system

Abstract

The system according to this embodiment aims to enable victims of traffic accidents to receive prompt and appropriate legal assistance. [Solution] The system according to this embodiment comprises an advice unit, an evidence analysis unit, and a negotiation support unit. The advice unit provides continuously operating AI legal advice. The evidence analysis unit performs AI-based evidence analysis using multiple data modals. The negotiation support unit provides negotiation support based on sentiment analysis.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that it was difficult for traffic accident victims to receive prompt and appropriate legal assistance.

[0005] The system according to the embodiment aims to enable traffic accident victims to receive prompt and appropriate legal assistance.

Means for Solving the Problems

[0006] The system according to the embodiment includes an advice unit, an evidence analysis unit, and a negotiation support unit. The advice unit provides AI legal advice that operates constantly. The evidence analysis unit performs evidence analysis by AI using a plurality of data modalities. The negotiation support unit provides negotiation support based on sentiment analysis.

Effects of the Invention

[0007] The system according to this embodiment allows victims of traffic accidents to receive prompt and appropriate legal assistance. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The legal support system according to an embodiment of the present invention is a comprehensive legal support platform for victims of traffic accidents. This legal support system provides 24-hour AI legal advice, evidence analysis by multimodal AI, and negotiation support based on sentiment analysis. Specifically, it has the following functions. First, it provides 24-hour AI legal advice. From immediately after a traffic accident occurs, victims can receive immediate legal advice from AI. This enables appropriate responses even in the chaotic situation immediately after an accident. For example, it provides specific guidance on how to collect evidence at the accident scene and how to automatically create necessary documents. Next, it performs evidence analysis by multimodal AI. The AI ​​uses image recognition technology to objectively analyze the accident situation and evaluate the validity of the evidence. For example, it analyzes photos and videos of the accident scene to clarify the cause of the accident and who is responsible. This allows victims to proceed with negotiations based on strong evidence. Furthermore, it provides negotiation support based on sentiment analysis. The AI ​​analyzes the emotions of the victim and the perpetrator and proposes the optimal negotiation strategy. For example, it simulates compensation and optimizes negotiation scenarios while taking into account the victim's emotional state. This allows victims to proceed with negotiations calmly and effectively. Furthermore, the platform offers support leveraging group assets, including 24-hour support via messaging services, secure compensation management through an electronic payment system, and face-to-face support through a nationwide network of branches. This ensures that victims can receive legal assistance anytime, anywhere. The platform aims to improve the current situation where traffic accident victims often lack access to experts and receive adequate support, thereby providing equitable legal assistance. Ultimately, the goal is to eliminate situations where traffic accident victims suffer in silence and realize equitable legal assistance for all. This will enable the legal assistance system to provide traffic accident victims with prompt and appropriate legal support.

[0029] The legal support system according to this embodiment comprises an advice unit, an evidence analysis unit, and a negotiation support unit. The advice unit provides continuously operating AI legal advice. Continuous operation means operating 24 hours a day, 365 days a year, or under specific conditions such as time zones. For example, the advice unit provides immediate legal advice to victims immediately after a traffic accident occurs. The advice unit can provide specific guidance, such as how to collect evidence at the accident scene and the automatic creation of necessary documents. The evidence analysis unit performs AI-based evidence analysis using multiple data modals. These multiple data modals include, for example, text data, image data, and audio data. For example, the evidence analysis unit analyzes photographs and videos of the accident scene to clarify the cause of the accident and who is responsible. The evidence analysis unit can objectively analyze the accident situation using image recognition technology and evaluate its effectiveness as evidence. The negotiation support unit provides negotiation support based on sentiment analysis. Sentiment analysis is the analysis of emotions based on the algorithms and emotion classification criteria used. For example, the negotiation support unit analyzes the emotions of victims and perpetrators and proposes the optimal negotiation strategy. The negotiation support department can simulate compensation amounts and optimize negotiation scenarios, taking into account the victim's emotional state. This allows the legal support system according to the embodiment to provide traffic accident victims with 24-hour legal advice, evidence analysis, and negotiation support.

[0030] The Advice Department provides AI-powered legal advice that operates continuously. Continuous operation means it operates 24 hours a day, 365 days a year, or under specific conditions such as time zones. For example, the Advice Department provides immediate legal advice to victims immediately after a traffic accident occurs. Specifically, when the Advice Department detects a traffic accident, it sends a notification to the victim's smartphone or device and provides guidance on initial responses at the accident scene. For example, it provides specific instructions on how to collect evidence at the accident scene, such as where to take photos and videos and how to record important information. It also has an automatic document creation function, which automatically generates documents to be submitted to the police and insurance companies based on the information entered by the victim. This allows victims to carry out the necessary procedures quickly and accurately. Furthermore, in order to provide customized advice tailored to the victim's situation, the Advice Department refers to a database of past cases and proposes the best course of action based on similar cases. For example, it analyzes data from past traffic accidents and provides advice based on what actions victims should take and what kind of evidence was effective. This allows victims to proceed with legal procedures more effectively. The advice department utilizes AI-powered natural language processing technology to provide quick and accurate answers to questions from victims. For example, if a victim asks, "What kind of evidence is needed in this case?", the AI ​​will suggest specific methods for collecting evidence based on past cases and legal knowledge. This helps victims alleviate their anxieties and take appropriate action.

[0031] The Evidence Analysis Department performs AI-powered evidence analysis using multiple data modals. These data modals include, for example, text data, image data, and audio data. For example, the Evidence Analysis Department analyzes photographs and videos of accident scenes to clarify the cause of the accident and determine responsibility. Specifically, it can use image recognition technology to objectively analyze the accident situation and evaluate its validity as evidence. For example, it can analyze vehicle damage and road conditions from photographs of the accident scene to identify the accident's mechanism. It can also analyze video data to recreate the moment of the accident and examine the actions of the perpetrator and victim in detail. Furthermore, by analyzing audio data, it can analyze conversations immediately after the accident and surrounding sounds to gain a more detailed understanding of the accident situation. The Evidence Analysis Department integrates this data to conduct a comprehensive evidence analysis and clarify the cause of the accident and determine responsibility. For example, it analyzes eyewitness testimonies and police reports as text data and compares them with image and audio data to confirm the consistency of the evidence. This increases the reliability of the evidence and allows it to be used as valid evidence in legal proceedings. The Evidence Analysis Department utilizes AI machine learning technology to learn evidence patterns based on past case data, thereby improving the accuracy of new evidence analysis. For example, by learning from past traffic accident data and detecting similar patterns, it can perform rapid and accurate evidence analysis. This allows the Evidence Analysis Department to provide victims and legal professionals with reliable evidence analysis results and support legal proceedings.

[0032] The Negotiation Support Department provides negotiation support based on sentiment analysis. Sentiment analysis involves analyzing emotions based on the algorithms and classification criteria used. Specifically, the Negotiation Support Department analyzes the emotions of victims and perpetrators and proposes the optimal negotiation strategy. For example, it can simulate compensation amounts and optimize negotiation scenarios while taking into account the victim's emotional state. Sentiment analysis uses natural language processing technology to extract and classify emotions from the statements and documents of victims and perpetrators. For example, it can detect emotions such as anger, sadness, and fear from the victim's statements and propose appropriate countermeasures. It can also analyze emotions from the perpetrator's statements to understand the progress of negotiations and the other party's intentions. Based on these sentiment analysis results, the Negotiation Support Department develops strategies to facilitate smooth negotiations between victims and perpetrators. For example, if the victim is feeling strong anger, it can provide advice to encourage a calm response, and the negotiation can proceed smoothly if the perpetrator expresses an apology. Also, if the victim is feeling anxious, it can present a concrete compensation simulation to provide reassurance and advance negotiations. Furthermore, the Negotiation Support Department uses AI to simulate negotiations and proposes optimal negotiation scenarios. For example, based on past negotiation data, it learns successful negotiation patterns in similar cases and presents the best solution for both the victim and the perpetrator. This allows the Negotiation Support Department to provide effective negotiation support while considering the emotions of both the victim and the perpetrator, leading to a swift and smooth resolution.

[0033] The evidence collection department can provide methods for collecting evidence. For example, the department can provide methods for collecting evidence in traffic accidents. These methods include, for example, taking photographs, recording audio, and collecting eyewitness testimonies. The evidence collection department can provide specific guidance to help victims collect appropriate evidence. For example, the department can provide detailed instructions on how to collect evidence at the accident scene to help victims ensure they collect the necessary evidence. The department can provide specific procedures and points to note for collecting evidence to help victims collect evidence effectively. In this way, the evidence collection department can help victims collect appropriate evidence by providing methods for collecting evidence in traffic accidents.

[0034] The document creation unit can automatically generate necessary documents. For example, it can automatically create necessary documents related to traffic accidents. These necessary documents include, for example, accident reports, medical records, and insurance claims. The document creation unit can help victims quickly and accurately create the necessary documents. For example, the unit can automatically generate the necessary documents simply by entering the details of the accident. The unit automatically formats and prepares the content of the documents, allowing victims to create them without any effort. In this way, the document creation unit can reduce the burden on victims by automatically generating the necessary documents related to traffic accidents.

[0035] The simulation unit can perform compensation simulations. For example, the simulation unit can simulate compensation in a traffic accident. Compensation simulations include, for example, the calculation model to be used and the factors to be considered. The simulation unit can help victims understand appropriate compensation. For example, the simulation unit can provide compensation simulation results simply by inputting detailed accident information. The simulation unit clearly shows the calculation methods and criteria for compensation, making it easy for victims to understand the content of the compensation. In this way, the simulation unit can help victims understand appropriate compensation by performing compensation simulations.

[0036] The optimization unit can optimize negotiation scenarios. For example, the optimization unit optimizes negotiation scenarios in traffic accidents. Negotiation scenarios include, for example, negotiation steps and factors to consider. The optimization unit can help victims negotiate effectively. For example, the optimization unit proposes an optimal negotiation scenario, taking into account the victim's emotional state and the progress of the negotiation. The optimization unit presents the negotiation scenario step by step, so that the victim does not have to process a lot of information at once. In this way, by optimizing the negotiation scenario, the optimization unit can help victims negotiate effectively.

[0037] The support department can provide ongoing support through messaging services. For example, the support department can provide 24 / 7 support. Ongoing support means providing support 24 hours a day, 365 days a year, or under specific conditions such as time zones. The support department can ensure that victims can receive assistance at any time. For example, the support department can respond quickly to victims' questions and concerns through messaging services. The support department can immediately provide victims with the information and advice they need, reducing their anxiety. This allows the support department to provide 24 / 7 support, ensuring that victims can receive assistance at any time.

[0038] The management department can ensure the secure management of compensation payments through an electronic payment system. For example, the management department can manage compensation payments securely. Secure compensation management includes, for example, the security technologies and management processes used. The management department can help victims receive their compensation with peace of mind. For example, the management department can use an electronic payment system to receive and manage compensation payments. The management department can record the transaction history of compensation payments and implement security measures to prevent fraudulent transactions. In this way, the management department can ensure the secure management of compensation payments and help victims receive their compensation with peace of mind.

[0039] The Face-to-Face Support Department can provide face-to-face support through its nationwide network of stores. For example, the Face-to-Face Support Department provides face-to-face support. This support includes, for example, the content of the consultation and the format of the support. The Face-to-Face Support Department can ensure that victims receive direct assistance. For example, the Face-to-Face Support Department can utilize its nationwide network of stores to allow victims to receive face-to-face support at a nearby store. The Face-to-Face Support Department provides expert advice and support according to the victim's consultation needs. In this way, the Face-to-Face Support Department can ensure that victims receive direct assistance by providing face-to-face support.

[0040] The advisory unit can apply different advice algorithms depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the advisory unit can provide a list of simple procedures and necessary documents. In the case of a serious accident, the advisory unit can also provide detailed legal procedures and contact information for experts. Furthermore, depending on the circumstances of the accident, the advisory unit can provide specific instructions on how to collect evidence at the scene and how to report to the police. This allows for more appropriate responses by providing advice tailored to the type and circumstances of the accident. Some or all of the above processing in the advisory unit may be performed using, for example, generative AI, or without the use of generative AI.

[0041] The advice unit can analyze a user's past legal consultation history and provide optimal advice. For example, the advice unit can provide advice on similar cases based on the content of past consultations. Furthermore, the advice unit can propose solutions to specific legal problems based on the user's past consultation history. In addition, the advice unit can analyze the user's past consultation history and provide advice to prevent recurrence. This allows for more effective legal support by providing advice based on past consultation history. Some or all of the above processes in the advice unit may be performed using, for example, generative AI, or without generative AI.

[0042] The advice unit can provide region-specific legal information when providing advice, taking into account the user's geographical location. For example, the advice unit can provide information on local traffic laws and procedures based on the user's location. It can also provide contact information for local legal aid agencies and professionals based on the user's location. Furthermore, the advice unit can provide information on local courts and police stations based on the user's location. This enables more appropriate legal assistance by providing region-specific legal information. Some or all of the above processing in the advice unit may be performed using, for example, generative AI, or without generative AI.

[0043] The advisory department can analyze a user's social media activity and provide relevant legal advice when offering advice. For example, the advisory department can collect information about accidents from a user's social media posts and provide appropriate advice. The advisory department can also identify legal risks from a user's social media activity and propose preventative measures. Furthermore, the advisory department can analyze a user's social media activity and provide advice on relevant legal issues. This enables more appropriate legal support by providing advice based on social media activity. Some or all of the above processing in the advisory department may be performed using, for example, generative AI, or without generative AI.

[0044] The evidence analysis unit can use image recognition technology to perform a detailed analysis of the accident scene and evaluate the validity of the evidence. For example, the evidence analysis unit can analyze photographs of the accident scene to assess the extent of vehicle damage. It can also analyze videos of the accident scene to reconstruct the circumstances of the accident. Furthermore, the evidence analysis unit can analyze images of the accident scene to evaluate their validity as evidence. In this way, by using image recognition technology, a detailed analysis of the accident scene becomes possible, and the validity of the evidence can be evaluated. Some or all of the above processing in the evidence analysis unit may be performed using, for example, generative AI, or without generative AI.

[0045] The evidence analysis unit can apply different analysis algorithms depending on the type of evidence. For example, in the case of photographic evidence, the evidence analysis unit can perform a detailed analysis using image recognition technology. In the case of video evidence, the evidence analysis unit can also reconstruct the circumstances of the accident using video analysis technology. Furthermore, in the case of documentary evidence, the evidence analysis unit can evaluate the content using text analysis technology. By applying analysis algorithms appropriate to the type of evidence, more appropriate evidence analysis becomes possible. Some or all of the above-described processes in the evidence analysis unit may be performed using, for example, generative AI, or without the use of generative AI.

[0046] The evidence analysis unit can prioritize the analysis of region-specific evidence by considering the user's geographical location information during evidence analysis. For example, the evidence analysis unit can prioritize the analysis of evidence related to local traffic laws based on the user's location. It can also prioritize the analysis of evidence related to local accident circumstances based on the user's location. Furthermore, the evidence analysis unit can prioritize the analysis of evidence related to local legal procedures based on the user's location. This allows for more appropriate evidence analysis by prioritizing the analysis of region-specific evidence. Some or all of the above processing in the evidence analysis unit may be performed using, for example, generative AI, or without generative AI.

[0047] The evidence analysis department can improve the accuracy of its analysis by referring to relevant legal literature during the evidence analysis process. For example, the evidence analysis department can improve the accuracy of its evidence analysis by referring to relevant legal literature depending on the type of accident. Furthermore, the evidence analysis department can also improve the accuracy of its evidence analysis by referring to relevant case law depending on the circumstances of the accident. In addition, the evidence analysis department can improve the accuracy of its evidence analysis by referring to relevant legal literature depending on the responsibility for the accident. Thus, the accuracy of the evidence analysis is improved by referring to relevant legal literature. Some or all of the above processes in the evidence analysis department may be performed using, for example, a generative AI, or without the use of a generative AI.

[0048] The Negotiation Support Department can analyze the negotiating partner's past negotiation history and propose the optimal negotiation strategy. For example, the Negotiation Support Department can analyze what negotiation strategies the negotiating partner has used in the past and propose the best strategy. The Negotiation Support Department can also identify and propose successful strategies from the negotiating partner's past negotiation history. Furthermore, the Negotiation Support Department can analyze the negotiating partner's past negotiation history and make suggestions to avoid failed strategies. By providing strategies based on past negotiation history, more effective negotiations become possible. Some or all of the above processes in the Negotiation Support Department may be performed using, for example, generative AI, or without generative AI.

[0049] The Negotiation Support Department can update negotiation strategies in real time according to the progress of negotiations. For example, the Negotiation Support Department can propose the optimal strategy in real time according to the progress of negotiations. The Negotiation Support Department can also analyze the reactions of the negotiating party according to the progress of negotiations and update the strategy accordingly. Furthermore, the Negotiation Support Department can adjust the direction of negotiations according to the progress of negotiations to aim for the optimal outcome. In this way, by updating negotiation strategies in real time, it is possible to provide the optimal strategy according to the progress of negotiations. Some or all of the above processes in the Negotiation Support Department may be performed using, for example, generative AI, or without the use of generative AI.

[0050] The Negotiation Support Department can provide region-specific negotiation strategies when providing negotiation support, taking into account the user's geographical location. For example, the Negotiation Support Department can provide negotiation strategies tailored to the local legal situation based on the user's location. It can also provide negotiation strategies tailored to the local culture and customs based on the user's location. Furthermore, the Negotiation Support Department can provide contact information for local legal support agencies and experts based on the user's location. This enables more appropriate negotiations by providing region-specific negotiation strategies. Some or all of the above processing in the Negotiation Support Department may be performed using, for example, generative AI, or without the use of generative AI.

[0051] The Negotiation Support Department can improve the accuracy of negotiation strategies by referring to relevant legal literature during negotiation support. For example, depending on the type of negotiation, the Negotiation Support Department can improve the accuracy of negotiation strategies by referring to relevant legal literature. Furthermore, depending on the circumstances of the negotiation, the Negotiation Support Department can also improve the accuracy of negotiation strategies by referring to relevant case law. In addition, depending on the responsibility in the negotiation, the Negotiation Support Department can improve the accuracy of negotiation strategies by referring to relevant legal literature. Thus, the accuracy of negotiation strategies is improved by referring to relevant legal literature. Some or all of the above processing in the Negotiation Support Department may be performed using, for example, generative AI, or without the use of generative AI.

[0052] The evidence collection unit can provide different evidence collection methods depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the collection unit can provide a simple evidence collection method. In the case of a serious accident, the collection unit can also provide a detailed evidence collection method. Furthermore, depending on the circumstances of the accident, the collection unit can provide specific instructions on how to collect evidence at the scene and how to report to the police. By providing evidence collection methods tailored to the type and circumstances of the accident, more appropriate evidence collection becomes possible. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without the use of a generative AI.

[0053] The collection unit can prioritize the collection of highly relevant evidence by considering the user's geographical location information during evidence collection. For example, the collection unit can prioritize the collection of evidence related to local traffic laws based on the user's location. It can also prioritize the collection of evidence related to local accident circumstances based on the user's location. Furthermore, it can prioritize the collection of evidence related to local legal procedures based on the user's location. This allows for more appropriate evidence collection by prioritizing the collection of region-specific evidence. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without the use of a generative AI.

[0054] The document creation unit can apply different document creation algorithms depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the unit can apply a simple document creation algorithm. In the case of a serious accident, the unit can also apply a detailed document creation algorithm. Furthermore, depending on the circumstances of the accident, the unit can provide a list of necessary documents and create the appropriate documents. This makes it possible to create more appropriate documents by applying a document creation algorithm that is appropriate for the type and circumstances of the accident. Some or all of the above processing in the document creation unit may be performed using, for example, a generative AI, or it may be performed without using a generative AI.

[0055] The document creation unit can prioritize the creation of region-specific documents by considering the user's geographical location information during document creation. For example, the creation unit can prioritize the creation of documents related to local traffic laws based on the user's location. It can also prioritize the creation of documents related to local accident situations based on the user's location. Furthermore, it can prioritize the creation of documents related to local legal procedures based on the user's location. This allows for the creation of more appropriate documents by prioritizing region-specific documents. Some or all of the above processing in the creation unit may be performed using, for example, a generative AI, or without using a generative AI.

[0056] The simulation unit can apply different simulation algorithms depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the simulation unit can apply a simple simulation algorithm. In the case of a serious accident, the simulation unit can also apply a detailed simulation algorithm. Furthermore, depending on the circumstances of the accident, the simulation unit can provide a list of necessary compensation amounts and perform an appropriate simulation. This makes it possible to perform a more accurate simulation by applying a simulation algorithm appropriate to the type and circumstances of the accident. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or it may be performed without using a generative AI.

[0057] The simulation unit can provide region-specific compensation simulations by taking into account the user's geographical location information during the simulation. For example, the simulation unit can provide compensation simulations related to local traffic laws based on the user's location. It can also provide compensation simulations related to local accident circumstances based on the user's location. Furthermore, the simulation unit can provide compensation simulations related to local legal procedures based on the user's location. By providing region-specific compensation simulations, more appropriate simulations become possible. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or without using a generative AI.

[0058] The optimization unit can update the negotiation scenario in real time according to the progress of the negotiation. For example, the optimization unit can propose the optimal scenario in real time according to the progress of the negotiation. The optimization unit can also analyze the reactions of the negotiating party according to the progress of the negotiation and update the scenario accordingly. Furthermore, the optimization unit can adjust the direction of the negotiation according to the progress of the negotiation to aim for the optimal result. In this way, by updating the negotiation scenario in real time, it is possible to provide the optimal scenario according to the progress of the negotiation. Some or all of the above processing in the optimization unit may be performed using, for example, generative AI, or without using generative AI.

[0059] The optimization unit can provide region-specific negotiation scenarios by considering the user's geographical location information when optimizing negotiation scenarios. For example, the optimization unit can provide negotiation scenarios that are appropriate to the local legal situation based on the user's location. It can also provide negotiation scenarios that are appropriate to the local culture and customs based on the user's location. Furthermore, the optimization unit can provide contact information for local legal aid organizations and experts based on the user's location. By providing region-specific negotiation scenarios, more appropriate negotiations become possible. Some or all of the above processing in the optimization unit may be performed using, for example, generative AI, or without generative AI.

[0060] The support department can provide different support methods depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the support department can provide simple support methods. In the case of a serious accident, the support department can also provide detailed support methods. Furthermore, depending on the circumstances of the accident, the support department can provide specific instructions on how to provide support at the scene and how to report to the police. This allows for more appropriate assistance by providing support methods tailored to the type and circumstances of the accident. Some or all of the above-described processes in the support department may be performed using, for example, generative AI, or without the use of generative AI.

[0061] The support unit can provide region-specific support by taking into account the user's geographical location when providing support. For example, the support unit can provide support related to local traffic laws based on the user's location. It can also provide support related to local accident situations based on the user's location. Furthermore, the support unit can provide support related to local legal procedures based on the user's location. By providing region-specific support, more appropriate assistance becomes possible. Some or all of the above processing in the support unit may be performed using, for example, generative AI, or without generative AI.

[0062] The management department can provide different compensation management methods depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the management department can provide a simple compensation management method. In the case of a serious accident, the management department can also provide a detailed compensation management method. Furthermore, depending on the circumstances of the accident, the management department can provide a list of necessary compensation and perform appropriate compensation management. This allows for more appropriate management by providing compensation management methods tailored to the type and circumstances of the accident. Some or all of the above processes in the management department may be performed using, for example, a generative AI, or not using a generative AI.

[0063] The management unit can provide region-specific compensation management by taking into account the user's geographical location information when managing compensation. For example, the management unit can provide compensation management related to local traffic laws based on the user's location. It can also provide compensation management related to local accident circumstances based on the user's location. Furthermore, the management unit can provide compensation management related to local legal procedures based on the user's location. This enables more appropriate management by providing region-specific compensation management. Some or all of the above processing in the management unit may be performed using, for example, a generative AI, or without the use of a generative AI.

[0064] The face-to-face support unit can provide different face-to-face support methods depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the face-to-face support unit can provide a simple face-to-face support method. In the case of a serious accident, the face-to-face support unit can also provide a detailed face-to-face support method. Furthermore, depending on the circumstances of the accident, the face-to-face support unit can provide specific instructions on how to provide face-to-face support at the scene and how to report to the police. This allows for more appropriate support by providing face-to-face support methods tailored to the type and circumstances of the accident. Some or all of the above processing in the face-to-face support unit may be performed using, for example, generative AI, or without the use of generative AI.

[0065] The face-to-face support unit can provide region-specific face-to-face support by taking into account the user's geographical location information when providing face-to-face support. For example, the face-to-face support unit can provide face-to-face support related to local traffic laws based on the user's location. It can also provide face-to-face support related to local accident situations based on the user's location. Furthermore, the face-to-face support unit can provide face-to-face support related to local legal procedures based on the user's location. This enables more appropriate support by providing region-specific face-to-face support. Some or all of the above processing in the face-to-face support unit may be performed using, for example, generative AI, or without generative AI.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The legal support system can also include an advice history analysis unit that analyzes the user's past legal consultation history and provides optimal advice. For example, the advice history analysis unit can provide advice for similar cases based on the user's past consultations. Furthermore, the advice history analysis unit can propose solutions to specific legal problems based on the user's past consultation history. In addition, the advice history analysis unit can analyze the user's past consultation history and provide advice to prevent recurrence. This enables more effective legal support by providing advice based on past consultation history.

[0068] The legal support system may also include a geographic information advisory section that provides region-specific legal information, taking into account the user's geographic location. For example, the geographic information advisory section could provide information on local traffic laws and procedures based on the user's location. It could also provide contact information for local legal support agencies and professionals based on the user's location. Furthermore, it could provide information on local courts and police stations based on the user's location. This allows for more appropriate legal support by providing region-specific legal information.

[0069] The legal support system may also include a geographic information evidence analysis unit that prioritizes the analysis of region-specific evidence, taking into account the user's geographic location. For example, the geographic information evidence analysis unit might prioritize the analysis of evidence related to local traffic laws based on the user's location. It could also prioritize the analysis of evidence related to local accident circumstances based on the user's location. Furthermore, it could prioritize the analysis of evidence related to local legal procedures based on the user's location. This allows for more appropriate evidence analysis by prioritizing the analysis of region-specific evidence.

[0070] The legal support system may further include a geographic information simulation unit that provides region-specific compensation simulations, taking into account the user's geographic location. For example, the geographic information simulation unit may provide compensation simulations related to local traffic laws based on the user's location. It may also provide compensation simulations related to local accident circumstances based on the user's location. Furthermore, the geographic information simulation unit may provide compensation simulations related to local legal procedures based on the user's location. This allows for more appropriate simulations by providing region-specific compensation simulations.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The Advice Unit provides continuously operating AI legal advice. Continuous operation means operating 24 hours a day, 365 days a year, or under specific conditions such as time zones. For example, the Advice Unit provides immediate legal advice to victims immediately after a traffic accident occurs. The Advice Unit can provide specific guidance, such as how to collect evidence at the accident scene and how to automatically create necessary documents. Step 2: The evidence analysis department performs AI-based evidence analysis using multiple data modals. These data modals include, for example, text data, image data, and audio data. The evidence analysis department analyzes, for example, photos and videos of the accident scene to clarify the cause of the accident and who is responsible. The evidence analysis department can use image recognition technology to objectively analyze the accident situation and evaluate its validity as evidence. Step 3: The Negotiation Support Department provides negotiation support based on sentiment analysis. Sentiment analysis involves analyzing emotions based on the algorithms and emotional classification criteria used. For example, the Negotiation Support Department analyzes the emotions of the victim and the perpetrator and proposes the optimal negotiation strategy. The Negotiation Support Department can also simulate compensation amounts and optimize negotiation scenarios, taking into account the victim's emotional state.

[0073] (Example of form 2) The legal support system according to an embodiment of the present invention is a comprehensive legal support platform for victims of traffic accidents. This legal support system provides 24-hour AI legal advice, evidence analysis by multimodal AI, and negotiation support based on sentiment analysis. Specifically, it has the following functions. First, it provides 24-hour AI legal advice. From immediately after a traffic accident occurs, victims can receive immediate legal advice from AI. This enables appropriate responses even in the chaotic situation immediately after an accident. For example, it provides specific guidance on how to collect evidence at the accident scene and how to automatically create necessary documents. Next, it performs evidence analysis by multimodal AI. The AI ​​uses image recognition technology to objectively analyze the accident situation and evaluate the validity of the evidence. For example, it analyzes photos and videos of the accident scene to clarify the cause of the accident and who is responsible. This allows victims to proceed with negotiations based on strong evidence. Furthermore, it provides negotiation support based on sentiment analysis. The AI ​​analyzes the emotions of the victim and the perpetrator and proposes the optimal negotiation strategy. For example, it simulates compensation and optimizes negotiation scenarios while taking into account the victim's emotional state. This allows victims to proceed with negotiations calmly and effectively. Furthermore, the platform offers support leveraging group assets, including 24-hour support via messaging services, secure compensation management through an electronic payment system, and face-to-face support through a nationwide network of branches. This ensures that victims can receive legal assistance anytime, anywhere. The platform aims to improve the current situation where traffic accident victims often lack access to experts and receive adequate support, thereby providing equitable legal assistance. Ultimately, the goal is to eliminate situations where traffic accident victims suffer in silence and realize equitable legal assistance for all. This will enable the legal assistance system to provide traffic accident victims with prompt and appropriate legal support.

[0074] The legal support system according to this embodiment comprises an advice unit, an evidence analysis unit, and a negotiation support unit. The advice unit provides continuously operating AI legal advice. Continuous operation means operating 24 hours a day, 365 days a year, or under specific conditions such as time zones. For example, the advice unit provides immediate legal advice to victims immediately after a traffic accident occurs. The advice unit can provide specific guidance, such as how to collect evidence at the accident scene and the automatic creation of necessary documents. The evidence analysis unit performs AI-based evidence analysis using multiple data modals. These multiple data modals include, for example, text data, image data, and audio data. For example, the evidence analysis unit analyzes photographs and videos of the accident scene to clarify the cause of the accident and who is responsible. The evidence analysis unit can objectively analyze the accident situation using image recognition technology and evaluate its effectiveness as evidence. The negotiation support unit provides negotiation support based on sentiment analysis. Sentiment analysis is the analysis of emotions based on the algorithms and emotion classification criteria used. For example, the negotiation support unit analyzes the emotions of victims and perpetrators and proposes the optimal negotiation strategy. The negotiation support department can simulate compensation amounts and optimize negotiation scenarios, taking into account the victim's emotional state. This allows the legal support system according to the embodiment to provide traffic accident victims with 24-hour legal advice, evidence analysis, and negotiation support.

[0075] The Advice Department provides AI-powered legal advice that operates continuously. Continuous operation means it operates 24 hours a day, 365 days a year, or under specific conditions such as time zones. For example, the Advice Department provides immediate legal advice to victims immediately after a traffic accident occurs. Specifically, when the Advice Department detects a traffic accident, it sends a notification to the victim's smartphone or device and provides guidance on initial responses at the accident scene. For example, it provides specific instructions on how to collect evidence at the accident scene, such as where to take photos and videos and how to record important information. It also has an automatic document creation function, which automatically generates documents to be submitted to the police and insurance companies based on the information entered by the victim. This allows victims to carry out the necessary procedures quickly and accurately. Furthermore, in order to provide customized advice tailored to the victim's situation, the Advice Department refers to a database of past cases and proposes the best course of action based on similar cases. For example, it analyzes data from past traffic accidents and provides advice based on what actions victims should take and what kind of evidence was effective. This allows victims to proceed with legal procedures more effectively. The advice department utilizes AI-powered natural language processing technology to provide quick and accurate answers to questions from victims. For example, if a victim asks, "What kind of evidence is needed in this case?", the AI ​​will suggest specific methods for collecting evidence based on past cases and legal knowledge. This helps victims alleviate their anxieties and take appropriate action.

[0076] The Evidence Analysis Department performs AI-powered evidence analysis using multiple data modals. These data modals include, for example, text data, image data, and audio data. For example, the Evidence Analysis Department analyzes photographs and videos of accident scenes to clarify the cause of the accident and determine responsibility. Specifically, it can use image recognition technology to objectively analyze the accident situation and evaluate its validity as evidence. For example, it can analyze vehicle damage and road conditions from photographs of the accident scene to identify the accident's mechanism. It can also analyze video data to recreate the moment of the accident and examine the actions of the perpetrator and victim in detail. Furthermore, by analyzing audio data, it can analyze conversations immediately after the accident and surrounding sounds to gain a more detailed understanding of the accident situation. The Evidence Analysis Department integrates this data to conduct a comprehensive evidence analysis and clarify the cause of the accident and determine responsibility. For example, it analyzes eyewitness testimonies and police reports as text data and compares them with image and audio data to confirm the consistency of the evidence. This increases the reliability of the evidence and allows it to be used as valid evidence in legal proceedings. The Evidence Analysis Department utilizes AI machine learning technology to learn evidence patterns based on past case data, thereby improving the accuracy of new evidence analysis. For example, by learning from past traffic accident data and detecting similar patterns, it can perform rapid and accurate evidence analysis. This allows the Evidence Analysis Department to provide victims and legal professionals with reliable evidence analysis results and support legal proceedings.

[0077] The Negotiation Support Department provides negotiation support based on sentiment analysis. Sentiment analysis involves analyzing emotions based on the algorithms and classification criteria used. Specifically, the Negotiation Support Department analyzes the emotions of victims and perpetrators and proposes the optimal negotiation strategy. For example, it can simulate compensation amounts and optimize negotiation scenarios while taking into account the victim's emotional state. Sentiment analysis uses natural language processing technology to extract and classify emotions from the statements and documents of victims and perpetrators. For example, it can detect emotions such as anger, sadness, and fear from the victim's statements and propose appropriate countermeasures. It can also analyze emotions from the perpetrator's statements to understand the progress of negotiations and the other party's intentions. Based on these sentiment analysis results, the Negotiation Support Department develops strategies to facilitate smooth negotiations between victims and perpetrators. For example, if the victim is feeling strong anger, it can provide advice to encourage a calm response, and the negotiation can proceed smoothly if the perpetrator expresses an apology. Also, if the victim is feeling anxious, it can present a concrete compensation simulation to provide reassurance and advance negotiations. Furthermore, the Negotiation Support Department uses AI to simulate negotiations and proposes optimal negotiation scenarios. For example, based on past negotiation data, it learns successful negotiation patterns in similar cases and presents the best solution for both the victim and the perpetrator. This allows the Negotiation Support Department to provide effective negotiation support while considering the emotions of both the victim and the perpetrator, leading to a swift and smooth resolution.

[0078] The evidence collection department can provide methods for collecting evidence. For example, the department can provide methods for collecting evidence in traffic accidents. These methods include, for example, taking photographs, recording audio, and collecting eyewitness testimonies. The evidence collection department can provide specific guidance to help victims collect appropriate evidence. For example, the department can provide detailed instructions on how to collect evidence at the accident scene to help victims ensure they collect the necessary evidence. The department can provide specific procedures and points to note for collecting evidence to help victims collect evidence effectively. In this way, the evidence collection department can help victims collect appropriate evidence by providing methods for collecting evidence in traffic accidents.

[0079] The document creation unit can automatically generate necessary documents. For example, it can automatically create necessary documents related to traffic accidents. These necessary documents include, for example, accident reports, medical records, and insurance claims. The document creation unit can help victims quickly and accurately create the necessary documents. For example, the unit can automatically generate the necessary documents simply by entering the details of the accident. The unit automatically formats and prepares the content of the documents, allowing victims to create them without any effort. In this way, the document creation unit can reduce the burden on victims by automatically generating the necessary documents related to traffic accidents.

[0080] The simulation unit can perform compensation simulations. For example, the simulation unit can simulate compensation in a traffic accident. Compensation simulations include, for example, the calculation model to be used and the factors to be considered. The simulation unit can help victims understand appropriate compensation. For example, the simulation unit can provide compensation simulation results simply by inputting detailed accident information. The simulation unit clearly shows the calculation methods and criteria for compensation, making it easy for victims to understand the content of the compensation. In this way, the simulation unit can help victims understand appropriate compensation by performing compensation simulations.

[0081] The optimization unit can optimize negotiation scenarios. For example, the optimization unit optimizes negotiation scenarios in traffic accidents. Negotiation scenarios include, for example, negotiation steps and factors to consider. The optimization unit can help victims negotiate effectively. For example, the optimization unit proposes an optimal negotiation scenario, taking into account the victim's emotional state and the progress of the negotiation. The optimization unit presents the negotiation scenario step by step, so that the victim does not have to process a lot of information at once. In this way, by optimizing the negotiation scenario, the optimization unit can help victims negotiate effectively.

[0082] The support department can provide ongoing support through messaging services. For example, the support department can provide 24 / 7 support. Ongoing support means providing support 24 hours a day, 365 days a year, or under specific conditions such as time zones. The support department can ensure that victims can receive assistance at any time. For example, the support department can respond quickly to victims' questions and concerns through messaging services. The support department can immediately provide victims with the information and advice they need, reducing their anxiety. This allows the support department to provide 24 / 7 support, ensuring that victims can receive assistance at any time.

[0083] The management department can ensure the secure management of compensation payments through an electronic payment system. For example, the management department can manage compensation payments securely. Secure compensation management includes, for example, the security technologies and management processes used. The management department can help victims receive their compensation with peace of mind. For example, the management department can use an electronic payment system to receive and manage compensation payments. The management department can record the transaction history of compensation payments and implement security measures to prevent fraudulent transactions. In this way, the management department can ensure the secure management of compensation payments and help victims receive their compensation with peace of mind.

[0084] The Face-to-Face Support Department can provide face-to-face support through its nationwide network of stores. For example, the Face-to-Face Support Department provides face-to-face support. This support includes, for example, the content of the consultation and the format of the support. The Face-to-Face Support Department can ensure that victims receive direct assistance. For example, the Face-to-Face Support Department can utilize its nationwide network of stores to allow victims to receive face-to-face support at a nearby store. The Face-to-Face Support Department provides expert advice and support according to the victim's consultation needs. In this way, the Face-to-Face Support Department can ensure that victims receive direct assistance by providing face-to-face support.

[0085] The advice unit can estimate the user's emotions and adjust the content and timing of advice based on those emotions. For example, if the user is stressed, the advice unit can provide simple and quick advice to reduce the user's burden. If the user is relaxed, the advice unit can also provide detailed legal information and explain it in a way that is easy for the user to understand. Furthermore, if the user is confused, the advice unit can provide advice step by step, so that the user does not have to process a lot of information at once. This allows for more appropriate legal support by providing advice that is tailored to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The advisory unit can apply different advice algorithms depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the advisory unit can provide a list of simple procedures and necessary documents. In the case of a serious accident, the advisory unit can also provide detailed legal procedures and contact information for experts. Furthermore, depending on the circumstances of the accident, the advisory unit can provide specific instructions on how to collect evidence at the scene and how to report to the police. This allows for more appropriate responses by providing advice tailored to the type and circumstances of the accident. Some or all of the above processing in the advisory unit may be performed using, for example, generative AI, or without the use of generative AI.

[0087] The advice unit can analyze a user's past legal consultation history and provide optimal advice. For example, the advice unit can provide advice on similar cases based on the content of past consultations. Furthermore, the advice unit can propose solutions to specific legal problems based on the user's past consultation history. In addition, the advice unit can analyze the user's past consultation history and provide advice to prevent recurrence. This allows for more effective legal support by providing advice based on past consultation history. Some or all of the above processes in the advice unit may be performed using, for example, generative AI, or without generative AI.

[0088] The advice unit can estimate the user's emotions and prioritize advice based on those emotions. For example, if the user is feeling highly anxious, the advice unit will prioritize providing the most important advice. If the user is calm, the advice unit can also provide advice that includes detailed information. Furthermore, if the user is in a hurry, the advice unit can prioritize providing advice that allows for a quick response. This enables more appropriate legal support by providing advice with priorities that match the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The advice unit can provide region-specific legal information when providing advice, taking into account the user's geographical location. For example, the advice unit can provide information on local traffic laws and procedures based on the user's location. It can also provide contact information for local legal aid agencies and professionals based on the user's location. Furthermore, the advice unit can provide information on local courts and police stations based on the user's location. This enables more appropriate legal assistance by providing region-specific legal information. Some or all of the above processing in the advice unit may be performed using, for example, generative AI, or without generative AI.

[0090] The advisory department can analyze a user's social media activity and provide relevant legal advice when offering advice. For example, the advisory department can collect information about accidents from a user's social media posts and provide appropriate advice. The advisory department can also identify legal risks from a user's social media activity and propose preventative measures. Furthermore, the advisory department can analyze a user's social media activity and provide advice on relevant legal issues. This enables more appropriate legal support by providing advice based on social media activity. Some or all of the above processing in the advisory department may be performed using, for example, generative AI, or without generative AI.

[0091] The evidence analysis unit can estimate the user's emotions and adjust the evidence analysis method based on the estimated emotions. For example, if the user is nervous, the evidence analysis unit can provide simple and easy-to-understand evidence analysis results. If the user is relaxed, the evidence analysis unit can also provide detailed evidence analysis results. Furthermore, if the user is confused, the evidence analysis unit can provide evidence analysis results step by step to aid understanding. This allows for more appropriate evidence analysis by performing evidence analysis according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The evidence analysis unit can use image recognition technology to perform a detailed analysis of the accident scene and evaluate the validity of the evidence. For example, the evidence analysis unit can analyze photographs of the accident scene to assess the extent of vehicle damage. It can also analyze videos of the accident scene to reconstruct the circumstances of the accident. Furthermore, the evidence analysis unit can analyze images of the accident scene to evaluate their validity as evidence. In this way, by using image recognition technology, a detailed analysis of the accident scene becomes possible, and the validity of the evidence can be evaluated. Some or all of the above processing in the evidence analysis unit may be performed using, for example, generative AI, or without generative AI.

[0093] The evidence analysis unit can apply different analysis algorithms depending on the type of evidence. For example, in the case of photographic evidence, the evidence analysis unit can perform a detailed analysis using image recognition technology. In the case of video evidence, the evidence analysis unit can also reconstruct the circumstances of the accident using video analysis technology. Furthermore, in the case of documentary evidence, the evidence analysis unit can evaluate the content using text analysis technology. By applying analysis algorithms appropriate to the type of evidence, more appropriate evidence analysis becomes possible. Some or all of the above-described processes in the evidence analysis unit may be performed using, for example, generative AI, or without the use of generative AI.

[0094] The evidence analysis unit can estimate the user's emotions and prioritize the evidence analysis based on those emotions. For example, if the user is feeling highly anxious, the evidence analysis unit will prioritize analyzing the most important evidence. If the user is calm, the evidence analysis unit can also perform a detailed evidence analysis. Furthermore, if the user is in a hurry, the evidence analysis unit can prioritize analyzing evidence that can be addressed quickly. This allows for more appropriate evidence analysis by prioritizing the analysis according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The evidence analysis unit can prioritize the analysis of region-specific evidence by considering the user's geographical location information during evidence analysis. For example, the evidence analysis unit can prioritize the analysis of evidence related to local traffic laws based on the user's location. It can also prioritize the analysis of evidence related to local accident circumstances based on the user's location. Furthermore, the evidence analysis unit can prioritize the analysis of evidence related to local legal procedures based on the user's location. This allows for more appropriate evidence analysis by prioritizing the analysis of region-specific evidence. Some or all of the above processing in the evidence analysis unit may be performed using, for example, generative AI, or without generative AI.

[0096] The evidence analysis department can improve the accuracy of its analysis by referring to relevant legal literature during the evidence analysis process. For example, the evidence analysis department can improve the accuracy of its evidence analysis by referring to relevant legal literature depending on the type of accident. Furthermore, the evidence analysis department can also improve the accuracy of its evidence analysis by referring to relevant case law depending on the circumstances of the accident. In addition, the evidence analysis department can improve the accuracy of its evidence analysis by referring to relevant legal literature depending on the responsibility for the accident. Thus, the accuracy of the evidence analysis is improved by referring to relevant legal literature. Some or all of the above processes in the evidence analysis department may be performed using, for example, a generative AI, or without the use of a generative AI.

[0097] The negotiation support unit can estimate the user's emotions and adjust the negotiation strategy based on those emotions. For example, if the user is nervous, the negotiation support unit can suggest a strategy to proceed with the negotiation calmly. If the user is relaxed, the negotiation support unit can also suggest a detailed negotiation strategy. Furthermore, if the user is confused, the negotiation support unit can suggest a step-by-step negotiation strategy to help them understand. This allows for more effective negotiations by providing negotiation strategies tailored to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The Negotiation Support Department can analyze the negotiating partner's past negotiation history and propose the optimal negotiation strategy. For example, the Negotiation Support Department can analyze what negotiation strategies the negotiating partner has used in the past and propose the best strategy. The Negotiation Support Department can also identify and propose successful strategies from the negotiating partner's past negotiation history. Furthermore, the Negotiation Support Department can analyze the negotiating partner's past negotiation history and make suggestions to avoid failed strategies. By providing strategies based on past negotiation history, more effective negotiations become possible. Some or all of the above processes in the Negotiation Support Department may be performed using, for example, generative AI, or without generative AI.

[0099] The Negotiation Support Department can update negotiation strategies in real time according to the progress of negotiations. For example, the Negotiation Support Department can propose the optimal strategy in real time according to the progress of negotiations. The Negotiation Support Department can also analyze the reactions of the negotiating party according to the progress of negotiations and update the strategy accordingly. Furthermore, the Negotiation Support Department can adjust the direction of negotiations according to the progress of negotiations to aim for the optimal outcome. In this way, by updating negotiation strategies in real time, it is possible to provide the optimal strategy according to the progress of negotiations. Some or all of the above processes in the Negotiation Support Department may be performed using, for example, generative AI, or without the use of generative AI.

[0100] The negotiation support unit can estimate the user's emotions and determine negotiation priorities based on those estimated emotions. For example, if the user is feeling highly anxious, the negotiation support unit will prioritize the most important negotiations. If the user is calm, the negotiation support unit can proceed with detailed negotiations. Furthermore, if the user is in a hurry, the negotiation support unit can prioritize negotiations that can be addressed quickly. This allows for more appropriate negotiations by prioritizing them according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The Negotiation Support Department can provide region-specific negotiation strategies when providing negotiation support, taking into account the user's geographical location. For example, the Negotiation Support Department can provide negotiation strategies tailored to the local legal situation based on the user's location. It can also provide negotiation strategies tailored to the local culture and customs based on the user's location. Furthermore, the Negotiation Support Department can provide contact information for local legal support agencies and experts based on the user's location. This enables more appropriate negotiations by providing region-specific negotiation strategies. Some or all of the above processing in the Negotiation Support Department may be performed using, for example, generative AI, or without the use of generative AI.

[0102] The Negotiation Support Department can improve the accuracy of negotiation strategies by referring to relevant legal literature during negotiation support. For example, depending on the type of negotiation, the Negotiation Support Department can improve the accuracy of negotiation strategies by referring to relevant legal literature. Furthermore, depending on the circumstances of the negotiation, the Negotiation Support Department can also improve the accuracy of negotiation strategies by referring to relevant case law. In addition, depending on the responsibility in the negotiation, the Negotiation Support Department can improve the accuracy of negotiation strategies by referring to relevant legal literature. Thus, the accuracy of negotiation strategies is improved by referring to relevant legal literature. Some or all of the above processing in the Negotiation Support Department may be performed using, for example, generative AI, or without the use of generative AI.

[0103] The collection unit can estimate the user's emotions and adjust the timing of evidence collection based on the estimated emotions. For example, if the user is nervous, the collection unit can delay the timing of evidence collection and wait for the user to calm down. Conversely, if the user is relaxed, the collection unit can accelerate the timing of evidence collection and respond quickly. Furthermore, if the user is confused, the collection unit can adjust the timing of evidence collection in stages to make it easier for the user to understand. This allows for more appropriate evidence collection by timing the collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The evidence collection unit can provide different evidence collection methods depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the collection unit can provide a simple evidence collection method. In the case of a serious accident, the collection unit can also provide a detailed evidence collection method. Furthermore, depending on the circumstances of the accident, the collection unit can provide specific instructions on how to collect evidence at the scene and how to report to the police. By providing evidence collection methods tailored to the type and circumstances of the accident, more appropriate evidence collection becomes possible. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without the use of a generative AI.

[0105] The data collection unit can estimate the user's emotions and determine the priority of evidence to collect based on the estimated emotions. For example, if the user is feeling highly anxious, the data collection unit will prioritize collecting the most important evidence. If the user is calm, the data collection unit can also collect detailed evidence. Furthermore, if the user is in a hurry, the data collection unit can prioritize collecting evidence that allows for a quick response. This enables more appropriate evidence collection by prioritizing evidence collection according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0106] The collection unit can prioritize the collection of highly relevant evidence by considering the user's geographical location information during evidence collection. For example, the collection unit can prioritize the collection of evidence related to local traffic laws based on the user's location. It can also prioritize the collection of evidence related to local accident circumstances based on the user's location. Furthermore, it can prioritize the collection of evidence related to local legal procedures based on the user's location. This allows for more appropriate evidence collection by prioritizing the collection of region-specific evidence. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without the use of a generative AI.

[0107] The creation unit can estimate the user's emotions and adjust the content and timing of document creation based on the estimated emotions. For example, if the user is nervous, the creation unit will create a simple and quick document. If the user is relaxed, the creation unit can also create a document containing detailed information. Furthermore, if the user is confused, the creation unit can create the document step by step to make it easier for the user to understand. This allows for more appropriate document creation by tailoring the document creation to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The document creation unit can apply different document creation algorithms depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the unit can apply a simple document creation algorithm. In the case of a serious accident, the unit can also apply a detailed document creation algorithm. Furthermore, depending on the circumstances of the accident, the unit can provide a list of necessary documents and create the appropriate documents. This makes it possible to create more appropriate documents by applying a document creation algorithm that is appropriate for the type and circumstances of the accident. Some or all of the above processing in the document creation unit may be performed using, for example, a generative AI, or it may be performed without using a generative AI.

[0109] The creation unit can estimate the user's emotions and determine the priority of documents to create based on those estimated emotions. For example, if the user is feeling highly anxious, the creation unit will prioritize creating the most important documents. If the user is calm, the creation unit can also create detailed documents. Furthermore, if the user is in a hurry, the creation unit can prioritize creating documents that can be handled quickly. This allows for more appropriate document creation by prioritizing documents according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The document creation unit can prioritize the creation of region-specific documents by considering the user's geographical location information during document creation. For example, the creation unit can prioritize the creation of documents related to local traffic laws based on the user's location. It can also prioritize the creation of documents related to local accident situations based on the user's location. Furthermore, it can prioritize the creation of documents related to local legal procedures based on the user's location. This allows for the creation of more appropriate documents by prioritizing region-specific documents. Some or all of the above processing in the creation unit may be performed using, for example, a generative AI, or without using a generative AI.

[0111] The simulation unit can estimate the user's emotions and adjust the content and timing of the compensation simulation based on the estimated emotions. For example, if the user is tense, the simulation unit will perform a simple and quick compensation simulation. If the user is relaxed, the simulation unit can also perform a compensation simulation with more detailed information. Furthermore, if the user is confused, the simulation unit can perform a step-by-step compensation simulation to make it easier for the user to understand. This allows for more appropriate simulations by performing compensation simulations that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0112] The simulation unit can apply different simulation algorithms depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the simulation unit can apply a simple simulation algorithm. In the case of a serious accident, the simulation unit can also apply a detailed simulation algorithm. Furthermore, depending on the circumstances of the accident, the simulation unit can provide a list of necessary compensation amounts and perform an appropriate simulation. This makes it possible to perform a more accurate simulation by applying a simulation algorithm appropriate to the type and circumstances of the accident. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or it may be performed without using a generative AI.

[0113] The simulation unit can estimate the user's emotions and determine the priority of simulations based on the estimated emotions. For example, if the user is feeling strong anxiety, the simulation unit will prioritize the most important simulations. If the user is calm, the simulation unit can also perform detailed simulations. Furthermore, if the user is in a hurry, the simulation unit can prioritize simulations that allow for a quick response. This allows for more appropriate simulations by prioritizing simulations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] The simulation unit can provide region-specific compensation simulations by taking into account the user's geographical location information during the simulation. For example, the simulation unit can provide compensation simulations related to local traffic laws based on the user's location. It can also provide compensation simulations related to local accident circumstances based on the user's location. Furthermore, the simulation unit can provide compensation simulations related to local legal procedures based on the user's location. By providing region-specific compensation simulations, more appropriate simulations become possible. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or without using a generative AI.

[0115] The optimization unit can estimate the user's emotions and optimize the negotiation scenario based on those emotions. For example, if the user is nervous, the optimization unit can provide a simple and quick negotiation scenario. If the user is relaxed, the optimization unit can also provide a negotiation scenario with more detailed information. Furthermore, if the user is confused, the optimization unit can provide a step-by-step negotiation scenario to make it easier for the user to understand. By optimizing the negotiation scenario according to the user's emotions, more effective negotiations become possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0116] The optimization unit can update the negotiation scenario in real time according to the progress of the negotiation. For example, the optimization unit can propose the optimal scenario in real time according to the progress of the negotiation. The optimization unit can also analyze the reactions of the negotiating party according to the progress of the negotiation and update the scenario accordingly. Furthermore, the optimization unit can adjust the direction of the negotiation according to the progress of the negotiation to aim for the optimal result. In this way, by updating the negotiation scenario in real time, it is possible to provide the optimal scenario according to the progress of the negotiation. Some or all of the above processing in the optimization unit may be performed using, for example, generative AI, or without using generative AI.

[0117] The optimization unit can estimate the user's emotions and determine the priority of negotiation scenarios to optimize based on those estimated emotions. For example, if the user is feeling highly anxious, the optimization unit will prioritize optimizing the most important negotiation scenarios. If the user is calm, the optimization unit can also optimize detailed negotiation scenarios. Furthermore, if the user is in a hurry, the optimization unit can prioritize optimizing negotiation scenarios that allow for quick responses. This enables more appropriate negotiations by optimizing negotiation scenarios according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0118] The optimization unit can provide region-specific negotiation scenarios by considering the user's geographical location information when optimizing negotiation scenarios. For example, the optimization unit can provide negotiation scenarios that are appropriate to the local legal situation based on the user's location. It can also provide negotiation scenarios that are appropriate to the local culture and customs based on the user's location. Furthermore, the optimization unit can provide contact information for local legal aid organizations and experts based on the user's location. By providing region-specific negotiation scenarios, more appropriate negotiations become possible. Some or all of the above processing in the optimization unit may be performed using, for example, generative AI, or without generative AI.

[0119] The support unit can estimate the user's emotions and adjust the content and timing of support based on the estimated emotions. For example, if the user is nervous, the support unit can provide simple and quick support. If the user is relaxed, the support unit can also provide support that includes detailed information. Furthermore, if the user is confused, the support unit can provide support step by step to make it easier for the user to understand. This allows for more appropriate assistance by providing support that is tailored to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0120] The support department can provide different support methods depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the support department can provide simple support methods. In the case of a serious accident, the support department can also provide detailed support methods. Furthermore, depending on the circumstances of the accident, the support department can provide specific instructions on how to provide support at the scene and how to report to the police. This allows for more appropriate assistance by providing support methods tailored to the type and circumstances of the accident. Some or all of the above-described processes in the support department may be performed using, for example, generative AI, or without the use of generative AI.

[0121] The support department can estimate the user's emotions and prioritize support based on those emotions. For example, if the user is feeling highly anxious, the support department will prioritize providing the most important support. If the user is calm, the support department can also provide detailed support. Furthermore, if the user is in a hurry, the support department can prioritize providing support that can be addressed quickly. This allows for more appropriate assistance by providing support in a priority order according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0122] The support unit can provide region-specific support by taking into account the user's geographical location when providing support. For example, the support unit can provide support related to local traffic laws based on the user's location. It can also provide support related to local accident situations based on the user's location. Furthermore, the support unit can provide support related to local legal procedures based on the user's location. By providing region-specific support, more appropriate assistance becomes possible. Some or all of the above processing in the support unit may be performed using, for example, generative AI, or without generative AI.

[0123] The management department can estimate the user's emotions and adjust the content and timing of compensation management based on the estimated emotions. For example, if the user is stressed, the management department can perform simple and rapid compensation management. If the user is relaxed, the management department can also perform compensation management that includes detailed information. Furthermore, if the user is confused, the management department can perform compensation management in stages to make it easier for the user to understand. This allows for more appropriate management by providing compensation management that is tailored to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0124] The management department can provide different compensation management methods depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the management department can provide a simple compensation management method. In the case of a serious accident, the management department can also provide a detailed compensation management method. Furthermore, depending on the circumstances of the accident, the management department can provide a list of necessary compensation and perform appropriate compensation management. This allows for more appropriate management by providing compensation management methods tailored to the type and circumstances of the accident. Some or all of the above processes in the management department may be performed using, for example, a generative AI, or not using a generative AI.

[0125] The management department can estimate the user's emotions and determine the priority of compensation management based on the estimated emotions. For example, if the user is feeling highly anxious, the management department will prioritize the most important compensation management. If the user is calm, the management department can also perform detailed compensation management. Furthermore, if the user is in a hurry, the management department can prioritize compensation management that can be addressed quickly. This allows for more appropriate management by prioritizing compensation management according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0126] The management unit can provide region-specific compensation management by taking into account the user's geographical location information when managing compensation. For example, the management unit can provide compensation management related to local traffic laws based on the user's location. It can also provide compensation management related to local accident circumstances based on the user's location. Furthermore, the management unit can provide compensation management related to local legal procedures based on the user's location. This enables more appropriate management by providing region-specific compensation management. Some or all of the above processing in the management unit may be performed using, for example, a generative AI, or without the use of a generative AI.

[0127] The face-to-face support unit can estimate the user's emotions and adjust the content and timing of face-to-face support based on the estimated emotions. For example, if the user is nervous, the face-to-face support unit can provide simple and quick face-to-face support. If the user is relaxed, the face-to-face support unit can also provide face-to-face support that includes detailed information. Furthermore, if the user is confused, the face-to-face support unit can provide face-to-face support in stages to make it easier for the user to understand. This allows for more appropriate support by providing face-to-face support that is tailored to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0128] The face-to-face support unit can provide different face-to-face support methods depending on the type and circumstances of the traffic accident. For example, in the case of a minor accident, the face-to-face support unit can provide a simple face-to-face support method. In the case of a serious accident, the face-to-face support unit can also provide a detailed face-to-face support method. Furthermore, depending on the circumstances of the accident, the face-to-face support unit can provide specific instructions on how to provide face-to-face support at the scene and how to report to the police. This allows for more appropriate support by providing face-to-face support methods tailored to the type and circumstances of the accident. Some or all of the above processing in the face-to-face support unit may be performed using, for example, generative AI, or without the use of generative AI.

[0129] The face-to-face support unit can estimate the user's emotions and prioritize face-to-face support based on those emotions. For example, if the user is feeling highly anxious, the face-to-face support unit will prioritize providing the most important face-to-face support. If the user is calm, the face-to-face support unit can also provide detailed face-to-face support. Furthermore, if the user is in a hurry, the face-to-face support unit can prioritize providing face-to-face support that can be handled quickly. This allows for more appropriate support by providing face-to-face support with priorities according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0130] The face-to-face support unit can provide region-specific face-to-face support by taking into account the user's geographical location information when providing face-to-face support. For example, the face-to-face support unit can provide face-to-face support related to local traffic laws based on the user's location. It can also provide face-to-face support related to local accident situations based on the user's location. Furthermore, the face-to-face support unit can provide face-to-face support related to local legal procedures based on the user's location. This enables more appropriate support by providing region-specific face-to-face support. Some or all of the above processing in the face-to-face support unit may be performed using, for example, generative AI, or without generative AI.

[0131] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0132] The legal support system can also include an advice history analysis unit that analyzes the user's past legal consultation history and provides optimal advice. For example, the advice history analysis unit can provide advice for similar cases based on the user's past consultations. Furthermore, the advice history analysis unit can propose solutions to specific legal problems based on the user's past consultation history. In addition, the advice history analysis unit can analyze the user's past consultation history and provide advice to prevent recurrence. This enables more effective legal support by providing advice based on past consultation history.

[0133] The legal support system may also include an emotion-adjusted evidence collection unit that estimates the user's emotions and adjusts the timing of evidence collection based on those emotions. For example, if the user is tense, the emotion-adjusted evidence collection unit may delay the timing of evidence collection and wait for the user to calm down. Conversely, if the user is relaxed, the emotion-adjusted evidence collection unit may accelerate the timing of evidence collection and respond quickly. Furthermore, if the user is confused, the emotion-adjusted evidence collection unit may adjust the timing of evidence collection in stages to make it easier for the user to understand. This allows for more appropriate evidence collection by timing it according to the user's emotions.

[0134] The legal support system may also include a geographic information advisory section that provides region-specific legal information, taking into account the user's geographic location. For example, the geographic information advisory section could provide information on local traffic laws and procedures based on the user's location. It could also provide contact information for local legal support agencies and professionals based on the user's location. Furthermore, it could provide information on local courts and police stations based on the user's location. This allows for more appropriate legal support by providing region-specific legal information.

[0135] The legal support system may also include an emotion adjustment simulation unit that estimates the user's emotions and adjusts the content and timing of the compensation simulation based on those emotions. For example, if the user is tense, the emotion adjustment simulation unit will perform a simple and quick compensation simulation. If the user is relaxed, the emotion adjustment simulation unit can also perform a compensation simulation with more detailed information. Furthermore, if the user is confused, the emotion adjustment simulation unit can perform a step-by-step compensation simulation to make it easier for the user to understand. This allows for more appropriate simulations by performing compensation simulations that are tailored to the user's emotions.

[0136] The legal support system may also include an emotion adjustment optimization unit that estimates the user's emotions and optimizes negotiation scenarios based on those emotions. For example, if the user is tense, the emotion adjustment optimization unit can provide a simple and quick negotiation scenario. If the user is relaxed, it can also provide a negotiation scenario with more detailed information. Furthermore, if the user is confused, the emotion adjustment optimization unit can provide a step-by-step negotiation scenario to make it easier for the user to understand. This allows for more effective negotiations by optimizing the negotiation scenario according to the user's emotions.

[0137] The legal support system may also include an emotion-adjusting support unit that estimates the user's emotions and adjusts the content and timing of support based on those emotions. For example, if the user is stressed, the emotion-adjusting support unit can provide simple and quick support. If the user is relaxed, it can also provide support that includes more detailed information. Furthermore, if the user is confused, the emotion-adjusting support unit can provide support in a step-by-step manner to make it easier for the user to understand. This allows for more appropriate support by providing assistance tailored to the user's emotions.

[0138] The legal support system may also include a geographic information evidence analysis unit that prioritizes the analysis of region-specific evidence, taking into account the user's geographic location. For example, the geographic information evidence analysis unit might prioritize the analysis of evidence related to local traffic laws based on the user's location. It could also prioritize the analysis of evidence related to local accident circumstances based on the user's location. Furthermore, it could prioritize the analysis of evidence related to local legal procedures based on the user's location. This allows for more appropriate evidence analysis by prioritizing the analysis of region-specific evidence.

[0139] The legal support system may also include an emotion-adjusted document creation unit that estimates the user's emotions and adjusts the content and timing of document creation based on those emotions. For example, if the user is stressed, the emotion-adjusted document creation unit will create a simple and quick document. If the user is relaxed, the emotion-adjusted document creation unit can also create a document containing detailed information. Furthermore, if the user is confused, the emotion-adjusted document creation unit can create a document in a step-by-step manner to make it easier for the user to understand. This allows for more appropriate document creation by tailoring the document creation to the user's emotions.

[0140] The legal support system may further include a geographic information simulation unit that provides region-specific compensation simulations, taking into account the user's geographic location. For example, the geographic information simulation unit may provide compensation simulations related to local traffic laws based on the user's location. It may also provide compensation simulations related to local accident circumstances based on the user's location. Furthermore, the geographic information simulation unit may provide compensation simulations related to local legal procedures based on the user's location. This allows for more appropriate simulations by providing region-specific compensation simulations.

[0141] The legal support system may also include an emotion adjustment management unit that estimates the user's emotions and adjusts the content and timing of compensation management based on those estimated emotions. For example, if the user is stressed, the emotion adjustment management unit can provide simple and rapid compensation management. If the user is relaxed, the emotion adjustment management unit can also provide compensation management with more detailed information. Furthermore, if the user is confused, the emotion adjustment management unit can provide compensation management in a step-by-step manner to make it easier for the user to understand. This allows for more appropriate management by providing compensation management that is tailored to the user's emotions.

[0142] The following briefly describes the processing flow for example form 2.

[0143] Step 1: The Advice Unit provides continuously operating AI legal advice. Continuous operation means operating 24 hours a day, 365 days a year, or under specific conditions such as time zones. For example, the Advice Unit provides immediate legal advice to victims immediately after a traffic accident occurs. The Advice Unit can provide specific guidance, such as how to collect evidence at the accident scene and how to automatically create necessary documents. Step 2: The evidence analysis department performs AI-based evidence analysis using multiple data modals. These data modals include, for example, text data, image data, and audio data. The evidence analysis department analyzes, for example, photos and videos of the accident scene to clarify the cause of the accident and who is responsible. The evidence analysis department can use image recognition technology to objectively analyze the accident situation and evaluate its validity as evidence. Step 3: The Negotiation Support Department provides negotiation support based on sentiment analysis. Sentiment analysis involves analyzing emotions based on the algorithms and emotional classification criteria used. For example, the Negotiation Support Department analyzes the emotions of the victim and the perpetrator and proposes the optimal negotiation strategy. The Negotiation Support Department can also simulate compensation amounts and optimize negotiation scenarios, taking into account the victim's emotional state.

[0144] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0146] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0147] Each of the multiple elements described above, including the advice unit, evidence analysis unit, negotiation support unit, collection unit, creation unit, simulation unit, optimization unit, support unit, management unit, and face-to-face support unit, is implemented by at least one of the smart device 14 and the data processing unit 12. For example, the advice unit is implemented by the control unit 46A of the smart device 14 and provides immediate legal advice to the victim immediately after a traffic accident occurs. The evidence analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes photographs and videos of the accident scene to clarify the cause of the accident and the responsibility. The negotiation support unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the emotions of the victim and perpetrator and proposes the optimal negotiation strategy. The collection unit provides an evidence collection method using the camera 42 and microphone 38B of the smart device 14. The creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and automatically creates the necessary documents. The simulation unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs a compensation simulation. The optimization unit is implemented by the specific processing unit 290 of the data processing device 12 and optimizes negotiation scenarios. The support unit is implemented by the control unit 46A of the smart device 14 and provides constant support through messaging services. The management unit is implemented by the specific processing unit 290 of the data processing device 12 and performs secure compensation management in the electronic payment system. The face-to-face support unit is implemented by the control unit 46A of the smart device 14 and provides face-to-face support through a nationwide store network. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0148] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0149] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0150] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0151] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0152] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0154] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0155] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements mentioned above, including the advice unit, evidence analysis unit, negotiation support unit, collection unit, creation unit, simulation unit, optimization unit, support unit, management unit, and face-to-face support unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the advice unit is implemented by the control unit 46A of the smart glasses 214 and provides immediate legal advice to the victim immediately after a traffic accident occurs. The evidence analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes photographs and videos of the accident scene to clarify the cause of the accident and the responsibility. The negotiation support unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the emotions of the victim and perpetrator and proposes the optimal negotiation strategy. The collection unit provides an evidence collection method using the camera 42 and microphone 238 of the smart glasses 214. The creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and automatically creates the necessary documents. The simulation unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs a compensation simulation. The optimization unit is implemented by the specific processing unit 290 of the data processing device 12 and optimizes negotiation scenarios. The support unit is implemented by the control unit 46A of the smart glasses 214 and provides constant support through messaging services. The management unit is implemented by the specific processing unit 290 of the data processing device 12 and performs secure compensation management in the electronic payment system. The face-to-face support unit is implemented by the control unit 46A of the smart glasses 214 and provides face-to-face support through a nationwide store network. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0164] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0165] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0166] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0167] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0168] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0169] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0170] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0171] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0172] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0173] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0174] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0175] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0176] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0177] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0178] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0179] Each of the multiple elements mentioned above, including the advice unit, evidence analysis unit, negotiation support unit, collection unit, creation unit, simulation unit, optimization unit, support unit, management unit, and face-to-face support unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the advice unit is implemented by the control unit 46A of the headset terminal 314 and provides immediate legal advice to the victim immediately after the traffic accident occurs. The evidence analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes photographs and videos of the accident scene to clarify the cause of the accident and the responsibility. The negotiation support unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the emotions of the victim and perpetrator to propose the optimal negotiation strategy. The collection unit provides an evidence collection method using the camera 42 and microphone 238 of the headset terminal 314. The creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and automatically creates the necessary documents. The simulation unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs a compensation simulation. The optimization unit is implemented by the specific processing unit 290 of the data processing device 12 and optimizes negotiation scenarios. The support unit is implemented by the control unit 46A of the headset terminal 314 and provides constant support through messaging services. The management unit is implemented by the specific processing unit 290 of the data processing device 12 and performs secure compensation management in the electronic payment system. The face-to-face support unit is implemented by the control unit 46A of the headset terminal 314 and provides face-to-face support through a nationwide store network. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0180] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0181] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0182] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0183] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0184] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0185] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0186] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0187] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0188] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0189] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0190] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0191] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0192] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0193] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0194] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0195] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0196] Each of the multiple elements described above, including the advice unit, evidence analysis unit, negotiation support unit, collection unit, creation unit, simulation unit, optimization unit, support unit, management unit, and face-to-face support unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the advice unit is implemented by the control unit 46A of the robot 414 and provides immediate legal advice to the victim immediately after a traffic accident occurs. The evidence analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes photographs and videos of the accident scene to clarify the cause of the accident and the responsibility. The negotiation support unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the emotions of the victim and perpetrator and proposes the optimal negotiation strategy. The collection unit provides a method for collecting evidence using the camera 42 and microphone 238 of the robot 414. The creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and automatically creates the necessary documents. The simulation unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs a compensation simulation. The optimization unit is implemented by the specific processing unit 290 of the data processing device 12 and optimizes negotiation scenarios. The support unit is implemented by the control unit 46A of the robot 414 and provides constant support through messaging services. The management unit is implemented by the specific processing unit 290 of the data processing device 12 and performs secure compensation management in the electronic payment system. The face-to-face support unit is implemented by the control unit 46A of the robot 414 and provides face-to-face support through a nationwide store network. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0197] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0198] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0199] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0200] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0201] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0202] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0203] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0204] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0205] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0206] 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.

[0207] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0208] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0209] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0210] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0211] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0212] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0213] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0214] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0215] (Note 1) An advisory department that provides continuously operating AI legal advice, The evidence analysis department performs AI-based evidence analysis using multiple data modals, It includes a Negotiation Support Department that provides negotiation support based on sentiment analysis. A system characterized by the following features. (Note 2) It includes a collection unit that provides methods for collecting evidence. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a creation unit that automatically generates necessary documents. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a simulation unit that performs compensation calculations. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a coordinating unit to adjust the negotiation scenario. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a support unit that provides constant support through messaging services. The system described in Appendix 1, characterized by the features described herein. (Note 7) The system includes a management department that handles the secure management of compensation payments within the electronic payment system. The system described in Appendix 1, characterized by the features described herein. (Note 8) We have a face-to-face support department that provides in-person support through our nationwide network of stores. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned advice section, It estimates the user's emotions and adjusts the content and timing of advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned advice section, Depending on the type and circumstances of the traffic accident, different advice algorithms will be applied. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned advice section, We analyze the user's past legal consultation history and provide the best possible advice. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned advice section, It estimates the user's emotions and prioritizes advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned advice section, When providing advice, we will consider the user's geographical location and provide region-specific legal information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned advice section, When providing advice, we analyze the user's social media activity and provide relevant legal advice. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned evidence analysis department, We estimate the user's emotions and adjust the evidence analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned evidence analysis department, Using image recognition technology, we conduct a detailed analysis of the accident scene and evaluate the validity of the evidence. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned evidence analysis department, Depending on the type of evidence, different analytical algorithms are applied. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned evidence analysis department, We estimate user sentiment and prioritize evidence analysis based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned evidence analysis department, During evidence analysis, the system prioritizes analyzing region-specific evidence by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned evidence analysis department, When analyzing evidence, referencing relevant legal literature improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned Negotiation Support Department, It estimates the user's emotions and adjusts negotiation strategies based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned Negotiation Support Department, We analyze the negotiating partner's past negotiation history and propose the optimal negotiation strategy. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned Negotiation Support Department, We update our negotiation strategy in real time as negotiations progress. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned Negotiation Support Department, The system estimates the user's emotions and determines negotiation priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned Negotiation Support Department, When providing negotiation support, we offer region-specific negotiation strategies that take into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned Negotiation Support Department, When providing negotiation support, we improve the accuracy of negotiation strategies by referring to relevant legal literature. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of evidence collection based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned collection unit is We offer different methods of evidence collection depending on the type and circumstances of the traffic accident. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned collection unit is Infer user sentiment and prioritize the evidence to collect based on that inferred sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned collection unit is When collecting evidence, the system prioritizes collecting highly relevant evidence by considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned creation unit, It estimates the user's emotions and adjusts the content and timing of document creation based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned creation unit, Depending on the type and circumstances of the traffic accident, different document creation algorithms will be applied. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned creation unit, It estimates the user's emotions and determines the priority of documents to create based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned creation unit, When creating documents, prioritize the creation of region-specific documents by considering the user's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned simulation unit, The system estimates the user's emotions and adjusts the content and timing of the compensation simulation based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 36) The aforementioned simulation unit, Depending on the type and circumstances of the traffic accident, different simulation algorithms are applied. The system described in Appendix 4, characterized by the features described herein. (Note 37) The aforementioned simulation unit, It estimates the user's emotions and determines the priority of simulations based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 38) The aforementioned simulation unit, During the simulation, the system takes into account the user's geographical location to provide region-specific compensation simulations. The system described in Appendix 4, characterized by the features described herein. (Note 39) The optimization unit, It estimates user emotions and optimizes negotiation scenarios based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 40) The optimization unit, The negotiation scenario will be updated in real time according to the progress of the negotiations. The system described in Appendix 5, characterized by the features described herein. (Note 41) The optimization unit, It estimates user sentiment and prioritizes negotiation scenarios to optimize them based on the estimated user sentiment. The system described in Appendix 5, characterized by the features described herein. (Note 42) The optimization unit, When optimizing negotiation scenarios, we provide region-specific negotiation scenarios that take into account the user's geographical location. The system described in Appendix 5, characterized by the features described herein. (Note 43) The aforementioned support unit is The system estimates the user's emotions and adjusts the content and timing of support based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 44) The aforementioned support unit is We provide different support methods depending on the type and circumstances of the traffic accident. The system described in Appendix 6, characterized by the features described herein. (Note 45) The aforementioned support unit is The system estimates the user's emotions and determines support priorities based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 46) The aforementioned support unit is When providing support, we take the user's geographical location into consideration to provide region-specific support. The system described in Appendix 6, characterized by the features described herein. (Note 47) The aforementioned management department, The system estimates user sentiment and adjusts the content and timing of compensation management based on the estimated user sentiment. The system described in Appendix 7, characterized by the features described herein. (Note 48) The aforementioned management department, We offer different compensation management methods depending on the type and circumstances of the traffic accident. The system described in Appendix 7, characterized by the features described herein. (Note 49) The aforementioned management department, The system estimates user sentiment and prioritizes compensation management based on the estimated user sentiment. The system described in Appendix 7, characterized by the features described herein. (Note 50) The aforementioned management department, When managing compensation payments, we provide region-specific compensation management that takes into account the user's geographical location. The system described in Appendix 7, characterized by the features described herein. (Supplementary Note 51) The face support unit estimates the user's emotion and adjusts the content and timing of face support based on the estimated user emotion The system according to Supplementary Note 8, characterized in that. (Supplementary Note 52) The face support unit provides different face support methods according to the type and situation of traffic accidents The system according to Supplementary Note 8, characterized in that. (Supplementary Note 53) The face support unit estimates the user's emotion and determines the priority of face support based on the estimated user emotion The system according to Supplementary Note 8, characterized in that. (Supplementary Note 54) The face support unit provides region-specific face support considering the user's geographical location information when providing face support The system according to Supplementary Note 8, characterized in that.

Explanation of Signs

[0216] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset-type terminal 414 Robot

Claims

1. An advisory department that provides continuously operating AI legal advice, The evidence analysis department performs AI-based evidence analysis using multiple data modals, It includes a Negotiation Support Department that provides negotiation support based on sentiment analysis. A system characterized by the following features.

2. It includes a collection unit that provides methods for collecting evidence. The system according to feature 1.

3. It includes a creation unit that automatically generates necessary documents. The system according to feature 1.

4. It includes a simulation unit that performs compensation calculations. The system according to feature 1.

5. It includes a coordinating unit to adjust the negotiation scenario. The system according to feature 1.

6. It includes a support unit that provides constant support through messaging services. The system according to feature 1.

7. The system includes a management department that handles the secure management of compensation payments within the electronic payment system. The system according to feature 1.

8. We have a face-to-face support department that provides in-person support through our nationwide network of stores. The system according to feature 1.

Images