI model" is a machine learning model that automatically generates relevant information and advice based on specific prompt sentences.

[0845] A "prompt statement" is an instruction given to a generative AI model, a text intended to guide the generation or processing of specific information.

[0846] This invention is a system for providing legal consultations and advice. It analyzes the legal consultation content entered by the user and provides prompt, accurate, and appropriate legal judgments. This system is implemented using the following hardware and software.

[0847] User input

[0848] Users enter specific legal questions using their devices. For example, they might ask, "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax." The devices used can include PCs, smartphones, and tablets. The entered data is retrieved through web forms or text boxes in applications.

[0849] Sending data

[0850] The terminal sends the entered data to the server. This transmission uses an HTTP POST request, and the data is encoded in JSON format. This enables efficient data transmission and reception.

[0851] Data reception and analysis

[0852] The server receives an HTTP request and decodes the JSON data to obtain text data. The server is a high-performance server machine used to execute computer programs. This text data is analyzed using a natural language processing engine, and key keywords are extracted. Libraries such as NLTK (Natural Language Toolkit) and spaCy are used for natural language processing. Furthermore, a generative AI model can be used to generate relevant information based on specific prompt statements.

[0853] Information retrieval and collection

[0854] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved using SQL queries and Elasticsearch. Web scraping techniques using Beautiful Soup and Selenium are utilized to collect information from the internet.

[0855] Formation of legal judgments

[0856] Based on the collected information, the server forms specific legal judgments appropriate to the user's situation. This involves applying pre-programmed legal logic. For example, it may show how to calculate inheritance tax and the necessary procedures. This process may also utilize an artificial intelligence inference engine, and information may be generated based on prompts using a generative AI model.

[0857] Diagramming of results

[0858] The server performs a diagramming process to make legal decisions easier to understand visually. For this purpose, libraries such as FlowChart.js and D3.js are used to convert the information into flowcharts and tables. For example, it may be visually presented as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0859] Sending and displaying results

[0860] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal parses the received data and displays it in a user-friendly format. This display may use a web page or application interface. The user can then obtain quick and accurate legal advice.

[0861] Specific example

[0862] For example, if a user inputs "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax," the following prompt could be input into the AI ​​model:

[0863] "Could you please explain the laws regarding inheritance? My father has passed away, and I have inherited some assets. I would like to know the necessary procedures and the amount of tax involved."

[0864] This allows users to obtain the necessary legal information on the spot and quickly begin taking concrete actions to resolve the problem.

[0865] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0866] Step 1:

[0867] The user enters their legal consultation details using a terminal. The text entered by the user is in the format of, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax." Once the user has finished entering the information, they click the "Submit" button. The input is done through a text box, and the output is a text file of the legal consultation.

[0868] Step 2:

[0869] The terminal sends the legal consultation details entered by the user to the server. This transmission uses an HTTP POST request, and the data is encoded in JSON format. For example, it is sent with the following JSON structure: "{"query": "My father has passed away, and I have inherited property. I would like to know the necessary procedures and tax amount"}". The input is text data, and the output is sent as JSON data.

[0870] Step 3:

[0871] The server receives an HTTP request and decodes the JSON data to obtain text data. The received data is parsed by an internal component. The input is JSON data, and the output is the parsed text data. The text data is stored in a variable within the server.

[0872] Step 4:

[0873] The server uses a natural language processing engine to extract key keywords from text data. For example, it might use NLTK or spaCy to extract keywords such as "inheritance," "property," and "tax amount." The natural language processing engine analyzes the text and identifies important words using a specific algorithm. The input is text data, and the output is a list of keywords.

[0874] Step 5:

[0875] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database contains legal texts, past case precedents, and regulatory documents, and data is quickly retrieved using SQL queries and Elasticsearch. Web scraping using Beautiful Soup and Selenium is used to collect information from the internet. The input is a list of keywords, and the output is data of relevant information.

[0876] Step 6:

[0877] The server uses the collected information to form specific legal judgments tailored to the user's situation. Calculations and reasoning are performed according to programmed legal logic, generating information such as "how to calculate inheritance tax" and "necessary procedures." Using a generative AI model, customized information based on prompts can also be generated for the user's situation. The input is relevant data, and the output is a legal judgment.

[0878] Step 7:

[0879] The server visualizes legal judgments in an easily understandable format. Libraries such as FlowChart.js and D3.js are used to convert the information into flowcharts and tables. For example, it might visually represent steps such as "Step 1: Inheritance Commencement," "Step 2: Property Valuation," "Step 3: Tax Calculation," and "Step 4: Document Preparation." The input is legal judgment data, and the output is generated as diagrammatic data.

[0880] Step 8:

[0881] The server re-encodes the diagrammed results into JSON format and sends them to the terminal. The terminal decodes the received data and displays it on the screen. The user visually reviews the results and understands the specific procedures and necessary actions. The input is diagrammed data, and the output provides the user with visually organized information.

[0882] This allows users to receive legal advice in a specific and easy-to-understand format.

[0883] (Application Example 1)

[0884] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0885] Conventional legal consultation systems struggle to quickly and accurately analyze user-submitted legal consultations and provide appropriate legal judgments. Furthermore, the lack of systems that present legal judgments in a visually clear and easy-to-understand format makes them difficult for users to comprehend. In particular, a system with adaptability to effectively respond to legal consultations attempted by users in virtual spaces is necessary.

[0886] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0887] In this invention, the server includes means for the user to input legal consultation details via a terminal, means for the terminal to transmit the input data to the server, means for the server to analyze the received data and extract key keywords, means for searching for relevant information from databases and networks, means for forming a legal judgment appropriate to the user's situation based on the collected information, means for diagramming the legal judgment and converting it into a visually easy-to-understand form, means for transmitting the diagrammed results to the terminal, and means for the terminal to display the received results to the user and make them visible in a virtual space. This enables rapid and accurate analysis of legal consultation details, provision of appropriate legal judgments, and display of results in a visually easy-to-understand format.

[0888] A "user" is a person who enters details of their legal consultation into a terminal and receives the information.

[0889] A "terminal" refers to a device used by a user to input details of their legal consultation, such as a smartphone, smart glasses, or head-mounted display.

[0890] A "server" is a computer system that analyzes received data, extracts keywords, and forms legal judgments.

[0891] "Data analysis" is the process by which a server receives data sent from a user, understands its content, and extracts key keywords.

[0892] "Key keywords" are important terms extracted when analyzing the legal consultation content entered by the user.

[0893] A "database" is an internal source of information that stores relevant legal information.

[0894] "Network" refers to the internet and other means of obtaining information, providing external sources for collecting legal information.

[0895] "Legal judgment" refers to the conclusions and advice that the server forms regarding the user's legal consultation based on extracted keywords and collected information.

[0896] "Diagramming" is the process of converting legal judgments into a visually easy-to-understand format.

[0897] "Visually easy-to-understand format" refers to information that has been converted into formats such as flowcharts and tables so that users can easily understand legal decisions.

[0898] A "virtual space" is a virtual information environment provided to users through devices such as smart glasses or head-mounted displays.

[0899] To implement this invention, a terminal such as a smartphone, smart glasses, or head-mounted display is used. First, the user inputs the details of their legal consultation via the terminal. For example, they might input, using voice or text input, "My father has passed away, and I have inherited property. I would like to know the necessary procedures and the amount of tax." The terminal then sends the input data to the server.

[0900] The server analyzes the received data and extracts key keywords. For this purpose, the server uses a natural language processing engine (e.g., SpaCy). Based on the extracted keywords, the server searches for relevant information from its internal database and network. The internal database contains legal texts and past case precedents, while external sources include legal information on the network. SQL queries, Elasticsearch, and web scraping techniques (e.g., Beautiful Soup, Selenium) are used for information retrieval.

[0901] Based on the collected information, the server forms a legal judgment appropriate to the user's situation. This legal judgment includes specific advice and procedural instructions. For example, information on how to calculate inheritance tax and the necessary procedures is provided. This legal judgment is then converted into a visually easy-to-understand format. Specifically, it is diagrammed into flowcharts and tables using FlowChart.js or D3.js.

[0902] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal receives this and displays it in a format that is easy for the user to understand. The displayed information is provided in a visually clear manner within the virtual space. For example, when using smart glasses, a flowchart of legal decisions is displayed in front of the user's eyes, allowing them to examine each step in detail.

[0903] As a concrete example, if a user enters the prompt, "My father has passed away, and I will inherit the land and house. How much inheritance tax will I have to pay?", the server will process it in the following steps: First, it will use a natural language processing engine to extract key keywords and collect relevant information from the database and network. Then, it will form a legal judgment appropriate to the user's situation, diagram it in flowchart format, and send it to the terminal. Finally, the user's smart glasses will display "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[0904] This allows users to quickly and accurately receive specific advice regarding their legal concerns.

[0905] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0906] Step 1:

[0907] The user enters the details of their legal consultation into their device.

[0908] Users use smartphones, smart glasses, or head-mounted displays to input data via voice or text. For example, they might input, "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax." The input data is in text format.

[0909] Step 2:

[0910] The terminal sends the entered data to the server.

[0911] The terminal encodes the input into JSON format and sends it to the server as an HTTP request. The input data is text data, and the encoded data is in JSON format. The server receives this.

[0912] Step 3:

[0913] The server analyzes the received data and extracts key keywords.

[0914] The server uses a natural language processing engine (e.g., SpaCy) to parse the data. The input is text data in JSON format, and the output after parsing is a list of key keywords (e.g., "inheritance," "property," "tax amount"). Specifically, the text is tokenized and specific parts of speech are extracted.

[0915] Step 4:

[0916] The server searches for relevant information from the database and network based on the extracted keywords.

[0917] The server searches its internal database using SQL queries and Elasticsearch, and gathers necessary information from the internet using Beautiful Soup and Selenium. The input is a list of key keywords, and the output is a set of related information (e.g., legal texts and past court precedents). Specifically, it converts keywords into queries and crawls databases and websites.

[0918] Step 5:

[0919] Based on the information collected by the server, legal judgments appropriate to the user's situation are formed.

[0920] The collected information is integrated, and legal judgments are made based on specific logic. The input is a set of relevant information, and the output is the text of the legal judgment conclusion or advice. In concrete terms, a rule-based algorithm is executed to derive the conclusion.

[0921] Step 6:

[0922] The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0923] The server uses FlowChart.js and D3.js to convert legal judgments into flowcharts and tabular formats. The input is the text of the legal judgment, and the output is visual flowchart or tabular image data. Specifically, it converts each step into a diagram and adds visual elements.

[0924] Step 7:

[0925] The server sends the diagrammed result to the terminal.

[0926] The server re-encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. The input is visual flowchart or tabular data, and the output is JSON data.

[0927] Step 8:

[0928] The results received by the device are displayed to the user and made visible within the virtual space.

[0929] The device decodes the received data and displays it on a smartphone, smart glasses, or head-mounted display. The input is data in JSON format, and the output is information displayed in a visually easy-to-understand format (e.g., "Step 1: Inheritance Commencement", "Step 2: Property Valuation", "Step 3: Tax Amount Calculation", "Step 4: Document Preparation"). Specifically, it analyzes the data and renders it on the screen.

[0930] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0931] This invention combines an emotion recognition engine with a system that provides legal consultation and advice, thereby offering legal judgments that take the user's emotions into consideration. This system includes the following elements and functions.

[0932] User input

[0933] The user uses a terminal to enter details of their legal consultation. For example, in an inquiry regarding inheritance issues, they might enter, "My father has passed away. There are assets to inherit, and I would like to know about the procedures and the amount of tax involved."

[0934] Sending and receiving data

[0935] The terminal encodes the input data into JSON format and sends it to the server as an HTTP POST request. The server receives this request and begins processing the data.

[0936] Data Analysis

[0937] The server decodes the received data and obtains text data. Next, it uses a natural language processing (NLP) engine to extract key keywords. For example, keywords such as "inheritance," "property," and "tax amount" are extracted.

[0938] emotion recognition

[0939] The server uses an emotion recognition engine to analyze emotions (joy, sadness, surprise, etc.) from the user's input data. The emotion recognition engine uses machine learning algorithms to evaluate the emotional state of the input text.

[0940] Searching for and collecting related information

[0941] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved using SQL queries and Elasticsearch. Web scraping techniques are used to collect information from the internet.

[0942] Formation of legal judgments

[0943] The server analyzes the collected information and forms the most appropriate legal judgment based on the user's specific situation and emotional state. For example, if the user is feeling anxious, it will provide legal advice that explains the process in a more careful and detailed manner.

[0944] Diagramming of results

[0945] The server visualizes legal decisions and converts them into a user-friendly format. It uses libraries such as FlowChart.js and D3.js to convert them into flowcharts and tables. For example, steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation" are included.

[0946] Sending and displaying results

[0947] The server encodes the diagrammed results into JSON format and sends them to the terminal. The terminal parses the received data and displays the results on the screen. This allows the user to receive legal advice in a specific and emotionally sensitive manner.

[0948] Specific example

[0949] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and tax amount," and if the user's feelings of grief are recognized,

[0950] 1. The user enters the details of their legal consultation into the terminal.

[0951] 2. The device sends data to the server.

[0952] 3. The server receives the data and retrieves the text data.

[0953] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0954] 5. The server analyzes the user's emotions using an emotion recognition engine and recognizes them as "sadness."

[0955] 6. The server collects relevant information from its internal database and the internet based on keywords and sentiment data.

[0956] 7. The server analyzes the collected information and forms specific legal judgments (e.g., detailed procedural explanations and reassuring advice) that are appropriate to the user's situation and feelings.

[0957] 8. The server diagrams legal judgments to make them visually easy to understand.

[0958] 9. The server sends the diagrammed results to the terminal.

[0959] 10. The terminal displays the results to the user.

[0960] This allows users to receive prompt and emotionally sensitive legal advice.

[0961] The following describes the processing flow.

[0962] Step 1:

[0963] The user enters specific legal questions into the device. For example, they might enter, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be owed."

[0964] Step 2:

[0965] The terminal encodes the input data into JSON format and sends it to the server using an HTTP POST request. The server's URL and endpoint are configured, and the data is sent to this endpoint.

[0966] Step 3:

[0967] The server decodes the JSON data from the received HTTP request to obtain text data. This makes the user's input available to the server.

[0968] Step 4:

[0969] The server uses a natural language processing (NLP) engine to analyze the text data. Specifically, it uses NLP libraries such as SpaCy and NLTK to extract key keywords (e.g., "inheritance," "property," "tax amount").

[0970] Step 5:

[0971] The server uses an emotion recognition engine to analyze emotions from the user's input text. Possible algorithms used include emotion classifiers and emotion analysis models (e.g., BERT or Sentiment140). Based on the user's text content, it identifies emotions such as "joy," "sadness," and "anxiety."

[0972] Step 6:

[0973] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database contains legal texts, past case precedents, and regulatory documents, from which necessary information is retrieved using SQL queries and Elasticsearch. Web scraping techniques are used to collect data from the internet. Specifically, libraries such as Beautiful Soup and Selenium are utilized.

[0974] Step 7:

[0975] The server uses the collected information to form legal judgments based on the user's specific situation and emotions. In certain cases, it will show how to calculate inheritance tax and the necessary procedures. If the emotional state is "sadness," a more careful and reassuring explanation will be provided.

[0976] Step 8:

[0977] The server visualizes the formed legal judgment and converts it into a format that is easy for the user to understand. It uses libraries such as FlowChart.js and D3.js to convert it into flowcharts and tables. For example, steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation" are visualized.

[0978] Step 9:

[0979] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. This data includes detailed instructions along with emotionally sensitive explanations.

[0980] Step 10:

[0981] The device decodes the received JSON data, analyzes the results, and displays them on the screen in a user-friendly format. The user can then review these results and obtain specific instructions and advice.

[0982] Specific example

[0983] If a user enters "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax," and the emotion recognition engine recognizes the emotion of "sadness":

[0984] 1. The user enters the details of their legal consultation into the terminal.

[0985] 2. The device sends data to the server.

[0986] 3. The server receives the data and retrieves the text data.

[0987] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[0988] 5. The server recognizes the emotion of "sadness" using its emotion recognition engine.

[0989] 6. The server collects relevant information from its internal database and the internet based on keywords and sentiment data.

[0990] 7. Based on the collected information, the server forms the most appropriate legal judgment for the user's situation and feelings (e.g., providing clear procedural explanations and reassurance).

[0991] 8. The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[0992] 9. The server sends the diagrammed results to the terminal.

[0993] 10. The device analyzes the results and displays them on the screen for the user to review.

[0994] This process allows users to receive prompt and emotionally sensitive legal advice.

[0995] (Example 2)

[0996] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0997] Conventional legal consultation systems rarely provide legal judgments that take into account the user's emotional state, relying solely on entered text data. Therefore, even when a user requires emotional support, this need is often not met. Users facing legal problems often experience stress and anxiety, making emotionally sensitive responses essential. Consequently, a system is needed that provides legal judgments while considering the user's emotions.

[0998] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing received data and extracting key keywords, means for analyzing emotions from user input data using an emotion recognition engine, and means for searching for relevant information from an internal database and the internet based on the extracted keywords and emotion data. This makes it possible to make legal judgments that take into account the user's emotional state.

[0999] A "user" is an individual or legal entity that uses the system to seek legal advice.

[1000] A "terminal" is a device used by a user to input data and send and receive data with a server. Specifically, this refers to computers, smartphones, tablets, and other similar devices.

[1001] A "server" is a device that receives and analyzes data transmitted from a terminal, and searches for and visualizes related information.

[1002] "Legal consultation content" refers to legal questions or issues entered by the user via their device. For example, it could be content related to specific cases such as inheritance, property division, or tax calculations.

[1003] "Data" refers to the text information entered by the user, the results of its analysis, and related information.

[1004] An "NLP engine" is software used for natural language processing and has the function of extracting key keywords from text data.

[1005] An "emotion recognition engine" is software that implements machine learning algorithms to analyze emotions from user input data.

[1006] "Keywords" are important terms in the user's legal consultation, extracted by the NLP engine. Examples include "inheritance," "property," and "tax amount."

[1007] "Emotional data" refers to information that indicates the emotional state contained in the user's input data, as analyzed by the emotion recognition engine.

[1008] "Related information" refers to information obtained from internal databases and the internet based on extracted keywords and sentiment data. This includes legal texts, past case precedents, and regulatory documents.

[1009] An "internal database" is a database that stores legal information, past court precedents, etc., and is used by the server to retrieve information using SQL queries and Elasticsearch.

[1010] "Information gathering from the internet" refers to the method of collecting relevant information from the internet using web scraping techniques.

[1011] "Legal judgment" refers to providing legal advice or judgments that are appropriate to the user's situation and emotional state, based on the information collected by the server.

[1012] "Diagramming" is the process of converting legal judgments into visually easy-to-understand forms such as flowcharts and tables.

[1013] A flowchart is a diagram that visually represents a series of procedures or processes, making it easier for users to understand the flow of those procedures.

[1014] This invention combines an emotion recognition engine with a system that provides legal consultation and advice, thereby offering legal judgments that take the user's emotions into consideration. This system includes the following elements and functions.

[1015] User input

[1016] The user uses a terminal to input details of their legal inquiry. For example, they might input, "My father has passed away. I have inherited assets, and I would like to know about the procedures and tax implications." The terminal accepts the input and prepares the text data.

[1017] Sending and receiving data

[1018] The terminal encodes the entered text data into JSON format and sends it to the server as an HTTP POST request. The server receives the HTTP request, decodes it, and retrieves the data.

[1019] Data analysis (keyword extraction)

[1020] The server decodes the received data to obtain text data. Next, it uses a natural language processing (NLP) engine to extract key keywords. Specifically, it utilizes libraries such as SpaCy and NLTK to extract important keywords such as "inheritance," "property," and "tax amount."

[1021] emotion recognition

[1022] The server inputs the received text data into an emotion recognition engine to analyze the user's emotions. This emotion recognition engine is a model trained using machine learning frameworks such as TensorFlow or PyTorch. Specifically, it classifies emotions such as "joy," "sadness," and "anxiety" from the input text.

[1023] Searching for and collecting related information

[1024] Based on extracted keywords and sentiment data, the server collects relevant information from its internal database (SQL queries and Elasticsearch) and the internet (web scraping). The internal database contains legal texts, past case precedents, and regulatory documents.

[1025] Formation of legal judgments

[1026] The server analyzes the collected information and forms the most appropriate legal judgment based on the user's specific situation and emotional state. For example, if the user is experiencing sadness, it will provide a more considerate and reassuring explanation of the procedure.

[1027] Diagramming of results

[1028] The server visualizes legal decisions and converts them into a user-friendly format. This involves using visual libraries such as FlowChart.js and D3.js to convert them into flowcharts and tables. Specific examples include steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[1029] Sending and displaying results

[1030] The server encodes the diagrammed results into JSON format and sends them to the terminal. The terminal parses the received data and displays it on the screen in a visually easy-to-understand format. Specifically, a flowchart and step-by-step explanations are displayed.

[1031] Specific example

[1032] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and tax amount," and if feelings of grief are recognized, the following steps will be taken.

[1033] 1. The user enters the details of their legal consultation into their device.

[1034] 2. The terminal sends the input data to the server.

[1035] 3. The server receives the data and retrieves the text data.

[1036] 4. The server uses an NLP engine to analyze the data and extract keywords such as "inheritance," "assets," and "tax amount."

[1037] 5. The server uses an emotion recognition engine to analyze the user's emotions and recognizes them as "sadness."

[1038] 6. The server collects relevant information from internal databases and the internet based on keywords and sentiment data.

[1039] 7. The server analyzes the collected information and forms specific legal judgments (e.g., detailed procedural explanations and reassuring advice) that are appropriate to the user's situation and feelings.

[1040] 8. The server visualizes legal judgments in a diagrammatic format, making them easy to understand visually.

[1041] 9. The server sends the diagrammed result to the terminal.

[1042] 10. The device displays the results to the user.

[1043] Concrete examples of prompt sentences for generative AI models

[1044] "My father has passed away, and I have inherited assets. I would like a detailed explanation of the necessary procedures and tax amounts. Please also perform sentiment analysis and provide particularly thorough explanations if the user is anxious."

[1045] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1046] Step 1:

[1047] The user enters their legal consultation details via the terminal. The input might include specific questions such as, "My father has passed away. I have inherited assets, and I would like to know about the procedures and tax implications." The terminal saves the text data entered by the user to its internal memory. At this stage, the output is the entered text data.

[1048] Step 2:

[1049] The terminal encodes the input data into JSON format and sends it to the server as an HTTP POST request. Specifically, it uses an encoder that converts text data into JSON format. The input is text data from the user, and the output is JSON data sent to the server.

[1050] Step 3:

[1051] The server receives an HTTP request, decodes the received JSON data, and retrieves text data. The input is JSON data sent from the terminal, and the output is the decoded text data. Specifically, the decoding process uses a JSON decoding library.

[1052] Step 4:

[1053] The server passes the decoded text data to a natural language processing (NLP) engine to extract key keywords. The input is text data, which the NLP engine (e.g., spaCy or NLTK) analyzes to extract key keywords (e.g., "inheritance," "property," "tax amount"). The output is a list of the extracted keywords.

[1054] Step 5:

[1055] The server inputs text data into an emotion recognition engine to analyze the user's emotions. The input is text data, and the emotion recognition engine uses machine learning algorithms to classify emotions such as "joy," "sadness," and "anxiety." The output is emotion data, and "sadness" is detected as an example.

[1056] Step 6:

[1057] The server collects relevant information from its internal database and the internet based on extracted keywords and sentiment data. The input consists of keywords and sentiment data, and the server executes SQL queries on the internal database or retrieves information from the internet using web scraping techniques. The output is a set of collected relevant information.

[1058] Step 7:

[1059] The server analyzes the collected information and forms the optimal legal judgment based on the user's specific situation and emotional state. The input consists of relevant information and the user's emotional data, and the server uses an analytical algorithm to make a legal judgment. The output is the formed legal judgment. For example, if the user is experiencing sadness, a more polite and reassuring explanation of the procedure will be generated.

[1060] Step 8:

[1061] The server visualizes legal judgments and converts them into a user-friendly format. The input is text data of legal judgments, which are converted into flowcharts and tables using visual libraries such as FlowChart.js and D3.js. The output is the visualized information.

[1062] Step 9:

[1063] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. The input is the diagrammed information, which is encoded using a JSON encoder. The output is the JSON data sent to the terminal.

[1064] Step 10:

[1065] The terminal decodes the JSON data received from the server and displays it on the screen in a visually easy-to-understand format. The input is JSON data sent from the server, which is decoded and then re-diagrammed. The specific output is a flowchart and step-by-step explanation visually displayed on the browser screen.

[1066] (Application Example 2)

[1067] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1068] Traditional legal consultation systems tended to provide only mechanical answers, failing to consider the user's emotional state. This made it difficult to offer appropriate legal advice tailored to the situation, resulting in a lack of support for users experiencing anxiety and stress. Furthermore, in the rapidly evolving security landscape, there was a growing need for a system that could provide legal judgments that took emotions into account.

[1069] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input legal consultation content via a terminal, means for the terminal to transmit the input data to the server, means for the server to analyze the received data and extract key keywords, means for the server to search for relevant information from an internal database and the internet based on the extracted keywords, means for the server to form a legal judgment appropriate to the user's situation based on the information collected, means for the server to diagram the legal judgment and convert it into a visually easy-to-understand form, means for the server to transmit the diagrammed result to the terminal, means for the terminal to display the received result to the user, and means for analyzing the user's emotions using an emotion recognition engine and providing a legal judgment that takes the emotion data into consideration. This makes it possible to provide legal advice that takes the user's emotions into consideration, and can support quick and appropriate legal judgments that respond to emotions, especially in security settings.

[1070] A "user" is a person who uses a terminal to seek legal advice.

[1071] A "terminal" is a device used by users to input legal consultation details and to send and receive data with the server.

[1072] A "server" is a central processing unit that analyzes received data, searches for and collects necessary information, and forms and diagrams legal judgments.

[1073] "Data" refers to information such as legal consultation details and emotion recognition results entered by the user via their device.

[1074] "Keywords" are words and phrases that are important for understanding the legal consultation content, extracted through natural language processing.

[1075] An "internal database" is an electronic database that holds legal information such as legal texts, past court precedents, and regulatory documents.

[1076] The "Internet" is a network used to obtain additional relevant information from external sources.

[1077] "Related information" refers to laws, precedents, and regulatory documents that are searched based on the content of the legal consultation.

[1078] A "legal judgment" is a decision that provides appropriate advice or instructions regarding legal matters.

[1079] "Diagramming" refers to the process of converting legal judgments into flowcharts or tables to make them visually easier to understand.

[1080] An "emotion recognition engine" is a system that uses a machine learning algorithm to analyze emotions from user input data and evaluate their content.

[1081] "Emotional data" refers to information that indicates the user's emotional state as analyzed by an emotion recognition engine.

[1082] This invention is a system in which a user inputs legal consultation details via a terminal, and a server analyzes, searches, judges, and diagrams the input content, finally sending the visualized results to the terminal for display. Furthermore, by incorporating an emotion recognition engine, it also provides legal advice that takes into account the user's emotional state.

[1083] Hardware and software to use

[1084] Hardware:

[1085] Devices (e.g., smart glasses, smartphones, head-mounted displays)

[1086] Server (cloud server)

[1087] software:

[1088] Natural language processing engine (e.g., Google NLP API)

[1089] Emotion recognition engine (e.g., Microsoft Azure Emotion API)

[1090] Databases (e.g., MySQL, Elasticsearch)

[1091] Visualization libraries (e.g., FlowChart.js)

[1092] Detailed explanation of data processing and data calculations.

[1093] Users input their legal consultation details using devices such as smart glasses or smartphones. The entered data is sent from the device to the server in JSON format. As a specific example, consider a case where a user inputs, "An intruder has entered the facility. How should I respond?"

[1094] The server decodes the received data to obtain text data. A natural language processing (NLP) engine is then used to extract key keywords from this text data. For example, keywords such as "intruder," "facility," and "response" might be extracted.

[1095] Next, the server uses an emotion recognition engine to analyze the user's input data to determine their emotions. For example, in the case of this prompt, emotions such as "tension" and "anxiety" are recognized.

[1096] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database includes laws, past cases, and regulatory documents, and is searched and retrieved using SQL queries and Elasticsearch.

[1097] Next, the server analyzes the retrieved and collected information to form the most appropriate legal judgment for the user's situation and emotional state. For example, if the user is anxious, it first advises them to calm down and then provides a step-by-step response plan in flowchart format.

[1098] Finally, the server visualizes the legal judgment it has formed and converts it into a flowchart or table using the FlowChart.js library. The visualized result is sent back to the terminal in JSON format, which the terminal parses and displays visually to the user. This allows the user to receive legal advice quickly and in an emotionally sensitive manner.

[1099] Specific example

[1100] Example of a prompt:

[1101] "An intruder has entered the facility. How should we respond?"

[1102] In this specific example, the user's input is analyzed along with their emotions such as "tension" and "anxiety," and appropriate legal response procedures (for example, advice on how to calm down or specific ways to deal with an intruder) are provided in flowchart format.

[1103] In this way, this system allows users to receive not only prompt on-site support but also emotional care, enabling them to deal with situations with greater peace of mind.

[1104] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1105] Step 1:

[1106] The user enters their legal consultation details into a device. The user enters their legal consultation details in text format using a device such as smart glasses or a smartphone. The user's input is captured by the device and stored as a prompt. For example, the prompt might read, "An intruder has entered the facility. How should I respond?"

[1107] Step 2:

[1108] The terminal sends the entered data to the server. The terminal encodes the entered text data into JSON format and sends it to the server as an HTTP POST request. The specific actions of this step are encoding and sending the HTTP request. The input is the legal consultation content entered by the user, and the output is the JSON data sent to the server.

[1109] Step 3:

[1110] The server analyzes the received data and extracts key keywords. The server decodes the received JSON data to obtain text data. Next, it uses a natural language processing engine (NLP engine) to extract key keywords. For example, keywords such as "intruder," "facility," and "response" may be extracted. In this step, the input is the JSON data sent to the server, and the output is the extracted keywords.

[1111] Step 4:

[1112] The server uses an emotion recognition engine to analyze emotions from the user's input data. The server inputs the extracted text data into the emotion recognition engine and analyzes emotions such as "tension" and "anxiety." In this step, the input is the text data sent to the server, and the output is the analyzed emotion data.

[1113] Step 5:

[1114] The server searches for relevant information from its internal database and the internet based on the extracted keywords and sentiment data. The server uses SQL queries and Elasticsearch to search for relevant laws and precedents in its internal database. It also collects additional information from the internet as needed. In this step, the input is keywords and sentiment data, and the output is a set of relevant information.

[1115] Step 6:

[1116] Based on the information collected by the server, it forms a legal judgment appropriate to the user's situation and emotional state. The server combines the collected legal information with the user's emotional state to make the optimal legal judgment. For example, if the user is anxious, it first provides calming advice and then carefully explains how to deal with the situation. In this step, the input is relevant information and emotional data, and the output is the formed legal judgment.

[1117] Step 7:

[1118] The server diagrams legal judgments and converts them into a visually easy-to-understand format. The server then uses the FlowChart.js library to convert the formed legal judgments into flowcharts and tables. By visually showing specific procedures and steps, it makes it easier for users to understand. In this step, the input is the legal judgment, and the output is a diagrammed flowchart or table.

[1119] Step 8:

[1120] The server sends the diagrammed result to the terminal. The server re-encodes the diagrammed data into JSON format and sends it to the terminal as an HTTP response. In this step, the input is the diagrammed legal judgment, and the output is the JSON data sent to the terminal.

[1121] Step 9:

[1122] The terminal displays the results it receives to the user. The terminal decodes the JSON data received from the server and displays the visual judgment result. The user can view the flowchart or tabular legal advice through smart glasses or a smartphone display. In this step, the input is the JSON data sent from the server, and the output is the visual result displayed to the user.

[1123] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1124] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1125] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1126] [Fourth Embodiment]

[1127] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1128] As shown in Figure 7, the 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.

[1129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1130] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1131] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1134] The controlled 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1135] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1136] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[1137] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1138] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1139] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1140] This invention is a system for providing legal consultation and advice, which analyzes the consultation content entered by the user and provides appropriate legal judgments quickly and accurately. This system is realized through the following main components and functions.

[1141] User input

[1142] The user uses their device to enter specific legal questions. For example, if they are asking a question about inheritance tax, they might enter, "My father has passed away, and I have inherited some assets. I would like to know the necessary procedures and the amount of tax."

[1143] Sending and receiving data

[1144] The terminal sends the entered information to the server. This transmission is done using an HTTP request, and the data is encoded in JSON format. The server receives this request and proceeds to the next step.

[1145] Data Analysis

[1146] The server decodes the received data to obtain text data. Then, it uses a natural language processing engine to extract key keywords. For example, "inheritance," "property," and "tax amount" might be extracted.

[1147] Searching for and collecting related information

[1148] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved quickly using SQL queries and Elasticsearch. Meanwhile, web scraping techniques are used to collect information from the internet, utilizing libraries such as Beautiful Soup and Selenium.

[1149] Formation of legal judgments

[1150] Based on the collected information, the server forms specific legal judgments tailored to the user's situation. For example, it may indicate how to calculate inheritance tax and the necessary procedures. This process executes pre-programmed legal logic.

[1151] Diagramming of results

[1152] The server performs a diagramming process to make legal decisions easier to understand. It uses libraries such as FlowChart.js and D3.js to convert the information into flowcharts and tables. Specifically, it is illustrated in the form of "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[1153] Sending and displaying results

[1154] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal parses the received data and displays it in a user-friendly format. This allows the user to quickly obtain specific legal advice.

[1155] Specific example

[1156] For example, if a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be paid," the following process will be performed:

[1157] 1. The user enters the details of their inquiry into the terminal.

[1158] 2. The device sends data to the server.

[1159] 3. The server analyzes the data and extracts keywords such as "inheritance," "assets," and "tax amount."

[1160] 4. The server collects relevant information from its internal database and the internet.

[1161] 5. The server will form specific legal judgments tailored to the user's situation (for example, how to calculate inheritance tax and the necessary procedures).

[1162] 6. The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[1163] 7. The server sends the diagrammed results to the terminal.

[1164] 8. The device displays the results to the user.

[1165] This allows users to obtain information to respond quickly and accurately, enabling them to make swift decisions regarding legal issues.

[1166] The following describes the processing flow.

[1167] Step 1:

[1168] The user enters specific legal questions into the device. For example, they might enter, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be owed."

[1169] Step 2:

[1170] The terminal receives the input text data and encodes it into JSON format. Then, it sends the data to the server using an HTTP POST request.

[1171] Step 3:

[1172] The server receives an HTTP request, decodes the received JSON data, and obtains text data.

[1173] Step 4:

[1174] The server uses a natural language processing (NLP) engine to analyze the text data. Specifically, it uses NLP libraries such as SpaCy and NLTK to extract key keywords (e.g., "inheritance," "property," "tax amount").

[1175] Step 5:

[1176] The server searches for relevant information from its internal database and the internet based on the extracted keywords. It retrieves legal texts and past case precedents from the internal database using SQL queries, and collects relevant information from the internet using web scraping techniques. For example, it might use Beautiful Soup or the Selenium library.

[1177] Step 6:

[1178] The server analyzes the collected information and forms legal judgments based on the user's specific situation. Using pre-programmed legal logic, it derives the method for calculating inheritance tax and the necessary procedural steps.

[1179] Step 7:

[1180] The server visualizes the resulting legal judgment in a way that is easy for the user to understand. It uses libraries such as FlowChart.js and D3.js to convert it into flowcharts or tables. For example, it could be structured as follows: "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," "Step 4: Document preparation."

[1181] Step 8:

[1182] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response.

[1183] Step 9:

[1184] The device decodes the received JSON data, parses the results, and displays them on the screen. This allows users to obtain specific legal advice in a visually easy-to-understand format.

[1185] Specific example

[1186] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be paid":

[1187] 1. The user enters the details of their legal consultation into the terminal.

[1188] 2. The device sends data to the server.

[1189] 3. The server receives the data and retrieves the text data.

[1190] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[1191] 5. The server searches for and retrieves correlation information from its internal database and the internet.

[1192] 6. The server uses legal logic to derive the inheritance tax calculation method and necessary procedures.

[1193] 7. The server visualizes legal judgments and converts them into a visually easy-to-understand format for the user.

[1194] 8. The server sends the diagrammed results to the terminal.

[1195] 9. The device analyzes the results and displays them on the screen for the user to review.

[1196] This allows users to receive prompt and accurate legal advice.

[1197] (Example 1)

[1198] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1199] Conventional legal consultation systems struggled to quickly and accurately analyze user-entered consultation content and provide appropriate legal advice. Furthermore, they lacked the technology to efficiently collect relevant information and display results in a visually easy-to-understand format. As a result, it was difficult for users to obtain appropriate legal judgments in a short amount of time. Additionally, natural language processing and information generation based on prompts were not fully utilized.

[1200] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1201] In this invention, the server includes means for analyzing received data and extracting key keywords, means for searching for relevant information from an internal database and the internet based on the extracted keywords, and means for forming a legal judgment appropriate to the user's situation based on the collected information. This enables the user to obtain appropriate legal advice quickly, accurately, and effectively.

[1202] A "user" is an entity that inputs questions or inquiries into the system to receive legal advice and information.

[1203] A "terminal" is an electronic device used by a user to input consultation details into the system, and it is a device that communicates data with the server.

[1204] A "server" is a central processing unit that analyzes data received from users, collects relevant information, forms legal judgments, and transmits them to terminals.

[1205] "Entered data" refers to information about legal consultations provided by the user to the system via their device.

[1206] A "natural language processing engine" is software or an algorithm used to analyze text data and extract key keywords.

[1207] "Keywords" are terms that are considered important in legal judgments and are extracted from the input data by a natural language processing engine.

[1208] An "internal database" is a database containing legal information such as legal texts, past court precedents, and regulatory documents, and is used as storage for servers to quickly retrieve information.

[1209] "Searching for relevant information on the internet" refers to the process of collecting necessary data from publicly available information on the internet using techniques such as web scraping.

[1210] "Legal judgment" refers to specific legal advice or opinions formed based on the user's situation, using information collected by the server.

[1211] "Diagramming in flowchart or tabular format" refers to a method of visually organizing formed legal judgments using libraries such as FlowChart.js or D3.js, making them easy for users to understand.

[1212] A "generative AI model" is a machine learning model that automatically generates relevant information and advice based on specific prompt sentences.

[1213] A "prompt statement" is an instruction given to a generative AI model, a text intended to guide the generation or processing of specific information.

[1214] This invention is a system for providing legal consultations and advice. It analyzes the legal consultation content entered by the user and provides prompt, accurate, and appropriate legal judgments. This system is implemented using the following hardware and software.

[1215] User input

[1216] Users enter specific legal questions using their devices. For example, they might ask, "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax." The devices used can include PCs, smartphones, and tablets. The entered data is retrieved through web forms or text boxes in applications.

[1217] Sending data

[1218] The terminal sends the entered data to the server. This transmission uses an HTTP POST request, and the data is encoded in JSON format. This enables efficient data transmission and reception.

[1219] Data reception and analysis

[1220] The server receives an HTTP request and decodes the JSON data to obtain text data. The server is a high-performance server machine used to execute computer programs. This text data is analyzed using a natural language processing engine, and key keywords are extracted. Libraries such as NLTK (Natural Language Toolkit) and spaCy are used for natural language processing. Furthermore, a generative AI model can be used to generate relevant information based on specific prompt statements.

[1221] Information retrieval and collection

[1222] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved using SQL queries and Elasticsearch. Web scraping techniques using Beautiful Soup and Selenium are utilized to collect information from the internet.

[1223] Formation of legal judgments

[1224] Based on the collected information, the server forms specific legal judgments appropriate to the user's situation. This involves applying pre-programmed legal logic. For example, it may show how to calculate inheritance tax and the necessary procedures. This process may also utilize an artificial intelligence inference engine, and information may be generated based on prompts using a generative AI model.

[1225] Diagramming of results

[1226] The server performs a diagramming process to make legal decisions easier to understand visually. For this purpose, libraries such as FlowChart.js and D3.js are used to convert the information into flowcharts and tables. For example, it may be visually presented as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[1227] Sending and displaying results

[1228] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal parses the received data and displays it in a user-friendly format. This display may use a web page or application interface. The user can then obtain quick and accurate legal advice.

[1229] Specific example

[1230] For example, if a user inputs "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax," the following prompt could be input into the AI ​​model:

[1231] "Could you please explain the laws regarding inheritance? My father has passed away, and I have inherited some assets. I would like to know the necessary procedures and the amount of tax involved."

[1232] This allows users to obtain the necessary legal information on the spot and quickly begin taking concrete actions to resolve the problem.

[1233] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1234] Step 1:

[1235] The user enters their legal consultation details using a terminal. The text entered by the user is in the format of, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax." Once the user has finished entering the information, they click the "Submit" button. The input is done through a text box, and the output is a text file of the legal consultation.

[1236] Step 2:

[1237] The terminal sends the legal consultation details entered by the user to the server. This transmission uses an HTTP POST request, and the data is encoded in JSON format. For example, it is sent with the following JSON structure: "{"query": "My father has passed away, and I have inherited property. I would like to know the necessary procedures and tax amount"}". The input is text data, and the output is sent as JSON data.

[1238] Step 3:

[1239] The server receives an HTTP request and decodes the JSON data to obtain text data. The received data is parsed by an internal component. The input is JSON data, and the output is the parsed text data. The text data is stored in a variable within the server.

[1240] Step 4:

[1241] The server uses a natural language processing engine to extract key keywords from text data. For example, it might use NLTK or spaCy to extract keywords such as "inheritance," "property," and "tax amount." The natural language processing engine analyzes the text and identifies important words using a specific algorithm. The input is text data, and the output is a list of keywords.

[1242] Step 5:

[1243] The server searches for relevant information from its internal database and the internet based on the extracted keywords. The internal database contains legal texts, past case precedents, and regulatory documents, and data is quickly retrieved using SQL queries and Elasticsearch. Web scraping using Beautiful Soup and Selenium is used to collect information from the internet. The input is a list of keywords, and the output is data of relevant information.

[1244] Step 6:

[1245] The server uses the collected information to form specific legal judgments tailored to the user's situation. Calculations and reasoning are performed according to programmed legal logic, generating information such as "how to calculate inheritance tax" and "necessary procedures." Using a generative AI model, customized information based on prompts can also be generated for the user's situation. The input is relevant data, and the output is a legal judgment.

[1246] Step 7:

[1247] The server visualizes legal judgments in an easily understandable format. Libraries such as FlowChart.js and D3.js are used to convert the information into flowcharts and tables. For example, it might visually represent steps such as "Step 1: Inheritance Commencement," "Step 2: Property Valuation," "Step 3: Tax Calculation," and "Step 4: Document Preparation." The input is legal judgment data, and the output is generated as diagrammatic data.

[1248] Step 8:

[1249] The server re-encodes the diagrammed results into JSON format and sends them to the terminal. The terminal decodes the received data and displays it on the screen. The user visually reviews the results and understands the specific procedures and necessary actions. The input is diagrammed data, and the output provides the user with visually organized information.

[1250] This allows users to receive legal advice in a specific and easy-to-understand format.

[1251] (Application Example 1)

[1252] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1253] Conventional legal consultation systems struggle to quickly and accurately analyze user-submitted legal consultations and provide appropriate legal judgments. Furthermore, the lack of systems that present legal judgments in a visually clear and easy-to-understand format makes them difficult for users to comprehend. In particular, a system with adaptability to effectively respond to legal consultations attempted by users in virtual spaces is necessary.

[1254] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1255] In this invention, the server includes means for the user to input legal consultation details via a terminal, means for the terminal to transmit the input data to the server, means for the server to analyze the received data and extract key keywords, means for searching for relevant information from databases and networks, means for forming a legal judgment appropriate to the user's situation based on the collected information, means for diagramming the legal judgment and converting it into a visually easy-to-understand form, means for transmitting the diagrammed results to the terminal, and means for the terminal to display the received results to the user and make them visible in a virtual space. This enables rapid and accurate analysis of legal consultation details, provision of appropriate legal judgments, and display of results in a visually easy-to-understand format.

[1256] A "user" is a person who enters details of their legal consultation into a terminal and receives the information.

[1257] A "terminal" refers to a device used by a user to input details of their legal consultation, such as a smartphone, smart glasses, or head-mounted display.

[1258] A "server" is a computer system that analyzes received data, extracts keywords, and forms legal judgments.

[1259] "Data analysis" is the process by which a server receives data sent from a user, understands its content, and extracts key keywords.

[1260] "Key keywords" are important terms extracted when analyzing the legal consultation content entered by the user.

[1261] A "database" is an internal source of information that stores relevant legal information.

[1262] "Network" refers to the internet and other means of obtaining information, providing external sources for collecting legal information.

[1263] "Legal judgment" refers to the conclusions and advice that the server forms regarding the user's legal consultation based on extracted keywords and collected information.

[1264] "Diagramming" is the process of converting legal judgments into a visually easy-to-understand format.

[1265] "Visually easy-to-understand format" refers to information that has been converted into formats such as flowcharts and tables so that users can easily understand legal decisions.

[1266] A "virtual space" is a virtual information environment provided to users through devices such as smart glasses or head-mounted displays.

[1267] To implement this invention, a terminal such as a smartphone, smart glasses, or head-mounted display is used. First, the user inputs the details of their legal consultation via the terminal. For example, they might input, using voice or text input, "My father has passed away, and I have inherited property. I would like to know the necessary procedures and the amount of tax." The terminal then sends the input data to the server.

[1268] The server analyzes the received data and extracts key keywords. For this purpose, the server uses a natural language processing engine (e.g., SpaCy). Based on the extracted keywords, the server searches for relevant information from its internal database and network. The internal database contains legal texts and past case precedents, while external sources include legal information on the network. SQL queries, Elasticsearch, and web scraping techniques (e.g., Beautiful Soup, Selenium) are used for information retrieval.

[1269] Based on the collected information, the server forms a legal judgment appropriate to the user's situation. This legal judgment includes specific advice and procedural instructions. For example, information on how to calculate inheritance tax and the necessary procedures is provided. This legal judgment is then converted into a visually easy-to-understand format. Specifically, it is diagrammed into flowcharts and tables using FlowChart.js or D3.js.

[1270] The server re-encodes the diagrammed results in JSON format and sends them to the terminal. The terminal receives this and displays it in a format that is easy for the user to understand. The displayed information is provided in a visually clear manner within the virtual space. For example, when using smart glasses, a flowchart of legal decisions is displayed in front of the user's eyes, allowing them to examine each step in detail.

[1271] As a concrete example, if a user enters the prompt, "My father has passed away, and I will inherit the land and house. How much inheritance tax will I have to pay?", the server will process it in the following steps: First, it will use a natural language processing engine to extract key keywords and collect relevant information from the database and network. Then, it will form a legal judgment appropriate to the user's situation, diagram it in flowchart format, and send it to the terminal. Finally, the user's smart glasses will display "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[1272] This allows users to quickly and accurately receive specific advice regarding their legal concerns.

[1273] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1274] Step 1:

[1275] The user enters the details of their legal consultation into their device.

[1276] Users use smartphones, smart glasses, or head-mounted displays to input data via voice or text. For example, they might input, "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax." The input data is in text format.

[1277] Step 2:

[1278] The terminal sends the entered data to the server.

[1279] The terminal encodes the input into JSON format and sends it to the server as an HTTP request. The input data is text data, and the encoded data is in JSON format. The server receives this.

[1280] Step 3:

[1281] The server analyzes the received data and extracts key keywords.

[1282] The server uses a natural language processing engine (e.g., SpaCy) to parse the data. The input is text data in JSON format, and the output after parsing is a list of key keywords (e.g., "inheritance," "property," "tax amount"). Specifically, the text is tokenized and specific parts of speech are extracted.

[1283] Step 4:

[1284] The server searches for relevant information from the database and network based on the extracted keywords.

[1285] The server searches its internal database using SQL queries and Elasticsearch, and gathers necessary information from the internet using Beautiful Soup and Selenium. The input is a list of key keywords, and the output is a set of related information (e.g., legal texts and past court precedents). Specifically, it converts keywords into queries and crawls databases and websites.

[1286] Step 5:

[1287] Based on the information collected by the server, legal judgments appropriate to the user's situation are formed.

[1288] The collected information is integrated, and legal judgments are made based on specific logic. The input is a set of relevant information, and the output is the text of the legal judgment conclusion or advice. In concrete terms, a rule-based algorithm is executed to derive the conclusion.

[1289] Step 6:

[1290] The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[1291] The server uses FlowChart.js and D3.js to convert legal judgments into flowcharts and tabular formats. The input is the text of the legal judgment, and the output is visual flowchart or tabular image data. Specifically, it converts each step into a diagram and adds visual elements.

[1292] Step 7:

[1293] The server sends the diagrammed result to the terminal.

[1294] The server re-encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. The input is visual flowchart or tabular data, and the output is JSON data.

[1295] Step 8:

[1296] The results received by the device are displayed to the user and made visible within the virtual space.

[1297] The device decodes the received data and displays it on a smartphone, smart glasses, or head-mounted display. The input is data in JSON format, and the output is information displayed in a visually easy-to-understand format (e.g., "Step 1: Inheritance Commencement", "Step 2: Property Valuation", "Step 3: Tax Amount Calculation", "Step 4: Document Preparation"). Specifically, it analyzes the data and renders it on the screen.

[1298] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1299] This invention combines an emotion recognition engine with a system that provides legal consultation and advice, thereby offering legal judgments that take the user's emotions into consideration. This system includes the following elements and functions.

[1300] User input

[1301] The user uses a terminal to enter details of their legal consultation. For example, in an inquiry regarding inheritance issues, they might enter, "My father has passed away. There are assets to inherit, and I would like to know about the procedures and the amount of tax involved."

[1302] Sending and receiving data

[1303] The terminal encodes the input data into JSON format and sends it to the server as an HTTP POST request. The server receives this request and begins processing the data.

[1304] Data Analysis

[1305] The server decodes the received data and obtains text data. Next, it uses a natural language processing (NLP) engine to extract key keywords. For example, keywords such as "inheritance," "property," and "tax amount" are extracted.

[1306] emotion recognition

[1307] The server uses an emotion recognition engine to analyze emotions (joy, sadness, surprise, etc.) from the user's input data. The emotion recognition engine uses machine learning algorithms to evaluate the emotional state of the input text.

[1308] Searching for and collecting related information

[1309] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database includes legal texts, past case precedents, and regulatory documents, and data is retrieved using SQL queries and Elasticsearch. Web scraping techniques are used to collect information from the internet.

[1310] Formation of legal judgments

[1311] The server analyzes the collected information and forms the most appropriate legal judgment based on the user's specific situation and emotional state. For example, if the user is feeling anxious, it will provide legal advice that explains the process in a more careful and detailed manner.

[1312] Diagramming of results

[1313] The server visualizes legal decisions and converts them into a user-friendly format. It uses libraries such as FlowChart.js and D3.js to convert them into flowcharts and tables. For example, steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation" are included.

[1314] Sending and displaying results

[1315] The server encodes the diagrammed results into JSON format and sends them to the terminal. The terminal parses the received data and displays the results on the screen. This allows the user to receive legal advice in a specific and emotionally sensitive manner.

[1316] Specific example

[1317] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and tax amount," and if the user's feelings of grief are recognized,

[1318] 1. The user enters the details of their legal consultation into the terminal.

[1319] 2. The device sends data to the server.

[1320] 3. The server receives the data and retrieves the text data.

[1321] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[1322] 5. The server analyzes the user's emotions using an emotion recognition engine and recognizes them as "sadness."

[1323] 6. The server collects relevant information from its internal database and the internet based on keywords and sentiment data.

[1324] 7. The server analyzes the collected information and forms specific legal judgments (e.g., detailed procedural explanations and reassuring advice) that are appropriate to the user's situation and feelings.

[1325] 8. The server diagrams legal judgments to make them visually easy to understand.

[1326] 9. The server sends the diagrammed results to the terminal.

[1327] 10. The terminal displays the results to the user.

[1328] This allows users to receive prompt and emotionally sensitive legal advice.

[1329] The following describes the processing flow.

[1330] Step 1:

[1331] The user enters specific legal questions into the device. For example, they might enter, "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and the amount of tax to be owed."

[1332] Step 2:

[1333] The terminal encodes the input data into JSON format and sends it to the server using an HTTP POST request. The server's URL and endpoint are configured, and the data is sent to this endpoint.

[1334] Step 3:

[1335] The server decodes the JSON data from the received HTTP request to obtain text data. This makes the user's input available to the server.

[1336] Step 4:

[1337] The server uses a natural language processing (NLP) engine to analyze the text data. Specifically, it uses NLP libraries such as SpaCy and NLTK to extract key keywords (e.g., "inheritance," "property," "tax amount").

[1338] Step 5:

[1339] The server uses an emotion recognition engine to analyze emotions from the user's input text. Possible algorithms used include emotion classifiers and emotion analysis models (e.g., BERT or Sentiment140). Based on the user's text content, it identifies emotions such as "joy," "sadness," and "anxiety."

[1340] Step 6:

[1341] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database contains legal texts, past case precedents, and regulatory documents, from which necessary information is retrieved using SQL queries and Elasticsearch. Web scraping techniques are used to collect data from the internet. Specifically, libraries such as Beautiful Soup and Selenium are utilized.

[1342] Step 7:

[1343] The server uses the collected information to form legal judgments based on the user's specific situation and emotions. In certain cases, it will show how to calculate inheritance tax and the necessary procedures. If the emotional state is "sadness," a more careful and reassuring explanation will be provided.

[1344] Step 8:

[1345] The server visualizes the formed legal judgment and converts it into a format that is easy for the user to understand. It uses libraries such as FlowChart.js and D3.js to convert it into flowcharts and tables. For example, steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation" are visualized.

[1346] Step 9:

[1347] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. This data includes detailed instructions along with emotionally sensitive explanations.

[1348] Step 10:

[1349] The device decodes the received JSON data, analyzes the results, and displays them on the screen in a user-friendly format. The user can then review these results and obtain specific instructions and advice.

[1350] Specific example

[1351] If a user enters "My father has passed away, and I have inherited assets. I want to know the necessary procedures and the amount of tax," and the emotion recognition engine recognizes the emotion of "sadness":

[1352] 1. The user enters the details of their legal consultation into the terminal.

[1353] 2. The device sends data to the server.

[1354] 3. The server receives the data and retrieves the text data.

[1355] 4. The server analyzes the data using an NLP engine and extracts keywords such as "inheritance," "assets," and "tax amount."

[1356] 5. The server recognizes the emotion of "sadness" using its emotion recognition engine.

[1357] 6. The server collects relevant information from its internal database and the internet based on keywords and sentiment data.

[1358] 7. Based on the collected information, the server forms the most appropriate legal judgment for the user's situation and feelings (e.g., providing clear procedural explanations and reassurance).

[1359] 8. The server diagrams legal judgments and converts them into a visually easy-to-understand format.

[1360] 9. The server sends the diagrammed results to the terminal.

[1361] 10. The device analyzes the results and displays them on the screen for the user to review.

[1362] This process allows users to receive prompt and emotionally sensitive legal advice.

[1363] (Example 2)

[1364] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1365] Conventional legal consultation systems rarely provide legal judgments that take into account the user's emotional state, relying solely on entered text data. Therefore, even when a user requires emotional support, this need is often not met. Users facing legal problems often experience stress and anxiety, making emotionally sensitive responses essential. Consequently, a system is needed that provides legal judgments while considering the user's emotions.

[1366] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing received data and extracting key keywords, means for analyzing emotions from user input data using an emotion recognition engine, and means for searching for relevant information from an internal database and the internet based on the extracted keywords and emotion data. This makes it possible to make legal judgments that take into account the user's emotional state.

[1367] A "user" is an individual or legal entity that uses the system to seek legal advice.

[1368] A "terminal" is a device used by a user to input data and send and receive data with a server. Specifically, this refers to computers, smartphones, tablets, and other similar devices.

[1369] A "server" is a device that receives and analyzes data transmitted from a terminal, and searches for and visualizes related information.

[1370] "Legal consultation content" refers to legal questions or issues entered by the user via their device. For example, it could be content related to specific cases such as inheritance, property division, or tax calculations.

[1371] "Data" refers to the text information entered by the user, the results of its analysis, and related information.

[1372] An "NLP engine" is software used for natural language processing and has the function of extracting key keywords from text data.

[1373] An "emotion recognition engine" is software that implements machine learning algorithms to analyze emotions from user input data.

[1374] "Keywords" are important terms in the user's legal consultation, extracted by the NLP engine. Examples include "inheritance," "property," and "tax amount."

[1375] "Emotional data" refers to information that indicates the emotional state contained in the user's input data, as analyzed by the emotion recognition engine.

[1376] "Related information" refers to information obtained from internal databases and the internet based on extracted keywords and sentiment data. This includes legal texts, past case precedents, and regulatory documents.

[1377] An "internal database" is a database that stores legal information, past court precedents, etc., and is used by the server to retrieve information using SQL queries and Elasticsearch.

[1378] "Information gathering from the internet" refers to the method of collecting relevant information from the internet using web scraping techniques.

[1379] "Legal judgment" refers to providing legal advice or judgments that are appropriate to the user's situation and emotional state, based on the information collected by the server.

[1380] "Diagramming" is the process of converting legal judgments into visually easy-to-understand forms such as flowcharts and tables.

[1381] A flowchart is a diagram that visually represents a series of procedures or processes, making it easier for users to understand the flow of those procedures.

[1382] This invention combines an emotion recognition engine with a system that provides legal consultation and advice, thereby offering legal judgments that take the user's emotions into consideration. This system includes the following elements and functions.

[1383] User input

[1384] The user uses a terminal to input details of their legal inquiry. For example, they might input, "My father has passed away. I have inherited assets, and I would like to know about the procedures and tax implications." The terminal accepts the input and prepares the text data.

[1385] Sending and receiving data

[1386] The terminal encodes the entered text data into JSON format and sends it to the server as an HTTP POST request. The server receives the HTTP request, decodes it, and retrieves the data.

[1387] Data analysis (keyword extraction)

[1388] The server decodes the received data to obtain text data. Next, it uses a natural language processing (NLP) engine to extract key keywords. Specifically, it utilizes libraries such as SpaCy and NLTK to extract important keywords such as "inheritance," "property," and "tax amount."

[1389] emotion recognition

[1390] The server inputs the received text data into an emotion recognition engine to analyze the user's emotions. This emotion recognition engine is a model trained using machine learning frameworks such as TensorFlow or PyTorch. Specifically, it classifies emotions such as "joy," "sadness," and "anxiety" from the input text.

[1391] Searching for and collecting related information

[1392] Based on extracted keywords and sentiment data, the server collects relevant information from its internal database (SQL queries and Elasticsearch) and the internet (web scraping). The internal database contains legal texts, past case precedents, and regulatory documents.

[1393] Formation of legal judgments

[1394] The server analyzes the collected information and forms the most appropriate legal judgment based on the user's specific situation and emotional state. For example, if the user is experiencing sadness, it will provide a more considerate and reassuring explanation of the procedure.

[1395] Diagramming of results

[1396] The server visualizes legal decisions and converts them into a user-friendly format. This involves using visual libraries such as FlowChart.js and D3.js to convert them into flowcharts and tables. Specific examples include steps such as "Step 1: Inheritance begins," "Step 2: Property valuation," "Step 3: Tax calculation," and "Step 4: Document preparation."

[1397] Sending and displaying results

[1398] The server encodes the diagrammed results into JSON format and sends them to the terminal. The terminal parses the received data and displays it on the screen in a visually easy-to-understand format. Specifically, a flowchart and step-by-step explanations are displayed.

[1399] Specific example

[1400] If a user enters "My father has passed away, and I have inherited assets. I would like to know the necessary procedures and tax amount," and if feelings of grief are recognized, the following steps will be taken.

[1401] 1. The user enters the details of their legal consultation into their device.

[1402] 2. The terminal sends the input data to the server.

[1403] 3. The server receives the data and retrieves the text data.

[1404] 4. The server uses an NLP engine to analyze the data and extract keywords such as "inheritance," "assets," and "tax amount."

[1405] 5. The server uses an emotion recognition engine to analyze the user's emotions and recognizes them as "sadness."

[1406] 6. The server collects relevant information from internal databases and the internet based on keywords and sentiment data.

[1407] 7. The server analyzes the collected information and forms specific legal judgments (e.g., detailed procedural explanations and reassuring advice) that are appropriate to the user's situation and feelings.

[1408] 8. The server visualizes legal judgments in a diagrammatic format, making them easy to understand visually.

[1409] 9. The server sends the diagrammed result to the terminal.

[1410] 10. The device displays the results to the user.

[1411] Concrete examples of prompt sentences for generative AI models

[1412] "My father has passed away, and I have inherited assets. I would like a detailed explanation of the necessary procedures and tax amounts. Please also perform sentiment analysis and provide particularly thorough explanations if the user is anxious."

[1413] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1414] Step 1:

[1415] The user enters their legal consultation details via the terminal. The input might include specific questions such as, "My father has passed away. I have inherited assets, and I would like to know about the procedures and tax implications." The terminal saves the text data entered by the user to its internal memory. At this stage, the output is the entered text data.

[1416] Step 2:

[1417] The terminal encodes the input data into JSON format and sends it to the server as an HTTP POST request. Specifically, it uses an encoder that converts text data into JSON format. The input is text data from the user, and the output is JSON data sent to the server.

[1418] Step 3:

[1419] The server receives an HTTP request, decodes the received JSON data, and retrieves text data. The input is JSON data sent from the terminal, and the output is the decoded text data. Specifically, the decoding process uses a JSON decoding library.

[1420] Step 4:

[1421] The server passes the decoded text data to a natural language processing (NLP) engine to extract key keywords. The input is text data, which the NLP engine (e.g., spaCy or NLTK) analyzes to extract key keywords (e.g., "inheritance," "property," "tax amount"). The output is a list of the extracted keywords.

[1422] Step 5:

[1423] The server inputs text data into an emotion recognition engine to analyze the user's emotions. The input is text data, and the emotion recognition engine uses machine learning algorithms to classify emotions such as "joy," "sadness," and "anxiety." The output is emotion data, and "sadness" is detected as an example.

[1424] Step 6:

[1425] The server collects relevant information from its internal database and the internet based on extracted keywords and sentiment data. The input consists of keywords and sentiment data, and the server executes SQL queries on the internal database or retrieves information from the internet using web scraping techniques. The output is a set of collected relevant information.

[1426] Step 7:

[1427] The server analyzes the collected information and forms the optimal legal judgment based on the user's specific situation and emotional state. The input consists of relevant information and the user's emotional data, and the server uses an analytical algorithm to make a legal judgment. The output is the formed legal judgment. For example, if the user is experiencing sadness, a more polite and reassuring explanation of the procedure will be generated.

[1428] Step 8:

[1429] The server visualizes legal judgments and converts them into a user-friendly format. The input is text data of legal judgments, which are converted into flowcharts and tables using visual libraries such as FlowChart.js and D3.js. The output is the visualized information.

[1430] Step 9:

[1431] The server encodes the diagrammed results into JSON format and sends them to the terminal as an HTTP response. The input is the diagrammed information, which is encoded using a JSON encoder. The output is the JSON data sent to the terminal.

[1432] Step 10:

[1433] The terminal decodes the JSON data received from the server and displays it on the screen in a visually easy-to-understand format. The input is JSON data sent from the server, which is decoded and then re-diagrammed. The specific output is a flowchart and step-by-step explanation visually displayed on the browser screen.

[1434] (Application Example 2)

[1435] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1436] Traditional legal consultation systems tended to provide only mechanical answers, failing to consider the user's emotional state. This made it difficult to offer appropriate legal advice tailored to the situation, resulting in a lack of support for users experiencing anxiety and stress. Furthermore, in the rapidly evolving security landscape, there was a growing need for a system that could provide legal judgments that took emotions into account.

[1437] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input legal consultation content via a terminal, means for the terminal to transmit the input data to the server, means for the server to analyze the received data and extract key keywords, means for the server to search for relevant information from an internal database and the internet based on the extracted keywords, means for the server to form a legal judgment appropriate to the user's situation based on the information collected, means for the server to diagram the legal judgment and convert it into a visually easy-to-understand form, means for the server to transmit the diagrammed result to the terminal, means for the terminal to display the received result to the user, and means for analyzing the user's emotions using an emotion recognition engine and providing a legal judgment that takes the emotion data into consideration. This makes it possible to provide legal advice that takes the user's emotions into consideration, and can support quick and appropriate legal judgments that respond to emotions, especially in security settings.

[1438] A "user" is a person who uses a terminal to seek legal advice.

[1439] A "terminal" is a device used by users to input legal consultation details and to send and receive data with the server.

[1440] A "server" is a central processing unit that analyzes received data, searches for and collects necessary information, and forms and diagrams legal judgments.

[1441] "Data" refers to information such as legal consultation details and emotion recognition results entered by the user via their device.

[1442] "Keywords" are words and phrases that are important for understanding the legal consultation content, extracted through natural language processing.

[1443] An "internal database" is an electronic database that holds legal information such as legal texts, past court precedents, and regulatory documents.

[1444] The "Internet" is a network used to obtain additional relevant information from external sources.

[1445] "Related information" refers to laws, precedents, and regulatory documents that are searched based on the content of the legal consultation.

[1446] A "legal judgment" is a decision that provides appropriate advice or instructions regarding legal matters.

[1447] "Diagramming" refers to the process of converting legal judgments into flowcharts or tables to make them visually easier to understand.

[1448] An "emotion recognition engine" is a system that uses a machine learning algorithm to analyze emotions from user input data and evaluate their content.

[1449] "Emotional data" refers to information that indicates the user's emotional state as analyzed by an emotion recognition engine.

[1450] This invention is a system in which a user inputs legal consultation details via a terminal, and a server analyzes, searches, judges, and diagrams the input content, finally sending the visualized results to the terminal for display. Furthermore, by incorporating an emotion recognition engine, it also provides legal advice that takes into account the user's emotional state.

[1451] Hardware and software to use

[1452] Hardware:

[1453] Devices (e.g., smart glasses, smartphones, head-mounted displays)

[1454] Server (cloud server)

[1455] software:

[1456] Natural language processing engine (e.g., Google NLP API)

[1457] Emotion recognition engine (e.g., Microsoft Azure Emotion API)

[1458] Databases (e.g., MySQL, Elasticsearch)

[1459] Visualization libraries (e.g., FlowChart.js)

[1460] Detailed explanation of data processing and data calculations.

[1461] Users input their legal consultation details using devices such as smart glasses or smartphones. The entered data is sent from the device to the server in JSON format. As a specific example, consider a case where a user inputs, "An intruder has entered the facility. How should I respond?"

[1462] The server decodes the received data to obtain text data. A natural language processing (NLP) engine is then used to extract key keywords from this text data. For example, keywords such as "intruder," "facility," and "response" might be extracted.

[1463] Next, the server uses an emotion recognition engine to analyze the user's input data to determine their emotions. For example, in the case of this prompt, emotions such as "tension" and "anxiety" are recognized.

[1464] The server searches for relevant information from its internal database and the internet based on extracted keywords and sentiment data. The internal database includes laws, past cases, and regulatory documents, and is searched and retrieved using SQL queries and Elasticsearch.

[1465] Next, the server analyzes the retrieved and collected information to form the most appropriate legal judgment for the user's situation and emotional state. For example, if the user is anxious, it first advises them to calm down and then provides a step-by-step response plan in flowchart format.

[1466] Finally, the server visualizes the legal judgment it has formed and converts it into a flowchart or table using the FlowChart.js library. The visualized result is sent back to the terminal in JSON format, which the terminal parses and displays visually to the user. This allows the user to receive legal advice quickly and in an emotionally sensitive manner.

[1467] Specific example

[1468] Example of a prompt:

[1469] "An intruder has entered the facility. How should we respond?"

[1470] In this specific example, the user's input is analyzed along with their emotions such as "tension" and "anxiety," and appropriate legal response procedures (for example, advice on how to calm down or specific ways to deal with an intruder) are provided in flowchart format.

[1471] In this way, this system allows users to receive not only prompt on-site support but also emotional care, enabling them to deal with situations with greater peace of mind.

[1472] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1473] Step 1:

[1474] The user enters their legal consultation details into a device. The user enters their legal consultation details in text format using a device such as smart glasses or a smartphone. The user's input is captured by the device and stored as a prompt. For example, the prompt might read, "An intruder has entered the facility. How should I respond?"

[1475] Step 2:

[1476] The terminal sends the entered data to the server. The terminal encodes the entered text data into JSON format and sends it to the server as an HTTP POST request. The specific actions of this step are encoding and sending the HTTP request. The input is the legal consultation content entered by the user, and the output is the JSON data sent to the server.

[1477] Step 3:

[1478] The server analyzes the received data and extracts key keywords. The server decodes the received JSON data to obtain text data. Next, it uses a natural language processing engine (NLP engine) to extract key keywords. For example, keywords such as "intruder," "facility," and "response" may be extracted. In this step, the input is the JSON data sent to the server, and the output is the extracted keywords.

[1479] Step 4:

[1480] The server uses an emotion recognition engine to analyze emotions from the user's input data. The server inputs the extracted text data into the emotion recognition engine and analyzes emotions such as "tension" and "anxiety." In this step, the input is the text data sent to the server, and the output is the analyzed emotion data.

[1481] Step 5:

[1482] The server searches for relevant information from its internal database and the internet based on the extracted keywords and sentiment data. The server uses SQL queries and Elasticsearch to search for relevant laws and precedents in its internal database. It also collects additional information from the internet as needed. In this step, the input is keywords and sentiment data, and the output is a set of relevant information.

[1483] Step 6:

[1484] Based on the information collected by the server, it forms a legal judgment appropriate to the user's situation and emotional state. The server combines the collected legal information with the user's emotional state to make the optimal legal judgment. For example, if the user is anxious, it first provides calming advice and then carefully explains how to deal with the situation. In this step, the input is relevant information and emotional data, and the output is the formed legal judgment.

[1485] Step 7:

[1486] The server diagrams legal judgments and converts them into a visually easy-to-understand format. The server then uses the FlowChart.js library to convert the formed legal judgments into flowcharts and tables. By visually showing specific procedures and steps, it makes it easier for users to understand. In this step, the input is the legal judgment, and the output is a diagrammed flowchart or table.

[1487] Step 8:

[1488] The server sends the diagrammed result to the terminal. The server re-encodes the diagrammed data into JSON format and sends it to the terminal as an HTTP response. In this step, the input is the diagrammed legal judgment, and the output is the JSON data sent to the terminal.

[1489] Step 9:

[1490] The terminal displays the results it receives to the user. The terminal decodes the JSON data received from the server and displays the visual judgment result. The user can view the flowchart or tabular legal advice through smart glasses or a smartphone display. In this step, the input is the JSON data sent from the server, and the output is the visual result displayed to the user.

[1491] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1492] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1493] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1494] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1495] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1496] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1497] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1498] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1499] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1500] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1501] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1502] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1503] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1504] 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.

[1505] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1506] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1507] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1508] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1509] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1510] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1511] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1512] The following is further disclosed regarding the embodiments described above.

[1513] (Claim 1)

[1514] A means for users to input legal consultation details via their device,

[1515] A means for the terminal to send the entered data to the server,

[1516] A means of analyzing the data received by the server and extracting key keywords,

[1517] The server has a means of searching for relevant information from its internal database and the internet based on the extracted keywords.

[1518] A means of forming legal judgments appropriate to the user's situation based on information collected by the server,

[1519] A means by which the server diagrams legal judgments and converts them into a visually easy-to-understand format,

[1520] A means for the server to send the diagrammed result to the terminal,

[1521] A means of displaying the results received by the terminal to the user,

[1522] A system that includes this.

[1523] (Claim 2)

[1524] The system according to claim 1, wherein the server uses a legal natural language processing engine to analyze received data and extract key keywords.

[1525] (Claim 3)

[1526] The system according to claim 1, wherein the server diagrams legal decisions in flowchart or tabular format.

[1527] "Example 1"

[1528] (Claim 1)

[1529] A means for users to input legal consultation details via their device,

[1530] A means for the terminal to send the entered data to the server,

[1531] A means of analyzing the data received by the server and extracting key keywords,

[1532] The server has a means of searching for relevant information from its internal database and the internet based on the extracted keywords.

[1533] A means of forming legal judgments appropriate to the user's situation based on information collected by the server,

[1534] The server provides a means to visualize legal judgments in a flowchart or tabular format, converting them into a visually easy-to-understand form.

[1535] A means for the server to send the diagrammed result to the terminal,

[1536] A means of displaying the results received by the terminal to the user,

[1537] A system that includes this.

[1538] (Claim 2)

[1539] The system according to claim 1, wherein the server uses a natural language processing engine to analyze the received data and extract key keywords.

[1540] (Claim 3)

[1541] The system according to claim 1, wherein the server uses a generated AI model to automatically generate relevant information based on a specific prompt statement.

[1542] "Application Example 1"

[1543] (Claim 1)

[1544] A means for users to input legal consultation details via their device,

[1545] A means for the terminal to send the entered data to the server,

[1546] A means of analyzing the data received by the server and extracting key keywords,

[1547] The server has means to search for relevant information from databases and networks based on extracted keywords,

[1548] A means of forming legal judgments appropriate to the user's situation based on information collected by the server,

[1549] A means by which the server diagrams legal judgments and converts them into a visually easy-to-understand format,

[1550] A means for the server to send the diagrammed result to the terminal,

[1551] A means of displaying the results received by the terminal to the user and making them visible in a virtual space,

[1552] A system that includes this.

[1553] (Claim 2)

[1554] The system according to claim 1, wherein the server uses a language processing engine to analyze the received data and extract key keywords.

[1555] (Claim 3)

[1556] The system according to claim 1, wherein the server diagrams legal decisions in flowchart or tabular format and displays them in a virtual space.

[1557] "Example 2 of combining an emotion engine"

[1558] (Claim 1)

[1559] A means for users to input legal consultation details via their device,

[1560] A means for the terminal to send the entered data to the server,

[1561] A means of analyzing the data received by the server and extracting key keywords,

[1562] A means by which the server analyzes emotions from user input data using an emotion recognition engine,

[1563] The server has means to search for relevant information from its internal database and the internet based on extracted keywords and sentiment data.

[1564] A means of forming legal judgments appropriate to the user's situation and emotional state based on information collected by the server,

[1565] A means by which the server diagrams legal judgments and converts them into a visually easy-to-understand format,

[1566] A means for the server to send the diagrammed result to the terminal,

[1567] A means of displaying the results received by the terminal to the user,

[1568] A system that includes this.

[1569] (Claim 2)

[1570] The system according to claim 1, wherein the server uses a legal natural language processing engine to analyze received data and extract key keywords.

[1571] (Claim 3)

[1572] The system according to claim 1, wherein the server diagrams legal decisions in flowchart or tabular format.

[1573] "Application example 2 when combining with an emotional engine"

[1574] (Claim 1)

[1575] A means for users to input legal consultation details via their device,

[1576] A means for the terminal to send the entered data to the server,

[1577] A means of analyzing the data received by the server and extracting key keywords,

[1578] The server has a means of searching for relevant information from its internal database and the internet based on the extracted keywords.

[1579] A means of forming legal judgments appropriate to the user's situation based on information collected by the server,

[1580] A means by which the server diagrams legal judgments and converts them into a visually easy-to-understand format,

[1581] A means for the server to send the diagrammed result to the terminal,

[1582] A means of displaying the results received by the terminal to the user,

[1583] A means of providing legal judgments that take into account the emotional data by analyzing the user's emotions using an emotion recognition engine,

[1584] A system that includes this.

[1585] (Claim 2)

[1586] The system according to claim 1, wherein the server uses a legal natural language processing engine to analyze received data and extract key keywords.

[1587] (Claim 3)

[1588] The system according to claim 1, wherein the server diagrams legal decisions in flowchart or tabular format. [Explanation of symbols]

[1589] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to input legal consultation details via their device, A means for the terminal to send the entered data to the server, A means of analyzing the data received by the server and extracting key keywords, The server has a means of searching for relevant information from its internal database and the internet based on the extracted keywords. A means of forming legal judgments appropriate to the user's situation based on information collected by the server, A means by which the server diagrams legal judgments and converts them into a visually easy-to-understand format, A means for the server to send the diagrammed result to the terminal, A means of displaying the results received by the terminal to the user, A system that includes this.

2. The system according to claim 1, wherein the server uses a legal natural language processing engine to analyze received data and extract key keywords.

3. The system according to claim 1, wherein the server diagrams legal decisions in flowchart or tabular format.

Images