system

Abstract

The system according to the embodiment aims to efficiently and accurately perform risk analysis and verdict prediction in civil trials. [Solution] A system according to an embodiment includes a risk analysis unit, an evidence analysis unit, a verdict analysis unit, and a simulation provision unit. The risk analysis unit identifies risks. The evidence analysis unit evaluates evidence based on the risks identified by the risk analysis unit. The verdict analysis unit predicts a verdict based on the evidence evaluated by the evidence analysis unit. The simulation provision unit provides a simulation based on the verdict outcome predicted by the verdict analysis unit.

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, risk analysis and verdict prediction in civil trials relied on human labor, making it difficult to make efficient and accurate predictions.

[0005] The system according to the embodiment aims to efficiently and accurately perform risk analysis and verdict prediction in civil trials. [Means for solving the problem]

[0006] The system according to the embodiment includes a risk analysis unit, an evidence analysis unit, a verdict analysis unit, and a simulation provision unit. The risk analysis unit identifies risks. The evidence analysis unit evaluates evidence based on the risks identified by the risk analysis unit. The verdict analysis unit predicts a verdict based on the evidence evaluated by the evidence analysis unit. The simulation provision unit provides a simulation based on the verdict outcome predicted by the verdict analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently and accurately perform risk analysis and verdict prediction in civil trials. [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) A risk analysis system according to an embodiment of the present invention provides simulations based on risk analysis, evidence analysis, and judgment analysis in civil trials. This risk analysis system uses a generation AI to perform risk analysis, evidence analysis, and judgment analysis for patent disputes, damage claims, accident responses, and other cases, and provides simulations based on the results. Targeting corporate legal and general affairs departments and individual business owners, the system supports both Japanese and international law (e.g., U.S., EU). The generation AI processes each element, making it unique in its ability to support international law and multiple languages. By providing simulations, users can predict the outcome of trials and develop appropriate countermeasures. For example, the risk analysis system includes a risk analysis unit that identifies risks in patent disputes, damage claims, accident responses, and other cases. Next, the system includes an evidence analysis unit that evaluates evidence based on the risks identified by the risk analysis unit. Furthermore, the system includes a judgment analysis unit that predicts a judgment based on the evidence evaluated by the evidence analysis unit. Finally, the system includes a simulation provider that provides simulations based on the judgment outcome predicted by the judgment analysis unit. This system targets corporate legal and general affairs departments and individual business owners, and supports both Japanese and international law (e.g., U.S., EU). Its unique feature is that the generative AI processes each element and is capable of supporting international law and multiple languages. By providing simulations, users can predict the outcome of trials and develop appropriate countermeasures. Regarding feasibility, it is necessary to refer to academic literature and the research of prominent experts regarding the logic. This allows the risk analysis system to provide simulations based on risk analysis, evidence analysis, and judgment analysis in civil trials.

[0029] A risk analysis system according to an embodiment includes a risk analysis unit, an evidence analysis unit, a judgment analysis unit, and a simulation providing unit. The risk analysis unit identifies risks in patent disputes, damage claims, accident responses, and the like. For example, in patent disputes, the risk analysis unit identifies the risk of patent infringement. In damage claims, the risk analysis unit can also identify the risk of damages due to contract breach. In accident responses, the risk analysis unit can also identify the risk of work-related accidents. The evidence analysis unit evaluates evidence based on the risks identified by the risk analysis unit. For example, in patent disputes, the evidence analysis unit evaluates patent documents and technical documents. In damage claims, the evidence analysis unit can also evaluate contracts and transaction records. In accident responses, the evidence analysis unit can also evaluate accident reports and witness testimony. The judgment analysis unit predicts a judgment based on the evidence evaluated by the evidence analysis unit. For example, in patent disputes, the judgment analysis unit predicts a judgment based on past case law data. In damage claims, the judgment analysis unit can also predict a judgment based on past case law data. Furthermore, the judgment analysis unit can predict a judgment based on past case data when responding to an accident. The simulation providing unit provides a simulation based on the judgment result predicted by the judgment analysis unit. For example, in a patent dispute, the simulation providing unit simulates the risk of patent infringement based on the judgment result. Furthermore, in a claim for damages, the simulation providing unit can simulate the risk of compensation for damages based on the judgment result. Furthermore, in an accident response, the simulation providing unit can simulate the risk of an industrial accident based on the judgment result. As a result, the risk analysis system according to the embodiment performs risk analysis, evidence analysis, judgment prediction, and simulation provision in a continuous flow.

[0030] The risk analysis unit can identify risks of patent disputes, claims for damages, and accident response. For example, in patent disputes, the risk analysis unit identifies the risk of patent infringement. For example, the risk analysis unit analyzes patent documents and technical documents to evaluate the possibility of patent infringement. The risk analysis unit can also identify the risk of compensation for damages due to breach of contract in claims for damages. For example, the risk analysis unit analyzes contracts and transaction records to evaluate the possibility of contract breach. The risk analysis unit can also identify the risk of work-related accidents in accident response. For example, the risk analysis unit analyzes accident reports and witness testimony to evaluate the possibility of work-related accidents. This enables detailed analysis of specific risks.

[0031] The evidence analysis unit can evaluate evidence based on the risks identified by the risk analysis unit. For example, in a patent dispute, the evidence analysis unit evaluates patent documents and technical documents. For example, the evidence analysis unit analyzes the contents of patent documents to evaluate evidence of patent infringement. The evidence analysis unit can also evaluate contracts and transaction records in a claim for damages. For example, the evidence analysis unit analyzes the contents of a contract to evaluate evidence of a breach of contract. The evidence analysis unit can also evaluate accident reports and witness testimony in an accident response. For example, the evidence analysis unit analyzes the contents of an accident report to evaluate evidence of a work-related accident. This enables risk-based evidence evaluation.

[0032] The judgment analysis unit can predict a judgment based on the evidence evaluated by the evidence analysis unit. For example, in patent disputes, the judgment analysis unit predicts a judgment based on past case data. For example, the judgment analysis unit analyzes past case data related to patent infringement and predicts a judgment. The judgment analysis unit can also predict a judgment based on past case data in claims for damages. For example, the judgment analysis unit analyzes past case data related to breach of contract and predicts a judgment. The judgment analysis unit can also predict a judgment based on past case data in accident response. For example, the judgment analysis unit analyzes past case data related to work-related accidents and predicts a judgment. This makes it possible to predict a judgment based on evidence.

[0033] The simulation providing unit can provide a simulation based on the judgment outcome predicted by the judgment analysis unit. For example, in a patent dispute, the simulation providing unit simulates the risk of patent infringement based on the judgment outcome. For example, the simulation providing unit evaluates the risk of patent infringement and simulates the impact if patent infringement occurs. The simulation providing unit can also simulate the risk of compensation for damages based on the judgment outcome in a claim for damages. For example, the simulation providing unit evaluates the risk of compensation for damages and simulates the impact if compensation for damages occurs. The simulation providing unit can also simulate the risk of work-related accidents based on the judgment outcome in accident response. For example, the simulation providing unit evaluates the risk of work-related accidents and simulates the impact if a work-related accident occurs. This makes it possible to provide simulations based on the judgment prediction results.

[0034] The simulation providing unit can provide the user with the simulation results. For example, in a patent dispute, the simulation providing unit simulates the risk of patent infringement and provides the result to the user. For example, the simulation providing unit evaluates the risk of patent infringement, simulates the impact of patent infringement if it occurs, and provides the result to the user. The simulation providing unit can also simulate the risk of compensation for damages in a claim for damages and provide the result to the user. For example, the simulation providing unit evaluates the risk of compensation for damages, simulates the impact of compensation for damages if it occurs, and provides the result to the user. The simulation providing unit can also simulate the risk of a work-related accident in an accident response and provide the result to the user. For example, the simulation providing unit evaluates the risk of a work-related accident, simulates the impact of a work-related accident if it occurs, and provides the result to the user. In this way, by providing the simulation results to the user, it is possible to predict the outcome of a trial and develop appropriate countermeasures.

[0035] The risk analysis unit can analyze past court case data and extract specific risk patterns. For example, the generation AI analyzes past patent dispute data and extracts specific risk patterns. For example, the risk analysis unit analyzes past data on patent infringement and extracts specific risk patterns. The risk analysis unit can also analyze past damages claim data and extract specific risk patterns. For example, the risk analysis unit analyzes past data on contract breaches and extracts specific risk patterns. The risk analysis unit can also analyze past accident response data and extract specific risk patterns. For example, the risk analysis unit analyzes past data on work-related accidents and extracts specific risk patterns. This makes it possible to extract risk patterns based on past court case data.

[0036] The risk analysis unit can automatically refer to relevant legal literature and precedents when identifying risks. For example, the risk analysis unit automatically refers to relevant Japanese legal literature when the generation AI identifies risks. For example, the risk analysis unit analyzes Japanese legal literature to collect information necessary for risk identification. The risk analysis unit can also automatically refer to relevant U.S. legal precedents when the generation AI identifies risks. For example, the risk analysis unit analyzes U.S. legal precedent data to collect information necessary for risk identification. The risk analysis unit can also automatically refer to relevant EU legal literature when the generation AI identifies risks. For example, the risk analysis unit analyzes EU legal literature to collect information necessary for risk identification. This automatically refers to relevant legal literature and precedents, improving the accuracy of risk identification.

[0037] The risk analysis unit can perform an analysis taking into account risks specific to the user's industry when identifying risks. For example, when the generation AI identifies risks, the risk analysis unit performs an analysis taking into account industry-specific risks for a user in the manufacturing industry. For example, the risk analysis unit identifies the risk of patent infringement in the manufacturing industry and performs an analysis taking into account industry-specific risks. The risk analysis unit can also perform an analysis taking into account industry-specific risks for a user in the IT industry when identifying risks. For example, the risk analysis unit identifies the risk of data leakage in the IT industry and performs an analysis taking into account industry-specific risks. The risk analysis unit can also perform an analysis taking into account industry-specific risks for a user in the medical industry when identifying risks. For example, the risk analysis unit identifies the risk of medical malpractice in the medical industry and performs an analysis taking into account industry-specific risks. This enables an analysis taking into account risks specific to the user's industry.

[0038] The risk analysis unit can evaluate risks taking into account the user's geographical legal environment when identifying risks. For example, the risk analysis unit evaluates risks taking into account the Japanese legal environment when the generation AI identifies risks. For example, the risk analysis unit analyzes Japanese laws and regulations and collects information necessary for risk identification. The risk analysis unit can also evaluate risks taking into account the U.S. legal environment when the generation AI identifies risks. For example, the risk analysis unit analyzes U.S. laws and regulations and collects information necessary for risk identification. The risk analysis unit can also evaluate risks taking into account the EU legal environment when the generation AI identifies risks. For example, the risk analysis unit analyzes EU laws and regulations and collects information necessary for risk identification. This enables risk evaluation taking into account the user's geographical legal environment.

[0039] The evidence analysis unit can automatically score the reliability and relevance of evidence when evaluating the evidence. For example, the evidence analysis unit scores the reliability of evidence when the generation AI evaluates the evidence. For example, the evidence analysis unit evaluates and scores the reliability of patent documents. The evidence analysis unit can also score the relevance of evidence when the generation AI evaluates the evidence. For example, the evidence analysis unit evaluates and scores the relevance of contracts. The evidence analysis unit can also comprehensively score the reliability and relevance of evidence when the generation AI evaluates the evidence. For example, the evidence analysis unit evaluates and scores the reliability and relevance of accident reports. This automatically scores the reliability and relevance of evidence, improving the accuracy of evidence evaluation.

[0040] The evidence analysis unit can take into account the background information of the evidence submitter when evaluating evidence. For example, the evidence analysis unit can take into account the professional background of the evidence submitter when the generation AI evaluates evidence. For example, the evidence analysis unit evaluates the professional background of the patent document submitter to determine the reliability of the evidence. The evidence analysis unit can also take into account the past reliability of the evidence submitter when the generation AI evaluates evidence. For example, the evidence analysis unit can evaluate the past reliability of the contract submitter to determine the reliability of the evidence. The evidence analysis unit can also take into account the expertise of the evidence submitter when the generation AI evaluates evidence. For example, the evidence analysis unit can evaluate the expertise of the accident report submitter to determine the reliability of the evidence. This makes it possible to perform an evaluation that takes into account the background information of the evidence submitter.

[0041] The evidence analysis unit can make an evaluation taking into account the timing and method of evidence submission when evaluating evidence. For example, when the generation AI evaluates evidence, the evidence analysis unit makes an evaluation taking into account the timing of evidence submission. For example, the evidence analysis unit evaluates the timing of patent document submission and determines the reliability of the evidence. The evidence analysis unit can also make an evaluation taking into account the method of evidence submission when the generation AI evaluates evidence. For example, the evidence analysis unit evaluates the method of contract submission and determines the reliability of the evidence. The evidence analysis unit can also make an evaluation taking into account the timing and method of evidence submission when the generation AI evaluates evidence. For example, the evidence analysis unit evaluates the timing and method of accident report submission and determines the reliability of the evidence. This makes it possible to make an evaluation taking into account the timing and method of evidence submission.

[0042] The evidence analysis unit can compare evidence with evidence from other related trials when evaluating the evidence. For example, when the generation AI evaluates evidence, the evidence analysis unit compares it with evidence from other related patent disputes and evaluates it. For example, the evidence analysis unit compares the contents of patent documents with evidence from other patent disputes and evaluates it. The evidence analysis unit can also compare the contents of contracts with evidence from other claims for damages and evaluate it. The evidence analysis unit can also compare the contents of accident reports with evidence from other related accident responses and evaluate it. For example, the evidence analysis unit compares the contents of accident reports with evidence from other accident responses and evaluates it. This makes it possible to evaluate evidence in comparison with evidence from other related trials.

[0043] The judgment analysis unit can improve the accuracy of the prediction when predicting a verdict by referring to past judgment data. For example, when the generation AI predicts a verdict, the judgment analysis unit improves the accuracy of the prediction by referring to judgment data on past patent disputes. For example, the judgment analysis unit analyzes past judgment data on patent infringement to improve the accuracy of the prediction. The judgment analysis unit can also improve the accuracy of the prediction when the generation AI predicts a verdict by referring to past judgment data on claims for damages. For example, the judgment analysis unit analyzes past judgment data on breach of contract to improve the accuracy of the prediction. The judgment analysis unit can also improve the accuracy of the prediction when the generation AI predicts a verdict by referring to judgment data on past accident responses. For example, the judgment analysis unit analyzes past judgment data on work-related accidents to improve the accuracy of the prediction. In this way, by referring to past judgment data, the accuracy of the prediction is improved.

[0044] The judgment analysis unit can take into account a judge's past judgment trends when predicting a verdict. For example, when the generation AI predicts a verdict, the judgment analysis unit takes into account a specific judge's past judgment trends when making a prediction. For example, the judgment analysis unit analyzes a specific judge's past judgment trends in patent disputes and makes a prediction. The judgment analysis unit can also take into account the past judgment trends of multiple judges when predicting a verdict. For example, the judgment analysis unit analyzes the past judgment trends of multiple judges in damage claims and makes a prediction. The judgment analysis unit can also take into account the relevance of a judge's past judgment trends and evidence when predicting a verdict. For example, the judgment analysis unit analyzes the relevance of a judge's past judgment trends and evidence in incident response and makes a prediction. This makes it possible to make predictions that take into account a judge's past judgment trends.

[0045] The judgment analysis unit can make predictions taking into account the progress of the trial and the status of evidence submission when predicting a verdict. For example, the judgment analysis unit makes predictions taking into account the progress of the trial when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes the progress of the trial in a patent dispute and makes a prediction. The judgment analysis unit can also make predictions taking into account the status of evidence submission when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes the status of evidence submission in a claim for damages and makes a prediction. The judgment analysis unit can also make predictions taking into account the progress of the trial and the status of evidence submission comprehensively when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes the progress of the trial and the status of evidence submission in an accident response and makes a prediction. This makes it possible to make predictions taking into account the progress of the trial and the status of evidence submission.

[0046] The judgment analysis unit can make predictions by referring to related legal literature and precedents when predicting a verdict. For example, when the generation AI predicts a verdict, the judgment analysis unit makes predictions by referring to related Japanese law literature. For example, the judgment analysis unit analyzes Japanese legal literature to collect information necessary for verdict prediction. The judgment analysis unit can also make predictions by referring to related U.S. law precedents when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes U.S. case law data to collect information necessary for verdict prediction. The judgment analysis unit can also make predictions by referring to related EU law literature when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes EU legal literature to collect information necessary for verdict prediction. This enables predictions to be made by referring to related legal literature and precedents.

[0047] The simulation providing unit can optimize the scenario by referring to past simulation results when providing a simulation. For example, when the generation AI provides a simulation, the simulation providing unit optimizes the scenario by referring to past simulation results of patent disputes. For example, the simulation providing unit analyzes past simulation results related to patent infringement and optimizes the scenario. The simulation providing unit can also optimize the scenario by referring to past simulation results of claims for damages when providing a simulation. For example, the simulation providing unit analyzes past simulation results related to breach of contract and optimizes the scenario. The simulation providing unit can also optimize the scenario by referring to past simulation results of accident responses when the generation AI provides a simulation. For example, the simulation providing unit analyzes past simulation results related to work-related accidents and optimizes the scenario. This makes it possible to optimize a scenario by referring to past simulation results.

[0048] The simulation providing unit can customize the scenario taking into account factors specific to the user's industry when providing the simulation. For example, when the generation AI provides a simulation, the simulation providing unit customizes the scenario for a user in the manufacturing industry by taking into account factors specific to the industry. For example, the simulation providing unit customizes the scenario by taking into account the risk of patent infringement in the manufacturing industry. The simulation providing unit can also customize the scenario for a user in the IT industry by taking into account factors specific to the industry when providing the simulation. For example, the simulation providing unit customizes the scenario by taking into account the risk of data leakage in the IT industry. The simulation providing unit can also customize the scenario for a user in the medical industry by taking into account factors specific to the industry when providing the simulation. For example, the simulation providing unit customizes the scenario by taking into account the risk of medical malpractice in the medical industry. This makes it possible to customize the scenario taking into account factors specific to the user's industry.

[0049] The simulation providing unit can provide a scenario taking into account the user's geographical legal environment when providing a simulation. For example, the simulation providing unit provides a scenario taking into account the Japanese legal environment when the generation AI provides a simulation. For example, the simulation providing unit analyzes Japanese laws and regulations and provides a simulation scenario. The simulation providing unit can also provide a scenario taking into account the U.S. legal environment when the generation AI provides a simulation. For example, the simulation providing unit analyzes U.S. laws and regulations and provides a simulation scenario. The simulation providing unit can also provide a scenario taking into account the EU legal environment when the generation AI provides a simulation. For example, the simulation providing unit analyzes EU laws and regulations and provides a simulation scenario. This makes it possible to provide a scenario taking into account the user's geographical legal environment.

[0050] The simulation providing unit can provide a scenario by referring to the simulation results of other related lawsuits when providing a simulation. For example, when the generation AI provides a simulation, the simulation providing unit provides a scenario by referring to the simulation results of other related patent disputes. For example, the simulation providing unit analyzes the simulation results of other lawsuits related to patent infringement and provides a scenario. The simulation providing unit can also provide a scenario by referring to the simulation results of other related claims for damages when providing a simulation. For example, the simulation providing unit analyzes the simulation results of other lawsuits related to breach of contract and provides a scenario. The simulation providing unit can also provide a scenario by referring to the simulation results of other related accident responses when the generation AI provides a simulation. For example, the simulation providing unit analyzes the simulation results of other lawsuits related to industrial accidents and provides a scenario. This makes it possible to provide a scenario by referring to the simulation results of other related lawsuits.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The risk analysis unit can refer to the user's work history and improve the accuracy of risk identification based on past examples of success and failure in risk response. For example, in a patent dispute, the risk analysis unit can refer to past examples of successful patent infringement responses to identify similar risks. In addition, in a claim for damages, the risk analysis unit can refer to past examples of unsuccessful responses to contract breaches to improve the accuracy of risk identification. In addition, in an accident response, the risk analysis unit can refer to past examples of successful responses to work-related accidents to improve the accuracy of risk identification. This makes it possible to identify risks using the user's work history.

[0053] The evidence analysis unit can take into account the credibility of the person who submitted the evidence when evaluating the reliability of the evidence. For example, in a patent dispute, the evidence analysis unit evaluates the past credibility of the person who submitted the patent document and determines the reliability of the evidence. In addition, in a claim for damages, the evidence analysis unit can evaluate the credibility of the person who submitted the contract and determine the reliability of the evidence. In addition, in an accident response, the evidence analysis unit can evaluate the credibility of the person who submitted the accident report and determine the reliability of the evidence. This makes it possible to evaluate evidence while taking into account the credibility of the person who submitted the evidence.

[0054] When predicting a verdict, the judgment analysis unit can take into account the judge's past judgment trends. For example, the judgment analysis unit analyzes the past judgment trends of a specific judge in patent disputes and makes a prediction. The judgment analysis unit can also analyze the past judgment trends of a specific judge in claims for damages and make a prediction. The judgment analysis unit can also analyze the past judgment trends of a specific judge in incident response and make a prediction. This makes it possible to make predictions that take into account the judge's past judgment trends.

[0055] When providing simulation results, the simulation provider can customize scenarios taking into account risks specific to the user's industry. For example, the simulation provider can provide a scenario that takes into account the risk of patent infringement for a user in the manufacturing industry. The simulation provider can also provide a scenario that takes into account the risk of data leakage for a user in the IT industry. The simulation provider can also provide a scenario that takes into account the risk of medical malpractice for a user in the medical industry. This makes it possible to provide simulations that take into account the risks specific to the user's industry.

[0056] The risk analysis unit can automatically refer to relevant legal literature and precedents when identifying risks. For example, when the generation AI identifies a risk, it automatically refers to relevant Japanese law literature. The risk analysis unit can also automatically refer to relevant U.S. law precedents when the generation AI identifies a risk. The risk analysis unit can also automatically refer to relevant EU law literature when the generation AI identifies a risk. This improves the accuracy of risk identification by automatically referring to relevant legal literature and precedents.

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

[0058] Step 1: The Risk Analysis Department identifies risks such as patent disputes, claims for damages, and accident response. For example, in patent disputes, it identifies the risk of patent infringement, in claims for damages it identifies the risk of damages due to breach of contract, and in accident response it identifies the risk of work-related accidents. Step 2: The Evidence Analysis Department evaluates evidence based on the risks identified by the Risk Analysis Department. For example, in patent disputes, the department evaluates patent documents and technical documents; in damage claims, the department evaluates contracts and transaction records; and in accident responses, the department evaluates accident reports and witness testimony. Step 3: The judgment analysis unit predicts the outcome of a judgment based on the evidence evaluated by the evidence analysis unit. For example, it predicts the outcome of a judgment in a patent dispute based on past case law data, in a claim for damages based on past case law data, and in an accident response based on past case law data. Step 4: The simulation provider provides simulations based on the judgment results predicted by the judgment analysis unit. For example, in patent disputes, it simulates the risk of patent infringement based on the judgment results, in damages claims it simulates the risk of damages based on the judgment results, and in accident response it simulates the risk of work-related accidents based on the judgment results.

[0059] (Example 2) A risk analysis system according to an embodiment of the present invention provides simulations based on risk analysis, evidence analysis, and judgment analysis in civil trials. This risk analysis system uses a generation AI to perform risk analysis, evidence analysis, and judgment analysis for patent disputes, damage claims, accident responses, and other cases, and provides simulations based on the results. Targeting corporate legal and general affairs departments and individual business owners, the system supports both Japanese and international law (e.g., U.S., EU). The generation AI processes each element, making it unique in its ability to support international law and multiple languages. By providing simulations, users can predict the outcome of trials and develop appropriate countermeasures. For example, the risk analysis system includes a risk analysis unit that identifies risks in patent disputes, damage claims, accident responses, and other cases. Next, the system includes an evidence analysis unit that evaluates evidence based on the risks identified by the risk analysis unit. Furthermore, the system includes a judgment analysis unit that predicts a judgment based on the evidence evaluated by the evidence analysis unit. Finally, the system includes a simulation provider that provides simulations based on the judgment outcome predicted by the judgment analysis unit. This system targets corporate legal and general affairs departments and individual business owners, and supports both Japanese and international law (e.g., U.S., EU). Its unique feature is that the generative AI processes each element and is capable of supporting international law and multiple languages. By providing simulations, users can predict the outcome of trials and develop appropriate countermeasures. Regarding feasibility, it is necessary to refer to academic literature and the research of prominent experts regarding the logic. This allows the risk analysis system to provide simulations based on risk analysis, evidence analysis, and judgment analysis in civil trials.

[0060] A risk analysis system according to an embodiment includes a risk analysis unit, an evidence analysis unit, a judgment analysis unit, and a simulation providing unit. The risk analysis unit identifies risks in patent disputes, damage claims, accident responses, and the like. For example, in patent disputes, the risk analysis unit identifies the risk of patent infringement. In damage claims, the risk analysis unit can also identify the risk of damages due to contract breach. In accident responses, the risk analysis unit can also identify the risk of work-related accidents. The evidence analysis unit evaluates evidence based on the risks identified by the risk analysis unit. For example, in patent disputes, the evidence analysis unit evaluates patent documents and technical documents. In damage claims, the evidence analysis unit can also evaluate contracts and transaction records. In accident responses, the evidence analysis unit can also evaluate accident reports and witness testimony. The judgment analysis unit predicts a judgment based on the evidence evaluated by the evidence analysis unit. For example, in patent disputes, the judgment analysis unit predicts a judgment based on past case law data. In damage claims, the judgment analysis unit can also predict a judgment based on past case law data. Furthermore, the judgment analysis unit can predict a judgment based on past case data when responding to an accident. The simulation providing unit provides a simulation based on the judgment result predicted by the judgment analysis unit. For example, in a patent dispute, the simulation providing unit simulates the risk of patent infringement based on the judgment result. Furthermore, in a claim for damages, the simulation providing unit can simulate the risk of compensation for damages based on the judgment result. Furthermore, in an accident response, the simulation providing unit can simulate the risk of an industrial accident based on the judgment result. As a result, the risk analysis system according to the embodiment performs risk analysis, evidence analysis, judgment prediction, and simulation provision in a continuous flow.

[0061] The risk analysis unit can identify risks of patent disputes, claims for damages, and accident response. For example, in patent disputes, the risk analysis unit identifies the risk of patent infringement. For example, the risk analysis unit analyzes patent documents and technical documents to evaluate the possibility of patent infringement. The risk analysis unit can also identify the risk of compensation for damages due to breach of contract in claims for damages. For example, the risk analysis unit analyzes contracts and transaction records to evaluate the possibility of contract breach. The risk analysis unit can also identify the risk of work-related accidents in accident response. For example, the risk analysis unit analyzes accident reports and witness testimony to evaluate the possibility of work-related accidents. This enables detailed analysis of specific risks.

[0062] The evidence analysis unit can evaluate evidence based on the risks identified by the risk analysis unit. For example, in a patent dispute, the evidence analysis unit evaluates patent documents and technical documents. For example, the evidence analysis unit analyzes the contents of patent documents to evaluate evidence of patent infringement. The evidence analysis unit can also evaluate contracts and transaction records in a claim for damages. For example, the evidence analysis unit analyzes the contents of a contract to evaluate evidence of a breach of contract. The evidence analysis unit can also evaluate accident reports and witness testimony in an accident response. For example, the evidence analysis unit analyzes the contents of an accident report to evaluate evidence of a work-related accident. This enables risk-based evidence evaluation.

[0063] The judgment analysis unit can predict a judgment based on the evidence evaluated by the evidence analysis unit. For example, in patent disputes, the judgment analysis unit predicts a judgment based on past case data. For example, the judgment analysis unit analyzes past case data related to patent infringement and predicts a judgment. The judgment analysis unit can also predict a judgment based on past case data in claims for damages. For example, the judgment analysis unit analyzes past case data related to breach of contract and predicts a judgment. The judgment analysis unit can also predict a judgment based on past case data in accident response. For example, the judgment analysis unit analyzes past case data related to work-related accidents and predicts a judgment. This makes it possible to predict a judgment based on evidence.

[0064] The simulation providing unit can provide a simulation based on the judgment outcome predicted by the judgment analysis unit. For example, in a patent dispute, the simulation providing unit simulates the risk of patent infringement based on the judgment outcome. For example, the simulation providing unit evaluates the risk of patent infringement and simulates the impact if patent infringement occurs. The simulation providing unit can also simulate the risk of compensation for damages based on the judgment outcome in a claim for damages. For example, the simulation providing unit evaluates the risk of compensation for damages and simulates the impact if compensation for damages occurs. The simulation providing unit can also simulate the risk of work-related accidents based on the judgment outcome in accident response. For example, the simulation providing unit evaluates the risk of work-related accidents and simulates the impact if a work-related accident occurs. This makes it possible to provide simulations based on the judgment prediction results.

[0065] The simulation providing unit can provide the user with the simulation results. For example, in a patent dispute, the simulation providing unit simulates the risk of patent infringement and provides the result to the user. For example, the simulation providing unit evaluates the risk of patent infringement, simulates the impact of patent infringement if it occurs, and provides the result to the user. The simulation providing unit can also simulate the risk of compensation for damages in a claim for damages and provide the result to the user. For example, the simulation providing unit evaluates the risk of compensation for damages, simulates the impact of compensation for damages if it occurs, and provides the result to the user. The simulation providing unit can also simulate the risk of a work-related accident in an accident response and provide the result to the user. For example, the simulation providing unit evaluates the risk of a work-related accident, simulates the impact of a work-related accident if it occurs, and provides the result to the user. In this way, by providing the simulation results to the user, it is possible to predict the outcome of a trial and develop appropriate countermeasures.

[0066] The risk analysis unit can estimate the user's emotions and adjust the risk identification method based on the estimated user emotions. For example, if the user is feeling anxious, the risk analysis unit can have the generating AI provide detailed explanations when identifying risks, giving the user a sense of security. For example, the risk analysis unit can provide detailed explanations when identifying the risk of patent infringement in a patent dispute, reducing the user's anxiety. Furthermore, if the user is relaxed, the risk analysis unit can provide concise explanations when identifying risks, allowing the generating AI to identify risks quickly. For example, the risk analysis unit can provide concise explanations when identifying the risk of damages due to breach of contract in a claim for damages, allowing the generating AI to identify risks quickly. Furthermore, if the user is in a hurry, the risk analysis unit can prioritize identifying only the most important risks when identifying risks. For example, the risk analysis unit can prioritize identifying only the most important risks when identifying the risk of work-related accidents in an accident response. This enables the risk identification method to be adjusted according to the user's emotions.

[0067] The risk analysis unit can analyze past court case data and extract specific risk patterns. For example, the generation AI analyzes past patent dispute data and extracts specific risk patterns. For example, the risk analysis unit analyzes past data on patent infringement and extracts specific risk patterns. The risk analysis unit can also analyze past damages claim data and extract specific risk patterns. For example, the risk analysis unit analyzes past data on contract breaches and extracts specific risk patterns. The risk analysis unit can also analyze past accident response data and extract specific risk patterns. For example, the risk analysis unit analyzes past data on work-related accidents and extracts specific risk patterns. This makes it possible to extract risk patterns based on past court case data.

[0068] The risk analysis unit can automatically refer to relevant legal literature and precedents when identifying risks. For example, the risk analysis unit automatically refers to relevant Japanese legal literature when the generation AI identifies risks. For example, the risk analysis unit analyzes Japanese legal literature to collect information necessary for risk identification. The risk analysis unit can also automatically refer to relevant U.S. legal precedents when the generation AI identifies risks. For example, the risk analysis unit analyzes U.S. legal precedent data to collect information necessary for risk identification. The risk analysis unit can also automatically refer to relevant EU legal literature when the generation AI identifies risks. For example, the risk analysis unit analyzes EU legal literature to collect information necessary for risk identification. This automatically refers to relevant legal literature and precedents, improving the accuracy of risk identification.

[0069] The risk analysis unit can estimate the user's emotions and determine risk priorities based on the estimated user emotions. For example, if the user is feeling anxious, the generation AI adjusts the risk priorities and responds first to the risk that will most reduce the user's anxiety. For example, in a patent dispute, the risk analysis unit prioritizes the risk of patent infringement to reduce the user's anxiety. Furthermore, if the user is relaxed, the generation AI adjusts the risk priorities and efficiently responds to risks. For example, in a claim for damages, the risk analysis unit efficiently identifies the risk of compensation for breach of contract. Furthermore, if the user is in a hurry, the generation AI adjusts the risk priorities and responds first to the most important risks. For example, in an accident response, the risk analysis unit prioritizes the risk of work-related accidents. This makes it possible to determine risk priorities according to the user's emotions.

[0070] The risk analysis unit can perform an analysis taking into account risks specific to the user's industry when identifying risks. For example, when the generation AI identifies risks, the risk analysis unit performs an analysis taking into account industry-specific risks for a user in the manufacturing industry. For example, the risk analysis unit identifies the risk of patent infringement in the manufacturing industry and performs an analysis taking into account industry-specific risks. The risk analysis unit can also perform an analysis taking into account industry-specific risks for a user in the IT industry when identifying risks. For example, the risk analysis unit identifies the risk of data leakage in the IT industry and performs an analysis taking into account industry-specific risks. The risk analysis unit can also perform an analysis taking into account industry-specific risks for a user in the medical industry when identifying risks. For example, the risk analysis unit identifies the risk of medical malpractice in the medical industry and performs an analysis taking into account industry-specific risks. This enables an analysis taking into account risks specific to the user's industry.

[0071] The risk analysis unit can evaluate risks taking into account the user's geographical legal environment when identifying risks. For example, the risk analysis unit evaluates risks taking into account the Japanese legal environment when the generation AI identifies risks. For example, the risk analysis unit analyzes Japanese laws and regulations and collects information necessary for risk identification. The risk analysis unit can also evaluate risks taking into account the U.S. legal environment when the generation AI identifies risks. For example, the risk analysis unit analyzes U.S. laws and regulations and collects information necessary for risk identification. The risk analysis unit can also evaluate risks taking into account the EU legal environment when the generation AI identifies risks. For example, the risk analysis unit analyzes EU laws and regulations and collects information necessary for risk identification. This enables risk evaluation taking into account the user's geographical legal environment.

[0072] The evidence analysis unit can estimate the user's emotions and adjust the evidence evaluation criteria based on the estimated user emotions. For example, if the user is feeling anxious, the generation AI adjusts the evidence evaluation criteria and provides a detailed explanation. For example, in a patent dispute, the evidence analysis unit adjusts the evaluation criteria for patent documents and provides a detailed explanation. Also, if the user is relaxed, the generation AI adjusts the evidence evaluation criteria and provides a concise explanation. For example, in a claim for damages, the evidence analysis unit adjusts the evaluation criteria for contracts and provides a concise explanation. Also, if the user is in a hurry, the generation AI adjusts the evidence evaluation criteria and prioritizes only the most important evidence. For example, in an accident response, the evidence analysis unit adjusts the evaluation criteria for accident reports and prioritizes only the most important evidence. This makes it possible to adjust the evidence evaluation criteria according to the user's emotions.

[0073] The evidence analysis unit can automatically score the reliability and relevance of evidence when evaluating the evidence. For example, the evidence analysis unit scores the reliability of evidence when the generation AI evaluates the evidence. For example, the evidence analysis unit evaluates and scores the reliability of patent documents. The evidence analysis unit can also score the relevance of evidence when the generation AI evaluates the evidence. For example, the evidence analysis unit evaluates and scores the relevance of contracts. The evidence analysis unit can also comprehensively score the reliability and relevance of evidence when the generation AI evaluates the evidence. For example, the evidence analysis unit evaluates and scores the reliability and relevance of accident reports. This automatically scores the reliability and relevance of evidence, improving the accuracy of evidence evaluation.

[0074] The evidence analysis unit can take into account the background information of the evidence submitter when evaluating evidence. For example, the evidence analysis unit can take into account the professional background of the evidence submitter when the generation AI evaluates evidence. For example, the evidence analysis unit evaluates the professional background of the patent document submitter to determine the reliability of the evidence. The evidence analysis unit can also take into account the past reliability of the evidence submitter when the generation AI evaluates evidence. For example, the evidence analysis unit can evaluate the past reliability of the contract submitter to determine the reliability of the evidence. The evidence analysis unit can also take into account the expertise of the evidence submitter when the generation AI evaluates evidence. For example, the evidence analysis unit can evaluate the expertise of the accident report submitter to determine the reliability of the evidence. This makes it possible to perform an evaluation that takes into account the background information of the evidence submitter.

[0075] The evidence analysis unit can estimate the user's emotions and adjust the importance of evidence based on the estimated user emotions. For example, if the user is feeling anxious, the generation AI adjusts the importance of evidence and provides a detailed explanation. For example, in a patent dispute, the evidence analysis unit adjusts the importance of patent documents and provides a detailed explanation. Also, if the user is relaxed, the generation AI adjusts the importance of evidence and provides a concise explanation. For example, in a claim for damages, the evidence analysis unit adjusts the importance of contracts and provides a concise explanation. Also, if the user is in a hurry, the generation AI adjusts the importance of evidence and prioritizes only the most important evidence. For example, in an accident response, the evidence analysis unit adjusts the importance of accident reports and prioritizes only the most important evidence. This makes it possible to adjust the importance of evidence according to the user's emotions.

[0076] The evidence analysis unit can make an evaluation taking into account the timing and method of evidence submission when evaluating evidence. For example, when the generation AI evaluates evidence, the evidence analysis unit makes an evaluation taking into account the timing of evidence submission. For example, the evidence analysis unit evaluates the timing of patent document submission and determines the reliability of the evidence. The evidence analysis unit can also make an evaluation taking into account the method of evidence submission when the generation AI evaluates evidence. For example, the evidence analysis unit evaluates the method of contract submission and determines the reliability of the evidence. The evidence analysis unit can also make an evaluation taking into account the timing and method of evidence submission when the generation AI evaluates evidence. For example, the evidence analysis unit evaluates the timing and method of accident report submission and determines the reliability of the evidence. This makes it possible to make an evaluation taking into account the timing and method of evidence submission.

[0077] The evidence analysis unit can compare evidence with evidence from other related trials when evaluating the evidence. For example, when the generation AI evaluates evidence, the evidence analysis unit compares it with evidence from other related patent disputes and evaluates it. For example, the evidence analysis unit compares the contents of patent documents with evidence from other patent disputes and evaluates it. The evidence analysis unit can also compare the contents of contracts with evidence from other claims for damages and evaluate it. The evidence analysis unit can also compare the contents of accident reports with evidence from other related accident responses and evaluate it. For example, the evidence analysis unit compares the contents of accident reports with evidence from other accident responses and evaluates it. This makes it possible to evaluate evidence in comparison with evidence from other related trials.

[0078] The verdict analysis unit can estimate the user's emotions and adjust the verdict prediction algorithm based on the estimated user emotions. For example, if the user is feeling anxious, the verdict analysis unit causes the generation AI to adjust the verdict prediction algorithm and provide a detailed explanation. For example, in a patent dispute, the verdict analysis unit adjusts the verdict prediction algorithm for patent infringement and provides a detailed explanation. Also, if the user is relaxed, the generation AI adjusts the verdict prediction algorithm and provides a concise explanation. For example, in a claim for damages, the verdict analysis unit adjusts the verdict prediction algorithm for breach of contract and provides a concise explanation. Also, if the user is in a hurry, the generation AI adjusts the verdict prediction algorithm and prioritizes providing only the most important prediction results. For example, in accident response, the verdict analysis unit adjusts the verdict prediction algorithm for work-related accidents and prioritizes providing only the most important prediction results. This makes it possible to adjust the verdict prediction algorithm according to the user's emotions.

[0079] The judgment analysis unit can improve the accuracy of the prediction when predicting a verdict by referring to past judgment data. For example, when the generation AI predicts a verdict, the judgment analysis unit improves the accuracy of the prediction by referring to judgment data on past patent disputes. For example, the judgment analysis unit analyzes past judgment data on patent infringement to improve the accuracy of the prediction. The judgment analysis unit can also improve the accuracy of the prediction when the generation AI predicts a verdict by referring to past judgment data on claims for damages. For example, the judgment analysis unit analyzes past judgment data on breach of contract to improve the accuracy of the prediction. The judgment analysis unit can also improve the accuracy of the prediction when the generation AI predicts a verdict by referring to judgment data on past accident responses. For example, the judgment analysis unit analyzes past judgment data on work-related accidents to improve the accuracy of the prediction. In this way, by referring to past judgment data, the accuracy of the prediction is improved.

[0080] The judgment analysis unit can take into account a judge's past judgment trends when predicting a verdict. For example, when the generation AI predicts a verdict, the judgment analysis unit takes into account a specific judge's past judgment trends when making a prediction. For example, the judgment analysis unit analyzes a specific judge's past judgment trends in patent disputes and makes a prediction. The judgment analysis unit can also take into account the past judgment trends of multiple judges when predicting a verdict. For example, the judgment analysis unit analyzes the past judgment trends of multiple judges in damage claims and makes a prediction. The judgment analysis unit can also take into account the relevance of a judge's past judgment trends and evidence when predicting a verdict. For example, the judgment analysis unit analyzes the relevance of a judge's past judgment trends and evidence in incident response and makes a prediction. This makes it possible to make predictions that take into account a judge's past judgment trends.

[0081] The verdict analysis unit can estimate the user's emotions and adjust the display method of the verdict prediction results based on the estimated user emotions. For example, if the user is feeling anxious, the verdict analysis unit adjusts the display method of the verdict prediction results and provides a detailed explanation. For example, in a patent dispute, the verdict analysis unit displays the predicted verdict results for patent infringement in detail to alleviate the user's anxiety. Furthermore, if the user is relaxed, the verdict analysis unit adjusts the display method of the verdict prediction results and provides a concise explanation. For example, in a claim for damages, the verdict analysis unit displays the predicted verdict results for breach of contract concisely to facilitate the user's understanding. Furthermore, if the user is in a hurry, the verdict analysis unit adjusts the display method of the verdict prediction results and prioritizes displaying only the most important predicted results. For example, in an accident response, the verdict analysis unit displays only the most important parts of the predicted verdict results for a work-related accident to support a rapid response. This makes it possible to adjust the display method of results according to the user's emotions.

[0082] The judgment analysis unit can make predictions taking into account the progress of the trial and the status of evidence submission when predicting a verdict. For example, the judgment analysis unit makes predictions taking into account the progress of the trial when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes the progress of the trial in a patent dispute and makes a prediction. The judgment analysis unit can also make predictions taking into account the status of evidence submission when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes the status of evidence submission in a claim for damages and makes a prediction. The judgment analysis unit can also make predictions taking into account the progress of the trial and the status of evidence submission comprehensively when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes the progress of the trial and the status of evidence submission in an accident response and makes a prediction. This makes it possible to make predictions taking into account the progress of the trial and the status of evidence submission.

[0083] The judgment analysis unit can make predictions by referring to related legal literature and precedents when predicting a verdict. For example, when the generation AI predicts a verdict, the judgment analysis unit makes predictions by referring to related Japanese law literature. For example, the judgment analysis unit analyzes Japanese legal literature to collect information necessary for verdict prediction. The judgment analysis unit can also make predictions by referring to related U.S. law precedents when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes U.S. case law data to collect information necessary for verdict prediction. The judgment analysis unit can also make predictions by referring to related EU law literature when the generation AI predicts a verdict. For example, the judgment analysis unit analyzes EU legal literature to collect information necessary for verdict prediction. This enables predictions to be made by referring to related legal literature and precedents.

[0084] The simulation provider can estimate the user's emotions and adjust the simulation scenario based on the estimated user emotions. For example, if the user feels anxious, the generation AI adjusts the simulation scenario and provides a detailed explanation. For example, in a patent dispute, the simulation provider adjusts a patent infringement simulation scenario in detail to alleviate the user's anxiety. Furthermore, if the user feels relaxed, the generation AI adjusts the simulation scenario and provides a concise explanation. For example, in a claim for damages, the simulation provider adjusts a breach of contract simulation scenario briefly to promote the user's understanding. Furthermore, if the user is in a hurry, the generation AI adjusts the simulation scenario and prioritizes providing only the most important scenario. For example, in an accident response, the simulation provider adjusts only the most important parts of a work-related accident simulation scenario to support a rapid response. This makes it possible to adjust the simulation scenario according to the user's emotions.

[0085] The simulation providing unit can optimize the scenario by referring to past simulation results when providing a simulation. For example, when the generation AI provides a simulation, the simulation providing unit optimizes the scenario by referring to past simulation results of patent disputes. For example, the simulation providing unit analyzes past simulation results related to patent infringement and optimizes the scenario. The simulation providing unit can also optimize the scenario by referring to past simulation results of claims for damages when providing a simulation. For example, the simulation providing unit analyzes past simulation results related to breach of contract and optimizes the scenario. The simulation providing unit can also optimize the scenario by referring to past simulation results of accident responses when the generation AI provides a simulation. For example, the simulation providing unit analyzes past simulation results related to work-related accidents and optimizes the scenario. This makes it possible to optimize a scenario by referring to past simulation results.

[0086] The simulation providing unit can customize the scenario taking into account factors specific to the user's industry when providing the simulation. For example, when the generation AI provides a simulation, the simulation providing unit customizes the scenario for a user in the manufacturing industry by taking into account factors specific to the industry. For example, the simulation providing unit customizes the scenario by taking into account the risk of patent infringement in the manufacturing industry. The simulation providing unit can also customize the scenario for a user in the IT industry by taking into account factors specific to the industry when providing the simulation. For example, the simulation providing unit customizes the scenario by taking into account the risk of data leakage in the IT industry. The simulation providing unit can also customize the scenario for a user in the medical industry by taking into account factors specific to the industry when providing the simulation. For example, the simulation providing unit customizes the scenario by taking into account the risk of medical malpractice in the medical industry. This makes it possible to customize the scenario taking into account factors specific to the user's industry.

[0087] The simulation provider can estimate the user's emotions and adjust the display method of the simulation results based on the estimated user emotions. For example, if the user feels anxious, the generation AI adjusts the display method of the simulation results and provides a detailed explanation. For example, in a patent dispute, the simulation provider displays detailed simulation results of patent infringement to reduce the user's anxiety. Furthermore, if the user feels relaxed, the generation AI adjusts the display method of the simulation results and provides a concise explanation. For example, in a claim for damages, the simulation provider displays the simulation results of a breach of contract concisely to promote the user's understanding. Furthermore, if the user is in a hurry, the generation AI adjusts the display method of the simulation results and prioritizes displaying only the most important results. For example, in an accident response, the simulation provider displays only the most important parts of the simulation results of a work-related accident to support a rapid response. This makes it possible to adjust the display method of the results according to the user's emotions.

[0088] The simulation providing unit can provide a scenario taking into account the user's geographical legal environment when providing a simulation. For example, the simulation providing unit provides a scenario taking into account the Japanese legal environment when the generation AI provides a simulation. For example, the simulation providing unit analyzes Japanese laws and regulations and provides a simulation scenario. The simulation providing unit can also provide a scenario taking into account the U.S. legal environment when the generation AI provides a simulation. For example, the simulation providing unit analyzes U.S. laws and regulations and provides a simulation scenario. The simulation providing unit can also provide a scenario taking into account the EU legal environment when the generation AI provides a simulation. For example, the simulation providing unit analyzes EU laws and regulations and provides a simulation scenario. This makes it possible to provide a scenario taking into account the user's geographical legal environment.

[0089] The simulation providing unit can provide a scenario by referring to the simulation results of other related lawsuits when providing a simulation. For example, when the generation AI provides a simulation, the simulation providing unit provides a scenario by referring to the simulation results of other related patent disputes. For example, the simulation providing unit analyzes the simulation results of other lawsuits related to patent infringement and provides a scenario. The simulation providing unit can also provide a scenario by referring to the simulation results of other related claims for damages when providing a simulation. For example, the simulation providing unit analyzes the simulation results of other lawsuits related to breach of contract and provides a scenario. The simulation providing unit can also provide a scenario by referring to the simulation results of other related accident responses when the generation AI provides a simulation. For example, the simulation providing unit analyzes the simulation results of other lawsuits related to industrial accidents and provides a scenario. This makes it possible to provide a scenario by referring to the simulation results of other related lawsuits. === Hard Collateral 1-1 === Each of the multiple elements, including the risk analysis unit, evidence analysis unit, judgment analysis unit, and simulation providing unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the risk analysis unit is realized by the control unit 46A of the smart device 14 and identifies risks such as patent disputes, claims for damages, and accident responses. The evidence analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates evidence based on the identified risks. The judgment analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and predicts a judgment based on the evaluated evidence. The simulation providing unit is realized, for example, by the control unit 46A of the smart device 14 and provides a simulation based on the predicted judgment outcome. === Hard Collateral 1-2 === Each of the multiple elements, including the risk analysis unit, evidence analysis unit, verdict analysis unit, and simulation providing unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the risk analysis unit is realized by the control unit 46A of the smart glasses 214 and identifies risks such as patent disputes, claims for damages, and accident responses. The evidence analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates evidence based on the identified risks. The verdict analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and predicts a verdict based on the evaluated evidence. The simulation providing unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides a simulation based on the predicted verdict outcome. === Hard Collateral 1-3 === Each of the multiple elements including the risk analysis unit, evidence analysis unit, verdict analysis unit, and simulation providing unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the risk analysis unit is realized by the control unit 46A of the headset type terminal 314 and identifies risks such as patent disputes, claims for damages, and accident responses. The evidence analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates evidence based on the identified risks. The verdict analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and predicts a verdict based on the evaluated evidence. The simulation providing unit is realized, for example, by the control unit 46A of the headset type terminal 314 and provides a simulation based on the predicted verdict outcome. === Hard Collateral 1-4 === Each of the multiple elements, including the risk analysis unit, evidence analysis unit, verdict analysis unit, and simulation providing unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the risk analysis unit is realized by the control unit 46A of the robot 414 and identifies risks such as patent disputes, claims for damages, and accident responses. The evidence analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates evidence based on the identified risks. The verdict analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and predicts a verdict based on the evaluated evidence. The simulation providing unit is realized, for example, by the control unit 46A of the robot 414 and provides a simulation based on the predicted verdict outcome.

[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 risk analysis unit can refer to the user's work history and improve the accuracy of risk identification based on past examples of success and failure in risk response. For example, in a patent dispute, the risk analysis unit can refer to past examples of successful patent infringement responses to identify similar risks. In addition, in a claim for damages, the risk analysis unit can refer to past examples of unsuccessful responses to contract breaches to improve the accuracy of risk identification. In addition, in an accident response, the risk analysis unit can refer to past examples of successful responses to work-related accidents to improve the accuracy of risk identification. This makes it possible to identify risks using the user's work history.

[0092] The evidence analysis unit can take into account the credibility of the person who submitted the evidence when evaluating the reliability of the evidence. For example, in a patent dispute, the evidence analysis unit evaluates the past credibility of the person who submitted the patent document and determines the reliability of the evidence. In addition, in a claim for damages, the evidence analysis unit can evaluate the credibility of the person who submitted the contract and determine the reliability of the evidence. In addition, in an accident response, the evidence analysis unit can evaluate the credibility of the person who submitted the accident report and determine the reliability of the evidence. This makes it possible to evaluate evidence while taking into account the credibility of the person who submitted the evidence.

[0093] When predicting a verdict, the judgment analysis unit can take into account the judge's past judgment trends. For example, the judgment analysis unit analyzes the past judgment trends of a specific judge in patent disputes and makes a prediction. The judgment analysis unit can also analyze the past judgment trends of a specific judge in claims for damages and make a prediction. The judgment analysis unit can also analyze the past judgment trends of a specific judge in incident response and make a prediction. This makes it possible to make predictions that take into account the judge's past judgment trends.

[0094] When providing simulation results, the simulation provider can customize scenarios taking into account risks specific to the user's industry. For example, the simulation provider can provide a scenario that takes into account the risk of patent infringement for a user in the manufacturing industry. The simulation provider can also provide a scenario that takes into account the risk of data leakage for a user in the IT industry. The simulation provider can also provide a scenario that takes into account the risk of medical malpractice for a user in the medical industry. This makes it possible to provide simulations that take into account the risks specific to the user's industry.

[0095] The risk analysis unit can estimate the user's emotions and adjust the risk identification method based on the estimated user emotions. For example, if the user is feeling anxious, the generation AI can provide detailed explanations when identifying risks, giving a sense of security. If the user is relaxed, the generation AI can provide concise explanations when identifying risks, allowing for quick risk identification. If the user is in a hurry, the generation AI can prioritize only the most important risks when identifying risks. This makes it possible to adjust the risk identification method according to the user's emotions.

[0096] The evidence analysis unit can estimate the user's emotions and adjust the evidence evaluation criteria based on the estimated user emotions. For example, if the user is feeling anxious, the generation AI can adjust the evidence evaluation criteria and provide a detailed explanation. If the user is relaxed, the generation AI can adjust the evidence evaluation criteria and provide a concise explanation. If the user is in a hurry, the generation AI can adjust the evidence evaluation criteria and prioritize evaluation of only the most important evidence. This makes it possible to adjust the evidence evaluation criteria according to the user's emotions.

[0097] The verdict analysis unit can estimate the user's emotions and adjust the verdict prediction algorithm based on the estimated user emotions. For example, if the user is feeling anxious, the generation AI can adjust the verdict prediction algorithm and provide a detailed explanation. If the user is relaxed, the generation AI can adjust the verdict prediction algorithm and provide a concise explanation. If the user is in a hurry, the generation AI can adjust the verdict prediction algorithm and prioritize providing only the most important prediction results. This makes it possible to adjust the verdict prediction algorithm according to the user's emotions.

[0098] The simulation providing unit can estimate the user's emotions and adjust the simulation scenario based on the estimated user emotions. For example, if the user is feeling anxious, the generation AI can adjust the simulation scenario and provide a detailed explanation. If the user is relaxed, the generation AI can adjust the simulation scenario and provide a concise explanation. If the user is in a hurry, the generation AI can adjust the simulation scenario and provide only the most important scenarios as a priority. This makes it possible to adjust the simulation scenario according to the user's emotions.

[0099] The simulation provider can estimate the user's emotions and adjust the display method of the simulation results based on the estimated user emotions. For example, if the user is feeling anxious, the generation AI can adjust the display method of the simulation results and provide a detailed explanation. If the user is relaxed, the generation AI can adjust the display method of the simulation results and provide a concise explanation. If the user is in a hurry, the generation AI can adjust the display method of the simulation results and prioritize displaying only the most important results. This makes it possible to adjust the display method of the results according to the user's emotions.

[0100] The risk analysis unit can automatically refer to relevant legal literature and precedents when identifying risks. For example, when the generation AI identifies a risk, it automatically refers to relevant Japanese law literature. The risk analysis unit can also automatically refer to relevant U.S. law precedents when the generation AI identifies a risk. The risk analysis unit can also automatically refer to relevant EU law literature when the generation AI identifies a risk. This improves the accuracy of risk identification by automatically referring to relevant legal literature and precedents.

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

[0102] Step 1: The Risk Analysis Department identifies risks such as patent disputes, claims for damages, and accident response. For example, in patent disputes, it identifies the risk of patent infringement, in claims for damages it identifies the risk of damages due to breach of contract, and in accident response it identifies the risk of work-related accidents. Step 2: The Evidence Analysis Department evaluates evidence based on the risks identified by the Risk Analysis Department. For example, in patent disputes, the department evaluates patent documents and technical documents; in damage claims, the department evaluates contracts and transaction records; and in accident responses, the department evaluates accident reports and witness testimony. Step 3: The judgment analysis unit predicts the outcome of a judgment based on the evidence evaluated by the evidence analysis unit. For example, it predicts the outcome of a judgment in a patent dispute based on past case law data, in a claim for damages based on past case law data, and in an accident response based on past case law data. Step 4: The simulation provider provides simulations based on the judgment results predicted by the judgment analysis unit. For example, in patent disputes, it simulates the risk of patent infringement based on the judgment results, in damages claims it simulates the risk of damages based on the judgment results, and in accident response it simulates the risk of work-related accidents based on the judgment results.

[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 (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[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] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0121] 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.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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 identification processing unit 290 using these models.

[0134] 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.

[0135] 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.

[0136] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification 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 the same process as the identification processing unit 290 using these models.

[0151] 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.

[0152] 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.

[0153] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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, in order to avoid confusion and to 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.

[0173] 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.

[0174] [Explanation of symbols]

[0175] 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 risk analysis department for identifying risks; an evidence analysis unit that evaluates evidence based on the risks identified by the risk analysis unit; a verdict analysis unit that predicts a verdict based on the evidence evaluated by the evidence analysis unit; a simulation providing unit that provides a simulation based on the judgment result predicted by the judgment analysis unit. A system characterized by:

2. The risk analysis unit Identify risks of patent disputes, damage claims, and accident response 2. The system of claim 1.

3. The evidence analysis unit Evaluating evidence based on the risks identified by the risk analysis unit.

2. The system of claim 1.

4. The judgment analysis unit Predicting a verdict based on the evidence evaluated by the evidence analysis unit 2. The system of claim 1.

5. The simulation providing unit Providing a simulation based on the judgment outcome predicted by the judgment analysis unit 2. The system of claim 1.

6. The simulation providing unit Providing simulation results to users 2. The system of claim 1.

7. The risk analysis unit Inferring user sentiment and adjusting risk identification methods based on the inferred user sentiment 2. The system of claim 1.

8. The risk analysis unit Analyzing past court cases and extracting specific risk patterns 2. The system of claim 1.

Images