system

Abstract

We provide the system. [Solution] Means for making legal databases accessible, A means for processing input case information and performing natural language analysis, A means of searching for relevant laws and precedents based on the analyzed information, A means of generating a draft judgment based on search results, A means of outputting the generated draft judgment, A system that includes this.

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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In legal judgment, conventional methods are easily affected by human and psychological factors and may lead to incorrect judgments. For this reason, it may be difficult for judges and legal professionals to make reliable, fair, and impartial judgments, and there is also a problem that the judgment process takes time. Furthermore, since the interpretation of laws depends on personal subjectivity, there is a risk of inconsistency. To solve these problems, a system that eliminates human subjectivity and realizes mechanical and consistent legal judgment based on laws and precedents is necessary.

Means for Solving the Problems

[0005] This invention provides a means for quickly searching for relevant laws and past precedents by utilizing a legal database. It includes a means for processing case information necessary for legal judgments using natural language processing and generating draft judgments based on that information, thereby enabling fair and impartial legal judgments. Furthermore, it aims for continuous accuracy improvement by accepting user feedback and updating the machine learning model. This system supports the processes of public institutions and corporations seeking trials and legal judgments, enabling efficient and reliable decision-making.

[0006] A "legal database" is an information system that stores and manages information related to laws and past court precedents in an accessible format.

[0007] "Case information" refers to information about specific facts and evidence necessary for making legal judgments.

[0008] "Natural language processing" is a technology that converts input text information into a format that is easy for a computer to understand and then analyzes it.

[0009] A "draft judgment" is a draft of a recommended legal decision generated by AI based on laws and precedents.

[0010] "Feedback information" refers to information that users provide to the system regarding their opinions and suggestions for improvement regarding the generated draft judgment.

[0011] A "machine learning model" refers to an algorithm that learns from large amounts of data and makes predictions and decisions based on given conditions.

[0012] "Public institutions or legal entities" refer to organizations such as government agencies and corporations that are responsible for making legal judgments and conducting evaluation processes. [Brief explanation of the drawing]

[0013] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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 to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 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 Example 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.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention presents an embodiment of a legal judgment support system in which a server, terminal, and user work in cooperation. The server efficiently manages laws and past precedents by accessing a legal database and can quickly and accurately search this information. Users can input specific case information using a terminal, and this information is transferred to the server and processed using natural language processing technology. Based on the analyzed information, the server searches for relevant laws and precedents and generates a draft judgment to derive the optimal legal decision.

[0035] In this system, user feedback is extremely important. By sending users' opinions and requests regarding draft judgments from their terminals to the server, the server can update its machine learning model and continuously improve the overall accuracy of the system. This will lead to more objective and fair interpretation of laws and regulations.

[0036] As a concrete example, consider a case where a user consults the system about a dispute related to their employment contract. The user inputs the relevant facts and contract details into the terminal. The server analyzes this information and extracts relevant labor laws and precedents. The server summarizes the legal opinion on the case in question and generates a draft judgment that would be beneficial to the user. This draft judgment can show the user specific steps they should take to resolve the problem.

[0037] In this way, this system supports legal judgments in courts, public institutions, corporate legal departments, etc., and provides a fair and impartial judgment process by eliminating human subjectivity.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user enters specific case information regarding legal troubles from their device. This includes details such as relevant facts, contracts, and evidence.

[0041] Step 2:

[0042] The terminal structures the input information, converts it into a data format, and sends it to the server. During this process, it performs basic checks to ensure there are no missing or inconsistent pieces of information.

[0043] Step 3:

[0044] The server processes the received case information using a natural language processing tool to extract keywords and legal concepts. Based on these analysis results, it searches the relevant legal database.

[0045] Step 4:

[0046] The server uses the extracted keywords to search the database for past precedents and relevant laws and regulations, identifying similar cases. During this process, it evaluates the scope and importance of the applicable laws and regulations.

[0047] Step 5:

[0048] Based on the search results, the server generates legal judgments and recommended rulings relevant to the case. The recommended rulings prioritize reasonableness and may offer interpretations from multiple perspectives.

[0049] Step 6:

[0050] The server sends the generated draft judgment to the terminal and presents it to the user. The draft judgment is logically structured and presents a concrete solution.

[0051] Step 7:

[0052] Users review the proposed judgments and provide feedback as needed. This feedback includes opinions on the validity and potential improvements of the proposed judgments.

[0053] Step 8:

[0054] The terminal sends user feedback to the server. The server stores the received feedback and uses it to refine the machine learning model, thereby improving the overall accuracy of the system.

[0055] (Example 1)

[0056] 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."

[0057] The current process of determining legal judgments presents challenges in making fair and efficient decisions, not only because it requires considerable time and effort to collect and analyze information, search for appropriate laws and precedents, and present legal judgments, but also because human subjectivity can interfere. This invention aims to provide a system that efficiently manages and analyzes legal information and supports swift and fair legal judgments.

[0058] 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.

[0059] In this invention, the server includes means for managing and making legal information accessible, means for processing input case content and performing natural language analysis, and means for searching for relevant rules and past cases based on the analysis results. This enables efficient management, analysis, and retrieval of legal information, supporting swift and fair legal decisions.

[0060] "Legal information" is a general term for information including laws, regulations, and related past precedents and cases.

[0061] "Means of making access possible" refers to methods that enable users and systems to efficiently access the information they need from a specific database or information source.

[0062] "Case details" refer to information about the specific problem or situation that the user is seeking advice on, and serve as basic data for making legal judgments.

[0063] "Natural language processing" is a technology that converts human language into a format that computers can easily understand and analyzes its meaning and characteristics.

[0064] A "generative AI model" is a type of artificial intelligence model that has the ability to generate new text and information based on input data.

[0065] A "draft legal judgment" refers to a legal opinion or proposal derived from a specific case, and may include specific guidelines for action.

[0066] "Evaluation information" refers to the opinions and feedback users give regarding the information and results provided by the system, and is used to improve the system.

[0067] A "learning algorithm" refers to a computational method used by computers to acquire new knowledge and skills from data, and is used to improve the accuracy and performance of a system.

[0068] This legal judgment support system functions through the collaboration of a server, terminals, and users. The server uses a powerful database management system (e.g., MySQL®, PostgreSQL, etc.) to manage and maintain access to legal information. This enables efficient searching of large amounts of data on laws and precedents. The server uses natural language processing libraries (e.g., Python's NLTK or SpaCy, etc.) to analyze the case content entered by the user and systematically understand its meaning.

[0069] The user inputs specific case information into the terminal, seeking legal judgment. The terminal provides an intuitive interface for user interaction. The input information is transmitted to the server via the terminal. For example, if a user is inquiring about legal matters related to a traffic accident, they would describe the specific situation and their questions in detail. Examples of prompts might include, "I want to know about compensation for damages in a traffic accident," or "I want to know about the laws regarding termination of employment contracts."

[0070] The server utilizes a generative AI model (such as a Transformer model) to generate draft legal judgments based on the analyzed information. This model possesses advanced reasoning capabilities, comprehensively evaluating relevant laws and precedents to derive the optimal legal judgment. The resulting draft legal judgment is then provided to the user via the terminal.

[0071] Users can consider practical actions based on the provided legal judgments. Furthermore, user feedback is sent to the server, and the system's accuracy is continuously improved through a learning algorithm. This process ensures that legal judgments become more objective and fair, providing users with practical information.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The user enters information about the case they wish to consult about into the system via their terminal. Specifically, they describe the background and related information of the case in text format in an input form. The input data is recorded on the terminal in an easy-to-understand format, such as "Consultation regarding compensation for damages in a traffic accident." The terminal then sends this information to the server.

[0075] Step 2:

[0076] The server passes the data received from the terminal to a natural language processing engine for text analysis. This analysis uses NLTK or SpaCy to extract keywords and important phrases from the input text and create a data structure. The extracted keywords (for example, "traffic accident" and "compensation") are used to query the legal database.

[0077] Step 3:

[0078] The server searches the legal database using keywords obtained from the analysis engine. It quickly identifies relevant laws and past precedents using SQL queries and retrieves them in an organized format. At this time, the server executes a search algorithm that utilizes indexes for efficiency.

[0079] Step 4:

[0080] The server inputs the searched laws and precedents into a generating AI model to create a legal judgment suitable for the case. This process utilizes Transformer models and other tools to perform reasoning based on legal information. The generated judgment is output as text, including specific legal measures and proposals.

[0081] Step 5:

[0082] The server sends the generated draft legal judgment to the terminal. The terminal displays this information in a visually easy-to-understand format to encourage user consideration. The display method can be customized according to the user's preference, such as a list format or step-by-step instructions.

[0083] Step 6:

[0084] Users provide feedback on the proposed judgment via their devices. Specifically, they input their opinions on the validity of the proposed judgment, requests for further information, etc., in text format and send them to the server.

[0085] Step 7:

[0086] The server passes user feedback to a machine learning algorithm to help improve the system. In this process, the received feedback is used as new training data to improve the accuracy of the generated AI model, thereby enhancing the quality of future legal decisions.

[0087] (Application Example 1)

[0088] 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."

[0089] There is a need to quickly and appropriately derive information protection measures based on security-related laws and case studies, particularly in the decision-making processes of companies and organizations. However, the sheer volume and complexity of information presents a challenge in making accurate judgments.

[0090] 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.

[0091] In this invention, the server includes means for making a legal information aggregation device accessible, means for analyzing input case information and performing language processing, means for searching for relevant laws and cases based on the analyzed information, and means for generating proposed protection measures based on information protection-related laws and cases. This makes it possible to quickly and accurately propose information protection measures to companies and organizations.

[0092] A "legal information aggregation device" is a mechanism for systematically collecting and managing information on various laws and precedents.

[0093] "Natural language processing" refers to technical methods for analyzing input text data and understanding its meaning and intent.

[0094] A "self-learning model" is an algorithm or system equipped with a learning function that uses user feedback to make more accurate judgments and suggestions.

[0095] A "proposal for information protection measures" is a proposal outlining specific legal and technically recommended policies and measures to ensure the security of information.

[0096] To realize this invention, the system operates by coordinating multiple components. The server plays a central role in performing the main processing. The server accesses the legal information aggregation device and analyzes the text sent by the user using language processing technology. Specific processing can be performed using the Python language or natural language processing libraries (e.g., NLTK or spaCy). The analyzed information becomes important data for querying relevant laws and cases.

[0097] The server then generates proposed protection measures based on information protection laws and case studies. This involves utilizing a self-learning model to improve the accuracy of the proposals by considering feedback from past users. This process could potentially utilize machine learning frameworks such as TENSORFLOW® or PyTorch.

[0098] Users can access the server via smartphones or computer terminals, input information, and receive generated protection proposals. User feedback is also used in the system's learning algorithms, contributing to improving the quality of the proposals.

[0099] As a concrete example, when a company reviews its policies to strengthen information security for employees working remotely, it provides recommendations for ensuring server security based on relevant laws and precedents. This allows companies to implement remote work with greater confidence. Another example of a prompt message would be, "What security policies should be adopted to strengthen employee data protection during remote work?"

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] Users use their devices to input information and questions related to remote work security. The input data is in natural language format and is sent from the device to the server.

[0103] Step 2:

[0104] The server analyzes the received input data using natural language processing techniques. Specifically, it uses Python and a natural language processing library (e.g., spaCy) to extract important keywords and context from the input data. This allows the server to prepare the information necessary for the next search phase.

[0105] Step 3:

[0106] Based on the analysis results, the server accesses the legal information aggregation device to search for relevant laws and past cases. The server uses the extracted keywords as queries to efficiently retrieve the corresponding laws and precedents from the legal database.

[0107] Step 4:

[0108] The server generates proposed protection measures based on search results, taking into account relevant laws and case studies related to information protection. Here, a self-learning model is utilized to create highly accurate suggestions that reflect past user feedback. TensorFlow is used to execute the generated AI model and construct appropriate protection measures.

[0109] Step 5:

[0110] The generated protection plan is sent from the server to the user's terminal, where the user receives it. The user can review the proposed plan and use it to further develop their security policy.

[0111] Step 6:

[0112] Users input feedback on the suggestions from their devices and send it to the server. This feedback data is used to update the self-learning model, contributing to improved accuracy of future suggestions.

[0113] 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.

[0114] This invention demonstrates a legal judgment support system incorporating an emotion engine. The server accesses a legal database and manages it to enable rapid retrieval of past precedents and laws. Users can input case information related to legal troubles using a terminal. The input information is first sent to the server and processed using natural language processing technology.

[0115] Furthermore, the newly integrated emotion engine analyzes the user's emotions from their input information. This emotion data is designed to be reflected in the server's process of generating legal judgments and draft rulings. In this process, the emotion data is used, for example, to adjust the tone and approach of the solution.

[0116] After the draft judgment is generated, the server sends it to the terminal and displays it to the user. At this point, the user interface is adjusted according to the emotional state recognized by the emotion engine. For example, if the server determines that the user is stressed, the displayed message can be made more friendly, or supportive information can be provided. The user can then use the generated draft judgment as a guideline for deciding on further actions.

[0117] As a concrete example, consider a scenario where a user consults the system about an issue related to their employment contract. The user inputs the case and related evidence into a terminal and sends it to the system. The server analyzes the case and searches for relevant laws and precedents. Furthermore, an emotion engine detects feelings of stress and anxiety from the user's description and adjusts the tone of the proposed judgment. Finally, the user is presented with a legal opinion and specific action plans regarding their consultation.

[0118] This system not only efficiently assists in legal judgments but also provides more comprehensive support by offering support that takes into account the user's feelings.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] Users input case information related to legal consultations or disputes into their devices. This may include a summary of the case, relevant evidence, and personal comments.

[0122] Step 2:

[0123] The terminal formats the data before sending the input information to the server. It also verifies that the information has been transferred correctly and completely.

[0124] Step 3:

[0125] The server analyzes the received case information using a natural language processing engine. This process involves extracting legal concepts and keywords from the text.

[0126] Step 4:

[0127] The server searches the legal database based on the extracted keywords and extracts relevant laws and precedents. This data is used to derive judgments and applicable laws for similar cases.

[0128] Step 5:

[0129] The server uses an emotion engine to analyze user input to determine emotions. It evaluates the type and intensity of emotions and determines how they might influence the verdict.

[0130] Step 6:

[0131] The server combines analyzed legal information and sentiment data to generate a draft judgment. This draft judgment is not only legally meaningful but also takes into account the user's emotional state.

[0132] Step 7:

[0133] The server sends the generated draft judgment to the terminal and displays it to the user. The display is customized according to the user's emotional state and includes supplementary explanations and support links as needed.

[0134] Step 8:

[0135] Users can review the proposed judgment and input feedback and necessary actions via their device. This feedback will be valuable data for future improvements.

[0136] Step 9:

[0137] The terminal sends user feedback information to the server, which uses this to refine the machine learning model. This allows for continuous improvement of the system's accuracy and the quality of user support.

[0138] (Example 2)

[0139] 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".

[0140] Conventional legal judgment support systems lack consideration for the user, providing uniform legal searches and draft judgments without regard for the user's emotions. Furthermore, the user interface and the tone of the draft judgments are not appropriately adjusted based on the user's emotions, potentially amplifying user anxiety. This results in a lack of comprehensive support for users, particularly in situations where emotions play a significant role in legal decisions.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes means for making a collection of legal information accessible, means for processing case data entered by the user and performing natural language analysis, means for searching for relevant laws and judgment cases based on the analyzed information, means for transmitting the generated draft decision to a terminal and displaying it to the user, and means for analyzing emotions and adjusting the draft decision to reflect the emotion data. This makes it possible to provide comprehensive legal judgment support while reflecting the user's emotions and providing a sense of security.

[0143] A "legal information collection" refers to a database that systematically organizes and aggregates data related to laws and regulations in a searchable format.

[0144] "Case data" refers to information about specific legal troubles entered by users, including related background and evidence.

[0145] "Natural language processing" is a technology that converts input text data into a form that is easy for machines to understand, and mainly refers to the process of syntactic analysis and keyword extraction of language.

[0146] "Case precedents" refer to information compiled from past court decisions, and are used as reference information regarding specific legal interpretations and judgments.

[0147] A "decision proposal" refers to a proposal that specifically suggests judgments and recommended actions regarding laws and regulations, based on the input data and analysis results.

[0148] "Emotional data" refers to information that represents the user's emotional state, extracted from user input and interactions.

[0149] "User interface" refers to the entirety of the screens, input forms, and display methods that users use when operating a system, and is a crucial element that influences the user experience.

[0150] The core of this legal judgment support system is the interaction of information between the server, the terminal, and the user. The following is a specific implementation.

[0151] First, users can use the terminal to input specific "case data" related to legal troubles. The terminal is equipped with an input support interface to help users enter the necessary information without hesitation. For example, if a user wants to consult about a dispute regarding an employment contract, they can input the details of the case and supporting documents.

[0152] Next, this input data is quickly sent to the server. The server performs "natural language analysis" on the received data. This analysis uses natural language processing libraries such as spaCy or NLTK to perform data tokenization and syntactic analysis.

[0153] After analysis by the server, access is made to a "legal information collection" containing information on laws and regulations. This database includes laws and past "judgment cases," and the server searches for appropriate laws and judgment cases based on the results of natural language analysis. SQL queries and other tools are used in this process.

[0154] Furthermore, the server activates an emotion engine and extracts "emotional data" based on user input. The engine utilizes emotion recognition technology, such as empathy or general emotion recognition software, to evaluate the user's emotional state and generate a "decision proposal" that considers emotional support as well as legal judgment.

[0155] The generated decision is sent back to the device. When displayed, the device's "user interface" is adjusted based on emotional data to provide appropriate legal advice while reducing the user's anxiety with a friendly tone. For example, if the user is feeling stressed, the displayed message will be adjusted to be more comforting.

[0156] An example of a prompt message would be, "Consider the user's emotional state regarding an issue related to employment contracts, and generate appropriate legal judgments and recommended solutions." Based on this information, the generating AI model would then provide an appropriate draft judgment.

[0157] In this way, the system provides comprehensive support that takes into account not only legal judgments but also the feelings of the users.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The user uses the terminal to input specific case data related to legal troubles. This input includes details of the background of the problem and relevant evidence. After input, the terminal formats this data and prepares it for transmission to the server.

[0161] Step 2:

[0162] Case data sent from the terminal is received by the server. The server first verifies the integrity of the input data, and then performs natural language processing. Specifically, it uses natural language processing libraries such as spaCy and NLTK to tokenize the text and perform semantic analysis. Through this analysis, keywords and related topics are extracted from the case data.

[0163] Step 3:

[0164] Based on the analyzed information, the server accesses a collection of legal information. Here, it uses SQL queries to search for relevant laws and court rulings. The server matches the case data with the extracted keywords to retrieve the most relevant legal information.

[0165] Step 4:

[0166] The server activates the emotion engine and performs emotion analysis based on the user's input data. This process utilizes emotion recognition software to analyze emotional vocabulary and expressions in the input text. As a result, data indicating the user's emotional state is generated.

[0167] Step 5:

[0168] Using emotional data and legal information, the server generates a decision proposal using a generative AI model. This process is guided by the prompt "Consider the user's emotional state regarding the issue of the employment contract and generate an appropriate legal judgment and recommended solution." The output is a legal judgment and solution that takes the user's emotions into consideration.

[0169] Step 6:

[0170] The generated decision proposal is sent from the server to the terminal. When the terminal displays the received decision proposal to the user, it adjusts the user interface based on emotional data. Specifically, if the user is stressed, the message displayed on the screen is set to a comforting tone.

[0171] Step 7:

[0172] The user reviews the proposed decision displayed on the terminal and decides what action to take next. At this stage, the user uses the information obtained from the system to decide, for example, whether to take legal action. If necessary, they can enter additional information and repeat the process.

[0173] (Application Example 2)

[0174] 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 device 14 will be referred to as the "terminal."

[0175] Legal disputes arising in electronic transactions are complex and stressful issues for users. In such situations, conventional legal judgment support systems often only offer abstract legal opinions without considering the user's feelings. Therefore, there has been a need for a system that reduces the emotional burden on users and provides substantive legal advice in a more user-friendly way.

[0176] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0177] In this invention, the server includes means for making a legal database accessible, means for processing input case information and performing natural language analysis, means for searching for relevant laws and precedents based on the analyzed information, means for analyzing and evaluating sentiment data, means for adjusting the draft judgment based on the user's emotional state, and means for outputting the adjusted draft judgment. This makes it possible to provide more user-friendly and accurate legal decision support that takes the user's emotions into consideration.

[0178] A "legal database" is a digital information repository that aggregates legal information such as laws, ordinances, and precedents, making it searchable and accessible.

[0179] "Case information" refers to information about specific cases or issues that users provide when seeking legal assistance.

[0180] "Natural language processing" is a technology that converts natural language, which humans use in everyday life, into a format that computers can understand and analyze.

[0181] "Case law" refers to a record of past judicial decisions and serves as a standard of information that is referenced in similar cases.

[0182] "Emotional data" refers to information that quantifies or categorizes emotional states extracted from user input.

[0183] A "draft judgment" is an initial solution or opinion on a legal issue, generated based on analyzed legal and sentiment data.

[0184] "Evaluation" is the act of judging the situation and value of things based on data and information, and analyzing them quantitatively or qualitatively.

[0185] "Output" refers to the process of displaying information or results processed by the system to the user.

[0186] The system for realizing this invention mainly consists of a server and a user terminal. The server maintains a legal database and processes case information entered from the user terminal using natural language processing technology.

[0187] First, the user enters case information about their legal trouble or problem into the terminal. This information is sent to the server, which analyzes the input information using a natural language processing library (e.g., SpaCy). The analyzed data is then cross-referenced with relevant laws and precedents in the legal database.

[0188] In parallel, the server uses a sentiment analysis engine (e.g., IBM Watson® Tone Analyzer) to extract sentiment data from user input. This sentiment data is integrated with information obtained from a legal database and used to generate draft judgments.

[0189] The generated draft judgment is adjusted to take the user's emotional state into consideration. For example, users who are detected as stressed will be presented with legal advice in a more approachable and comforting tone. In this way, the final draft judgment is output to the user's device.

[0190] As a concrete example, a user facing a problem with an unfair claim might enter the prompt, "Is this claim legitimate? Please tell me how to resolve this." The server then analyzes the input and presents emotionally appropriate solutions along with relevant case law. This process ensures that the user receives support both emotionally and legally.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The user's device collects data through an interface that inputs case information related to legal troubles. The input data includes text describing the user's specific problem or situation. This data is then sent to the server.

[0194] Step 2:

[0195] The server processes the received input data using natural language processing (NLP) techniques. This process utilizes a natural language processing library such as SpaCy to structure the input data (tokenization, part-of-speech tagging, etc.) and understand its content. As a result, the analyzed semantic content is obtained.

[0196] Step 3:

[0197] Based on the analyzed data, the server searches for relevant laws and precedents in the legal database. The search uses keywords and phrases contained in the input data to perform matching and obtain relevant legal information.

[0198] Step 4:

[0199] Simultaneously, the server begins sentiment analysis. Using tools like IBM Watson Tone Analyzer, it extracts sentiment data from the user's input. From this sentiment data, it determines the user's emotional state, such as stress levels and feelings of well-being.

[0200] Step 5:

[0201] The server integrates legal search results and sentiment data to generate draft judgments. This process uses a generative AI model to generate specific solutions and advice. The generated draft judgments include recommended actions based on the law.

[0202] Step 6:

[0203] The server considers the user's emotional state and adjusts the tone of the draft judgment. Based on emotional data, it generates messages in a friendly tone and gentle phrasing that are particularly appropriate for emotional states requiring special consideration (e.g., high stress levels).

[0204] Step 7:

[0205] Finally, the server sends the adjusted draft judgment to the user's device. The user can receive legal advice in a clear and user-friendly format on their device. This advice serves as specific guidance to directly address the issues the user is facing.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] This invention presents an embodiment of a legal judgment support system in which a server, terminal, and user work in cooperation. The server efficiently manages laws and past precedents by accessing a legal database and can quickly and accurately search this information. Users can input specific case information using a terminal, and this information is transferred to the server and processed using natural language processing technology. Based on the analyzed information, the server searches for relevant laws and precedents and generates a draft judgment to derive the optimal legal decision.

[0223] In this system, user feedback is extremely important. By sending users' opinions and requests regarding draft judgments from their terminals to the server, the server can update its machine learning model and continuously improve the overall accuracy of the system. This will lead to more objective and fair interpretation of laws and regulations.

[0224] As a concrete example, consider a case where a user consults the system about a dispute related to their employment contract. The user inputs the relevant facts and contract details into the terminal. The server analyzes this information and extracts relevant labor laws and precedents. The server summarizes the legal opinion on the case in question and generates a draft judgment that would be beneficial to the user. This draft judgment can show the user specific steps they should take to resolve the problem.

[0225] In this way, this system supports legal judgments in courts, public institutions, corporate legal departments, etc., and provides a fair and impartial judgment process by eliminating human subjectivity.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The user enters specific case information regarding legal troubles from their device. This includes details such as relevant facts, contracts, and evidence.

[0229] Step 2:

[0230] The terminal structures the input information, converts it into a data format, and sends it to the server. During this process, it performs basic checks to ensure there are no missing or inconsistent pieces of information.

[0231] Step 3:

[0232] The server processes the received case information using a natural language processing tool to extract keywords and legal concepts. Based on these analysis results, it searches the relevant legal database.

[0233] Step 4:

[0234] The server uses the extracted keywords to search the database for past precedents and relevant laws and regulations, identifying similar cases. During this process, it evaluates the scope and importance of the applicable laws and regulations.

[0235] Step 5:

[0236] Based on the search results, the server generates legal judgments and recommended rulings relevant to the case. The recommended rulings prioritize reasonableness and may offer interpretations from multiple perspectives.

[0237] Step 6:

[0238] The server sends the generated draft judgment to the terminal and presents it to the user. The draft judgment is logically structured and presents a concrete solution.

[0239] Step 7:

[0240] Users review the proposed judgments and provide feedback as needed. This feedback includes opinions on the validity and potential improvements of the proposed judgments.

[0241] Step 8:

[0242] The terminal sends user feedback to the server. The server stores the received feedback and uses it to refine the machine learning model, thereby improving the overall accuracy of the system.

[0243] (Example 1)

[0244] 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."

[0245] The current process of determining legal judgments presents challenges in making fair and efficient decisions, not only because it requires considerable time and effort to collect and analyze information, search for appropriate laws and precedents, and present legal judgments, but also because human subjectivity can interfere. This invention aims to provide a system that efficiently manages and analyzes legal information and supports swift and fair legal judgments.

[0246] 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.

[0247] In this invention, the server includes means for managing and making legal information accessible, means for processing input case content and performing natural language analysis, and means for searching for relevant rules and past cases based on the analysis results. This enables efficient management, analysis, and retrieval of legal information, supporting swift and fair legal decisions.

[0248] "Legal information" is a general term for information including laws, regulations, and related past precedents and cases.

[0249] "Means of making access possible" refers to methods that enable users and systems to efficiently access the information they need from a specific database or information source.

[0250] "Case details" refer to information about the specific problem or situation that the user is seeking advice on, and serve as basic data for making legal judgments.

[0251] "Natural language processing" is a technology that converts human language into a format that computers can easily understand and analyzes its meaning and characteristics.

[0252] A "generative AI model" is a type of artificial intelligence model that has the ability to generate new text and information based on input data.

[0253] A "draft legal judgment" refers to a legal opinion or proposal derived from a specific case, and may include specific guidelines for action.

[0254] "Evaluation information" refers to the opinions and feedback users give regarding the information and results provided by the system, and is used to improve the system.

[0255] A "learning algorithm" refers to a computational method used by computers to acquire new knowledge and skills from data, and is used to improve the accuracy and performance of a system.

[0256] This legal judgment support system functions through the collaboration of a server, terminals, and users. The server uses a powerful database management system (e.g., MySQL, PostgreSQL, etc.) to manage and maintain access to legal information. This enables efficient searching of large amounts of data on laws and precedents. The server uses natural language processing libraries (e.g., Python's NLTK or SpaCy, etc.) to analyze the case content entered by the user and systematically understand its meaning.

[0257] The user inputs specific case information into the terminal, seeking legal judgment. The terminal provides an intuitive interface for user interaction. The input information is transmitted to the server via the terminal. For example, if a user is inquiring about legal matters related to a traffic accident, they would describe the specific situation and their questions in detail. Examples of prompts might include, "I want to know about compensation for damages in a traffic accident," or "I want to know about the laws regarding termination of employment contracts."

[0258] The server utilizes a generative AI model (such as a Transformer model) to generate draft legal judgments based on the analyzed information. This model possesses advanced reasoning capabilities, comprehensively evaluating relevant laws and precedents to derive the optimal legal judgment. The resulting draft legal judgment is then provided to the user via the terminal.

[0259] Users can consider practical actions based on the provided legal judgments. Furthermore, user feedback is sent to the server, and the system's accuracy is continuously improved through a learning algorithm. This process ensures that legal judgments become more objective and fair, providing users with practical information.

[0260] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0261] Step 1:

[0262] The user enters information about the case they wish to consult about into the system via their terminal. Specifically, they describe the background and related information of the case in text format in an input form. The input data is recorded on the terminal in an easy-to-understand format, such as "Consultation regarding compensation for damages in a traffic accident." The terminal then sends this information to the server.

[0263] Step 2:

[0264] The server passes the data received from the terminal to a natural language processing engine for text analysis. This analysis uses NLTK or SpaCy to extract keywords and important phrases from the input text and create a data structure. The extracted keywords (for example, "traffic accident" and "compensation") are used to query the legal database.

[0265] Step 3:

[0266] The server searches the legal database using keywords obtained from the analysis engine. It quickly identifies relevant laws and past precedents using SQL queries and retrieves them in an organized format. At this time, the server executes a search algorithm that utilizes indexes for efficiency.

[0267] Step 4:

[0268] The server inputs the searched laws and precedents into a generating AI model to create a legal judgment suitable for the case. This process utilizes Transformer models and other tools to perform reasoning based on legal information. The generated judgment is output as text, including specific legal measures and proposals.

[0269] Step 5:

[0270] The server sends the generated draft legal judgment to the terminal. The terminal displays this information in a visually easy-to-understand format to encourage user consideration. The display method can be customized according to the user's preference, such as a list format or step-by-step instructions.

[0271] Step 6:

[0272] Users provide feedback on the proposed judgment via their devices. Specifically, they input their opinions on the validity of the proposed judgment, requests for further information, etc., in text format and send them to the server.

[0273] Step 7:

[0274] The server passes user feedback to a machine learning algorithm to help improve the system. In this process, the received feedback is used as new training data to improve the accuracy of the generated AI model, thereby enhancing the quality of future legal decisions.

[0275] (Application Example 1)

[0276] 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."

[0277] There is a need to quickly and appropriately derive information protection measures based on security-related laws and case studies, particularly in the decision-making processes of companies and organizations. However, the sheer volume and complexity of information presents a challenge in making accurate judgments.

[0278] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0279] In this invention, the server includes means for making the legal information integration apparatus accessible, means for analyzing the input case information and performing language processing, means for searching for relevant laws and cases based on the analyzed information, and means for generating a protection plan based on the information protection-related laws and cases. Thereby, it becomes possible to quickly and accurately propose an information protection policy for enterprises and organizations.

[0280] The "legal information integration apparatus" is an organization for systematically collecting and managing information on various laws and cases.

[0281] "Language processing" is a technical method for analyzing the input text data and understanding its meaning and intention.

[0282] The "self-learning model" is an algorithm or system equipped with a learning function for making more accurate judgments and proposals based on feedback from users.

[0283] The "information protection plan" is a proposal indicating specific policies and means recommended legally and technically to ensure the security of information.

[0284] To implement this invention, the system operates by coordinating a plurality of components. The server plays a central role in performing the main processing. The server accesses the legal information integration apparatus and analyzes the text transmitted from the user using language processing technology. For specific processing, the Python language and natural language processing libraries (for example, NLTK and spaCy) can be used. The analyzed information becomes important data for querying relevant laws and cases.

[0285] The server then generates protection plans based on information protection-related laws and regulations and cases. In this process, a self-learning model is utilized to consider feedback from past users and make proposals with improved accuracy. It is conceivable to use TensorFlow or PyTorch as the machine learning framework in this process.

[0286] Users can access the server through smartphones or computer terminals, input information, and receive the generated protection plans. User feedback is also utilized in the system's learning algorithm, which is a factor that enhances the quality of the proposals.

[0287] As a specific example, when a company reviews policies to strengthen information security during employees' remote work, the server shows recommended measures to ensure security based on relevant laws and precedents. Receiving this, the company can introduce remote work with greater confidence. Also, examples of prompt sentences include "What security policies should be adopted to strengthen the data protection of employees in remote work?"

[0288] The flow of a specific process in Application Example 1 will be described using FIG. 12.

[0289] Step 1:

[0290] The user uses the terminal to input information and questions regarding the security of remote work. The input data is in natural language form and is sent from the terminal to the server.

[0291] Step 2:

[0292] The server analyzes the received input data using language processing technology. Specifically, Python and a natural language processing library (e.g., spaCy) are used to extract important keywords and context from the input data. This enables the server to prepare the information necessary for the next search phase.

[0293] Step 3:

[0294] Based on the analysis results, the server accesses the legal information aggregation device to search for relevant laws and past cases. The server uses the extracted keywords as queries to efficiently retrieve the corresponding laws and precedents from the legal database.

[0295] Step 4:

[0296] The server generates proposed protection measures based on search results, taking into account relevant laws and case studies related to information protection. Here, a self-learning model is utilized to create highly accurate suggestions that reflect past user feedback. TensorFlow is used to execute the generated AI model and construct appropriate protection measures.

[0297] Step 5:

[0298] The generated protection plan is sent from the server to the user's terminal, where the user receives it. The user can review the proposed plan and use it to further develop their security policy.

[0299] Step 6:

[0300] Users input feedback on the suggestions from their devices and send it to the server. This feedback data is used to update the self-learning model, contributing to improved accuracy of future suggestions.

[0301] 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.

[0302] This invention shows a form in which an emotion engine is incorporated into a legal judgment support system. The server accesses a legal database and manages it so that past cases and laws can be quickly retrieved. The user can input case information related to legal troubles using a terminal. The input information is first sent to the server and processed using natural language analysis technology.

[0303] Furthermore, the newly incorporated emotion engine analyzes the emotion from the user's input information. This emotion data is designed to be reflected in the process of legal judgment and the generation of judgment proposals by the server. In this process, the emotion data is used as an element to adjust, for example, the tone or approach of the solution.

[0304] After the judgment proposal is generated, the server sends it to the terminal and displays it to the user. At this time, the user interface is adjusted according to the emotional state recognized by the emotion engine. For example, if the user is judged to be feeling stressed, it is possible to make the display message more friendly or provide support information. The user can use it as a guideline when deciding further actions based on the generated judgment proposal.

[0305] As a specific example, consider a scenario where a user consults the system about a problem related to an employment contract. The user inputs evidence related to the case into the terminal and sends it to the system. The server analyzes the case and searches for relevant laws and cases. Furthermore, the emotion engine detects emotions of stress and anxiety from the user's description and adjusts the tone of the judgment proposal. Finally, the user is presented with a legal opinion and a specific action plan for the consultation content.

[0306] This system not only efficiently supports legal judgment but also provides more comprehensive support by considering the user's emotions.

[0307] The following describes the processing flow.

[0308] Step 1:

[0309] Users input case information related to legal consultations or disputes into their devices. This may include a summary of the case, relevant evidence, and personal comments.

[0310] Step 2:

[0311] The terminal formats the data before sending the input information to the server. It also verifies that the information has been transferred correctly and completely.

[0312] Step 3:

[0313] The server analyzes the received case information using a natural language processing engine. This process involves extracting legal concepts and keywords from the text.

[0314] Step 4:

[0315] The server searches the legal database based on the extracted keywords and extracts relevant laws and precedents. This data is used to derive judgments and applicable laws for similar cases.

[0316] Step 5:

[0317] The server uses an emotion engine to analyze user input to determine emotions. It evaluates the type and intensity of emotions and determines how they might influence the verdict.

[0318] Step 6:

[0319] The server combines analyzed legal information and sentiment data to generate a draft judgment. This draft judgment is not only legally meaningful but also takes into account the user's emotional state.

[0320] Step 7:

[0321] The server sends the generated draft judgment to the terminal and displays it to the user. The display is customized according to the user's emotional state and includes supplementary explanations and support links as needed.

[0322] Step 8:

[0323] Users can review the proposed judgment and input feedback and necessary actions via their device. This feedback will be valuable data for future improvements.

[0324] Step 9:

[0325] The terminal sends user feedback information to the server, which uses this to refine the machine learning model. This allows for continuous improvement of the system's accuracy and the quality of user support.

[0326] (Example 2)

[0327] 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".

[0328] Conventional legal judgment support systems lack consideration for the user, providing uniform legal searches and draft judgments without regard for the user's emotions. Furthermore, the user interface and the tone of the draft judgments are not appropriately adjusted based on the user's emotions, potentially amplifying user anxiety. This results in a lack of comprehensive support for users, particularly in situations where emotions play a significant role in legal decisions.

[0329] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0330] In this invention, the server includes means for making a collection of legal information accessible, means for processing case data entered by the user and performing natural language analysis, means for searching for relevant laws and judgment cases based on the analyzed information, means for transmitting the generated draft decision to a terminal and displaying it to the user, and means for analyzing emotions and adjusting the draft decision to reflect the emotion data. This makes it possible to provide comprehensive legal judgment support while reflecting the user's emotions and providing a sense of security.

[0331] A "legal information collection" refers to a database that systematically organizes and aggregates data related to laws and regulations in a searchable format.

[0332] "Case data" refers to information about specific legal troubles entered by users, including related background and evidence.

[0333] "Natural language processing" is a technology that converts input text data into a form that is easy for machines to understand, and mainly refers to the process of syntactic analysis and keyword extraction of language.

[0334] "Case precedents" refer to information compiled from past court decisions, and are used as reference information regarding specific legal interpretations and judgments.

[0335] A "decision proposal" refers to a proposal that specifically suggests judgments and recommended actions regarding laws and regulations, based on the input data and analysis results.

[0336] "Emotional data" refers to information that represents the user's emotional state, extracted from user input and interactions.

[0337] "User interface" refers to the entirety of the screens, input forms, and display methods that users use when operating a system, and is a crucial element that influences the user experience.

[0338] The core of this legal judgment support system is the interaction of information between the server, the terminal, and the user. The following is a specific implementation.

[0339] First, users can use the terminal to input specific "case data" related to legal troubles. The terminal is equipped with an input support interface to help users enter the necessary information without hesitation. For example, if a user wants to consult about a dispute regarding an employment contract, they can input the details of the case and supporting documents.

[0340] Next, this input data is quickly sent to the server. The server performs "natural language analysis" on the received data. This analysis uses natural language processing libraries such as spaCy or NLTK to perform data tokenization and syntactic analysis.

[0341] After analysis by the server, access is made to a "legal information collection" containing information on laws and regulations. This database includes laws and past "judgment cases," and the server searches for appropriate laws and judgment cases based on the results of natural language analysis. SQL queries and other tools are used in this process.

[0342] Furthermore, the server activates an emotion engine and extracts "emotional data" based on user input. The engine utilizes emotion recognition technology, such as empathy or general emotion recognition software, to evaluate the user's emotional state and generate a "decision proposal" that considers emotional support as well as legal judgment.

[0343] The generated decision is sent back to the device. When displayed, the device's "user interface" is adjusted based on emotional data to provide appropriate legal advice while reducing the user's anxiety with a friendly tone. For example, if the user is feeling stressed, the displayed message will be adjusted to be more comforting.

[0344] An example of a prompt message would be, "Consider the user's emotional state regarding an issue related to employment contracts, and generate appropriate legal judgments and recommended solutions." Based on this information, the generating AI model would then provide an appropriate draft judgment.

[0345] In this way, the system provides comprehensive support that takes into account not only legal judgments but also the feelings of the users.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] The user uses the terminal to input specific case data related to legal troubles. This input includes details of the background of the problem and relevant evidence. After input, the terminal formats this data and prepares it for transmission to the server.

[0349] Step 2:

[0350] Case data sent from the terminal is received by the server. The server first verifies the integrity of the input data, and then performs natural language processing. Specifically, it uses natural language processing libraries such as spaCy and NLTK to tokenize the text and perform semantic analysis. Through this analysis, keywords and related topics are extracted from the case data.

[0351] Step 3:

[0352] Based on the analyzed information, the server accesses a collection of legal information. Here, it uses SQL queries to search for relevant laws and court rulings. The server matches the case data with the extracted keywords to retrieve the most relevant legal information.

[0353] Step 4:

[0354] The server activates the emotion engine and performs emotion analysis based on the user's input data. This process utilizes emotion recognition software to analyze emotional vocabulary and expressions in the input text. As a result, data indicating the user's emotional state is generated.

[0355] Step 5:

[0356] Using emotional data and legal information, the server generates a decision proposal using a generative AI model. This process is guided by the prompt "Consider the user's emotional state regarding the issue of the employment contract and generate an appropriate legal judgment and recommended solution." The output is a legal judgment and solution that takes the user's emotions into consideration.

[0357] Step 6:

[0358] The generated decision proposal is sent from the server to the terminal. When the terminal displays the received decision proposal to the user, it adjusts the user interface based on emotional data. Specifically, if the user is stressed, the message displayed on the screen is set to a comforting tone.

[0359] Step 7:

[0360] The user reviews the proposed decision displayed on the terminal and decides what action to take next. At this stage, the user uses the information obtained from the system to decide, for example, whether to take legal action. If necessary, they can enter additional information and repeat the process.

[0361] (Application Example 2)

[0362] 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."

[0363] Legal disputes arising in electronic transactions are complex and stressful issues for users. In such situations, conventional legal judgment support systems often only offer abstract legal opinions without considering the user's feelings. Therefore, there has been a need for a system that reduces the emotional burden on users and provides substantive legal advice in a more user-friendly way.

[0364] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0365] In this invention, the server includes means for making a legal database accessible, means for processing input case information and performing natural language analysis, means for searching for relevant laws and precedents based on the analyzed information, means for analyzing and evaluating sentiment data, means for adjusting the draft judgment based on the user's emotional state, and means for outputting the adjusted draft judgment. This makes it possible to provide more user-friendly and accurate legal decision support that takes the user's emotions into consideration.

[0366] A "legal database" is a digital information repository that aggregates legal information such as laws, ordinances, and precedents, making it searchable and accessible.

[0367] "Case information" refers to information about specific cases or issues that users provide when seeking legal assistance.

[0368] "Natural language processing" is a technology that converts natural language, which humans use in everyday life, into a format that computers can understand and analyze.

[0369] "Case law" refers to a record of past judicial decisions and serves as a standard of information that is referenced in similar cases.

[0370] "Emotional data" refers to information that quantifies or categorizes emotional states extracted from user input.

[0371] A "draft judgment" is an initial solution or opinion on a legal issue, generated based on analyzed legal and sentiment data.

[0372] "Evaluation" is the act of judging the situation and value of things based on data and information, and analyzing them quantitatively or qualitatively.

[0373] "Output" refers to the process of displaying information or results processed by the system to the user.

[0374] The system for realizing this invention mainly consists of a server and a user terminal. The server maintains a legal database and processes case information entered from the user terminal using natural language processing technology.

[0375] First, the user enters case information about their legal trouble or problem into the terminal. This information is sent to the server, which analyzes the input information using a natural language processing library (e.g., SpaCy). The analyzed data is then cross-referenced with relevant laws and precedents in the legal database.

[0376] In parallel, the server uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to extract sentiment data from user input. This sentiment data is integrated with information obtained from a legal database and used to generate draft judgments.

[0377] The generated draft judgment is adjusted to take the user's emotional state into consideration. For example, users who are detected as stressed will be presented with legal advice in a more approachable and comforting tone. In this way, the final draft judgment is output to the user's device.

[0378] As a concrete example, a user facing a problem with an unfair claim might enter the prompt, "Is this claim legitimate? Please tell me how to resolve this." The server then analyzes the input and presents emotionally appropriate solutions along with relevant case law. This process ensures that the user receives support both emotionally and legally.

[0379] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0380] Step 1:

[0381] The user's device collects data through an interface that inputs case information related to legal troubles. The input data includes text describing the user's specific problem or situation. This data is then sent to the server.

[0382] Step 2:

[0383] The server processes the received input data using natural language processing (NLP) techniques. This process utilizes a natural language processing library such as SpaCy to structure the input data (tokenization, part-of-speech tagging, etc.) and understand its content. As a result, the analyzed semantic content is obtained.

[0384] Step 3:

[0385] Based on the analyzed data, the server searches for relevant laws and precedents in the legal database. The search uses keywords and phrases contained in the input data to perform matching and obtain relevant legal information.

[0386] Step 4:

[0387] Simultaneously, the server begins sentiment analysis. Using tools like IBM Watson Tone Analyzer, it extracts sentiment data from the user's input. From this sentiment data, it determines the user's emotional state, such as stress levels and feelings of well-being.

[0388] Step 5:

[0389] The server integrates legal search results and sentiment data to generate draft judgments. This process uses a generative AI model to generate specific solutions and advice. The generated draft judgments include recommended actions based on the law.

[0390] Step 6:

[0391] The server considers the user's emotional state and adjusts the tone of the draft judgment. Based on emotional data, it generates messages in a friendly tone and gentle phrasing that are particularly appropriate for emotional states requiring special consideration (e.g., high stress levels).

[0392] Step 7:

[0393] Finally, the server sends the adjusted draft judgment to the user's device. The user can receive legal advice in a clear and user-friendly format on their device. This advice serves as specific guidance to directly address the issues the user is facing.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Third Embodiment]

[0398] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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".

[0410] This invention presents an embodiment of a legal judgment support system in which a server, terminal, and user work in cooperation. The server efficiently manages laws and past precedents by accessing a legal database and can quickly and accurately search this information. Users can input specific case information using a terminal, and this information is transferred to the server and processed using natural language processing technology. Based on the analyzed information, the server searches for relevant laws and precedents and generates a draft judgment to derive the optimal legal decision.

[0411] In this system, user feedback is extremely important. By sending users' opinions and requests regarding draft judgments from their terminals to the server, the server can update its machine learning model and continuously improve the overall accuracy of the system. This will lead to more objective and fair interpretation of laws and regulations.

[0412] As a concrete example, consider a case where a user consults the system about a dispute related to their employment contract. The user inputs the relevant facts and contract details into the terminal. The server analyzes this information and extracts relevant labor laws and precedents. The server summarizes the legal opinion on the case in question and generates a draft judgment that would be beneficial to the user. This draft judgment can show the user specific steps they should take to resolve the problem.

[0413] In this way, this system supports legal judgments in courts, public institutions, corporate legal departments, etc., and provides a fair and impartial judgment process by eliminating human subjectivity.

[0414] The following describes the processing flow.

[0415] Step 1:

[0416] The user enters specific case information regarding legal troubles from their device. This includes details such as relevant facts, contracts, and evidence.

[0417] Step 2:

[0418] The terminal structures the input information, converts it into a data format, and sends it to the server. During this process, it performs basic checks to ensure there are no missing or inconsistent pieces of information.

[0419] Step 3:

[0420] The server processes the received case information using a natural language processing tool to extract keywords and legal concepts. Based on these analysis results, it searches the relevant legal database.

[0421] Step 4:

[0422] The server uses the extracted keywords to search the database for past precedents and relevant laws and regulations, identifying similar cases. During this process, it evaluates the scope and importance of the applicable laws and regulations.

[0423] Step 5:

[0424] Based on the search results, the server generates legal judgments and recommended rulings relevant to the case. The recommended rulings prioritize reasonableness and may offer interpretations from multiple perspectives.

[0425] Step 6:

[0426] The server sends the generated draft judgment to the terminal and presents it to the user. The draft judgment is logically structured and presents a concrete solution.

[0427] Step 7:

[0428] Users review the proposed judgments and provide feedback as needed. This feedback includes opinions on the validity and potential improvements of the proposed judgments.

[0429] Step 8:

[0430] The terminal sends user feedback to the server. The server stores the received feedback and uses it to refine the machine learning model, thereby improving the overall accuracy of the system.

[0431] (Example 1)

[0432] 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."

[0433] The current process of determining legal judgments presents challenges in making fair and efficient decisions, not only because it requires considerable time and effort to collect and analyze information, search for appropriate laws and precedents, and present legal judgments, but also because human subjectivity can interfere. This invention aims to provide a system that efficiently manages and analyzes legal information and supports swift and fair legal judgments.

[0434] 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.

[0435] In this invention, the server includes means for managing and making legal information accessible, means for processing input case content and performing natural language analysis, and means for searching for relevant rules and past cases based on the analysis results. This enables efficient management, analysis, and retrieval of legal information, supporting swift and fair legal decisions.

[0436] "Legal information" is a general term for information including laws, regulations, and related past precedents and cases.

[0437] "Means of making access possible" refers to methods that enable users and systems to efficiently access the information they need from a specific database or information source.

[0438] "Case details" refer to information about the specific problem or situation that the user is seeking advice on, and serve as basic data for making legal judgments.

[0439] "Natural language processing" is a technology that converts human language into a format that computers can easily understand and analyzes its meaning and characteristics.

[0440] A "generative AI model" is a type of artificial intelligence model that has the ability to generate new text and information based on input data.

[0441] A "draft legal judgment" refers to a legal opinion or proposal derived from a specific case, and may include specific guidelines for action.

[0442] "Evaluation information" refers to the opinions and feedback users give regarding the information and results provided by the system, and is used to improve the system.

[0443] A "learning algorithm" refers to a computational method used by computers to acquire new knowledge and skills from data, and is used to improve the accuracy and performance of a system.

[0444] This legal judgment support system functions through the collaboration of a server, terminals, and users. The server uses a powerful database management system (e.g., MySQL, PostgreSQL, etc.) to manage and maintain access to legal information. This enables efficient searching of large amounts of data on laws and precedents. The server uses natural language processing libraries (e.g., Python's NLTK or SpaCy, etc.) to analyze the case content entered by the user and systematically understand its meaning.

[0445] The user inputs specific case information into the terminal, seeking legal judgment. The terminal provides an intuitive interface for user interaction. The input information is transmitted to the server via the terminal. For example, if a user is inquiring about legal matters related to a traffic accident, they would describe the specific situation and their questions in detail. Examples of prompts might include, "I want to know about compensation for damages in a traffic accident," or "I want to know about the laws regarding termination of employment contracts."

[0446] The server utilizes a generative AI model (such as a Transformer model) to generate draft legal judgments based on the analyzed information. This model possesses advanced reasoning capabilities, comprehensively evaluating relevant laws and precedents to derive the optimal legal judgment. The resulting draft legal judgment is then provided to the user via the terminal.

[0447] Users can consider practical actions based on the provided legal judgments. Furthermore, user feedback is sent to the server, and the system's accuracy is continuously improved through a learning algorithm. This process ensures that legal judgments become more objective and fair, providing users with practical information.

[0448] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0449] Step 1:

[0450] The user enters information about the case they wish to consult about into the system via their terminal. Specifically, they describe the background and related information of the case in text format in an input form. The input data is recorded on the terminal in an easy-to-understand format, such as "Consultation regarding compensation for damages in a traffic accident." The terminal then sends this information to the server.

[0451] Step 2:

[0452] The server passes the data received from the terminal to a natural language processing engine for text analysis. This analysis uses NLTK or SpaCy to extract keywords and important phrases from the input text and create a data structure. The extracted keywords (for example, "traffic accident" and "compensation") are used to query the legal database.

[0453] Step 3:

[0454] The server searches the legal database using keywords obtained from the analysis engine. It quickly identifies relevant laws and past precedents using SQL queries and retrieves them in an organized format. At this time, the server executes a search algorithm that utilizes indexes for efficiency.

[0455] Step 4:

[0456] The server inputs the searched laws and precedents into a generating AI model to create a legal judgment suitable for the case. This process utilizes Transformer models and other tools to perform reasoning based on legal information. The generated judgment is output as text, including specific legal measures and proposals.

[0457] Step 5:

[0458] The server sends the generated draft legal judgment to the terminal. The terminal displays this information in a visually easy-to-understand format to encourage user consideration. The display method can be customized according to the user's preference, such as a list format or step-by-step instructions.

[0459] Step 6:

[0460] Users provide feedback on the proposed judgment via their devices. Specifically, they input their opinions on the validity of the proposed judgment, requests for further information, etc., in text format and send them to the server.

[0461] Step 7:

[0462] The server passes user feedback to a machine learning algorithm to help improve the system. In this process, the received feedback is used as new training data to improve the accuracy of the generated AI model, thereby enhancing the quality of future legal decisions.

[0463] (Application Example 1)

[0464] 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."

[0465] There is a need to quickly and appropriately derive information protection measures based on security-related laws and case studies, particularly in the decision-making processes of companies and organizations. However, the sheer volume and complexity of information presents a challenge in making accurate judgments.

[0466] 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.

[0467] In this invention, the server includes means for making a legal information aggregation device accessible, means for analyzing input case information and performing language processing, means for searching for relevant laws and cases based on the analyzed information, and means for generating proposed protection measures based on information protection-related laws and cases. This makes it possible to quickly and accurately propose information protection measures to companies and organizations.

[0468] A "legal information aggregation device" is a mechanism for systematically collecting and managing information on various laws and precedents.

[0469] "Natural language processing" refers to technical methods for analyzing input text data and understanding its meaning and intent.

[0470] A "self-learning model" is an algorithm or system equipped with a learning function that uses user feedback to make more accurate judgments and suggestions.

[0471] A "proposal for information protection measures" is a proposal outlining specific legal and technically recommended policies and measures to ensure the security of information.

[0472] To realize this invention, the system operates by coordinating multiple components. The server plays a central role in performing the main processing. The server accesses the legal information aggregation device and analyzes the text sent by the user using language processing technology. Specific processing can be performed using the Python language or natural language processing libraries (e.g., NLTK or spaCy). The analyzed information becomes important data for querying relevant laws and cases.

[0473] The server then generates proposed protection measures based on relevant laws and case studies concerning information protection. This involves utilizing self-learning models to improve the accuracy of the proposals by considering feedback from past users. This process could potentially utilize machine learning frameworks such as TensorFlow or PyTorch.

[0474] Users can access the server via smartphones or computer terminals, input information, and receive generated protection proposals. User feedback is also used in the system's learning algorithms, contributing to improving the quality of the proposals.

[0475] As a concrete example, when a company reviews its policies to strengthen information security for employees working remotely, it provides recommendations for ensuring server security based on relevant laws and precedents. This allows companies to implement remote work with greater confidence. Another example of a prompt message would be, "What security policies should be adopted to strengthen employee data protection during remote work?"

[0476] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0477] Step 1:

[0478] Users use their devices to input information and questions related to remote work security. The input data is in natural language format and is sent from the device to the server.

[0479] Step 2:

[0480] The server analyzes the received input data using natural language processing techniques. Specifically, it uses Python and a natural language processing library (e.g., spaCy) to extract important keywords and context from the input data. This allows the server to prepare the information necessary for the next search phase.

[0481] Step 3:

[0482] Based on the analysis results, the server accesses the legal information aggregation device to search for relevant laws and past cases. The server uses the extracted keywords as queries to efficiently retrieve the corresponding laws and precedents from the legal database.

[0483] Step 4:

[0484] The server generates proposed protection measures based on search results, taking into account relevant laws and case studies related to information protection. Here, a self-learning model is utilized to create highly accurate suggestions that reflect past user feedback. TensorFlow is used to execute the generated AI model and construct appropriate protection measures.

[0485] Step 5:

[0486] The generated protection plan is sent from the server to the user's terminal, where the user receives it. The user can review the proposed plan and use it to further develop their security policy.

[0487] Step 6:

[0488] Users input feedback on the suggestions from their devices and send it to the server. This feedback data is used to update the self-learning model, contributing to improved accuracy of future suggestions.

[0489] 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.

[0490] This invention demonstrates a legal judgment support system incorporating an emotion engine. The server accesses a legal database and manages it to enable rapid retrieval of past precedents and laws. Users can input case information related to legal troubles using a terminal. The input information is first sent to the server and processed using natural language processing technology.

[0491] Furthermore, the newly integrated emotion engine analyzes the user's emotions from their input information. This emotion data is designed to be reflected in the server's process of generating legal judgments and draft rulings. In this process, the emotion data is used, for example, to adjust the tone and approach of the solution.

[0492] After the draft judgment is generated, the server sends it to the terminal and displays it to the user. At this point, the user interface is adjusted according to the emotional state recognized by the emotion engine. For example, if the server determines that the user is stressed, the displayed message can be made more friendly, or supportive information can be provided. The user can then use the generated draft judgment as a guideline for deciding on further actions.

[0493] As a concrete example, consider a scenario where a user consults the system about an issue related to their employment contract. The user inputs the case and related evidence into a terminal and sends it to the system. The server analyzes the case and searches for relevant laws and precedents. Furthermore, an emotion engine detects feelings of stress and anxiety from the user's description and adjusts the tone of the proposed judgment. Finally, the user is presented with a legal opinion and specific action plans regarding their consultation.

[0494] This system not only efficiently assists in legal judgments but also provides more comprehensive support by offering support that takes into account the user's feelings.

[0495] The following describes the processing flow.

[0496] Step 1:

[0497] Users input case information related to legal consultations or disputes into their devices. This may include a summary of the case, relevant evidence, and personal comments.

[0498] Step 2:

[0499] The terminal formats the data before sending the input information to the server. It also verifies that the information has been transferred correctly and completely.

[0500] Step 3:

[0501] The server analyzes the received case information using a natural language processing engine. This process involves extracting legal concepts and keywords from the text.

[0502] Step 4:

[0503] The server searches the legal database based on the extracted keywords and extracts relevant laws and precedents. This data is used to derive judgments and applicable laws for similar cases.

[0504] Step 5:

[0505] The server uses an emotion engine to analyze user input to determine emotions. It evaluates the type and intensity of emotions and determines how they might influence the verdict.

[0506] Step 6:

[0507] The server combines analyzed legal information and sentiment data to generate a draft judgment. This draft judgment is not only legally meaningful but also takes into account the user's emotional state.

[0508] Step 7:

[0509] The server sends the generated draft judgment to the terminal and displays it to the user. The display is customized according to the user's emotional state and includes supplementary explanations and support links as needed.

[0510] Step 8:

[0511] Users can review the proposed judgment and input feedback and necessary actions via their device. This feedback will be valuable data for future improvements.

[0512] Step 9:

[0513] The terminal sends user feedback information to the server, which uses this to refine the machine learning model. This allows for continuous improvement of the system's accuracy and the quality of user support.

[0514] (Example 2)

[0515] 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."

[0516] Conventional legal judgment support systems lack consideration for the user, providing uniform legal searches and draft judgments without regard for the user's emotions. Furthermore, the user interface and the tone of the draft judgments are not appropriately adjusted based on the user's emotions, potentially amplifying user anxiety. This results in a lack of comprehensive support for users, particularly in situations where emotions play a significant role in legal decisions.

[0517] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0518] In this invention, the server includes means for making a collection of legal information accessible, means for processing case data entered by the user and performing natural language analysis, means for searching for relevant laws and judgment cases based on the analyzed information, means for transmitting the generated draft decision to a terminal and displaying it to the user, and means for analyzing emotions and adjusting the draft decision to reflect the emotion data. This makes it possible to provide comprehensive legal judgment support while reflecting the user's emotions and providing a sense of security.

[0519] A "legal information collection" refers to a database that systematically organizes and aggregates data related to laws and regulations in a searchable format.

[0520] "Case data" refers to information about specific legal troubles entered by users, including related background and evidence.

[0521] "Natural language processing" is a technology that converts input text data into a form that is easy for machines to understand, and mainly refers to the process of syntactic analysis and keyword extraction of language.

[0522] "Case precedents" refer to information compiled from past court decisions, and are used as reference information regarding specific legal interpretations and judgments.

[0523] A "decision proposal" refers to a proposal that specifically suggests judgments and recommended actions regarding laws and regulations, based on the input data and analysis results.

[0524] "Emotional data" refers to information that represents the user's emotional state, extracted from user input and interactions.

[0525] "User interface" refers to the entirety of the screens, input forms, and display methods that users use when operating a system, and is a crucial element that influences the user experience.

[0526] The core of this legal judgment support system is the interaction of information between the server, the terminal, and the user. The following is a specific implementation.

[0527] First, users can use the terminal to input specific "case data" related to legal troubles. The terminal is equipped with an input support interface to help users enter the necessary information without hesitation. For example, if a user wants to consult about a dispute regarding an employment contract, they can input the details of the case and supporting documents.

[0528] Next, this input data is quickly sent to the server. The server performs "natural language analysis" on the received data. This analysis uses natural language processing libraries such as spaCy or NLTK to perform data tokenization and syntactic analysis.

[0529] After analysis by the server, access is made to a "legal information collection" containing information on laws and regulations. This database includes laws and past "judgment cases," and the server searches for appropriate laws and judgment cases based on the results of natural language analysis. SQL queries and other tools are used in this process.

[0530] Furthermore, the server activates an emotion engine and extracts "emotional data" based on user input. The engine utilizes emotion recognition technology, such as empathy or general emotion recognition software, to evaluate the user's emotional state and generate a "decision proposal" that considers emotional support as well as legal judgment.

[0531] The generated decision is sent back to the device. When displayed, the device's "user interface" is adjusted based on emotional data to provide appropriate legal advice while reducing the user's anxiety with a friendly tone. For example, if the user is feeling stressed, the displayed message will be adjusted to be more comforting.

[0532] An example of a prompt message would be, "Consider the user's emotional state regarding an issue related to employment contracts, and generate appropriate legal judgments and recommended solutions." Based on this information, the generating AI model would then provide an appropriate draft judgment.

[0533] In this way, the system provides comprehensive support that takes into account not only legal judgments but also the feelings of the users.

[0534] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0535] Step 1:

[0536] The user uses the terminal to input specific case data related to legal troubles. This input includes details of the background of the problem and relevant evidence. After input, the terminal formats this data and prepares it for transmission to the server.

[0537] Step 2:

[0538] Case data sent from the terminal is received by the server. The server first verifies the integrity of the input data, and then performs natural language processing. Specifically, it uses natural language processing libraries such as spaCy and NLTK to tokenize the text and perform semantic analysis. Through this analysis, keywords and related topics are extracted from the case data.

[0539] Step 3:

[0540] Based on the analyzed information, the server accesses a collection of legal information. Here, it uses SQL queries to search for relevant laws and court rulings. The server matches the case data with the extracted keywords to retrieve the most relevant legal information.

[0541] Step 4:

[0542] The server activates the emotion engine and performs emotion analysis based on the user's input data. This process utilizes emotion recognition software to analyze emotional vocabulary and expressions in the input text. As a result, data indicating the user's emotional state is generated.

[0543] Step 5:

[0544] Using emotional data and legal information, the server generates a decision proposal using a generative AI model. This process is guided by the prompt "Consider the user's emotional state regarding the issue of the employment contract and generate an appropriate legal judgment and recommended solution." The output is a legal judgment and solution that takes the user's emotions into consideration.

[0545] Step 6:

[0546] The generated decision proposal is sent from the server to the terminal. When the terminal displays the received decision proposal to the user, it adjusts the user interface based on emotional data. Specifically, if the user is stressed, the message displayed on the screen is set to a comforting tone.

[0547] Step 7:

[0548] The user reviews the proposed decision displayed on the terminal and decides what action to take next. At this stage, the user uses the information obtained from the system to decide, for example, whether to take legal action. If necessary, they can enter additional information and repeat the process.

[0549] (Application Example 2)

[0550] 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."

[0551] Legal disputes arising in electronic transactions are complex and stressful issues for users. In such situations, conventional legal judgment support systems often only offer abstract legal opinions without considering the user's feelings. Therefore, there has been a need for a system that reduces the emotional burden on users and provides substantive legal advice in a more user-friendly way.

[0552] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0553] In this invention, the server includes means for making a legal database accessible, means for processing input case information and performing natural language analysis, means for searching for relevant laws and precedents based on the analyzed information, means for analyzing and evaluating sentiment data, means for adjusting the draft judgment based on the user's emotional state, and means for outputting the adjusted draft judgment. This makes it possible to provide more user-friendly and accurate legal decision support that takes the user's emotions into consideration.

[0554] A "legal database" is a digital information repository that aggregates legal information such as laws, ordinances, and precedents, making it searchable and accessible.

[0555] "Case information" refers to information about specific cases or issues that users provide when seeking legal assistance.

[0556] "Natural language processing" is a technology that converts natural language, which humans use in everyday life, into a format that computers can understand and analyze.

[0557] "Case law" refers to a record of past judicial decisions and serves as a standard of information that is referenced in similar cases.

[0558] "Emotional data" refers to information that quantifies or categorizes emotional states extracted from user input.

[0559] A "draft judgment" is an initial solution or opinion on a legal issue, generated based on analyzed legal and sentiment data.

[0560] "Evaluation" is the act of judging the situation and value of things based on data and information, and analyzing them quantitatively or qualitatively.

[0561] "Output" refers to the process of displaying information or results processed by the system to the user.

[0562] The system for realizing this invention mainly consists of a server and a user terminal. The server maintains a legal database and processes case information entered from the user terminal using natural language processing technology.

[0563] First, the user enters case information about their legal trouble or problem into the terminal. This information is sent to the server, which analyzes the input information using a natural language processing library (e.g., SpaCy). The analyzed data is then cross-referenced with relevant laws and precedents in the legal database.

[0564] In parallel, the server uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to extract sentiment data from user input. This sentiment data is integrated with information obtained from a legal database and used to generate draft judgments.

[0565] The generated draft judgment is adjusted to take the user's emotional state into consideration. For example, users who are detected as stressed will be presented with legal advice in a more approachable and comforting tone. In this way, the final draft judgment is output to the user's device.

[0566] As a concrete example, a user facing a problem with an unfair claim might enter the prompt, "Is this claim legitimate? Please tell me how to resolve this." The server then analyzes the input and presents emotionally appropriate solutions along with relevant case law. This process ensures that the user receives support both emotionally and legally.

[0567] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0568] Step 1:

[0569] The user's device collects data through an interface that inputs case information related to legal troubles. The input data includes text describing the user's specific problem or situation. This data is then sent to the server.

[0570] Step 2:

[0571] The server processes the received input data using natural language processing (NLP) techniques. This process utilizes a natural language processing library such as SpaCy to structure the input data (tokenization, part-of-speech tagging, etc.) and understand its content. As a result, the analyzed semantic content is obtained.

[0572] Step 3:

[0573] Based on the analyzed data, the server searches for relevant laws and precedents in the legal database. The search uses keywords and phrases contained in the input data to perform matching and obtain relevant legal information.

[0574] Step 4:

[0575] Simultaneously, the server begins sentiment analysis. Using tools like IBM Watson Tone Analyzer, it extracts sentiment data from the user's input. From this sentiment data, it determines the user's emotional state, such as stress levels and feelings of well-being.

[0576] Step 5:

[0577] The server integrates legal search results and sentiment data to generate draft judgments. This process uses a generative AI model to generate specific solutions and advice. The generated draft judgments include recommended actions based on the law.

[0578] Step 6:

[0579] The server considers the user's emotional state and adjusts the tone of the draft judgment. Based on emotional data, it generates messages in a friendly tone and gentle phrasing that are particularly appropriate for emotional states requiring special consideration (e.g., high stress levels).

[0580] Step 7:

[0581] Finally, the server sends the adjusted draft judgment to the user's device. The user can receive legal advice in a clear and user-friendly format on their device. This advice serves as specific guidance to directly address the issues the user is facing.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] [Fourth Embodiment]

[0586] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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".

[0599] This invention presents an embodiment of a legal judgment support system in which a server, terminal, and user work in cooperation. The server efficiently manages laws and past precedents by accessing a legal database and can quickly and accurately search this information. Users can input specific case information using a terminal, and this information is transferred to the server and processed using natural language processing technology. Based on the analyzed information, the server searches for relevant laws and precedents and generates a draft judgment to derive the optimal legal decision.

[0600] In this system, user feedback is extremely important. By sending users' opinions and requests regarding draft judgments from their terminals to the server, the server can update its machine learning model and continuously improve the overall accuracy of the system. This will lead to more objective and fair interpretation of laws and regulations.

[0601] As a concrete example, consider a case where a user consults the system about a dispute related to their employment contract. The user inputs the relevant facts and contract details into the terminal. The server analyzes this information and extracts relevant labor laws and precedents. The server summarizes the legal opinion on the case in question and generates a draft judgment that would be beneficial to the user. This draft judgment can show the user specific steps they should take to resolve the problem.

[0602] In this way, this system supports legal judgments in courts, public institutions, corporate legal departments, etc., and provides a fair and impartial judgment process by eliminating human subjectivity.

[0603] The following describes the processing flow.

[0604] Step 1:

[0605] The user enters specific case information regarding legal troubles from their device. This includes details such as relevant facts, contracts, and evidence.

[0606] Step 2:

[0607] The terminal structures the input information, converts it into a data format, and sends it to the server. During this process, it performs basic checks to ensure there are no missing or inconsistent pieces of information.

[0608] Step 3:

[0609] The server processes the received case information using a natural language processing tool to extract keywords and legal concepts. Based on these analysis results, it searches the relevant legal database.

[0610] Step 4:

[0611] The server uses the extracted keywords to search the database for past precedents and relevant laws and regulations, identifying similar cases. During this process, it evaluates the scope and importance of the applicable laws and regulations.

[0612] Step 5:

[0613] Based on the search results, the server generates legal judgments and recommended rulings relevant to the case. The recommended rulings prioritize reasonableness and may offer interpretations from multiple perspectives.

[0614] Step 6:

[0615] The server sends the generated draft judgment to the terminal and presents it to the user. The draft judgment is logically structured and presents a concrete solution.

[0616] Step 7:

[0617] Users review the proposed judgments and provide feedback as needed. This feedback includes opinions on the validity and potential improvements of the proposed judgments.

[0618] Step 8:

[0619] The terminal sends user feedback to the server. The server stores the received feedback and uses it to refine the machine learning model, thereby improving the overall accuracy of the system.

[0620] (Example 1)

[0621] 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".

[0622] The current process of determining legal judgments presents challenges in making fair and efficient decisions, not only because it requires considerable time and effort to collect and analyze information, search for appropriate laws and precedents, and present legal judgments, but also because human subjectivity can interfere. This invention aims to provide a system that efficiently manages and analyzes legal information and supports swift and fair legal judgments.

[0623] 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.

[0624] In this invention, the server includes means for managing and making legal information accessible, means for processing input case content and performing natural language analysis, and means for searching for relevant rules and past cases based on the analysis results. This enables efficient management, analysis, and retrieval of legal information, supporting swift and fair legal decisions.

[0625] "Legal information" is a general term for information including laws, regulations, and related past precedents and cases.

[0626] "Means of making access possible" refers to methods that enable users and systems to efficiently access the information they need from a specific database or information source.

[0627] "Case details" refer to information about the specific problem or situation that the user is seeking advice on, and serve as basic data for making legal judgments.

[0628] "Natural language processing" is a technology that converts human language into a format that computers can easily understand and analyzes its meaning and characteristics.

[0629] A "generative AI model" is a type of artificial intelligence model that has the ability to generate new text and information based on input data.

[0630] A "draft legal judgment" refers to a legal opinion or proposal derived from a specific case, and may include specific guidelines for action.

[0631] "Evaluation information" refers to the opinions and feedback users give regarding the information and results provided by the system, and is used to improve the system.

[0632] A "learning algorithm" refers to a computational method used by computers to acquire new knowledge and skills from data, and is used to improve the accuracy and performance of a system.

[0633] This legal judgment support system functions through the collaboration of a server, terminals, and users. The server uses a powerful database management system (e.g., MySQL, PostgreSQL, etc.) to manage and maintain access to legal information. This enables efficient searching of large amounts of data on laws and precedents. The server uses natural language processing libraries (e.g., Python's NLTK or SpaCy, etc.) to analyze the case content entered by the user and systematically understand its meaning.

[0634] The user inputs specific case information into the terminal, seeking legal judgment. The terminal provides an intuitive interface for user interaction. The input information is transmitted to the server via the terminal. For example, if a user is inquiring about legal matters related to a traffic accident, they would describe the specific situation and their questions in detail. Examples of prompts might include, "I want to know about compensation for damages in a traffic accident," or "I want to know about the laws regarding termination of employment contracts."

[0635] The server utilizes a generative AI model (such as a Transformer model) to generate draft legal judgments based on the analyzed information. This model possesses advanced reasoning capabilities, comprehensively evaluating relevant laws and precedents to derive the optimal legal judgment. The resulting draft legal judgment is then provided to the user via the terminal.

[0636] Users can consider practical actions based on the provided legal judgments. Furthermore, user feedback is sent to the server, and the system's accuracy is continuously improved through a learning algorithm. This process ensures that legal judgments become more objective and fair, providing users with practical information.

[0637] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0638] Step 1:

[0639] The user enters information about the case they wish to consult about into the system via their terminal. Specifically, they describe the background and related information of the case in text format in an input form. The input data is recorded on the terminal in an easy-to-understand format, such as "Consultation regarding compensation for damages in a traffic accident." The terminal then sends this information to the server.

[0640] Step 2:

[0641] The server passes the data received from the terminal to a natural language processing engine for text analysis. This analysis uses NLTK or SpaCy to extract keywords and important phrases from the input text and create a data structure. The extracted keywords (for example, "traffic accident" and "compensation") are used to query the legal database.

[0642] Step 3:

[0643] The server searches the legal database using keywords obtained from the analysis engine. It quickly identifies relevant laws and past precedents using SQL queries and retrieves them in an organized format. At this time, the server executes a search algorithm that utilizes indexes for efficiency.

[0644] Step 4:

[0645] The server inputs the searched laws and precedents into a generating AI model to create a legal judgment suitable for the case. This process utilizes Transformer models and other tools to perform reasoning based on legal information. The generated judgment is output as text, including specific legal measures and proposals.

[0646] Step 5:

[0647] The server sends the generated draft legal judgment to the terminal. The terminal displays this information in a visually easy-to-understand format to encourage user consideration. The display method can be customized according to the user's preference, such as a list format or step-by-step instructions.

[0648] Step 6:

[0649] Users provide feedback on the proposed judgment via their devices. Specifically, they input their opinions on the validity of the proposed judgment, requests for further information, etc., in text format and send them to the server.

[0650] Step 7:

[0651] The server passes user feedback to a machine learning algorithm to help improve the system. In this process, the received feedback is used as new training data to improve the accuracy of the generated AI model, thereby enhancing the quality of future legal decisions.

[0652] (Application Example 1)

[0653] 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".

[0654] There is a need to quickly and appropriately derive information protection measures based on security-related laws and case studies, particularly in the decision-making processes of companies and organizations. However, the sheer volume and complexity of information presents a challenge in making accurate judgments.

[0655] 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.

[0656] In this invention, the server includes means for making a legal information aggregation device accessible, means for analyzing input case information and performing language processing, means for searching for relevant laws and cases based on the analyzed information, and means for generating proposed protection measures based on information protection-related laws and cases. This makes it possible to quickly and accurately propose information protection measures to companies and organizations.

[0657] A "legal information aggregation device" is a mechanism for systematically collecting and managing information on various laws and precedents.

[0658] "Natural language processing" refers to technical methods for analyzing input text data and understanding its meaning and intent.

[0659] A "self-learning model" is an algorithm or system equipped with a learning function that uses user feedback to make more accurate judgments and suggestions.

[0660] A "proposal for information protection measures" is a proposal outlining specific legal and technically recommended policies and measures to ensure the security of information.

[0661] To realize this invention, the system operates by coordinating multiple components. The server plays a central role in performing the main processing. The server accesses the legal information aggregation device and analyzes the text sent by the user using language processing technology. Specific processing can be performed using the Python language or natural language processing libraries (e.g., NLTK or spaCy). The analyzed information becomes important data for querying relevant laws and cases.

[0662] The server then generates proposed protection measures based on relevant laws and case studies concerning information protection. This involves utilizing self-learning models to improve the accuracy of the proposals by considering feedback from past users. This process could potentially utilize machine learning frameworks such as TensorFlow or PyTorch.

[0663] Users can access the server via smartphones or computer terminals, input information, and receive generated protection proposals. User feedback is also used in the system's learning algorithms, contributing to improving the quality of the proposals.

[0664] As a concrete example, when a company reviews its policies to strengthen information security for employees working remotely, it provides recommendations for ensuring server security based on relevant laws and precedents. This allows companies to implement remote work with greater confidence. Another example of a prompt message would be, "What security policies should be adopted to strengthen employee data protection during remote work?"

[0665] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0666] Step 1:

[0667] Users use their devices to input information and questions related to remote work security. The input data is in natural language format and is sent from the device to the server.

[0668] Step 2:

[0669] The server analyzes the received input data using natural language processing techniques. Specifically, it uses Python and a natural language processing library (e.g., spaCy) to extract important keywords and context from the input data. This allows the server to prepare the information necessary for the next search phase.

[0670] Step 3:

[0671] Based on the analysis results, the server accesses the legal information aggregation device to search for relevant laws and past cases. The server uses the extracted keywords as queries to efficiently retrieve the corresponding laws and precedents from the legal database.

[0672] Step 4:

[0673] The server generates proposed protection measures based on search results, taking into account relevant laws and case studies related to information protection. Here, a self-learning model is utilized to create highly accurate suggestions that reflect past user feedback. TensorFlow is used to execute the generated AI model and construct appropriate protection measures.

[0674] Step 5:

[0675] The generated protection plan is sent from the server to the user's terminal, where the user receives it. The user can review the proposed plan and use it to further develop their security policy.

[0676] Step 6:

[0677] Users input feedback on the suggestions from their devices and send it to the server. This feedback data is used to update the self-learning model, contributing to improved accuracy of future suggestions.

[0678] 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.

[0679] This invention demonstrates a legal judgment support system incorporating an emotion engine. The server accesses a legal database and manages it to enable rapid retrieval of past precedents and laws. Users can input case information related to legal troubles using a terminal. The input information is first sent to the server and processed using natural language processing technology.

[0680] Furthermore, the newly integrated emotion engine analyzes the user's emotions from their input information. This emotion data is designed to be reflected in the server's process of generating legal judgments and draft rulings. In this process, the emotion data is used, for example, to adjust the tone and approach of the solution.

[0681] After the draft judgment is generated, the server sends it to the terminal and displays it to the user. At this point, the user interface is adjusted according to the emotional state recognized by the emotion engine. For example, if the server determines that the user is stressed, the displayed message can be made more friendly, or supportive information can be provided. The user can then use the generated draft judgment as a guideline for deciding on further actions.

[0682] As a concrete example, consider a scenario where a user consults the system about an issue related to their employment contract. The user inputs the case and related evidence into a terminal and sends it to the system. The server analyzes the case and searches for relevant laws and precedents. Furthermore, an emotion engine detects feelings of stress and anxiety from the user's description and adjusts the tone of the proposed judgment. Finally, the user is presented with a legal opinion and specific action plans regarding their consultation.

[0683] This system not only efficiently assists in legal judgments but also provides more comprehensive support by offering support that takes into account the user's feelings.

[0684] The following describes the processing flow.

[0685] Step 1:

[0686] Users input case information related to legal consultations or disputes into their devices. This may include a summary of the case, relevant evidence, and personal comments.

[0687] Step 2:

[0688] The terminal formats the data before sending the input information to the server. It also verifies that the information has been transferred correctly and completely.

[0689] Step 3:

[0690] The server analyzes the received case information using a natural language processing engine. This process involves extracting legal concepts and keywords from the text.

[0691] Step 4:

[0692] The server searches the legal database based on the extracted keywords and extracts relevant laws and precedents. This data is used to derive judgments and applicable laws for similar cases.

[0693] Step 5:

[0694] The server uses an emotion engine to analyze user input to determine emotions. It evaluates the type and intensity of emotions and determines how they might influence the verdict.

[0695] Step 6:

[0696] The server combines analyzed legal information and sentiment data to generate a draft judgment. This draft judgment is not only legally meaningful but also takes into account the user's emotional state.

[0697] Step 7:

[0698] The server sends the generated draft judgment to the terminal and displays it to the user. The display is customized according to the user's emotional state and includes supplementary explanations and support links as needed.

[0699] Step 8:

[0700] Users can review the proposed judgment and input feedback and necessary actions via their device. This feedback will be valuable data for future improvements.

[0701] Step 9:

[0702] The terminal sends user feedback information to the server, which uses this to refine the machine learning model. This allows for continuous improvement of the system's accuracy and the quality of user support.

[0703] (Example 2)

[0704] 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".

[0705] Conventional legal judgment support systems lack consideration for the user, providing uniform legal searches and draft judgments without regard for the user's emotions. Furthermore, the user interface and the tone of the draft judgments are not appropriately adjusted based on the user's emotions, potentially amplifying user anxiety. This results in a lack of comprehensive support for users, particularly in situations where emotions play a significant role in legal decisions.

[0706] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0707] In this invention, the server includes means for making a collection of legal information accessible, means for processing case data entered by the user and performing natural language analysis, means for searching for relevant laws and judgment cases based on the analyzed information, means for transmitting the generated draft decision to a terminal and displaying it to the user, and means for analyzing emotions and adjusting the draft decision to reflect the emotion data. This makes it possible to provide comprehensive legal judgment support while reflecting the user's emotions and providing a sense of security.

[0708] A "legal information collection" refers to a database that systematically organizes and aggregates data related to laws and regulations in a searchable format.

[0709] "Case data" refers to information about specific legal troubles entered by users, including related background and evidence.

[0710] "Natural language processing" is a technology that converts input text data into a form that is easy for machines to understand, and mainly refers to the process of syntactic analysis and keyword extraction of language.

[0711] "Case precedents" refer to information compiled from past court decisions, and are used as reference information regarding specific legal interpretations and judgments.

[0712] A "decision proposal" refers to a proposal that specifically suggests judgments and recommended actions regarding laws and regulations, based on the input data and analysis results.

[0713] "Emotional data" refers to information that represents the user's emotional state, extracted from user input and interactions.

[0714] "User interface" refers to the entirety of the screens, input forms, and display methods that users use when operating a system, and is a crucial element that influences the user experience.

[0715] The core of this legal judgment support system is the interaction of information between the server, the terminal, and the user. The following is a specific implementation.

[0716] First, users can use the terminal to input specific "case data" related to legal troubles. The terminal is equipped with an input support interface to help users enter the necessary information without hesitation. For example, if a user wants to consult about a dispute regarding an employment contract, they can input the details of the case and supporting documents.

[0717] Next, this input data is quickly sent to the server. The server performs "natural language analysis" on the received data. This analysis uses natural language processing libraries such as spaCy or NLTK to perform data tokenization and syntactic analysis.

[0718] After analysis by the server, access is made to a "legal information collection" containing information on laws and regulations. This database includes laws and past "judgment cases," and the server searches for appropriate laws and judgment cases based on the results of natural language analysis. SQL queries and other tools are used in this process.

[0719] Furthermore, the server activates an emotion engine and extracts "emotional data" based on user input. The engine utilizes emotion recognition technology, such as empathy or general emotion recognition software, to evaluate the user's emotional state and generate a "decision proposal" that considers emotional support as well as legal judgment.

[0720] The generated decision is sent back to the device. When displayed, the device's "user interface" is adjusted based on emotional data to provide appropriate legal advice while reducing the user's anxiety with a friendly tone. For example, if the user is feeling stressed, the displayed message will be adjusted to be more comforting.

[0721] An example of a prompt message would be, "Consider the user's emotional state regarding an issue related to employment contracts, and generate appropriate legal judgments and recommended solutions." Based on this information, the generating AI model would then provide an appropriate draft judgment.

[0722] In this way, the system provides comprehensive support that takes into account not only legal judgments but also the feelings of the users.

[0723] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0724] Step 1:

[0725] The user uses the terminal to input specific case data related to legal troubles. This input includes details of the background of the problem and relevant evidence. After input, the terminal formats this data and prepares it for transmission to the server.

[0726] Step 2:

[0727] Case data sent from the terminal is received by the server. The server first verifies the integrity of the input data, and then performs natural language processing. Specifically, it uses natural language processing libraries such as spaCy and NLTK to tokenize the text and perform semantic analysis. Through this analysis, keywords and related topics are extracted from the case data.

[0728] Step 3:

[0729] Based on the analyzed information, the server accesses a collection of legal information. Here, it uses SQL queries to search for relevant laws and court rulings. The server matches the case data with the extracted keywords to retrieve the most relevant legal information.

[0730] Step 4:

[0731] The server activates the emotion engine and performs emotion analysis based on the user's input data. This process utilizes emotion recognition software to analyze emotional vocabulary and expressions in the input text. As a result, data indicating the user's emotional state is generated.

[0732] Step 5:

[0733] Using emotional data and legal information, the server generates a decision proposal using a generative AI model. This process is guided by the prompt "Consider the user's emotional state regarding the issue of the employment contract and generate an appropriate legal judgment and recommended solution." The output is a legal judgment and solution that takes the user's emotions into consideration.

[0734] Step 6:

[0735] The generated decision proposal is sent from the server to the terminal. When the terminal displays the received decision proposal to the user, it adjusts the user interface based on emotional data. Specifically, if the user is stressed, the message displayed on the screen is set to a comforting tone.

[0736] Step 7:

[0737] The user reviews the proposed decision displayed on the terminal and decides what action to take next. At this stage, the user uses the information obtained from the system to decide, for example, whether to take legal action. If necessary, they can enter additional information and repeat the process.

[0738] (Application Example 2)

[0739] 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".

[0740] Legal disputes arising in electronic transactions are complex and stressful issues for users. In such situations, conventional legal judgment support systems often only offer abstract legal opinions without considering the user's feelings. Therefore, there has been a need for a system that reduces the emotional burden on users and provides substantive legal advice in a more user-friendly way.

[0741] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0742] In this invention, the server includes means for making a legal database accessible, means for processing input case information and performing natural language analysis, means for searching for relevant laws and precedents based on the analyzed information, means for analyzing and evaluating sentiment data, means for adjusting the draft judgment based on the user's emotional state, and means for outputting the adjusted draft judgment. This makes it possible to provide more user-friendly and accurate legal decision support that takes the user's emotions into consideration.

[0743] A "legal database" is a digital information repository that aggregates legal information such as laws, ordinances, and precedents, making it searchable and accessible.

[0744] "Case information" refers to information about specific cases or issues that users provide when seeking legal assistance.

[0745] "Natural language processing" is a technology that converts natural language, which humans use in everyday life, into a format that computers can understand and analyze.

[0746] "Case law" refers to a record of past judicial decisions and serves as a standard of information that is referenced in similar cases.

[0747] "Emotional data" refers to information that quantifies or categorizes emotional states extracted from user input.

[0748] A "draft judgment" is an initial solution or opinion on a legal issue, generated based on analyzed legal and sentiment data.

[0749] "Evaluation" is the act of judging the situation and value of things based on data and information, and analyzing them quantitatively or qualitatively.

[0750] "Output" refers to the process of displaying information or results processed by the system to the user.

[0751] The system for realizing this invention mainly consists of a server and a user terminal. The server maintains a legal database and processes case information entered from the user terminal using natural language processing technology.

[0752] First, the user enters case information about their legal trouble or problem into the terminal. This information is sent to the server, which analyzes the input information using a natural language processing library (e.g., SpaCy). The analyzed data is then cross-referenced with relevant laws and precedents in the legal database.

[0753] In parallel, the server uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to extract sentiment data from user input. This sentiment data is integrated with information obtained from a legal database and used to generate draft judgments.

[0754] The generated draft judgment is adjusted to take the user's emotional state into consideration. For example, users who are detected as stressed will be presented with legal advice in a more approachable and comforting tone. In this way, the final draft judgment is output to the user's device.

[0755] As a concrete example, a user facing a problem with an unfair claim might enter the prompt, "Is this claim legitimate? Please tell me how to resolve this." The server then analyzes the input and presents emotionally appropriate solutions along with relevant case law. This process ensures that the user receives support both emotionally and legally.

[0756] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0757] Step 1:

[0758] The user's device collects data through an interface that inputs case information related to legal troubles. The input data includes text describing the user's specific problem or situation. This data is then sent to the server.

[0759] Step 2:

[0760] The server processes the received input data using natural language processing (NLP) techniques. This process utilizes a natural language processing library such as SpaCy to structure the input data (tokenization, part-of-speech tagging, etc.) and understand its content. As a result, the analyzed semantic content is obtained.

[0761] Step 3:

[0762] Based on the analyzed data, the server searches for relevant laws and precedents in the legal database. The search uses keywords and phrases contained in the input data to perform matching and obtain relevant legal information.

[0763] Step 4:

[0764] Simultaneously, the server begins sentiment analysis. Using tools like IBM Watson Tone Analyzer, it extracts sentiment data from the user's input. From this sentiment data, it determines the user's emotional state, such as stress levels and feelings of well-being.

[0765] Step 5:

[0766] The server integrates legal search results and sentiment data to generate draft judgments. This process uses a generative AI model to generate specific solutions and advice. The generated draft judgments include recommended actions based on the law.

[0767] Step 6:

[0768] The server considers the user's emotional state and adjusts the tone of the draft judgment. Based on emotional data, it generates messages in a friendly tone and gentle phrasing that are particularly appropriate for emotional states requiring special consideration (e.g., high stress levels).

[0769] Step 7:

[0770] Finally, the server sends the adjusted draft judgment to the user's device. The user can receive legal advice in a clear and user-friendly format on their device. This advice serves as specific guidance to directly address the issues the user is facing.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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."

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] The following is further disclosed regarding the embodiments described above.

[0793] (Claim 1)

[0794] Means for making legal databases accessible,

[0795] A means for processing input case information and performing natural language analysis,

[0796] A means of searching for relevant laws and precedents based on the analyzed information,

[0797] A means of generating a draft judgment based on search results,

[0798] A means of outputting the generated draft judgment,

[0799] A system that includes this.

[0800] (Claim 2)

[0801] The system according to claim 1, comprising means for receiving user feedback information and updating a machine learning model based on that feedback.

[0802] (Claim 3)

[0803] The system according to claim 1, further comprising means for supporting evaluation and judgment processes in public institutions or corporations.

[0804] "Example 1"

[0805] (Claim 1)

[0806] Means for managing and making legal information accessible,

[0807] A means of processing the input case content and performing natural language analysis,

[0808] A means of searching for relevant rules and past cases based on the analysis results,

[0809] A method using a generative AI model to generate legal judgment proposals based on search results,

[0810] A means of outputting the generated legal judgment draft,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, comprising means for receiving evaluation information from users and updating the learning algorithm based on that information.

[0814] (Claim 3)

[0815] The system according to claim 1, further comprising means for supporting evaluation and judgment processes in administrative agencies or corporations.

[0816] "Application Example 1"

[0817] (Claim 1)

[0818] Means for making the legal information aggregation device accessible,

[0819] A means for analyzing input case information and performing language processing,

[0820] A means of searching for relevant laws and cases based on the analyzed information,

[0821] A means for generating a decision proposal based on search results,

[0822] A means of presenting the generated decision proposal,

[0823] A means for generating draft protection measures based on information protection-related laws and cases,

[0824] A device that includes this.

[0825] (Claim 2)

[0826] The apparatus according to claim 1, comprising means for receiving evaluation information from users and updating a self-learning model based on that information.

[0827] (Claim 3)

[0828] The apparatus according to claim 1, further comprising means for assisting evaluation and judgment processes in a public facility or organization.

[0829] "Example 2 of combining an emotion engine"

[0830] (Claim 1)

[0831] Means for making a collection of legal information accessible,

[0832] A means of processing case data entered by users and performing natural language analysis,

[0833] A means of searching for relevant laws and court cases based on the analyzed information,

[0834] A means for generating a decision based on search results,

[0835] A means of analyzing emotions from user input data and adjusting decision proposals based on that emotional data,

[0836] A means of transmitting the generated decision to a terminal and displaying it to the user,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, comprising means for adjusting the user interface according to the user's emotional state.

[0840] (Claim 3)

[0841] The system according to claim 1, further comprising means for supporting evaluation and decision-making processes in public bodies or organizations and for providing support based on user sentiment.

[0842] "Application example 2 when combining with an emotional engine"

[0843] (Claim 1)

[0844] Means for making legal databases accessible,

[0845] A means for processing input case information and performing natural language analysis,

[0846] A means of searching for relevant laws and precedents based on the analyzed information,

[0847] Methods for analyzing and evaluating emotional data,

[0848] A means of adjusting the draft judgment based on the emotional state of the user,

[0849] A means of outputting the adjusted draft judgment,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, comprising means for receiving user feedback information and updating a machine learning model based on that feedback.

[0853] (Claim 3)

[0854] The system according to claim 1, further comprising means for supporting evaluation and decision-making processes in electronic transaction processes and for providing legal advice that takes user sentiment into consideration. [Explanation of symbols]

[0855] 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. Means for making legal databases accessible, A means for processing input case information and performing natural language analysis, A means of searching for relevant laws and precedents based on the analyzed information, A means of generating a draft judgment based on search results, A means of outputting the generated draft judgment, A system that includes this.

2. The system according to claim 1, comprising means for receiving user feedback information and updating a machine learning model based on that feedback.

3. The system according to claim 1, further comprising means for supporting evaluation and judgment processes in public institutions or corporations.

Images