System

Abstract

An object of the system according to the embodiment is to reduce man-hours in the creation of a statement and to generate an investigation draft assuming an appropriate guilt.SOLUTION: A system according to an embodiment includes a generative AI model, a learning unit, an interactive prompt inputting unit, a guilt assuming unit, and a protocol generating unit. The generative AI model is compatible with Japanese languages and laws. The learning unit learns representative precedents and anonymized past reports. The interactive prompt input unit grasps the situation of the incident in detail. The guilt hypothesizer hypothesizes the appropriate guilt. The report plan generation unit generates a summary of a report plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, creating a statement record required a significant amount of work, and it was particularly difficult to determine appropriate charges based on the circumstances of the case and to generate a draft statement.

[0005] The system according to the embodiment aims to reduce the amount of work required to prepare a statement and to generate a draft statement that assumes an appropriate name for the crime. [Means for solving the problem]

[0006] The system according to the embodiment comprises a generative AI model, a learning unit, an interactive prompt input unit, a charge name assumption unit, and a report draft generation unit. The generative AI model has an affinity with Japanese language and law. The learning unit studies representative legal precedents and anonymized past reports. The interactive prompt input unit grasps the details of the circumstances of the case. The charge name assumption unit assumes an appropriate charge name. The report draft generation unit generates the outline of the report draft. [Effects of the Invention]

[0007] The system according to the embodiment can reduce the amount of work required to prepare a statement and generate a draft statement that assumes appropriate charges. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The system for generating a statement draft according to an embodiment of the present invention is a system that generates a statement draft while protecting investigative secrets in a high-security domestic environment by using a generation AI model that is compatible with Japanese language and law. As a result, the system for generating a statement draft can efficiently generate a statement draft and reduce the burden on investigators.

[0029] A system for generating a draft statement according to an embodiment includes a generative AI model, a learning unit, an interactive prompt input unit, a charge estimation unit, and a draft statement generation unit. The generative AI model has an affinity with Japanese language and law. The learning unit learns from representative legal precedents and anonymized past statements. For example, the learning unit retrieves past legal precedents from a database and trains the generative AI model. The learning unit also collects anonymized past statements and trains the generative AI model. The interactive prompt input unit grasps the details of the circumstances of the case. For example, the interactive prompt input unit collects information entered by investigators, such as the location and date of the incident and the suspect's behavior. The interactive prompt input unit also allows investigators to input questions to the generative AI, and the generative AI generates answers to those questions. The charge estimation unit estimates an appropriate charge. For example, the charge estimation unit determines an appropriate charge based on the collected information. The charge estimation unit also takes into account points that prosecutors and judges prioritize in similar cases to estimate a charge. The draft report generation unit generates the outline of the draft report. For example, the draft report generation unit creates the outline of the draft report based on the name of the crime assumed by the generation AI. The draft report generation unit also generates the details of the draft report based on the circumstances of the case and related information. This allows the statement draft generation system to efficiently generate draft statement reports using a generative AI model that is compatible with Japanese language and law.

[0030] The learning unit can additionally learn precedents and records specific to a specific region or culture, enabling it to respond to local laws and customs. For example, the learning unit additionally learns precedents and records specific to a specific region (e.g., the Kansai region or the Tohoku region). This makes it possible to generate draft records that correspond to local laws and customs. The learning unit also teaches the generation AI information about local cultures and customs, generating draft records that reflect the characteristics of each region. For example, it generates draft records for incidents related to local festivals and events. The learning unit also learns local crime trends and law enforcement characteristics, allowing the generation AI to generate draft records that correspond to local situations. For example, it generates draft records for crimes that frequently occur in a specific region. This makes it possible to generate draft records that correspond to local laws and customs.

[0031] The learning unit emphasizes and learns keywords and phrases that are considered particularly important in past precedents and transcripts, enabling it to prioritize the extraction of important information. For example, the learning unit emphasizes and learns keywords and phrases that frequently appear in past precedents and transcripts. This allows for the prioritized extraction of important information and improves the accuracy of draft transcripts. The learning unit also develops algorithms for emphasizing important keywords and phrases and incorporates them into the generation AI. For example, important elements such as "alibi" and "eyewitness testimony" are emphasized and learned. The learning unit also adds a function to analyze past precedents and transcripts and automatically extract important information. This allows the generation AI to prioritize learning important information and improve the quality of draft transcripts. This allows for the prioritized extraction of important information and improves the accuracy of draft transcripts.

[0032] The learning unit can study precedents and records based on other legal systems, enabling the generation of draft records from an international perspective. For example, the learning unit can have the generation AI study precedents and records based on American law or European law, enabling the generation of draft records from an international perspective. This generates draft records that can also be used for international cases. The learning unit can also have the generation AI learn information about the legal systems of other countries, generating draft records that incorporate an international perspective. For example, it can generate draft records related to international crimes. The learning unit can also analyze precedents and records based on international legal systems and have the generation AI learn from them. This generates draft records that are compatible with different legal systems. This makes it possible to generate draft records from an international perspective.

[0033] The learning unit can learn from audio data and video data and generate a draft report based on multimodal information. For example, the learning unit has the generation AI learn from audio data and video data and generate a draft report based on multimodal information. For example, it analyzes the suspect's audio statement and footage of the crime scene and reflects this in the draft report. The learning unit also uses speech recognition technology and video analysis technology to have the generation AI learn from the audio data and video data. This allows for the generation of a draft report that includes more detailed information. For example, it analyzes the suspect's audio statement and footage of the crime scene and reflects this in the draft report. The learning unit also develops an algorithm that integrates multimodal information and incorporates it into the generation AI. This allows for the integration and analysis of audio data and video data to generate a draft report. This makes it possible to generate a draft report based on multimodal information.

[0034] The interactive prompt input unit can refer to data on similar past cases and generate more specific questions. For example, the interactive prompt input unit adds a function to have the generation AI refer to data on similar past cases and generate specific questions when inputting an interactive prompt. For example, it generates a question such as, "What kind of evidence was considered important in similar past cases?" The interactive prompt input unit also builds a database of similar cases and develops a system in which the generation AI generates specific questions based on that data. For example, it generates a question such as, "What is the important evidence in this case?" The interactive prompt input unit also analyzes data on similar past cases and develops an algorithm that generates specific questions when the generation AI inputs an interactive prompt. For example, it could "generate detailed questions about the suspect's alibi." This makes it possible to generate specific questions based on data on similar past cases.

[0035] The interactive prompt input unit can understand the investigator's intent and generate answers that are in line with that intent. For example, the interactive prompt input unit adds a function to the generation AI that understands the investigator's intent, building a system that generates answers that are in line with that intent. For example, "generate appropriate answers to questions about the evidence sought by the investigator." The interactive prompt input unit also develops an algorithm that analyzes the investigator's intent and incorporates it into the generation AI. This allows answers to be generated that are in line with the investigator's intent. For example, "generate specific answers based on the information sought by the investigator." The interactive prompt input unit also provides the generation AI with learning data to understand the investigator's intent, adding the ability to generate answers that are in line with the investigator's intent. For example, "generate detailed answers about the evidence sought by the investigator." This allows answers to be generated that are in line with the investigator's intent.

[0036] The interactive prompt input unit can accept input in different languages ​​and achieve multilingual support using a translation function. For example, the interactive prompt input unit adds a function to accept input in different languages ​​to the generation AI and uses the translation function to build a system that achieves multilingual support. For example, it accepts input in English or Chinese and translates it into Japanese for processing. The interactive prompt input unit also develops a multilingual translation algorithm and incorporates it into the generation AI. This allows input in different languages ​​to be translated in real time and an appropriate answer to be generated. For example, input in French is translated into Japanese for processing. The interactive prompt input unit also develops an interface that accepts input in different languages ​​and incorporates it into the generation AI. This allows multilingual support to be achieved and input in different languages ​​is translated and processed. For example, input in Spanish is translated into Japanese for processing. This allows multilingual support to be achieved.

[0037] The interactive prompt input unit can add a function to accept voice input or gesture input, enabling more intuitive operation. The interactive prompt input unit, for example, adds a function to accept voice input or gesture input to the generation AI, building a system that enables more intuitive operation. For example, it accepts voice question input or gesture operation. The interactive prompt input unit also uses voice recognition technology or gesture recognition technology to add a function to accept voice input or gesture input to the generation AI. This enables more intuitive operation. For example, it accepts voice question input or gesture operation. The interactive prompt input unit also develops an interface that accepts voice input or gesture input and incorporates it into the generation AI. This enables more intuitive operation. For example, it accepts voice question input or gesture operation. This enables more intuitive operation.

[0038] The charge prediction unit learns by emphasizing elements that are considered particularly important in past court cases and reports, enabling it to prioritize the extraction of important information. For example, the charge prediction unit has the generation AI learn by emphasizing important elements that frequently appear in past court cases and reports. This allows it to prioritize the extraction of important information and improve the accuracy of draft reports. The charge prediction unit also develops algorithms to emphasize important elements and incorporates them into the generation AI. For example, it has the AI ​​learn by emphasizing important elements such as "alibis" and "eyewitness testimony." The charge prediction unit also adds a function to analyze past court cases and reports and automatically extract important information. This allows the generation AI to prioritize learning important information and improve the quality of draft reports. This allows it to prioritize the extraction of important information and improve the accuracy of draft reports.

[0039] The crime assumption unit can simultaneously assume multiple crimes depending on the circumstances of the case and generate the outline of a draft report for each crime. For example, the crime assumption unit adds a function to the generation AI that simultaneously assumes multiple crimes depending on the circumstances of the case and generates the outline of a draft report for each crime. For example, it assumes both theft and fraud and generates a draft report for each. The crime assumption unit also develops an algorithm that simultaneously assumes multiple crimes and incorporates it into the generation AI. This allows it to generate multiple draft reports depending on the circumstances of the case. For example, it assumes both assault and assault and generates a draft report for each. The crime assumption unit also adds a function that analyzes the circumstances of the case and simultaneously assumes multiple crimes. This allows the generation AI to generate multiple draft reports depending on the circumstances of the case. For example, it assumes both robbery and theft and generates a draft report for each. This allows it to generate multiple draft reports depending on the circumstances of the case.

[0040] The charge assumption unit can assume charges based on different legal systems and generate the outline of a draft report that corresponds to each legal system. For example, the charge assumption unit adds a function to the generation AI that assumes charges based on different legal systems (e.g., American law or European law) and generates the outline of a draft report that corresponds to each legal system. This allows for the generation of draft reports that can also be handled internationally. The charge assumption unit also develops an algorithm that assumes charges based on different legal systems and incorporates it into the generation AI. This allows for the generation of draft reports that correspond to different legal systems. For example, it assumes charges based on American law and generates a draft report that corresponds to that. The charge assumption unit also has the generation AI learn information about different legal systems and adds a function that generates a draft report that corresponds to that different legal system. This allows for the generation of draft reports that incorporate an international perspective. For example, it assumes charges based on European law and generates a draft report that corresponds to that. This allows for the generation of draft reports that correspond to different legal systems.

[0041] The charge estimation unit can grasp the circumstances of a case in detail based on audio and video data and generate the outline of a draft report. For example, the charge estimation unit adds the function of having the generation AI learn audio and video data to grasp the circumstances of a case in detail and generate the outline of a draft report. For example, it analyzes the suspect's audio statement and video footage of the crime scene and reflects this in the draft report. The charge estimation unit also uses voice recognition and video analysis technology to have the generation AI learn audio and video data. This generates a draft report with more detailed information. For example, it analyzes the suspect's audio statement and video footage of the crime scene and reflects this in the draft report. The charge estimation unit also develops an algorithm that integrates multimodal information and incorporates it into the generation AI. This allows it to integrate and analyze audio and video data and generate a draft report. For example, it analyzes the suspect's audio statement and video footage of the crime scene and reflects this in the draft report. This allows it to grasp the circumstances of a case in detail and generate the outline of a draft report.

[0042] The latest security protocols can be introduced into the operating environment of the generative AI to strengthen data encryption and access control. For example, the latest security protocols can be introduced into the operating environment of the generative AI to strengthen data encryption and access control. For example, encryption protocols such as TLS and SSL can be used. Also, algorithms for strengthening security protocols can be developed in the operating environment of the generative AI and incorporated into the operating environment of the generative AI. This strengthens data encryption and access control. For example, encryption algorithms such as AES and RSA can be used. Also, security protocols for strengthening data encryption and access control can be introduced in the operating environment of the generative AI. This minimizes the risk of unauthorized access from outside and information leaks. For example, a VPN or firewall can be used. This strengthens data encryption and access control and improves security.

[0043] Regular security audits can be conducted in the operating environment of the generative AI, and a system can be established to detect and address security risks early. In the operating environment of the generative AI, for example, regular security audits can be conducted and a system can be established to detect and address security risks early. For example, security audits can be conducted monthly or quarterly. In addition, protocols for conducting security audits in the operating environment of the generative AI can be developed and incorporated into the operating environment of the generative AI. This will enable early detection and addressing of security risks. For example, vulnerability scans and penetration tests can be conducted. In addition, an audit system can be established in the operating environment of the generative AI to detect and address security risks early. This will minimize security risks. For example, a security incident response team can be established. This will enable early detection and addressing of security risks.

[0044] It is possible to provide environments with different security levels, allowing the optimum security environment to be selected depending on the application. For example, in the operating environment of the generative AI, environments with different security levels can be provided, and a system can be built that allows the optimum security environment to be selected depending on the application. For example, the highest level of security environment can be provided for highly confidential data. In addition, an interface for selecting the security level can be developed and incorporated into the operating environment of the generative AI. This allows the optimum security environment to be selected depending on the application. For example, the user selects the security level. In addition, environments with different security levels can be provided, and a system can be developed that automatically selects the optimum security environment depending on the application. For example, the security level can be automatically set depending on the confidentiality of the data. This allows the optimum security environment to be selected depending on the application.

[0045] By introducing physical security measures, the risk of information leakage can be minimized. For example, physical security measures can be introduced in the operating environment of the generative AI to minimize the risk of information leakage. For example, a biometric authentication system can be introduced to strengthen access control. Physical security measures such as surveillance cameras and security gates can also be introduced to protect the operating environment of the generative AI. This minimizes the risk of information leakage. For example, surveillance cameras can be installed and monitored 24 hours a day. Protocols for strengthening physical security measures can also be developed and incorporated into the operating environment of the generative AI. This minimizes the risk of information leakage. For example, biometric authentication systems and surveillance cameras can be linked. This minimizes the risk of information leakage.

[0046] Based on the outline of a draft report generated by the generation AI, templates and guidelines can be provided to enable investigators to create reports efficiently. For example, a system can be built that provides templates and guidelines to enable investigators to create reports efficiently based on the outline of a draft report generated by the generation AI. For example, guidelines can be provided that show the procedures and points to note when creating a report. In addition, a template for creating a report can be developed, and a system can be built that automatically generates templates based on the outline of a draft report generated by the generation AI. This allows investigators to create reports efficiently. For example, report formats and items can be automatically generated. In addition, a system can be developed that provides guidelines to enable investigators to create reports efficiently based on the outline of a draft report generated by the generation AI. For example, guidelines can be provided that show points to pay attention to and important elements when creating a report. This allows investigators to create reports efficiently.

[0047] Based on the outline of a draft report generated by the generative AI, links to relevant databases and materials can be provided to enable investigators to quickly gather the information they need. Based on the outline of a draft report generated by the generative AI, for example, a system will be built that provides links to relevant databases and materials so that investigators can quickly gather the information they need. For example, links to relevant precedents and legal documents will be provided. In addition, an algorithm will be developed that automatically generates links to databases and materials and incorporated into the generative AI. This will allow investigators to quickly gather the information they need. For example, links to relevant precedents and legal documents will be automatically generated. In addition, based on the outline of a draft report generated by the generative AI, a system will be developed that provides links to relevant databases and materials so that investigators can quickly gather the information they need. For example, links to relevant precedents and legal documents will be provided. This will allow investigators to quickly gather the information they need.

[0048] Based on the outline of a draft report generated by the generation AI, it is possible to simultaneously create reports that correspond to different legal systems. A function will be added to simultaneously create reports that correspond to different legal systems (for example, American law and European law) based on the outline of a draft report generated by the generation AI. This will allow reports to be created that can also be used in international cases. In addition, the generation AI will develop an algorithm that simultaneously creates reports that correspond to different legal systems and incorporate it into the generation AI. This will allow reports that correspond to different legal systems to be simultaneously created. For example, reports that correspond to American law and European law will be simultaneously created. In addition, the generation AI will learn information about different legal systems and add a function to simultaneously create reports that correspond to different legal systems. This will allow reports that incorporate an international perspective. For example, reports that correspond to American law and European law will be simultaneously created. This will allow reports that correspond to different legal systems to be simultaneously created.

[0049] Based on the outline of a draft report generated by the generation AI, it is possible to create a report more intuitively using voice input or gesture input. Based on the outline of a draft report generated by the generation AI, a function is added to create a report more intuitively using voice input or gesture input, for example. For example, voice question input or gesture operation is accepted. In addition, the generation AI adds a function to accept voice input or gesture input using voice recognition technology or gesture recognition technology. This makes it possible to create a report more intuitively. For example, voice question input or gesture operation is accepted. In addition, the generation AI develops an interface that accepts voice input or gesture input and incorporates it into the generation AI. This makes it possible to create a report more intuitively. For example, voice question input or gesture operation is accepted. This makes it possible to create a report more intuitively.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The statement draft generation system can further include a speech recognition unit. The speech recognition unit can convert the investigator's dictation into text in real time and input it into the interactive prompt input unit. For example, when an investigator dictates the details of a case, the content can be automatically converted into text and input into the generative AI model. The speech recognition unit can also accept the investigator's instructions via voice and perform appropriate operations. For example, it can accept voice instructions such as "proceed to the next question" or "return to the previous question." This allows the investigator to operate the system without using their hands, making it possible to generate a statement draft efficiently.

[0052] The statement draft generation system can further include an image analysis unit. The image analysis unit can analyze photos and videos of the crime scene, extract important information, and reflect it in the draft report. For example, it can analyze the location and condition of evidence from photos of the crime scene and record it in the draft report. The image analysis unit can also perform facial recognition of suspects and witnesses and add related information to the draft report. For example, it can analyze a photo of a suspect's face and reflect their past criminal history and related information in the draft report. This makes it possible to generate a detailed draft report based on visual information.

[0053] The statement draft generation system can further include a data integration unit. The data integration unit can collect information from multiple data sources, integrate it, and reflect it in the draft statement. For example, it can collect information from police databases and public databases and provide it to the generative AI model. The data integration unit can also integrate data in different formats to provide consistent information. For example, it can integrate text data, audio data, and image data and reflect it in the draft statement. This makes it possible to generate a comprehensive draft statement that integrates information from multiple data sources.

[0054] The statement draft generation system can further include a real-time translation unit. The real-time translation unit can translate inputs in different languages ​​in real time and provide them to the generative AI model. For example, the real-time translation unit can translate statements from foreign suspects or witnesses in real time and reflect them in the draft statement. In addition, when investigators ask questions in a different language, the real-time translation unit can translate those questions in real time and convey them to the suspect or witness. This allows for efficient generation of draft statements across language barriers.

[0055] The system for generating a draft statement can further include a privacy protection unit. The privacy protection unit can automatically anonymize personal information included in the draft statement to protect privacy. For example, the names and addresses of suspects and witnesses can be anonymized and included in the draft statement. The privacy protection unit can also provide a function to protect personal information when sharing the draft statement. For example, it can provide a function to mask specific information when sharing the draft statement. This allows the draft statement to be generated and shared while protecting personal information.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The generative AI model has an affinity with Japanese language and law, enabling processing suited to the Japanese legal system and linguistic characteristics. Step 2: The learning unit learns from representative legal precedents and anonymized past records. For example, the learning unit retrieves past legal precedents from a database and trains the generative AI model. The learning unit also collects anonymized past records and trains the generative AI model. Step 3: The interactive prompt input unit grasps the details of the incident. For example, the interactive prompt input unit collects information entered by the investigator, such as the location and date of the incident and the suspect's behavior. The interactive prompt input unit also allows the investigator to enter questions for the generation AI, which then generates answers to those questions. Step 4: The Charge Prediction Unit predicts an appropriate charge. For example, the generation AI determines an appropriate charge based on the collected information. The Charge Prediction Unit also predicts a charge by taking into account points that prosecutors and judges place importance on in similar cases. Step 5: The report draft generation unit generates the outline of the report draft. For example, the report draft generation unit creates the outline of the report draft based on the crime assumed by the generation AI. The report draft generation unit also generates details of the report draft based on the circumstances of the case and related information.

[0058] (Example 2) The system for generating a statement draft according to an embodiment of the present invention is a system that generates a statement draft while protecting investigative secrets in a high-security domestic environment by using a generation AI model that is compatible with Japanese language and law. As a result, the system for generating a statement draft can efficiently generate a statement draft and reduce the burden on investigators.

[0059] A system for generating a draft statement according to an embodiment includes a generative AI model, a learning unit, an interactive prompt input unit, a charge estimation unit, and a draft statement generation unit. The generative AI model has an affinity with Japanese language and law. The learning unit learns from representative legal precedents and anonymized past statements. For example, the learning unit retrieves past legal precedents from a database and trains the generative AI model. The learning unit also collects anonymized past statements and trains the generative AI model. The interactive prompt input unit grasps the details of the circumstances of the case. For example, the interactive prompt input unit collects information entered by investigators, such as the location and date of the incident and the suspect's behavior. The interactive prompt input unit also allows investigators to input questions to the generative AI, and the generative AI generates answers to those questions. The charge estimation unit estimates an appropriate charge. For example, the charge estimation unit determines an appropriate charge based on the collected information. The charge estimation unit also takes into account points that prosecutors and judges prioritize in similar cases to estimate a charge. The draft report generation unit generates the outline of the draft report. For example, the draft report generation unit creates the outline of the draft report based on the name of the crime assumed by the generation AI. The draft report generation unit also generates the details of the draft report based on the circumstances of the case and related information. This allows the statement draft generation system to efficiently generate draft statement reports using a generative AI model that is compatible with Japanese language and law.

[0060] The learning unit can additionally learn precedents and records specific to a specific region or culture, enabling it to respond to local laws and customs. For example, the learning unit additionally learns precedents and records specific to a specific region (e.g., the Kansai region or the Tohoku region). This makes it possible to generate draft records that correspond to local laws and customs. The learning unit also teaches the generation AI information about local cultures and customs, generating draft records that reflect the characteristics of each region. For example, it generates draft records for incidents related to local festivals and events. The learning unit also learns local crime trends and law enforcement characteristics, allowing the generation AI to generate draft records that correspond to local situations. For example, it generates draft records for crimes that frequently occur in a specific region. This makes it possible to generate draft records that correspond to local laws and customs.

[0061] The learning unit emphasizes and learns keywords and phrases that are considered particularly important in past precedents and transcripts, enabling it to prioritize the extraction of important information. For example, the learning unit emphasizes and learns keywords and phrases that frequently appear in past precedents and transcripts. This allows for the prioritized extraction of important information and improves the accuracy of draft transcripts. The learning unit also develops algorithms for emphasizing important keywords and phrases and incorporates them into the generation AI. For example, important elements such as "alibi" and "eyewitness testimony" are emphasized and learned. The learning unit also adds a function to analyze past precedents and transcripts and automatically extract important information. This allows the generation AI to prioritize learning important information and improve the quality of draft transcripts. This allows for the prioritized extraction of important information and improves the accuracy of draft transcripts.

[0062] The learning unit uses the emotion estimation function to learn the emotional elements contained in past reports and generate a draft report that is easy to empathize with emotionally. For example, the learning unit uses the emotion estimation function to analyze the emotional elements contained in past reports and have the generation AI learn them. This generates a draft report that is easy to empathize with emotionally. The learning unit also develops an algorithm that emphasizes the emotional elements of past reports and incorporates it into the generation AI. For example, emotions such as "sadness" and "anger" are emphasized for learning. The learning unit also uses the emotion estimation function to analyze the emotional elements contained in the draft report and generate a draft report that is easy to empathize with emotionally. For example, a draft report that reflects the emotions of the victim is generated. This makes it possible to generate a draft report that is easy to empathize with emotionally.

[0063] The learning unit can study precedents and records based on other legal systems, enabling the generation of draft records from an international perspective. For example, the learning unit can have the generation AI study precedents and records based on American law or European law, enabling the generation of draft records from an international perspective. This generates draft records that can also be used for international cases. The learning unit can also have the generation AI learn information about the legal systems of other countries, generating draft records that incorporate an international perspective. For example, it can generate draft records related to international crimes. The learning unit can also analyze precedents and records based on international legal systems and have the generation AI learn from them. This generates draft records that are compatible with different legal systems. This makes it possible to generate draft records from an international perspective.

[0064] The learning unit can learn from audio data and video data and generate a draft report based on multimodal information. For example, the learning unit has the generation AI learn from audio data and video data and generate a draft report based on multimodal information. For example, it analyzes the suspect's audio statement and footage of the crime scene and reflects this in the draft report. The learning unit also uses speech recognition technology and video analysis technology to have the generation AI learn from the audio data and video data. This allows for the generation of a draft report that includes more detailed information. For example, it analyzes the suspect's audio statement and footage of the crime scene and reflects this in the draft report. The learning unit also develops an algorithm that integrates multimodal information and incorporates it into the generation AI. This allows for the integration and analysis of audio data and video data to generate a draft report. This makes it possible to generate a draft report based on multimodal information.

[0065] The learning unit uses the emotion estimation function to provide real-time feedback of the user's emotional responses as the generative AI learns, thereby optimizing the learning process. For example, the learning unit uses the emotion estimation function to build a system that provides real-time feedback of the user's emotional responses as the generative AI learns. This optimizes the learning process. The learning unit also analyzes the user's emotional responses in real time and adjusts the generative AI's learning process based on the results. For example, it prioritizes learning data with a high number of positive emotional responses. The learning unit also develops a system that dynamically adjusts the generative AI's learning process based on emotion estimation data. For example, it selects learning data according to changes in the user's emotions. This allows the learning process to be optimized based on the user's emotional responses.

[0066] The interactive prompt input unit can refer to data on similar past cases and generate more specific questions. For example, the interactive prompt input unit adds a function to have the generation AI refer to data on similar past cases and generate specific questions when inputting an interactive prompt. For example, it generates a question such as, "What kind of evidence was considered important in similar past cases?" The interactive prompt input unit also builds a database of similar cases and develops a system in which the generation AI generates specific questions based on that data. For example, it generates a question such as, "What is the important evidence in this case?" The interactive prompt input unit also analyzes data on similar past cases and develops an algorithm that generates specific questions when the generation AI inputs an interactive prompt. For example, it could "generate detailed questions about the suspect's alibi." This makes it possible to generate specific questions based on data on similar past cases.

[0067] The interactive prompt input unit can understand the investigator's intent and generate answers that are in line with that intent. For example, the interactive prompt input unit adds a function to the generation AI that understands the investigator's intent, building a system that generates answers that are in line with that intent. For example, "generate appropriate answers to questions about the evidence sought by the investigator." The interactive prompt input unit also develops an algorithm that analyzes the investigator's intent and incorporates it into the generation AI. This allows answers to be generated that are in line with the investigator's intent. For example, "generate specific answers based on the information sought by the investigator." The interactive prompt input unit also provides the generation AI with learning data to understand the investigator's intent, adding the ability to generate answers that are in line with the investigator's intent. For example, "generate detailed answers about the evidence sought by the investigator." This allows answers to be generated that are in line with the investigator's intent.

[0068] The interactive prompt input unit can use the emotion estimation function to estimate the emotions of an investigator during a dialogue and generate appropriate questions and answers based on those emotions. For example, the interactive prompt input unit uses the emotion estimation function to estimate the emotions of an investigator during a dialogue in real time and builds a system that generates appropriate questions and answers based on those emotions. For example, if an investigator is feeling stressed, it generates questions that will relax the investigator. The interactive prompt input unit also develops an algorithm that analyzes the investigator's emotions and incorporates it into the generation AI. This generates appropriate questions and answers based on the investigator's emotions. For example, if the investigator is anxious, it generates questions that will help the investigator respond calmly. The interactive prompt input unit also develops a system that generates questions and answers based on the emotion estimation data based on the investigator's emotions during a dialogue. For example, if the investigator is tired, it generates concise questions and answers. This makes it possible to generate appropriate questions and answers based on the investigator's emotions.

[0069] The interactive prompt input unit can accept input in different languages ​​and achieve multilingual support using a translation function. For example, the interactive prompt input unit adds a function to accept input in different languages ​​to the generation AI and uses the translation function to build a system that achieves multilingual support. For example, it accepts input in English or Chinese and translates it into Japanese for processing. The interactive prompt input unit also develops a multilingual translation algorithm and incorporates it into the generation AI. This allows input in different languages ​​to be translated in real time and an appropriate answer to be generated. For example, input in French is translated into Japanese for processing. The interactive prompt input unit also develops an interface that accepts input in different languages ​​and incorporates it into the generation AI. This allows multilingual support to be achieved and input in different languages ​​is translated and processed. For example, input in Spanish is translated into Japanese for processing. This allows multilingual support to be achieved.

[0070] The interactive prompt input unit can add a function to accept voice input or gesture input, enabling more intuitive operation. The interactive prompt input unit, for example, adds a function to accept voice input or gesture input to the generation AI, building a system that enables more intuitive operation. For example, it accepts voice question input or gesture operation. The interactive prompt input unit also uses voice recognition technology or gesture recognition technology to add a function to accept voice input or gesture input to the generation AI. This enables more intuitive operation. For example, it accepts voice question input or gesture operation. The interactive prompt input unit also develops an interface that accepts voice input or gesture input and incorporates it into the generation AI. This enables more intuitive operation. For example, it accepts voice question input or gesture operation. This enables more intuitive operation.

[0071] The interactive prompt input unit can use an emotion estimation function to monitor the user's emotions during a conversation in real time and provide feedback according to the emotions. The interactive prompt input unit, for example, uses the emotion estimation function to monitor the user's emotions during a conversation in real time and build a system that provides feedback according to those emotions. For example, if the user is feeling anxious, it provides reassuring feedback. The interactive prompt input unit also develops an algorithm that analyzes the user's emotions and incorporates it into the generation AI. This provides feedback according to the emotions. For example, if the user is feeling stressed, it provides relaxing feedback. The interactive prompt input unit also develops a system that provides feedback according to the user's emotions during a conversation based on the emotion estimation data. For example, if the user is tired, it provides brief feedback. This makes it possible to provide feedback according to the user's emotions.

[0072] The charge prediction unit learns by emphasizing elements that are considered particularly important in past court cases and reports, enabling it to prioritize the extraction of important information. For example, the charge prediction unit has the generation AI learn by emphasizing important elements that frequently appear in past court cases and reports. This allows it to prioritize the extraction of important information and improve the accuracy of draft reports. The charge prediction unit also develops algorithms to emphasize important elements and incorporates them into the generation AI. For example, it has the AI ​​learn by emphasizing important elements such as "alibis" and "eyewitness testimony." The charge prediction unit also adds a function to analyze past court cases and reports and automatically extract important information. This allows the generation AI to prioritize learning important information and improve the quality of draft reports. This allows it to prioritize the extraction of important information and improve the accuracy of draft reports.

[0073] The crime assumption unit can simultaneously assume multiple crimes depending on the circumstances of the case and generate the outline of a draft report for each crime. For example, the crime assumption unit adds a function to the generation AI that simultaneously assumes multiple crimes depending on the circumstances of the case and generates the outline of a draft report for each crime. For example, it assumes both theft and fraud and generates a draft report for each. The crime assumption unit also develops an algorithm that simultaneously assumes multiple crimes and incorporates it into the generation AI. This allows it to generate multiple draft reports depending on the circumstances of the case. For example, it assumes both assault and assault and generates a draft report for each. The crime assumption unit also adds a function that analyzes the circumstances of the case and simultaneously assumes multiple crimes. This allows the generation AI to generate multiple draft reports depending on the circumstances of the case. For example, it assumes both robbery and theft and generates a draft report for each. This allows it to generate multiple draft reports depending on the circumstances of the case.

[0074] The charge estimation unit can use the emotion estimation function to analyze emotional elements included in the outline of a draft report and generate a draft report that is easy to empathize with emotionally. The charge estimation unit, for example, uses the emotion estimation function to analyze emotional elements included in the outline of a draft report and build a system that generates a draft report that is easy to empathize with emotionally. For example, a draft report that reflects the victim's emotions is generated. The charge estimation unit also develops an algorithm for emphasizing emotional elements in a draft report and incorporates it into the generation AI. This generates a draft report that is easy to empathize with emotionally. For example, a draft report that reflects the victim's sadness and anger is generated. The charge estimation unit also develops a system based on the emotion estimation data to analyze emotional elements in a draft report and generate a draft report that is easy to empathize with emotionally. For example, a draft report that reflects the victim's emotions is generated. This allows for the generation of a draft report that is easy to empathize with emotionally.

[0075] The charge assumption unit can assume charges based on different legal systems and generate the outline of a draft report that corresponds to each legal system. For example, the charge assumption unit adds a function to the generation AI that assumes charges based on different legal systems (e.g., American law or European law) and generates the outline of a draft report that corresponds to each legal system. This allows for the generation of draft reports that can also be handled internationally. The charge assumption unit also develops an algorithm that assumes charges based on different legal systems and incorporates it into the generation AI. This allows for the generation of draft reports that correspond to different legal systems. For example, it assumes charges based on American law and generates a draft report that corresponds to that. The charge assumption unit also has the generation AI learn information about different legal systems and adds a function that generates a draft report that corresponds to that different legal system. This allows for the generation of draft reports that incorporate an international perspective. For example, it assumes charges based on European law and generates a draft report that corresponds to that. This allows for the generation of draft reports that correspond to different legal systems.

[0076] The charge estimation unit can grasp the circumstances of a case in detail based on audio and video data and generate the outline of a draft report. For example, the charge estimation unit adds the function of having the generation AI learn audio and video data to grasp the circumstances of a case in detail and generate the outline of a draft report. For example, it analyzes the suspect's audio statement and video footage of the crime scene and reflects this in the draft report. The charge estimation unit also uses voice recognition and video analysis technology to have the generation AI learn audio and video data. This generates a draft report with more detailed information. For example, it analyzes the suspect's audio statement and video footage of the crime scene and reflects this in the draft report. The charge estimation unit also develops an algorithm that integrates multimodal information and incorporates it into the generation AI. This allows it to integrate and analyze audio and video data and generate a draft report. For example, it analyzes the suspect's audio statement and video footage of the crime scene and reflects this in the draft report. This allows it to grasp the circumstances of a case in detail and generate the outline of a draft report.

[0077] The charge name assumption unit can use the emotion estimation function to monitor the user's emotional reaction to the outline of the draft report in real time, and generate an optimal draft report in accordance with the emotion. The charge name assumption unit, for example, uses the emotion estimation function to monitor the user's emotional reaction to the outline of the draft report in real time, and builds a system that generates an optimal draft report in accordance with the emotion. For example, a draft report that the user can easily empathize with is generated. The charge name assumption unit also develops an algorithm that analyzes the user's emotional reaction in real time and adjusts the outline of the draft report based on the results. This generates an optimal draft report in accordance with the emotion. For example, a draft report that the user can easily empathize with is generated. The charge name assumption unit also develops a system that dynamically adjusts the outline of the draft report based on the emotion estimation data. This generates an optimal draft report in accordance with the user's emotion. For example, a draft report that the user can easily empathize with is generated. This makes it possible to generate an optimal draft report in accordance with the user's emotion.

[0078] The latest security protocols can be introduced into the operating environment of the generative AI to strengthen data encryption and access control. For example, the latest security protocols can be introduced into the operating environment of the generative AI to strengthen data encryption and access control. For example, encryption protocols such as TLS and SSL can be used. Also, algorithms for strengthening security protocols can be developed in the operating environment of the generative AI and incorporated into the operating environment of the generative AI. This strengthens data encryption and access control. For example, encryption algorithms such as AES and RSA can be used. Also, security protocols for strengthening data encryption and access control can be introduced in the operating environment of the generative AI. This minimizes the risk of unauthorized access from outside and information leaks. For example, a VPN or firewall can be used. This strengthens data encryption and access control and improves security.

[0079] Regular security audits can be conducted in the operating environment of the generative AI, and a system can be established to detect and address security risks early. In the operating environment of the generative AI, for example, regular security audits can be conducted and a system can be established to detect and address security risks early. For example, security audits can be conducted monthly or quarterly. In addition, protocols for conducting security audits in the operating environment of the generative AI can be developed and incorporated into the operating environment of the generative AI. This will enable early detection and addressing of security risks. For example, vulnerability scans and penetration tests can be conducted. In addition, an audit system can be established in the operating environment of the generative AI to detect and address security risks early. This will minimize security risks. For example, a security incident response team can be established. This will enable early detection and addressing of security risks.

[0080] The emotion estimation function can be used to monitor a user's emotions in a security environment and provide feedback to reduce stress and anxiety. Using the emotion estimation function, for example, we will build a system that monitors a user's emotions in a security environment in real time and provides feedback to reduce stress and anxiety. For example, if a user is feeling anxious, we will provide reassuring feedback. We will also use the emotion estimation function to develop an algorithm that analyzes a user's emotions and incorporate it into the generative AI. This will provide feedback that corresponds to the emotion. For example, if a user is feeling stressed, we will provide relaxing feedback. We will also develop a system that provides feedback that corresponds to a user's emotions in a security environment based on the emotion estimation data. For example, if a user is tired, we will provide brief feedback. This will allow us to provide feedback to reduce the user's stress and anxiety.

[0081] It is possible to provide environments with different security levels, allowing the optimum security environment to be selected depending on the application. For example, in the operating environment of the generative AI, environments with different security levels can be provided, and a system can be built that allows the optimum security environment to be selected depending on the application. For example, the highest level of security environment can be provided for highly confidential data. In addition, an interface for selecting the security level can be developed and incorporated into the operating environment of the generative AI. This allows the optimum security environment to be selected depending on the application. For example, the user selects the security level. In addition, environments with different security levels can be provided, and a system can be developed that automatically selects the optimum security environment depending on the application. For example, the security level can be automatically set depending on the confidentiality of the data. This allows the optimum security environment to be selected depending on the application.

[0082] By introducing physical security measures, the risk of information leakage can be minimized. For example, physical security measures can be introduced in the operating environment of the generative AI to minimize the risk of information leakage. For example, a biometric authentication system can be introduced to strengthen access control. Physical security measures such as surveillance cameras and security gates can also be introduced to protect the operating environment of the generative AI. This minimizes the risk of information leakage. For example, surveillance cameras can be installed and monitored 24 hours a day. Protocols for strengthening physical security measures can also be developed and incorporated into the operating environment of the generative AI. This minimizes the risk of information leakage. For example, biometric authentication systems and surveillance cameras can be linked. This minimizes the risk of information leakage.

[0083] The emotion estimation function can be used to monitor a user's emotions in a security environment in real time and suggest security measures according to their emotions. Using the emotion estimation function, for example, we will build a system that monitors a user's emotions in a security environment in real time and suggests security measures according to those emotions. For example, if a user is feeling anxious, additional security measures will be suggested. We will also use the emotion estimation function to develop an algorithm that analyzes user emotions and incorporate it into the generative AI. This will allow us to suggest security measures according to their emotions. For example, if a user is feeling stressed, we will suggest security measures that will relax them. We will also develop a system that uses the emotion estimation data to suggest security measures according to a user's emotions in a security environment. For example, if a user is tired, we will suggest simple security measures. This will allow us to suggest security measures according to the user's emotions.

[0084] Based on the outline of a draft report generated by the generation AI, templates and guidelines can be provided to enable investigators to create reports efficiently. For example, a system can be built that provides templates and guidelines to enable investigators to create reports efficiently based on the outline of a draft report generated by the generation AI. For example, guidelines can be provided that show the procedures and points to note when creating a report. In addition, a template for creating a report can be developed, and a system can be built that automatically generates templates based on the outline of a draft report generated by the generation AI. This allows investigators to create reports efficiently. For example, report formats and items can be automatically generated. In addition, a system can be developed that provides guidelines to enable investigators to create reports efficiently based on the outline of a draft report generated by the generation AI. For example, guidelines can be provided that show points to pay attention to and important elements when creating a report. This allows investigators to create reports efficiently.

[0085] Based on the outline of a draft report generated by the generative AI, links to relevant databases and materials can be provided to enable investigators to quickly gather the information they need. Based on the outline of a draft report generated by the generative AI, for example, a system will be built that provides links to relevant databases and materials so that investigators can quickly gather the information they need. For example, links to relevant precedents and legal documents will be provided. In addition, an algorithm will be developed that automatically generates links to databases and materials and incorporated into the generative AI. This will allow investigators to quickly gather the information they need. For example, links to relevant precedents and legal documents will be automatically generated. In addition, based on the outline of a draft report generated by the generative AI, a system will be developed that provides links to relevant databases and materials so that investigators can quickly gather the information they need. For example, links to relevant precedents and legal documents will be provided. This will allow investigators to quickly gather the information they need.

[0086] The emotion estimation function can be used to monitor the emotions of investigators while they are writing reports and provide feedback to reduce stress and fatigue. Using the emotion estimation function, for example, we will build a system that monitors the emotions of investigators while they are writing reports in real time and provides feedback to reduce stress and fatigue. For example, if an investigator is tired, feedback is provided encouraging them to take a break. We will also use the emotion estimation function to develop an algorithm that analyzes investigators' emotions and incorporate it into the generative AI. This will provide feedback based on the emotions. For example, if an investigator is feeling stressed, feedback to help them relax is provided. We will also develop a system that provides feedback based on the emotion estimation data based on the emotions of investigators while they are writing reports. For example, if an investigator is tired, brief feedback is provided. This will allow us to provide feedback to reduce the investigator's stress and fatigue.

[0087] Based on the outline of a draft report generated by the generation AI, it is possible to simultaneously create reports that correspond to different legal systems. A function will be added to simultaneously create reports that correspond to different legal systems (for example, American law and European law) based on the outline of a draft report generated by the generation AI. This will allow reports to be created that can also be used in international cases. In addition, the generation AI will develop an algorithm that simultaneously creates reports that correspond to different legal systems and incorporate it into the generation AI. This will allow reports that correspond to different legal systems to be simultaneously created. For example, reports that correspond to American law and European law will be simultaneously created. In addition, the generation AI will learn information about different legal systems and add a function to simultaneously create reports that correspond to different legal systems. This will allow reports that incorporate an international perspective. For example, reports that correspond to American law and European law will be simultaneously created. This will allow reports that correspond to different legal systems to be simultaneously created.

[0088] Based on the outline of a draft report generated by the generation AI, it is possible to create a report more intuitively using voice input or gesture input. Based on the outline of a draft report generated by the generation AI, a function is added to create a report more intuitively using voice input or gesture input, for example. For example, voice question input or gesture operation is accepted. In addition, the generation AI adds a function to accept voice input or gesture input using voice recognition technology or gesture recognition technology. This makes it possible to create a report more intuitively. For example, voice question input or gesture operation is accepted. In addition, the generation AI develops an interface that accepts voice input or gesture input and incorporates it into the generation AI. This makes it possible to create a report more intuitively. For example, voice question input or gesture operation is accepted. This makes it possible to create a report more intuitively.

[0089] Using the emotion estimation function, it is possible to monitor the user's emotions while creating a report in real time and propose the optimal report creation method based on that emotion. Using the emotion estimation function, for example, we will build a system that monitors the user's emotions while creating a report in real time and proposes the optimal report creation method based on that emotion. For example, if the user is feeling anxious, we will propose a report creation method that reassures them. We will also use the emotion estimation function to develop an algorithm that analyzes the user's emotions and incorporate it into the generative AI. This will propose the optimal report creation method based on the user's emotions. For example, if the user is feeling stressed, we will propose a report creation method that relaxes them. We will also develop a system that uses emotion estimation data to propose the optimal report creation method based on the user's emotions while creating a report. For example, if the user is tired, we will propose a simple report creation method. This will make it possible to propose the optimal report creation method based on the user's emotions.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The statement draft generation system can further include a speech recognition unit. The speech recognition unit can convert the investigator's dictation into text in real time and input it into the interactive prompt input unit. For example, when an investigator dictates the details of a case, the content can be automatically converted into text and input into the generative AI model. The speech recognition unit can also accept the investigator's instructions via voice and perform appropriate operations. For example, it can accept voice instructions such as "proceed to the next question" or "return to the previous question." This allows the investigator to operate the system without using their hands, making it possible to generate a statement draft efficiently.

[0092] The statement draft generation system can further include an image analysis unit. The image analysis unit can analyze photos and videos of the crime scene, extract important information, and reflect it in the draft report. For example, it can analyze the location and condition of evidence from photos of the crime scene and record it in the draft report. The image analysis unit can also perform facial recognition of suspects and witnesses and add related information to the draft report. For example, it can analyze a photo of a suspect's face and reflect their past criminal history and related information in the draft report. This makes it possible to generate a detailed draft report based on visual information.

[0093] The statement draft generation system can further include a data integration unit. The data integration unit can collect information from multiple data sources, integrate it, and reflect it in the draft statement. For example, it can collect information from police databases and public databases and provide it to the generative AI model. The data integration unit can also integrate data in different formats to provide consistent information. For example, it can integrate text data, audio data, and image data and reflect it in the draft statement. This makes it possible to generate a comprehensive draft statement that integrates information from multiple data sources.

[0094] The statement draft generation system can further include a real-time translation unit. The real-time translation unit can translate inputs in different languages ​​in real time and provide them to the generative AI model. For example, the real-time translation unit can translate statements from foreign suspects or witnesses in real time and reflect them in the draft statement. In addition, when investigators ask questions in a different language, the real-time translation unit can translate those questions in real time and convey them to the suspect or witness. This allows for efficient generation of draft statements across language barriers.

[0095] The system for generating a draft statement can further include a privacy protection unit. The privacy protection unit can automatically anonymize personal information included in the draft statement to protect privacy. For example, the names and addresses of suspects and witnesses can be anonymized and included in the draft statement. The privacy protection unit can also provide a function to protect personal information when sharing the draft statement. For example, it can provide a function to mask specific information when sharing the draft statement. This allows the draft statement to be generated and shared while protecting personal information.

[0096] The statement draft generation system can further use an emotion estimation function to estimate the emotions of suspects and witnesses and generate a draft statement based on those emotions. For example, if a suspect is feeling fear, the system can generate a draft statement that reflects those emotions. The emotion estimation function can also be used to analyze the emotions of witnesses and adjust the draft statement based on those emotions. For example, if a witness is feeling sad, the system can generate a draft statement that reflects those emotions. This makes it possible to generate a draft statement that is easy to empathize with emotionally.

[0097] The statement draft generation system can also use an emotion estimation function to monitor the investigator's emotions in real time and provide feedback according to those emotions. For example, if the investigator is feeling stressed, feedback to help them relax can be provided. The emotion estimation function can also be used to analyze the investigator's emotions and adjust the statement draft generation process based on those emotions. For example, if the investigator is feeling anxious, feedback to help them respond calmly can be provided. This makes it possible to support the generation of optimal statement drafts according to the investigator's emotions.

[0098] The statement draft generation system can further use an emotion estimation function to evaluate the emotional impact of the contents of the draft statement on victims and witnesses and make adjustments to minimize that impact. For example, if the contents of the draft statement cause excessive stress to the victim, the content can be adjusted. Also, if the contents of the draft statement cause anxiety to witnesses, the emotion estimation function can be used to adjust the content. This makes it possible to minimize the emotional impact of the contents of the draft statement on those involved.

[0099] The statement draft generation system can further use emotion estimation to evaluate the emotional impact of the contents of the draft statement on judges and prosecutors, and adjust the draft statement taking that impact into account. For example, if the contents of the draft statement cause excessive prejudice toward the judge, the system can adjust the contents. Also, if the contents of the draft statement cause inappropriate emotions toward the prosecutor, the system can adjust the contents. This minimizes the emotional impact of the contents of the draft statement on legal parties.

[0100] The statement draft generation system can further use an emotion estimation function to evaluate the emotional impact that the contents of the draft statement will have on the suspect and adjust the draft statement taking that impact into account. For example, if the contents of the draft statement cause excessive fear in the suspect, the contents can be adjusted. Also, if the contents of the draft statement cause inappropriate emotions in the suspect, the emotion estimation function can be used to adjust the contents. This makes it possible to minimize the emotional impact that the contents of the draft statement have on the suspect.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The generative AI model has an affinity with Japanese language and law, enabling processing suited to the Japanese legal system and linguistic characteristics. Step 2: The learning unit learns from representative legal precedents and anonymized past records. For example, the learning unit retrieves past legal precedents from a database and trains the generative AI model. The learning unit also collects anonymized past records and trains the generative AI model. Step 3: The interactive prompt input unit grasps the details of the incident. For example, the interactive prompt input unit collects information entered by the investigator, such as the location and date of the incident and the suspect's behavior. The interactive prompt input unit also allows the investigator to enter questions for the generation AI, which then generates answers to those questions. Step 4: The Charge Prediction Unit predicts an appropriate charge. For example, the generation AI determines an appropriate charge based on the collected information. The Charge Prediction Unit also predicts a charge by taking into account points that prosecutors and judges place importance on in similar cases. Step 5: The report draft generation unit generates the outline of the report draft. For example, the report draft generation unit creates the outline of the report draft based on the crime assumed by the generation AI. The report draft generation unit also generates details of the report draft based on the circumstances of the case and related information.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] 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.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] 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.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] 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.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] 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.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A generative AI model with affinity to Japanese language and law, The study department studies representative legal precedents and anonymized past records, An interactive prompt input section that grasps the details of the incident situation, a crime name prediction unit that predicts an appropriate crime name; a report draft generation unit that generates the outline of a report draft; A system characterized by:

2. The learning unit Additional study of case law and records specific to a particular region or culture to enable you to respond to local laws and customs 2. The system of claim 1.

3. The learning unit Emphasizes and learns particularly important keywords and phrases from past precedents and records, and prioritizes the extraction of important information 2. The system of claim 1.

4. The learning unit Learns emotional elements contained in past transcripts and generates transcripts that are likely to resonate emotionally 2. The system of claim 1.

5. The learning unit It learns from precedents and transcripts from other legal systems, enabling the generation of transcripts from an international perspective.

2. The system of claim 1.

6. The learning unit It also learns from audio or video data and generates draft transcripts based on multimodal information.

2. The system of claim 1.

7. The learning unit As the generative AI learns, it receives real-time feedback from the user's emotional reactions to optimize the learning process.

2. The system of claim 1.

8. The interactive prompt input unit includes: Referencing data on similar past cases to generate more specific questions 2. The system of claim 1.

Images