System

Abstract

To provide a system capable of efficiently detecting potential risks and problems hidden in user behavior.SOLUTION: The system in an embodiment includes a reception unit, an inquiry unit, an identification unit, an analysis unit, and a proposal unit. The reception unit receives an input of a summary of user actions. The inquiry unit repeats the question based on the information input by the reception unit. The identification unit identifies risk based on the information obtained by the inquiry unit. The analysis unit analyzes whether the risk identified by the identification unit develops into a concrete problem. The proposal unit proposes the risk analyzed by the analysis unit and specific measures therefor.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have the disadvantage that it is difficult to efficiently detect potential risks and problems hidden in user behavior.

[0005] The system according to the embodiment aims to efficiently detect potential risks and problems hidden in user behavior. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, a questioning unit, an identification unit, an analysis unit, and a proposal unit. The receiving unit inputs an overview of a user's behavior. The questioning unit repeatedly asks questions based on the information input by the receiving unit. The identification unit identifies risks based on the information obtained by the questioning unit. The analysis unit analyzes whether the risks identified by the identification unit will develop into specific problems. The proposal unit proposes the risks analyzed by the analysis unit and specific countermeasures for those risks. Effect of the Invention

[0007] The system according to the embodiment can efficiently detect potential risks and problems hidden in user behavior. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The risk detection system according to the embodiment of the present invention is a system that detects potential risks and problems hidden in the user's actions in an interactive format. This risk detection system starts with the user simply inputting "what they have done in the past" and "what they are going to do in the future". Next, the AI ​​repeatedly asks questions that dig deeper into the content. For example, questions such as "What activities did you do at your travel destination?" and "What are your specific plans for your new project?" This brings up details of the action. The AI ​​identifies elements that could be risks based on the user's answers. For example, safety in activities at the travel destination and fundraising risks for a new project. Furthermore, the AI ​​analyzes what problems the risks could develop into. For example, the risk of safety leading to an accident, or the risk of fundraising leading to the interruption of a project. Finally, the AI ​​proposes risks and countermeasures to the user. For example, "take sufficient safety measures for activities at your travel destination" or "review your fundraising plan for the new project". This allows the user to grasp potential risks and problems hidden in their actions in advance and take appropriate measures. This enables the risk detection system to detect potential risks and problems lurking in user behavior in advance and take appropriate measures.

[0029] The risk detection system according to the embodiment includes a reception unit, a questioning unit, an identification unit, an analysis unit, and a proposal unit. The reception unit inputs an overview of the user's behavior. The overview of the user's behavior includes, for example, the type, frequency, and location of the behavior, but is not limited to such examples. The reception unit provides an interface for inputting, for example, the user's past behavior and the behavior that he or she is going to perform in the future. The questioning unit repeats detailed questions based on the information input by the reception unit. The questioning unit asks in-depth questions, for example, to find out the details of the user's behavior. For example, the questioning unit asks questions such as "What activities did you do at your travel destination?" and "What are your specific plans for your new project?" The identification unit identifies risks based on the information obtained by the questioning unit. The identification unit analyzes information using AI, for example, to identify risks lurking in the user's behavior. For example, the identification unit identifies safety risks in activities at your travel destination and risks in raising funds for your new project. The analysis unit analyzes what kind of problems the risks identified by the identification unit will develop into. The analysis unit analyzes information using AI, for example, to analyze the possibility that the identified risk will develop into a specific problem. For example, it analyzes the possibility that a safety risk will lead to an accident, or that a fundraising risk will lead to the interruption of a project. The suggestion unit proposes the risks analyzed by the analysis unit and countermeasures therefor to the user. The suggestion unit analyzes information using AI, for example, to propose risks and countermeasures therefor to the user. For example, it makes suggestions such as "take sufficient safety measures for activities at the travel destination" and "review the fundraising plan for the new project." As a result, the risk detection system according to the embodiment can detect potential risks and problems lurking in the user's behavior in advance and take appropriate measures.

[0030] The reception unit inputs an outline of the user's behavior. The outline of the user's behavior includes, but is not limited to, the type, frequency, and location of the behavior. The reception unit provides, for example, an interface for inputting the user's past behavior and the behavior he or she is going to perform in the future. Specifically, the reception unit has a graphical user interface (GUI) that the user can intuitively operate, and the user can input information using a drop-down menu, a check box, and a text input field. For example, if the user is planning a trip, the user can input the country and city of the destination, the travel period, the type of planned activity, and the like. In addition, detailed information about past behavior can be input in a similar manner. Furthermore, the reception unit has a voice input function, and the user can also input the outline of the behavior by voice. The voice input is converted into text using natural language processing technology and is imported into the system. This allows the user to easily input information, and promotes the use of the system. The reception unit centrally manages the input information and stores it in a database to be provided to the subsequent questioning unit and identification unit. The database is secured and uses encryption technology to protect the user's privacy. This enables the reception unit to efficiently collect detailed information regarding user behavior, thereby improving the accuracy and reliability of the entire system.

[0031] The questioning unit repeatedly asks detailed questions based on the information input by the reception unit. For example, the questioning unit asks probing questions to find out the details of the user's actions. For example, the questioning unit asks questions such as "What activities did you do at your travel destination?" and "What are your specific plans for your new project?". The questioning unit uses AI to analyze the user's input and generates appropriate questions. Specifically, the questioning unit uses natural language processing technology to understand the user's input and automatically generate questions to draw out relevant detailed information. For example, if the user inputs "I'm planning to hike at my travel destination," the questioning unit generates specific questions such as "What is the hiking route like?" and "What equipment do I need while hiking?". The questioning unit can also ask more detailed questions based on the user's answers. For example, if the user answers "I'm raising funds for my new project," the questioning unit asks additional questions such as "What is the method of raising funds?" and "What is the target amount of fundraising?". This allows the questioning unit to efficiently collect detailed information about the user's actions and enrich the data to be provided to the identification unit and analysis unit. Furthermore, the questioning unit can analyze the content of the user's answers in real time and adjust the content and order of the questions as necessary, making it possible to reliably collect necessary information while reducing the burden on the user.

[0032] The identification unit identifies risks based on the information obtained by the question unit. For example, the identification unit uses AI to analyze information to identify risks lurking in the user's behavior. For example, the identification unit identifies safety risks in activities at a travel destination and risks in fundraising for a new project. Specifically, the identification unit uses a machine learning algorithm to evaluate risks based on past data and statistical information. For example, the identification unit analyzes security information at the travel destination and past accident data to evaluate risks associated with a specific activity. In addition, for a new project, the identification unit evaluates risks based on the success rate of similar projects in the past and the difficulty of fundraising. The identification unit comprehensively analyzes these pieces of information to identify risks associated with the user's behavior. Furthermore, the identification unit can incorporate information that is updated in real time and perform risk evaluations continuously. For example, weather information and local news at the travel destination can be obtained in real time and reflected in the risk evaluation. As a result, the identification unit can always perform risk evaluations based on the latest information and provide accurate risk information to the user. The identification unit provides the results of the risk evaluation to the analysis unit and provides data for analyzing the possibility of development of a specific problem. As a result, the identification unit can quickly and accurately identify risks lurking in the user's behavior and improve the risk management capability of the entire system.

[0033] The analysis unit analyzes what kind of problem the risk identified by the identification unit will develop into. For example, the analysis unit uses AI to analyze information to analyze the possibility that the identified risk will develop into a specific problem. For example, it analyzes the possibility that a safety risk will lead to an accident, or that a fundraising risk will lead to the interruption of a project. Specifically, the analysis unit uses simulation technology to predict what impact the identified risk will have in reality. For example, for safety risks in activities at a travel destination, a simulation is performed based on past accident data and local environmental information to predict the probability of an accident occurring and its scope of impact. In addition, for fundraising risks in a new project, a simulation is performed based on the progress of fundraising and market trends to predict the possibility of project interruption due to lack of funds. Based on these simulation results, the analysis unit can evaluate the possibility that the risk will develop into a specific problem and show the user the severity and scope of the risk. In addition, the analysis unit can use past data and statistical information to analyze risk trends and patterns. This can be useful for long-term risk assessment and planning of preventive measures. The analysis unit provides the analysis results to the proposal unit and provides data for proposing specific measures to the user. This enables the analysis unit to perform detailed analysis of the specific impact of risks, thereby improving the risk management capabilities of the entire system.

[0034] The suggestion unit proposes the risks analyzed by the analysis unit and their countermeasures to the user. For example, the suggestion unit uses AI to analyze information in order to propose risks and their countermeasures to the user. For example, the suggestion unit makes suggestions such as "take sufficient safety measures for activities at the travel destination" and "review the fundraising plan for the new project". Specifically, the suggestion unit presents specific countermeasures to the user based on the risk assessment results provided by the analysis unit. For example, for safety risks in activities at the travel destination, the suggestion unit proposes specific countermeasures such as "check local safety guidelines and prepare necessary equipment" and "avoid dangerous areas". In addition, for the risk of fundraising in a new project, the suggestion unit proposes specific countermeasures such as "consider multiple fundraising methods and diversify risks" and "regularly review the progress of fundraising and revise the plan as necessary". The suggestion unit can select and present the optimal countermeasures according to the user's situation and needs. Furthermore, the suggestion unit can collect feedback from the user and continuously improve the accuracy and effectiveness of the proposals. For example, the suggestion unit collects the results of the user's implementation of the proposed countermeasures as feedback, and improves the proposal algorithm based on that data. This allows the proposal unit to always provide the user with optimal countermeasure proposals, maximizing the effectiveness of risk management. The proposal unit is equipped with a visual interface and notification functions to communicate the proposal contents to the user in an easy-to-understand manner, and supports the user in quickly implementing countermeasures. This allows the proposal unit to provide the user with specific and executable countermeasures, enhancing the effectiveness of risk management.

[0035] The questioning unit can repeatedly ask detailed questions to find out the details of the user's behavior. The questioning unit, for example, asks probing questions to find out the details of the user's behavior. For example, the questioning unit asks questions such as "What activities did you do at your travel destination?" or "What are your specific plans for your new project?". The questioning unit can also ask more detailed questions based on the user's answers. For example, if the user answers "I went skydiving at my travel destination," the questioning unit can ask questions such as "What safety measures did you take when skydiving?". This allows the questioning unit to effectively find out the details of the user's behavior. Some or all of the above-mentioned processing in the questioning unit may be performed, for example, using AI, or may be performed without using AI. For example, the questioning unit can input the user's answers to AI and ask detailed questions based on the questions generated by AI.

[0036] The identification unit can identify risks inherent in the user's behavior. For example, the identification unit uses AI to analyze information to identify risks lurking in the user's behavior. For example, the identification unit identifies safety risks in activities at a travel destination and risks in fundraising for a new project. The identification unit uses AI to analyze information to identify elements that may be risks based on the user's answers. For example, if the user answers "I went skydiving at my travel destination," the identification unit can ask questions such as "What safety measures did you take when skydiving?" and identify safety risks based on the answers. This allows the identification unit to effectively identify risks lurking in the user's behavior. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the identification unit can input the user's answers to the generation AI and identify risks based on the results of risk identification generated by the generation AI.

[0037] The analysis unit can analyze whether the identified risk develops into a specific problem. The analysis unit, for example, uses AI to analyze information in order to analyze the possibility that the identified risk will develop into a specific problem. For example, the analysis unit analyzes the possibility that a safety risk will lead to an accident, or that a fundraising risk will lead to the interruption of a project. The analysis unit uses AI to analyze information in order to analyze what kind of problem the risk will develop into based on the risk identified by the identification unit. For example, if a user answers that "I went skydiving at my travel destination" and the identification unit identifies a safety risk, the analysis unit can perform an analysis such as "What kind of accident is likely to occur during skydiving?" This allows the analysis unit to effectively analyze what kind of problem the risk will develop into. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the risk identified by the identification unit into the generation AI and analyze the risk based on the analysis result generated by the generation AI.

[0038] The suggestion unit can suggest risks and specific measures to the user. The suggestion unit, for example, uses AI to analyze information in order to suggest risks and measures to the user. For example, the suggestion unit makes suggestions such as "take sufficient safety measures for activities at the travel destination" and "review the fundraising plan for the new project". The suggestion unit analyzes information using AI in order to suggest risks and measures to the user based on the risks analyzed by the analysis unit. For example, if the user answers "I went skydiving at my travel destination", the identification unit identifies a safety risk, and the analysis unit analyzes the possibility that the risk may lead to an accident, the suggestion unit can make suggestions such as "take sufficient safety measures when skydiving". This allows the suggestion unit to effectively suggest risks and measures to the user. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the suggestion unit can input the risks analyzed by the analysis unit to the generation AI and propose measures to the risk based on the proposal results generated by the generation AI.

[0039] The reception unit can analyze the user's past behavior history and select the optimal input method. For example, the reception unit preferentially suggests an input method (such as voice or text) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used in a specific time period from the user's past behavior history. Furthermore, the reception unit can also analyze the user's past behavior history and suggest the most efficient input method. This allows the reception unit to provide the optimal input method based on the user's past behavior history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's past behavior history data to the generation AI and select the optimal input method based on the input method proposal result generated by the generation AI.

[0040] The reception unit can filter the summary of the behavior based on the user's current situation and field of interest when inputting the behavior summary. For example, the reception unit preferentially inputs highly relevant behavior based on the user's current situation. The reception unit can also filter related behaviors based on the user's field of interest to simplify the input. Furthermore, the reception unit can also suggest an optimal input method in consideration of the user's current situation and field of interest. This allows the reception unit to simplify the input based on the user's current situation and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the user's current situation and field of interest to the generation AI and simplify the input based on the filtering result generated by the generation AI.

[0041] The reception unit can preferentially input highly relevant actions in consideration of the geographical location information of the user when inputting an overview of the action. The reception unit preferentially inputs highly relevant actions based on, for example, the user's current location. The reception unit can also suggest optimal actions in consideration of the geographical location information of the user. Furthermore, the reception unit can preferentially input highly relevant actions in consideration of the distance from the user's current location. This allows the reception unit to preferentially input highly relevant actions based on the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the geographical location information data of the user to the generation AI and preferentially input highly relevant actions based on the action proposal result generated by the generation AI.

[0042] The reception unit can analyze the user's social media activity and input related actions when inputting an overview of the action. The reception unit, for example, analyzes the user's social media activity and suggests related actions. The reception unit can also predict a specific action from the user's social media activity and simplify the input. Furthermore, the reception unit can input an optimal action based on the user's social media activity. This allows the reception unit to input related actions based on the user's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity data to the generation AI and input related actions based on the action proposal result generated by the generation AI.

[0043] The questioning unit can adjust the level of detail of the question based on the importance of the behavior when asking a question. For example, the questioning unit asks a detailed question for a behavior with a high level of importance. Also, the questioning unit can ask a concise question for a behavior with a low level of importance. Furthermore, the questioning unit can adjust the level of detail of the question according to the importance of the behavior. As a result, the questioning unit can ask a more appropriate question by adjusting the level of detail of the question according to the importance of the behavior. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input the importance data of the behavior to the generation AI and ask a question based on the level of detail of the question generated by the generation AI.

[0044] The questioning unit can apply different questioning algorithms depending on the category of the behavior when asking a question. For example, the questioning unit applies a questioning algorithm specialized for travel to a behavior related to travel. In addition, the questioning unit can also apply a questioning algorithm specialized for project management to a behavior related to a project. Furthermore, the questioning unit can apply a questioning algorithm specialized for daily life to a behavior related to daily life. In this way, the questioning unit can ask more effective questions by applying an appropriate questioning algorithm depending on the category of the behavior. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input behavior category data to the generation AI and ask a question based on a questioning algorithm generated by the generation AI.

[0045] The questioning unit can determine the priority of questions based on the time when the action was performed when asking a question. For example, the questioning unit prioritizes questions about the most recent action. The questioning unit can also postpone questions about past actions. Furthermore, the questioning unit can adjust the priority of questions according to the time when the action was performed. This allows the questioning unit to ask more appropriate questions by determining the priority of questions based on the time when the action was performed. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input data on the time when the action was performed to the generation AI and ask a question based on the priority of questions generated by the generation AI.

[0046] The questioning unit can adjust the order of questions based on the relevance of behaviors when asking a question. For example, the questioning unit prioritizes questions about highly relevant behaviors. Also, the questioning unit can postpone questions about less relevant behaviors. Furthermore, the questioning unit can adjust the order of questions according to the relevance of behaviors. In this way, the questioning unit can ask more appropriate questions by adjusting the order of questions based on the relevance of behaviors. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input behavior relevance data to a generation AI and ask questions based on the order of questions generated by the generation AI.

[0047] The identification unit can improve the accuracy of identification by considering the interrelationships of actions when identifying risks. For example, when multiple actions are related, the identification unit identifies risks by considering the interrelationships. The identification unit can also analyze the interrelationships of actions and improve the accuracy of identification. Furthermore, the identification unit can also improve the accuracy of risk identification by considering the interrelationships of actions. In this way, the identification unit can improve the accuracy of risk identification by considering the interrelationships of actions. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the interrelationship data of actions to the generation AI and improve the accuracy of identification based on the result of risk identification generated by the generation AI.

[0048] The identification unit can identify risks by taking into consideration attribute information of the person who performs the action when identifying risks. The identification unit can identify risks by taking into consideration, for example, the age and sex of the person who performs the action. The identification unit can also identify risks by taking into consideration the occupation and experience of the person who performs the action. Furthermore, the identification unit can improve the accuracy of risk identification based on the attribute information of the person who performs the action. As a result, the identification unit can improve the accuracy of risk identification by taking into consideration the attribute information of the person who performs the action. Some or all of the above-mentioned processing in the identification unit can be performed, for example, using AI or without using AI. For example, the identification unit can input attribute information data of the person who performs the action into the generation AI and perform identification based on the result of risk identification generated by the generation AI.

[0049] The identification unit can perform risk identification by taking into consideration the geographic distribution of the behavior. The identification unit identifies risks, for example, by taking into consideration the geographic distribution of the behavior. The identification unit can also improve the accuracy of risk identification based on the geographic distribution. Furthermore, the identification unit can analyze the geographic distribution of the behavior and identify the risk. In this way, the identification unit can improve the accuracy of risk identification by taking into consideration the geographic distribution of the behavior. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the geographic distribution data of the behavior to the generation AI and perform identification based on the result of risk identification generated by the generation AI.

[0050] The identification unit can improve the accuracy of the identification by referring to literature related to the behavior when identifying a risk. The identification unit can, for example, improve the accuracy of risk identification by referring to literature related to the behavior. The identification unit can also improve the accuracy of risk identification based on related literature. Furthermore, the identification unit can identify a risk by referring to literature related to the behavior. Thereby, the identification unit can improve the accuracy of risk identification by referring to literature related to the behavior. A part or all of the above-mentioned processing in the identification unit can be performed, for example, using AI or can be performed without using AI. For example, the identification unit can input literature data related to the behavior to the generation AI and perform identification based on the result of risk identification generated by the generation AI.

[0051] The analysis unit can predict a current risk by referring to past risk data during analysis. The analysis unit can predict a current risk based on, for example, past risk data. The analysis unit can also predict the probability of risk occurrence by referring to past risk data. Furthermore, the analysis unit can analyze past risk data and predict a current risk. In this way, the analysis unit can effectively predict a current risk by referring to past risk data. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis unit can input past risk data to a generation AI and predict a current risk based on a risk prediction result generated by the generation AI.

[0052] The analysis unit can apply different analysis methods to each category of behavior during analysis. For example, the analysis unit applies an analysis method specialized for travel to a behavior related to travel. The analysis unit can also apply an analysis method specialized for project management to a behavior related to a project. The analysis unit can also apply an analysis method specialized for daily life to a behavior related to daily life. This allows the analysis unit to perform more effective analysis by applying an appropriate analysis method according to the category of the behavior. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input behavior category data to the generation AI and perform analysis based on the analysis method generated by the generation AI.

[0053] The analysis unit can analyze the change in risk based on the time when the action was performed during the analysis. For example, the analysis unit prioritizes the analysis of the risk related to the most recent action. The analysis unit can also postpone the analysis of the risk related to the past action. Furthermore, the analysis unit can analyze the change in risk according to the time when the action was performed. This allows the analysis unit to effectively analyze the change in risk based on the time when the action was performed. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the data on the time when the action was performed to the generation AI, and analyze the risk based on the analysis result of the risk change generated by the generation AI.

[0054] The analysis unit can analyze risk by referring to market data related to the behavior during analysis. The analysis unit can, for example, analyze risk by referring to market data related to the behavior. The analysis unit can also analyze the probability of risk occurrence based on the market data. Furthermore, the analysis unit can analyze risk by referring to market data related to the behavior. This allows the analysis unit to effectively analyze risk by referring to market data related to the behavior. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI, or can be performed without using AI. For example, the analysis unit can input market data related to the behavior to the generation AI and analyze risk based on the risk analysis result generated by the generation AI.

[0055] The suggestion unit can adjust the level of detail of the proposal based on the importance of the risk when making a proposal. For example, the suggestion unit makes a detailed proposal for a risk with a high importance. The suggestion unit can also make a concise proposal for a risk with a low importance. Furthermore, the suggestion unit can adjust the level of detail of the proposal according to the importance of the risk. As a result, the suggestion unit can make a more appropriate proposal by adjusting the level of detail of the proposal according to the importance of the risk. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input risk importance data to the generation AI and make a proposal based on the level of detail of the proposal generated by the generation AI.

[0056] The suggestion unit can apply different suggestion algorithms depending on the risk category at the time of suggestion. For example, the suggestion unit applies a suggestion algorithm specialized for travel to risks related to travel. The suggestion unit can also apply a suggestion algorithm specialized for project management to risks related to projects. The suggestion unit can also apply a suggestion algorithm specialized for daily life to risks related to daily life. This allows the suggestion unit to make more effective suggestions by applying an appropriate suggestion algorithm depending on the risk category. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input risk category data to the generation AI and make a suggestion based on the suggestion algorithm generated by the generation AI.

[0057] The suggestion unit can determine the priority of the proposal based on the time of risk occurrence at the time of proposal. For example, the suggestion unit prioritizes proposals related to the most recent risk. The suggestion unit can also postpone proposals related to past risks. Furthermore, the suggestion unit can adjust the priority of the proposal according to the time of risk occurrence. In this way, the suggestion unit can make more appropriate proposals by determining the priority of the proposal based on the time of risk occurrence. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input risk occurrence time data to the generation AI and make a proposal based on the priority of the proposal generated by the generation AI.

[0058] The suggestion unit can adjust the order of the proposal based on the relevance of the risks when making a proposal. For example, the suggestion unit prioritizes proposals related to highly relevant risks. The suggestion unit can also postpone proposals related to less relevant risks. Furthermore, the suggestion unit can adjust the order of the proposal according to the relevance of the risks. In this way, the suggestion unit can make more appropriate proposals by adjusting the order of the proposal based on the relevance of the risks. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input risk relevance data to the generation AI and make a proposal based on the order of proposals generated by the generation AI.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The risk detection system may further include a learning unit that learns the user's behavioral patterns. The learning unit collects the user's past behavioral data and analyzes the behavioral patterns. For example, it can identify the behaviors that the user frequently performs or the behaviors that the user performs during a specific time period. This allows the risk detection system to predict risks based on the user's behavioral patterns and perform more accurate risk detection. The learning unit can also detect changes in the user's behavioral patterns and identify new risks. For example, if the user starts a new hobby, it can identify risks related to the hobby. Furthermore, the learning unit can predict the probability of risk occurrence based on the user's behavioral patterns and determine the priority order of risks. This allows the risk detection system to propose more effective risk countermeasures based on the user's behavioral patterns.

[0061] The questioning unit can ask questions by referring to external data related to the user's behavior. For example, the questioning unit can ask questions based on the weather information and security information of the travel destination. This allows the questioning unit to ask questions that take into account external factors related to the user's behavior. The questioning unit can also ask questions based on past data related to the user's behavior. For example, the questioning unit can ask questions based on information about travel destinations that the user has visited in the past. Furthermore, the questioning unit can also ask questions based on trend data related to the user's behavior. This allows the questioning unit to ask questions that take into account the latest information related to the user's behavior.

[0062] The identification unit can identify risks by considering legal regulations related to the user's behavior. For example, the identification unit can identify risks by considering legal regulations of a travel destination and legal regulations related to a new project. This allows the identification unit to effectively identify legal risks related to the user's behavior. The identification unit can also identify risks by considering industry standards related to the user's behavior. For example, the identification unit can identify risks by considering industry standards in a new project. Furthermore, the identification unit can also identify risks by considering social factors related to the user's behavior. This allows the identification unit to effectively identify various risks related to the user's behavior.

[0063] The analysis unit can analyze risks by referring to economic data related to the user's behavior. For example, the analysis unit can analyze risks based on the economic situation and market trends in a new project. This allows the analysis unit to effectively analyze economic risks related to the user's behavior. The analysis unit can also analyze risks by referring to technical data related to the user's behavior. For example, the analysis unit can analyze technical risks in a new project. Furthermore, the analysis unit can also analyze risks by referring to environmental data related to the user's behavior. This allows the analysis unit to effectively analyze various risks related to the user's behavior.

[0064] The suggestion unit can make a suggestion by referring to past success cases related to the user's behavior. For example, the suggestion unit can make a suggestion based on the success cases of other users who performed similar actions in the past. This allows the suggestion unit to make a suggestion based on the track record related to the user's behavior. The suggestion unit can also make a suggestion by referring to the opinions of experts related to the user's behavior. For example, the suggestion unit can make a suggestion based on the opinions of experts on a new project. Furthermore, the suggestion unit can make a suggestion by referring to the latest research results related to the user's behavior. This allows the suggestion unit to make a suggestion based on a variety of information related to the user's behavior.

[0065] The process flow of the first embodiment will be briefly described below.

[0066] Step 1: The reception unit inputs an overview of the user's behavior. The overview of the user's behavior includes the type, frequency, and location of the behavior. The reception unit provides an interface for the user to input the behavior that the user has performed in the past and the behavior that the user is going to perform in the future. Step 2: The questioning section repeats detailed questions based on the information entered by the reception section. The questioning section asks probing questions to find out the details of the user's actions. For example, it asks questions such as "What activities did you do at your travel destination?" or "What are your specific plans for your new project?" Step 3: The identification unit identifies risks based on the information obtained by the questioning unit. The identification unit uses AI to analyze the information to identify risks hidden in the user's behavior. For example, it identifies safety risks in activities at a travel destination or funding risks in a new project. Step 4: The analysis unit analyzes what kind of problems the risks identified by the identification unit will develop into. The analysis unit uses AI to analyze the information to analyze the possibility that the identified risks will develop into specific problems. For example, it analyzes the possibility that a safety risk will lead to an accident, or that a funding risk will lead to the suspension of a project. Step 5: The proposal unit proposes the risks analyzed by the analysis unit and countermeasures to the user. The proposal unit uses AI to analyze information in order to propose risks and countermeasures to the user. For example, it makes suggestions such as "take sufficient safety measures for activities at travel destinations" or "review the fundraising plan for new projects."

[0067] (Example 2) The risk detection system according to the embodiment of the present invention is a system that detects potential risks and problems hidden in the user's actions in an interactive format. This risk detection system starts with the user simply inputting "what they have done in the past" and "what they are going to do in the future". Next, the AI ​​repeatedly asks questions that dig deeper into the content. For example, questions such as "What activities did you do at your travel destination?" and "What are your specific plans for your new project?" This brings up details of the action. The AI ​​identifies elements that could be risks based on the user's answers. For example, safety in activities at the travel destination and fundraising risks for a new project. Furthermore, the AI ​​analyzes what problems the risks could develop into. For example, the risk of safety leading to an accident, or the risk of fundraising leading to the interruption of a project. Finally, the AI ​​proposes risks and countermeasures to the user. For example, "take sufficient safety measures for activities at your travel destination" or "review your fundraising plan for the new project". This allows the user to grasp potential risks and problems hidden in their actions in advance and take appropriate measures. This enables the risk detection system to detect potential risks and problems lurking in user behavior in advance and take appropriate measures.

[0068] The risk detection system according to the embodiment includes a reception unit, a questioning unit, an identification unit, an analysis unit, and a proposal unit. The reception unit inputs an overview of the user's behavior. The overview of the user's behavior includes, for example, the type, frequency, and location of the behavior, but is not limited to such examples. The reception unit provides an interface for inputting, for example, the user's past behavior and the behavior that he or she is going to perform in the future. The questioning unit repeats detailed questions based on the information input by the reception unit. The questioning unit asks in-depth questions, for example, to find out the details of the user's behavior. For example, the questioning unit asks questions such as "What activities did you do at your travel destination?" and "What are your specific plans for your new project?" The identification unit identifies risks based on the information obtained by the questioning unit. The identification unit analyzes information using AI, for example, to identify risks lurking in the user's behavior. For example, the identification unit identifies safety risks in activities at your travel destination and risks in raising funds for your new project. The analysis unit analyzes what kind of problems the risks identified by the identification unit will develop into. The analysis unit analyzes information using AI, for example, to analyze the possibility that the identified risk will develop into a specific problem. For example, it analyzes the possibility that a safety risk will lead to an accident, or the possibility that a fundraising risk will lead to the interruption of a project. The suggestion unit proposes the risks analyzed by the analysis unit and countermeasures therefor to the user. The suggestion unit analyzes information using AI, for example, to propose risks and countermeasures therefor to the user. For example, it makes suggestions such as "take sufficient safety measures for activities at the travel destination" and "review the fundraising plan for the new project." As a result, the risk detection system according to the embodiment can detect potential risks and problems lurking in the user's behavior in advance and take appropriate measures.

[0069] The reception unit inputs an outline of the user's behavior. The outline of the user's behavior includes, but is not limited to, the type, frequency, and location of the behavior. The reception unit provides, for example, an interface for inputting the user's past behavior and the behavior he or she is going to perform in the future. Specifically, the reception unit has a graphical user interface (GUI) that the user can intuitively operate, and the user can input information using a drop-down menu, a check box, and a text input field. For example, if the user is planning a trip, the user can input the country and city of the destination, the travel period, the type of planned activity, and the like. In addition, detailed information about past behavior can be input in a similar manner. Furthermore, the reception unit has a voice input function, and the user can also input the outline of the behavior by voice. The voice input is converted into text using natural language processing technology and is imported into the system. This allows the user to easily input information, and promotes the use of the system. The reception unit centrally manages the input information and stores it in a database to be provided to the subsequent questioning unit and identification unit. The database is secured and uses encryption technology to protect the user's privacy. This enables the reception unit to efficiently collect detailed information regarding user behavior, thereby improving the accuracy and reliability of the entire system.

[0070] The questioning unit repeatedly asks detailed questions based on the information input by the reception unit. For example, the questioning unit asks probing questions to find out the details of the user's actions. For example, the questioning unit asks questions such as "What activities did you do at your travel destination?" and "What are your specific plans for your new project?". The questioning unit uses AI to analyze the user's input and generates appropriate questions. Specifically, the questioning unit uses natural language processing technology to understand the user's input and automatically generate questions to draw out relevant detailed information. For example, if the user inputs "I'm planning to hike at my travel destination," the questioning unit generates specific questions such as "What is the hiking route like?" and "What equipment do I need while hiking?". The questioning unit can also ask more detailed questions based on the user's answers. For example, if the user answers "I'm raising funds for my new project," the questioning unit asks additional questions such as "What is the method of raising funds?" and "What is the target amount of fundraising?". This allows the questioning unit to efficiently collect detailed information about the user's actions and enrich the data to be provided to the identification unit and analysis unit. Furthermore, the questioning unit can analyze the content of the user's answers in real time and adjust the content and order of the questions as necessary, making it possible to reliably collect necessary information while reducing the burden on the user.

[0071] The identification unit identifies risks based on the information obtained by the question unit. For example, the identification unit uses AI to analyze information to identify risks lurking in the user's behavior. For example, the identification unit identifies safety risks in activities at a travel destination and risks in fundraising for a new project. Specifically, the identification unit uses a machine learning algorithm to evaluate risks based on past data and statistical information. For example, the identification unit analyzes security information at the travel destination and past accident data to evaluate risks associated with a specific activity. In addition, for a new project, the identification unit evaluates risks based on the success rate of similar projects in the past and the difficulty of fundraising. The identification unit comprehensively analyzes these pieces of information to identify risks associated with the user's behavior. Furthermore, the identification unit can incorporate information that is updated in real time and perform risk evaluations continuously. For example, weather information and local news at the travel destination can be obtained in real time and reflected in the risk evaluation. As a result, the identification unit can always perform risk evaluations based on the latest information and provide accurate risk information to the user. The identification unit provides the results of the risk evaluation to the analysis unit and provides data for analyzing the possibility of development of a specific problem. As a result, the identification unit can quickly and accurately identify risks lurking in the user's behavior and improve the risk management capability of the entire system.

[0072] The analysis unit analyzes what kind of problem the risk identified by the identification unit will develop into. For example, the analysis unit uses AI to analyze information to analyze the possibility that the identified risk will develop into a specific problem. For example, it analyzes the possibility that a safety risk will lead to an accident, or that a fundraising risk will lead to the interruption of a project. Specifically, the analysis unit uses simulation technology to predict what impact the identified risk will have in reality. For example, for safety risks in activities at a travel destination, a simulation is performed based on past accident data and local environmental information to predict the probability of an accident occurring and its scope of impact. In addition, for fundraising risks in a new project, a simulation is performed based on the progress of fundraising and market trends to predict the possibility of project interruption due to lack of funds. Based on these simulation results, the analysis unit can evaluate the possibility that the risk will develop into a specific problem and show the user the severity and scope of the risk. In addition, the analysis unit can use past data and statistical information to analyze risk trends and patterns. This can be useful for long-term risk assessment and planning of preventive measures. The analysis unit provides the analysis results to the proposal unit and provides data for proposing specific measures to the user. This enables the analysis unit to perform detailed analysis of the specific impact of risks, thereby improving the risk management capabilities of the entire system.

[0073] The suggestion unit proposes the risks analyzed by the analysis unit and their countermeasures to the user. For example, the suggestion unit uses AI to analyze information in order to propose risks and their countermeasures to the user. For example, the suggestion unit makes suggestions such as "take sufficient safety measures for activities at the travel destination" and "review the fundraising plan for the new project". Specifically, the suggestion unit presents specific countermeasures to the user based on the risk assessment results provided by the analysis unit. For example, for safety risks in activities at the travel destination, the suggestion unit proposes specific countermeasures such as "check local safety guidelines and prepare necessary equipment" and "avoid dangerous areas". In addition, for the risk of fundraising in a new project, the suggestion unit proposes specific countermeasures such as "consider multiple fundraising methods and diversify risks" and "regularly review the progress of fundraising and revise the plan as necessary". The suggestion unit can select and present the optimal countermeasures according to the user's situation and needs. Furthermore, the suggestion unit can collect feedback from the user and continuously improve the accuracy and effectiveness of the proposals. For example, the suggestion unit collects the results of the user's implementation of the proposed countermeasures as feedback, and improves the proposal algorithm based on that data. This allows the proposal unit to always provide the user with optimal countermeasure proposals, maximizing the effectiveness of risk management. The proposal unit is equipped with a visual interface and notification functions to communicate the proposal contents to the user in an easy-to-understand manner, and supports the user in quickly implementing countermeasures. This allows the proposal unit to provide the user with specific and executable countermeasures, enhancing the effectiveness of risk management.

[0074] The questioning unit can repeatedly ask detailed questions to find out the details of the user's behavior. The questioning unit, for example, asks probing questions to find out the details of the user's behavior. For example, the questioning unit asks questions such as "What activities did you do at your travel destination?" or "What are your specific plans for your new project?". The questioning unit can also ask more detailed questions based on the user's answers. For example, if the user answers "I went skydiving at my travel destination," the questioning unit can ask questions such as "What safety measures did you take when skydiving?". This allows the questioning unit to effectively find out the details of the user's behavior. Some or all of the above-mentioned processing in the questioning unit may be performed, for example, using AI, or may be performed without using AI. For example, the questioning unit can input the user's answers to AI and ask detailed questions based on the questions generated by AI.

[0075] The identification unit can identify risks inherent in the user's behavior. For example, the identification unit uses AI to analyze information to identify risks lurking in the user's behavior. For example, the identification unit identifies safety risks in activities at a travel destination and risks in fundraising for a new project. The identification unit uses AI to analyze information to identify elements that may be risks based on the user's answers. For example, if the user answers "I went skydiving at my travel destination," the identification unit can ask questions such as "What safety measures did you take when skydiving?" and identify safety risks based on the answers. This allows the identification unit to effectively identify risks lurking in the user's behavior. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the identification unit can input the user's answers to the generation AI and identify risks based on the results of risk identification generated by the generation AI.

[0076] The analysis unit can analyze whether the identified risk develops into a specific problem. The analysis unit, for example, uses AI to analyze information in order to analyze the possibility that the identified risk will develop into a specific problem. For example, the analysis unit analyzes the possibility that a safety risk will lead to an accident, or that a fundraising risk will lead to the interruption of a project. The analysis unit uses AI to analyze information in order to analyze what kind of problem the risk will develop into based on the risk identified by the identification unit. For example, if a user answers that "I went skydiving at my travel destination" and the identification unit identifies a safety risk, the analysis unit can perform an analysis such as "What kind of accident is likely to occur during skydiving?" This allows the analysis unit to effectively analyze what kind of problem the risk will develop into. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the risk identified by the identification unit into the generation AI and analyze the risk based on the analysis result generated by the generation AI.

[0077] The suggestion unit can suggest risks and specific measures to the user. The suggestion unit, for example, uses AI to analyze information in order to suggest risks and measures to the user. For example, the suggestion unit makes suggestions such as "take sufficient safety measures for activities at the travel destination" and "review the fundraising plan for the new project". The suggestion unit analyzes information using AI in order to suggest risks and measures to the user based on the risks analyzed by the analysis unit. For example, if the user answers "I went skydiving at my travel destination", the identification unit identifies a safety risk, and the analysis unit analyzes the possibility that the risk may lead to an accident, the suggestion unit can make suggestions such as "take sufficient safety measures when skydiving". This allows the suggestion unit to effectively suggest risks and measures to the user. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the suggestion unit can input the risks analyzed by the analysis unit to the generation AI and propose measures to the risk based on the proposal results generated by the generation AI.

[0078] The reception unit can estimate the user's emotion and adjust the timing of input based on the estimated user's emotion. For example, when the user is feeling stressed, the reception unit can delay the timing of input to provide an environment in which the user can relax. In addition, when the user is relaxed, the reception unit can also advance the timing of input to promote smooth dialogue. Furthermore, when the user is in a hurry, the reception unit can speed up the timing of input to efficiently collect information. Thereby, the reception unit can provide a more appropriate input environment by adjusting the timing of input according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and adjust the timing of input based on the emotion estimation result generated by the generation AI.

[0079] The reception unit can analyze the user's past behavior history and select the optimal input method. For example, the reception unit preferentially suggests an input method (such as voice or text) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used in a specific time period from the user's past behavior history. Furthermore, the reception unit can also analyze the user's past behavior history and suggest the most efficient input method. This allows the reception unit to provide the optimal input method based on the user's past behavior history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's past behavior history data to the generation AI and select the optimal input method based on the input method proposal result generated by the generation AI.

[0080] The reception unit can filter the summary of the behavior based on the user's current situation and field of interest when inputting the behavior summary. For example, the reception unit preferentially inputs highly relevant behavior based on the user's current situation. The reception unit can also filter related behaviors based on the user's field of interest to simplify the input. Furthermore, the reception unit can also suggest an optimal input method in consideration of the user's current situation and field of interest. This allows the reception unit to simplify the input based on the user's current situation and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the user's current situation and field of interest to the generation AI and simplify the input based on the filtering result generated by the generation AI.

[0081] The reception unit can estimate the user's emotion and determine the priority of the actions to be input based on the estimated user's emotion. For example, when the user is feeling stressed, the reception unit postpones actions with low importance and prioritizes actions with high importance. In addition, when the user is relaxed, the reception unit can input all actions evenly. Furthermore, when the user is in a hurry, the reception unit can input the most important action with priority. In this way, the reception unit can provide a more appropriate input order by determining the priority of actions according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and determine the priority of the actions based on the emotion estimation result generated by the generation AI.

[0082] The reception unit can preferentially input highly relevant actions in consideration of the geographical location information of the user when inputting an overview of the action. The reception unit preferentially inputs highly relevant actions based on, for example, the user's current location. The reception unit can also suggest optimal actions in consideration of the geographical location information of the user. Furthermore, the reception unit can preferentially input highly relevant actions in consideration of the distance from the user's current location. This allows the reception unit to preferentially input highly relevant actions based on the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the geographical location information data of the user to the generation AI and preferentially input highly relevant actions based on the action proposal result generated by the generation AI.

[0083] The reception unit can analyze the user's social media activity and input related actions when inputting an overview of the action. The reception unit, for example, analyzes the user's social media activity and suggests related actions. The reception unit can also predict a specific action from the user's social media activity and simplify the input. Furthermore, the reception unit can input an optimal action based on the user's social media activity. This allows the reception unit to input related actions based on the user's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity data to the generation AI and input related actions based on the action proposal result generated by the generation AI.

[0084] The questioning unit can estimate the user's emotion and adjust the way of expressing the question based on the estimated user's emotion. For example, if the user is nervous, the questioning unit can ask the question in a gentle tone. Also, if the user is relaxed, the questioning unit can ask the question in a friendly tone. Furthermore, if the user is in a hurry, the questioning unit can ask a concise and quick question. This allows the questioning unit to ask a more appropriate question by adjusting the way of expressing the question according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input the user's emotion data to the generation AI and adjust the way of expressing the question based on the emotion estimation result generated by the generation AI.

[0085] The questioning unit can adjust the level of detail of the question based on the importance of the behavior when asking a question. For example, the questioning unit asks a detailed question for a behavior with a high level of importance. Also, the questioning unit can ask a concise question for a behavior with a low level of importance. Furthermore, the questioning unit can adjust the level of detail of the question according to the importance of the behavior. As a result, the questioning unit can ask a more appropriate question by adjusting the level of detail of the question according to the importance of the behavior. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input the importance data of the behavior to the generation AI and ask a question based on the level of detail of the question generated by the generation AI.

[0086] The questioning unit can apply different questioning algorithms depending on the category of the behavior when asking a question. For example, the questioning unit applies a questioning algorithm specialized for travel to a behavior related to travel. In addition, the questioning unit can also apply a questioning algorithm specialized for project management to a behavior related to a project. Furthermore, the questioning unit can apply a questioning algorithm specialized for daily life to a behavior related to daily life. In this way, the questioning unit can ask more effective questions by applying an appropriate questioning algorithm depending on the category of the behavior. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input behavior category data to the generation AI and ask a question based on a questioning algorithm generated by the generation AI.

[0087] The questioning unit can estimate the user's emotion and adjust the length of the question based on the estimated user's emotion. For example, when the user is nervous, the questioning unit can ask a short and concise question. Furthermore, when the user is relaxed, the questioning unit can also ask a detailed question. Furthermore, when the user is in a hurry, the questioning unit can also ask a short question that can be answered quickly. This allows the questioning unit to ask a more appropriate question by adjusting the length of the question according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input the user's emotion data to the generation AI and adjust the length of the question based on the emotion estimation result generated by the generation AI.

[0088] The questioning unit can determine the priority of questions based on the time when the action was performed when asking a question. For example, the questioning unit prioritizes questions about the most recent action. The questioning unit can also postpone questions about past actions. Furthermore, the questioning unit can adjust the priority of questions according to the time when the action was performed. This allows the questioning unit to ask more appropriate questions by determining the priority of questions based on the time when the action was performed. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input data on the time when the action was performed to the generation AI and ask a question based on the priority of questions generated by the generation AI.

[0089] The questioning unit can adjust the order of questions based on the relevance of behaviors when asking a question. For example, the questioning unit prioritizes questions about highly relevant behaviors. Also, the questioning unit can postpone questions about less relevant behaviors. Furthermore, the questioning unit can adjust the order of questions according to the relevance of behaviors. In this way, the questioning unit can ask more appropriate questions by adjusting the order of questions based on the relevance of behaviors. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input behavior relevance data to a generation AI and ask questions based on the order of questions generated by the generation AI.

[0090] The identification unit can estimate the user's emotion and adjust the criteria for risk identification based on the estimated user's emotion. For example, when the user is nervous, the identification unit can tighten the criteria for risk identification. Also, when the user is relaxed, the identification unit can also relax the criteria for risk identification. Furthermore, when the user is in a hurry, the identification unit can quickly apply the criteria for risk identification. In this way, the identification unit can perform more appropriate risk identification by adjusting the criteria for risk identification according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input the user's emotion data to the generation AI and adjust the criteria for risk identification based on the emotion estimation result generated by the generation AI.

[0091] The identification unit can improve the accuracy of identification by considering the interrelationships of actions when identifying risks. For example, when multiple actions are related, the identification unit identifies risks by considering the interrelationships. The identification unit can also analyze the interrelationships of actions and improve the accuracy of identification. Furthermore, the identification unit can also improve the accuracy of risk identification by considering the interrelationships of actions. In this way, the identification unit can improve the accuracy of risk identification by considering the interrelationships of actions. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the interrelationship data of actions to the generation AI and improve the accuracy of identification based on the result of risk identification generated by the generation AI.

[0092] The identification unit can identify risks by taking into consideration attribute information of the person who performs the action when identifying risks. The identification unit can identify risks by taking into consideration, for example, the age and sex of the person who performs the action. The identification unit can also identify risks by taking into consideration the occupation and experience of the person who performs the action. Furthermore, the identification unit can improve the accuracy of risk identification based on the attribute information of the person who performs the action. As a result, the identification unit can improve the accuracy of risk identification by taking into consideration the attribute information of the person who performs the action. Some or all of the above-mentioned processing in the identification unit can be performed, for example, using AI or without using AI. For example, the identification unit can input attribute information data of the person who performs the action into the generation AI and perform identification based on the result of risk identification generated by the generation AI.

[0093] The identification unit can estimate the user's emotion and adjust the display order of the identified risks based on the estimated user's emotion. For example, when the user is nervous, the identification unit preferentially displays risks with high importance. In addition, when the user is relaxed, the identification unit can also display all risks evenly. Furthermore, when the user is in a hurry, the identification unit can also preferentially display the most important risks. In this way, the identification unit can perform more appropriate risk display by adjusting the display order of risks according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input the user's emotion data to the generation AI and adjust the display order of risks based on the emotion estimation result generated by the generation AI.

[0094] The identification unit can perform risk identification by taking into consideration the geographic distribution of the behavior. The identification unit identifies risks, for example, by taking into consideration the geographic distribution of the behavior. The identification unit can also improve the accuracy of risk identification based on the geographic distribution. Furthermore, the identification unit can analyze the geographic distribution of the behavior and identify the risk. In this way, the identification unit can improve the accuracy of risk identification by taking into consideration the geographic distribution of the behavior. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the geographic distribution data of the behavior to the generation AI and perform identification based on the result of risk identification generated by the generation AI.

[0095] The identification unit can improve the accuracy of the identification by referring to literature related to the behavior when identifying a risk. The identification unit can, for example, improve the accuracy of risk identification by referring to literature related to the behavior. The identification unit can also improve the accuracy of risk identification based on related literature. Furthermore, the identification unit can identify a risk by referring to literature related to the behavior. Thereby, the identification unit can improve the accuracy of risk identification by referring to literature related to the behavior. A part or all of the above-mentioned processing in the identification unit can be performed, for example, using AI or can be performed without using AI. For example, the identification unit can input literature data related to the behavior to the generation AI and perform identification based on the result of risk identification generated by the generation AI.

[0096] The analysis unit can estimate the user's emotion and adjust the display method of the analysis based on the estimated user's emotion. For example, when the user is nervous, the analysis unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the analysis unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the analysis unit can also provide a display method that focuses on the main points. In this way, the analysis unit can provide a more appropriate analysis result by adjusting the display method of the analysis according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and adjust the display method of the analysis based on the emotion estimation result generated by the generation AI.

[0097] The analysis unit can predict a current risk by referring to past risk data during analysis. The analysis unit can predict a current risk based on, for example, past risk data. The analysis unit can also predict the probability of risk occurrence by referring to past risk data. Furthermore, the analysis unit can analyze past risk data and predict a current risk. In this way, the analysis unit can effectively predict a current risk by referring to past risk data. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis unit can input past risk data to a generation AI and predict a current risk based on a risk prediction result generated by the generation AI.

[0098] The analysis unit can apply different analysis methods to each category of behavior during analysis. For example, the analysis unit applies an analysis method specialized for travel to a behavior related to travel. The analysis unit can also apply an analysis method specialized for project management to a behavior related to a project. The analysis unit can also apply an analysis method specialized for daily life to a behavior related to daily life. This allows the analysis unit to perform more effective analysis by applying an appropriate analysis method according to the category of the behavior. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input behavior category data to the generation AI and perform analysis based on the analysis method generated by the generation AI.

[0099] The analysis unit can estimate the user's emotion and adjust the importance of the analysis based on the estimated user's emotion. For example, when the user is nervous, the analysis unit prioritizes the analysis of a risk with a high importance. In addition, when the user is relaxed, the analysis unit can also analyze all risks equally. Furthermore, when the user is in a hurry, the analysis unit can also prioritize the analysis of the most important risk. In this way, the analysis unit can provide a more appropriate analysis result by adjusting the importance of the analysis according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and adjust the importance of the analysis based on the emotion estimation result generated by the generation AI.

[0100] The analysis unit can analyze the change in risk based on the time when the action was performed during the analysis. For example, the analysis unit prioritizes the analysis of the risk related to the most recent action. The analysis unit can also postpone the analysis of the risk related to the past action. Furthermore, the analysis unit can analyze the change in risk according to the time when the action was performed. This allows the analysis unit to effectively analyze the change in risk based on the time when the action was performed. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the data on the time when the action was performed to the generation AI, and analyze the risk based on the analysis result of the risk change generated by the generation AI.

[0101] The analysis unit can analyze risk by referring to market data related to the behavior during analysis. The analysis unit can, for example, analyze risk by referring to market data related to the behavior. The analysis unit can also analyze the probability of risk occurrence based on the market data. Furthermore, the analysis unit can analyze risk by referring to market data related to the behavior. This allows the analysis unit to effectively analyze risk by referring to market data related to the behavior. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI, or can be performed without using AI. For example, the analysis unit can input market data related to the behavior to the generation AI and analyze risk based on the risk analysis result generated by the generation AI.

[0102] The suggestion unit can estimate the user's emotion and adjust the way of expressing the suggestion based on the estimated emotion of the user. For example, when the user is nervous, the suggestion unit makes the suggestion in a gentle tone. Also, when the user is relaxed, the suggestion unit can make the suggestion in a friendly tone. Furthermore, when the user is in a hurry, the suggestion unit can make a concise and quick suggestion. This allows the suggestion unit to make a more appropriate suggestion by adjusting the way of expressing the suggestion according to the emotion of the user. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the user's emotion data to the generation AI and adjust the way of expressing the suggestion based on the emotion estimation result generated by the generation AI.

[0103] The suggestion unit can adjust the level of detail of the proposal based on the importance of the risk when making a proposal. For example, the suggestion unit makes a detailed proposal for a risk with a high importance. The suggestion unit can also make a concise proposal for a risk with a low importance. Furthermore, the suggestion unit can adjust the level of detail of the proposal according to the importance of the risk. As a result, the suggestion unit can make a more appropriate proposal by adjusting the level of detail of the proposal according to the importance of the risk. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input risk importance data to the generation AI and make a proposal based on the level of detail of the proposal generated by the generation AI.

[0104] The suggestion unit can apply different suggestion algorithms depending on the risk category at the time of suggestion. For example, the suggestion unit applies a suggestion algorithm specialized for travel to risks related to travel. The suggestion unit can also apply a suggestion algorithm specialized for project management to risks related to projects. The suggestion unit can also apply a suggestion algorithm specialized for daily life to risks related to daily life. This allows the suggestion unit to make more effective suggestions by applying an appropriate suggestion algorithm depending on the risk category. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input risk category data to the generation AI and make a suggestion based on the suggestion algorithm generated by the generation AI.

[0105] The suggestion unit can estimate the user's emotion and adjust the length of the suggestion based on the estimated user's emotion. For example, when the user is nervous, the suggestion unit can make a short and concise suggestion. In addition, when the user is relaxed, the suggestion unit can also make a detailed suggestion. Furthermore, when the user is in a hurry, the suggestion unit can make a short suggestion that can be quickly answered. In this way, the suggestion unit can adjust the length of the suggestion according to the user's emotion and make a more appropriate suggestion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the user's emotion data to the generation AI and adjust the length of the suggestion based on the emotion estimation result generated by the generation AI.

[0106] The suggestion unit can determine the priority of the proposal based on the time of risk occurrence at the time of proposal. For example, the suggestion unit prioritizes proposals related to the most recent risk. The suggestion unit can also postpone proposals related to past risks. Furthermore, the suggestion unit can adjust the priority of the proposal according to the time of risk occurrence. In this way, the suggestion unit can make more appropriate proposals by determining the priority of the proposal based on the time of risk occurrence. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input risk occurrence time data to the generation AI and make a proposal based on the priority of the proposal generated by the generation AI.

[0107] The suggestion unit can adjust the order of the proposal based on the relevance of the risks when making a proposal. For example, the suggestion unit prioritizes proposals related to highly relevant risks. The suggestion unit can also postpone proposals related to less relevant risks. Furthermore, the suggestion unit can adjust the order of the proposal according to the relevance of the risks. In this way, the suggestion unit can make more appropriate proposals by adjusting the order of the proposal based on the relevance of the risks. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input risk relevance data to the generation AI and make a proposal based on the order of proposals generated by the generation AI.

[0108] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0109] The risk detection system may further include a learning unit that learns the user's behavioral patterns. The learning unit collects the user's past behavioral data and analyzes the behavioral patterns. For example, it can identify the behaviors that the user frequently performs or the behaviors that the user performs during a specific time period. This allows the risk detection system to predict risks based on the user's behavioral patterns and perform more accurate risk detection. The learning unit can also detect changes in the user's behavioral patterns and identify new risks. For example, if the user starts a new hobby, it can identify risks related to the hobby. Furthermore, the learning unit can predict the probability of risk occurrence based on the user's behavioral patterns and determine the priority order of risks. This allows the risk detection system to propose more effective risk countermeasures based on the user's behavioral patterns.

[0110] The questioning unit can ask questions by referring to external data related to the user's behavior. For example, the questioning unit can ask questions based on the weather information and security information of the travel destination. This allows the questioning unit to ask questions that take into account external factors related to the user's behavior. The questioning unit can also ask questions based on past data related to the user's behavior. For example, the questioning unit can ask questions based on information about travel destinations that the user has visited in the past. Furthermore, the questioning unit can also ask questions based on trend data related to the user's behavior. This allows the questioning unit to ask questions that take into account the latest information related to the user's behavior.

[0111] The identification unit can identify risks by considering legal regulations related to the user's behavior. For example, the identification unit can identify risks by considering legal regulations of a travel destination and legal regulations related to a new project. This allows the identification unit to effectively identify legal risks related to the user's behavior. The identification unit can also identify risks by considering industry standards related to the user's behavior. For example, the identification unit can identify risks by considering industry standards in a new project. Furthermore, the identification unit can also identify risks by considering social factors related to the user's behavior. This allows the identification unit to effectively identify various risks related to the user's behavior.

[0112] The analysis unit can analyze risks by referring to economic data related to the user's behavior. For example, the analysis unit can analyze risks based on the economic situation and market trends in a new project. This allows the analysis unit to effectively analyze economic risks related to the user's behavior. The analysis unit can also analyze risks by referring to technical data related to the user's behavior. For example, the analysis unit can analyze technical risks in a new project. Furthermore, the analysis unit can also analyze risks by referring to environmental data related to the user's behavior. This allows the analysis unit to effectively analyze various risks related to the user's behavior.

[0113] The suggestion unit can make a suggestion by referring to past success cases related to the user's behavior. For example, the suggestion unit can make a suggestion based on the success cases of other users who performed similar actions in the past. This allows the suggestion unit to make a suggestion based on the track record related to the user's behavior. The suggestion unit can also make a suggestion by referring to the opinions of experts related to the user's behavior. For example, the suggestion unit can make a suggestion based on the opinions of experts on a new project. Furthermore, the suggestion unit can make a suggestion by referring to the latest research results related to the user's behavior. This allows the suggestion unit to make a suggestion based on a variety of information related to the user's behavior.

[0114] The reception unit can estimate the user's emotion and customize the input interface based on the estimated user's emotion. For example, when the user is stressed, a simple and intuitive interface is provided. Also, when the user is relaxed, an interface that allows detailed information to be input can be provided. Furthermore, when the user is in a hurry, an interface that allows quick input can be provided. This allows the reception unit to provide an optimal input interface according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and customize the input interface based on the emotion estimation result generated by the generation AI.

[0115] The questioning unit can estimate the user's emotion and adjust the timing of the question based on the estimated user's emotion. For example, when the user is stressed, the timing of the question can be delayed to provide a relaxing environment. Also, when the user is relaxed, the timing of the question can be advanced to promote smooth dialogue. Furthermore, when the user is in a hurry, the question can be asked quickly to efficiently collect information. In this way, the questioning unit can provide a more appropriate questioning environment by adjusting the timing of the question according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the questioning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the questioning unit can input the user's emotion data to the generation AI and adjust the timing of the question based on the emotion estimation result generated by the generation AI.

[0116] The identification unit can estimate the user's emotion and determine the priority of risk identification based on the estimated user's emotion. For example, when the user is stressed, it prioritizes and identifies risks with high importance. Also, when the user is relaxed, it can identify all risks equally. Furthermore, when the user is in a hurry, it can identify the most important risk with priority. In this way, the identification unit can determine the priority of risk identification according to the user's emotion, thereby performing more appropriate risk identification. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input the user's emotion data to the generation AI and determine the priority of risk identification based on the emotion estimation result generated by the generation AI.

[0117] The analysis unit can estimate the user's emotion and adjust the depth of the analysis based on the estimated user's emotion. For example, if the user is nervous, a concise and to the point analysis is performed. Also, if the user is relaxed, a detailed analysis can be performed. Furthermore, if the user is in a hurry, the analysis can be performed quickly and the result can be provided. In this way, the analysis unit can provide a more appropriate analysis result by adjusting the depth of the analysis according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and adjust the depth of the analysis based on the emotion estimation result generated by the generation AI.

[0118] The suggestion unit can estimate the user's emotion and determine the priority of suggestions based on the estimated user's emotion. For example, when the user is stressed, the suggestion unit can prioritize suggestions with high importance. Also, when the user is relaxed, all suggestions can be made equally. Furthermore, when the user is in a hurry, the suggestion unit can prioritize the most important suggestions. In this way, the suggestion unit can make more appropriate suggestions by determining the priority of suggestions according to the user's emotion. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the user's emotion data to the generation AI and determine the priority of suggestions based on the emotion estimation result generated by the generation AI.

[0119] The process flow of the second embodiment will be briefly described below.

[0120] Step 1: The reception unit inputs an overview of the user's behavior. The overview of the user's behavior includes the type, frequency, and location of the behavior. The reception unit provides an interface for the user to input the behavior that the user has performed in the past and the behavior that the user is going to perform in the future. Step 2: The questioning section repeats detailed questions based on the information entered by the reception section. The questioning section asks probing questions to find out the details of the user's actions. For example, it asks questions such as "What activities did you do at your travel destination?" or "What are your specific plans for your new project?" Step 3: The identification unit identifies risks based on the information obtained by the questioning unit. The identification unit uses AI to analyze the information to identify risks hidden in the user's behavior. For example, it identifies safety risks in activities at a travel destination or funding risks in a new project. Step 4: The analysis unit analyzes what kind of problems the risks identified by the identification unit will develop into. The analysis unit uses AI to analyze the information to analyze the possibility that the identified risks will develop into specific problems. For example, it analyzes the possibility that a safety risk will lead to an accident, or that a funding risk will lead to the suspension of a project. Step 5: The proposal unit proposes the risks analyzed by the analysis unit and countermeasures to the user. The proposal unit uses AI to analyze information in order to propose risks and countermeasures to the user. For example, it makes suggestions such as "take sufficient safety measures for activities at travel destinations" or "review the fundraising plan for new projects."

[0121] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0122] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0123] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0124] Each of the multiple elements including the above-mentioned reception unit, question unit, identification unit, analysis unit, and proposal unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14, and provides an interface for the user to input an overview of the behavior. The question unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and asks questions to find out details of the user's behavior. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies risks hidden in the user's behavior. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and analyzes what kind of problem the identified risk will develop into. The proposal unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and proposes risks and measures therefor to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0125] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0126] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0127] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0128] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0129] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0131] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0132] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0133] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0135] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0136] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0137] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0139] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements including the above-mentioned reception unit, question unit, identification unit, analysis unit, and suggestion unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and provides an interface for the user to input an overview of the behavior. The question unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and asks questions to find out details of the user's behavior. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies risks hidden in the user's behavior. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and analyzes what kind of problem the identified risk will develop into. The suggestion unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and suggests risks and measures therefor to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0141] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0142] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0143] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0148] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0149] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0151] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0153] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements including the above-mentioned reception unit, question unit, identification unit, analysis unit, and proposal unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314, and provides an interface for the user to input an overview of the behavior. The question unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and asks questions to find out details of the user's behavior. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies risks hidden in the user's behavior. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and analyzes what kind of problem the identified risk will develop into. The proposal unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and proposes risks and measures therefor to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0157] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0158] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0159] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0161] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0164] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0165] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0166] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0167] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0168] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0170] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0172] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0173] Each of the multiple elements including the above-mentioned reception unit, question unit, identification unit, analysis unit, and proposal unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, and provides an interface for the user to input an overview of the behavior. The question unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and asks questions to find out details of the user's behavior. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies risks hidden in the user's behavior. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and analyzes what kind of problem the identified risk will develop into. The proposal unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and proposes risks and measures therefor to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0174] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0175] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0176] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0177] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0178] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0179] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0180] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0181] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0182] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0183] In addition, 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 upon request from the data processing device 12.

[0184] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0185] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0186] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0187] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0188] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0189] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0190] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0191] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0192] (Appendix 1) A reception unit for inputting an overview of a user's behavior; a questioning unit that repeats questions based on the information input by the receiving unit; an identification unit that identifies a risk based on the information obtained by the inquiry unit; an analysis unit that analyzes whether the risk identified by the identification unit develops into a specific problem; a proposal unit that proposes the risk analyzed by the analysis unit and a specific countermeasure against the risk, A system characterized by: (Appendix 2) The interrogation unit is Ask detailed questions to find out more about user behavior 2. The system of claim 1, (Appendix 3) The identification unit is Identify risks inherent in user behavior 2. The system of claim 1, (Appendix 4) The analysis unit is Analyze whether the identified risks develop into concrete problems 2. The system of claim 1, (Appendix 5) The suggestion unit, Propose risks and specific countermeasures to users 2. The system of claim 1, (Appendix 6) The reception unit is Estimate the user's emotions and adjust the timing of inputs based on the estimated user emotions. 2. The system of claim 1, (Appendix 7) The reception unit is Analyze the user's past behavior history and select the optimal input method 2. The system of claim 1, (Appendix 8) The reception unit is Filtering event summaries based on the user's current situation and interests 2. The system of claim 1, (Appendix 9) The reception unit is Estimate the user's emotions and prioritize the actions to be input based on the estimated user emotions. 2. The system of claim 1, (Appendix 10) The reception unit is When entering an event summary, the system considers the user's geographic location and prioritizes relevant events. 2. The system of claim 1, (Appendix 11) The reception unit is Analyze user's social media activity and enter related actions when entering an action summary 2. The system of claim 1, (Appendix 12) The interrogation unit is Infer user sentiment and adjust question wording based on the inferred sentiment 2. The system of claim 1, (Appendix 13) The interrogation unit is When asking questions, adjust the level of detail in your questions based on the importance of the action 2. The system of claim 1, (Appendix 14) The interrogation unit is When asking questions, apply different questioning algorithms depending on the category of the behavior 2. The system of claim 1, (Appendix 15) The interrogation unit is Infer user sentiment and adjust question length based on the estimated user sentiment 2. The system of claim 1, (Appendix 16) The interrogation unit is When asking questions, prioritize questions based on when actions should be taken 2. The system of claim 1, (Appendix 17) The interrogation unit is When asking questions, adjust the order of questions based on behavioral relevance 2. The system of claim 1, (Appendix 18) The identification unit is Inferring user sentiment and adjusting risk identification criteria based on the inferred user sentiment 2. The system of claim 1, (Appendix 19) The identification unit is Improve risk identification by considering correlations of actions 2. The system of claim 1, (Appendix 20) The identification unit is When identifying risks, consider the attributes of the person who will take action. 2. The system of claim 1, (Appendix 21) The identification unit is Inferring user sentiment and adjusting the display order of identified risks based on the inferred user sentiment 2. The system of claim 1, (Appendix 22) The identification unit is When identifying risks, consider the geographic distribution of behavior. 2. The system of claim 1, (Appendix 23) The identification unit is When identifying risks, refer to behavioral literature to improve accuracy. 2. The system of claim 1, (Appendix 24) The analysis unit is Infer user sentiment and adjust how analytics are displayed based on the inferred user sentiment 2. The system of claim 1, (Appendix 25) The analysis unit is During analysis, historical risk data is referenced to predict current risks 2. The system of claim 1, (Appendix 26) The analysis unit is During analysis, different analysis methods are applied to different categories of behavior. 2. The system of claim 1, (Appendix 27) The analysis unit is Inferring user emotions and adjusting the importance of analysis based on the estimated user emotions 2. The system of claim 1, (Appendix 28) The analysis unit is During analysis, analyze changes in risk based on when actions are taken 2. The system of claim 1, (Appendix 29) The analysis unit is During analysis, we look at relevant market data for your actions to analyze risk 2. The system of claim 1, (Appendix 30) The suggestion unit, Infer user emotions and adjust the presentation of suggestions based on the inferred user emotions 2. The system of claim 1, (Appendix 31) The suggestion unit, When making a proposal, adjust the level of detail in the proposal based on the severity of the risk 2. The system of claim 1, (Appendix 32) The suggestion unit, When making suggestions, apply different suggestion algorithms depending on the risk category 2. The system of claim 1, (Appendix 33) The suggestion unit, Infer user sentiment and adjust the length of suggestions based on the estimated user sentiment 2. The system of claim 1, (Appendix 34) The suggestion unit, At the time of proposal, prioritize proposals based on when the risk occurs 2. The system of claim 1, (Appendix 35) The suggestion unit, When making suggestions, adjust the order of suggestions based on risk relevance 2. The system of claim 1, [Explanation of symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit for inputting an overview of a user's behavior; a questioning unit that repeatedly asks detailed questions based on the information input by the reception unit; an identification unit that identifies a risk based on the information obtained by the inquiry unit; an analysis unit that analyzes whether the risk identified by the identification unit develops into a specific problem; a proposal unit that proposes the risk analyzed by the analysis unit and a specific countermeasure against the risk, A system characterized by:

2. The interrogation unit is Ask detailed questions to find out more about user behavior 2. The system of claim 1 .

3. The identification unit is Identify risks inherent in user behavior 2. The system of claim 1 .

4. The reception unit is Estimate the user's emotions and adjust the timing of inputs based on the estimated user emotions.

2. The system of claim 1 .

5. The reception unit is Analyze the user's past behavior history and select the optimal input method 2. The system of claim 1 .

6. The reception unit is Filtering event summaries based on the user's current situation and interests 2. The system of claim 1 .

Images