System

Abstract

An object of a system according to an embodiment is to enable an elderly person to appropriately manage financial assets, prevent crime, and manage expenses.SOLUTION: A system includes a daily conversation collection part, a learning part, an asset management support part, a crime prevention support part, and an expense management part. The daily conversation collection unit collects daily conversations of the elderly person. The learning unit learns the daily conversation collected by the daily conversation collection unit. The asset management support unit supports asset management based on the content learned by the learning unit. The crime prevention support unit supports crime prevention on the basis of the content learned by the learning unit. The expense management unit manages expenses on the basis of the content learned by the learning unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have made it difficult for seniors to properly manage their financial assets, prevent crime, and manage their spending.

[0005] The system according to the embodiment aims to help elderly people manage their financial assets appropriately, prevent crime, and manage their expenses. [Means for solving the problem]

[0006] The system according to the embodiment includes a daily conversation collection unit, a learning unit, an asset management support unit, a crime prevention support unit, and an expenditure management unit. The daily conversation collection unit collects daily conversations of elderly people. The learning unit learns the daily conversations collected by the daily conversation collection unit. The asset management support unit supports asset management based on the content learned by the learning unit. The crime prevention support unit supports crime prevention based on the content learned by the learning unit. The expenditure management unit manages expenditures based on the content learned by the learning unit. [Effects of the Invention]

[0007] The system according to the embodiment enables elderly people to properly manage their financial assets, prevent crime, and manage their expenses. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's 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 read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The Self-Trust System according to an embodiment of the present invention is a system that creates an AI clone that learns from the everyday conversations of elderly people and supports appropriate asset management, crime prevention, and appropriate spending. As a result, the Self-Trust System can address issues such as the decline in cognitive ability of elderly people, the increasing sophistication of financial products, the sophistication of bank transfer fraud, and the increasing complexity of financial institution procedures, thereby realizing appropriate asset management, crime prevention, and appropriate spending.

[0029] The personal trust system according to the embodiment includes a daily conversation collection unit, a learning unit, an asset management support unit, a crime prevention support unit, and an expenditure management unit. The daily conversation collection unit collects daily conversations of elderly people. For example, it collects them as audio data. The daily conversation collection unit can also collect them as text data. For example, it converts the content of the conversations into text and collects them. The learning unit learns the daily conversations collected by the daily conversation collection unit. For example, it learns using a machine learning algorithm. The learning unit can also perform data preprocessing. For example, it performs noise removal and data normalization. The asset management support unit supports asset management based on the content learned by the learning unit. For example, it provides investment advice. The asset management support unit can also perform risk assessment. For example, it conducts a risk assessment test. The crime prevention support unit supports crime prevention based on the content learned by the learning unit. For example, it issues fraud prevention alerts. The crime prevention support unit can also provide security measures. For example, it supports the introduction of security software. The expenditure management unit manages expenditures based on the content learned by the learning unit. For example, it sets a budget. The expenditure management unit can also track expenditures. For example, it can record and analyze expenditure histories. As a result, the self-trust system according to the embodiment can address issues such as the decline in cognitive ability of the elderly, the increasing sophistication of financial products, the increasing sophistication of bank transfer fraud, and the increasing complexity of financial institution procedures, thereby achieving appropriate asset management, crime prevention, and appropriate expenditures.

[0030] The learning unit can collect not only everyday conversations but also the content of social media or emails, allowing it to learn a wider range of communication patterns. For example, the learning unit collects the content of social media and emails used by the elderly and analyzes it together with everyday conversations. For example, it analyzes the content of social media posts and email exchanges to learn communication patterns. The learning unit can also specify the type of social media platform to collect data from. For example, it can collect data from specific platforms such as Facebook, Twitter, and Instagram. Furthermore, the learning unit can specify the format and type of email to collect. For example, it can collect text emails, HTML emails, emails with attachments, etc. This allows it to learn the communication patterns of the elderly more broadly, enabling more accurate support.

[0031] The learning unit can improve the quality of communication by feeding back what it has learned from everyday conversations to family members or caregivers. For example, the learning unit constructs a system that feeds back what it has learned from the elderly person's everyday conversations to family members or caregivers. For example, it notifies the family of the content of the conversation or changes in emotions. The learning unit can also specify the specific method and content of the feedback. For example, it provides feedback in the form of a report. The learning unit can also perform real-time notifications and periodic updates. For example, it can notify changes in emotions in real time and periodically update the content of the conversation. Furthermore, the learning unit can specify the scope and definition of family members and caregivers. For example, it can target relatives, family members living together, close relatives, etc. In this way, the quality of communication can be improved by feeding back what it has learned from the elderly person's everyday conversations to family members and caregivers.

[0032] The learning unit can analyze everyday conversations and suggest recreational activities based on hobbies or interests. The learning unit, for example, analyzes everyday conversations of elderly people and builds a system that suggests recreational activities based on their hobbies and interests. For example, it extracts hobbies and interests from the content of the conversations and suggests recreational activities. The learning unit can also specify the specific type and range of hobbies and interests. For example, it targets hobbies such as sports, music, and reading. Furthermore, the learning unit can also specify the specific type and content of recreational activities. For example, it suggests recreational activities such as games, travel, and crafts. In this way, the quality of life can be improved by analyzing everyday conversations of elderly people and suggesting recreational activities based on their hobbies and interests.

[0033] The asset management support unit can analyze the elderly person's past investment history and propose a customized investment plan based on their individual risk tolerance. The asset management support unit, for example, builds a system that analyzes the elderly person's past investment history and proposes a customized investment plan based on their individual risk tolerance. For example, the asset management support unit calculates risk tolerance based on the past investment history and proposes an optimal investment plan. The asset management support unit can also specify the specific content and scope of the investment history. For example, past investment amounts, investment destinations, investment periods, etc. are targeted. Furthermore, the asset management support unit can also specify specific evaluation criteria and methods for risk tolerance. For example, evaluation is based on risk assessment tests and past investment behavior. This enables more appropriate asset management by analyzing the elderly person's past investment history and proposing an investment plan based on their individual risk tolerance.

[0034] The asset management support department can develop long-term asset management plans that take into account the lifestyle and health condition of the elderly. The asset management support department, for example, analyzes the lifestyle and health condition of the elderly and builds a system that develops long-term asset management plans. For example, it proposes an optimal asset management plan based on the lifestyle and health condition. The asset management support department can also specify the specific content and scope of the lifestyle. For example, it can target daily routines, hobbies, diet, etc. Furthermore, the asset management support department can also specify specific evaluation criteria and methods for health condition. For example, it can evaluate based on medical records and fitness tracker data. This enables more appropriate asset management by developing long-term asset management plans that take into account the lifestyle and health condition of the elderly.

[0035] The asset management support department can share the asset management information of the elderly person with family members or trusted third parties and jointly manage assets. The asset management support department, for example, builds a system for sharing the asset management information of the elderly person with family members or trusted third parties. For example, asset management information is shared in real time and asset management is jointly carried out. The asset management support department can also specify the specific content and scope of the asset management information. For example, investment portfolios, risk assessments, investment histories, etc. are targeted. Furthermore, the asset management support department can also specify the specific scope and definition of third parties. For example, financial advisors, trust companies, legal representatives, etc. are targeted. This allows the asset management information of the elderly person to be shared with family members or trusted third parties and jointly manage assets, enabling more appropriate asset management.

[0036] The asset management support department can provide educational content related to asset management for the elderly, thereby improving their financial literacy. The asset management support department, for example, builds a system for providing educational content related to asset management for the elderly. For example, it provides online courses and video tutorials to improve financial literacy. The asset management support department can also specify the specific content and format of the educational content. For example, it can provide online courses, video tutorials, workshops, etc. Furthermore, the asset management support department can also specify specific evaluation criteria and methods for improving financial literacy. For example, it can evaluate basic financial knowledge, understanding of investments, risk management ability, etc. In this way, providing educational content related to asset management for the elderly and improving financial literacy can enable more appropriate asset management.

[0037] The crime prevention support department can analyze the transaction history of elderly people and develop advanced algorithms to detect abnormal patterns. The crime prevention support department, for example, analyzes the transaction history of elderly people and develops advanced algorithms to detect abnormal patterns. For example, it analyzes fluctuations in transaction frequency and amounts to detect abnormal patterns. The crime prevention support department can also specify the specific content and scope of the transaction history. For example, it can target past transaction amounts, transaction partners, transaction dates and times, etc. Furthermore, the crime prevention support department can also specify specific detection methods and criteria for abnormal patterns. For example, it can detect abnormal patterns based on sudden increases in transaction frequency or the occurrence of large-amount transactions. In this way, by analyzing the transaction history of elderly people and developing advanced algorithms to detect abnormal patterns, more appropriate crime prevention becomes possible.

[0038] The crime prevention support department can propose individually customized crime prevention measures by taking into account the living environment and behavioral patterns of the elderly. For example, the crime prevention support department can analyze the living environment and behavioral patterns of the elderly and build a system that proposes individually customized crime prevention measures. For example, it can propose optimal crime prevention measures based on the living environment and behavioral patterns. The crime prevention support department can also specify the specific content and scope of the living environment. For example, it can target the type of residence, surrounding environment, lifestyle habits, etc. Furthermore, the crime prevention support department can also specify the specific content and method of crime prevention measures. For example, it can propose the introduction of a security system, community monitoring activities, etc. This allows for more appropriate crime prevention by proposing individually customized crime prevention measures by taking into account the living environment and behavioral patterns of the elderly.

[0039] The crime prevention support department can share the elderly person's transaction history with family members or trusted third parties and monitor it jointly. The crime prevention support department, for example, builds a system for sharing the elderly person's transaction history with family members or trusted third parties. For example, the transaction history is shared in real time and monitored jointly. The crime prevention support department can also specify the specific content and scope of the transaction history. For example, past transaction amounts, trading partners, transaction dates and times, etc. are targeted. Furthermore, the crime prevention support department can also specify the specific method and scope of monitoring. For example, real-time monitoring, periodic checks, anomaly detection alerts, etc. are used. In this way, by sharing the elderly person's transaction history with family members or trusted third parties and monitoring it jointly, more appropriate crime prevention is possible.

[0040] The crime prevention support department can provide crime prevention education programs for seniors, allowing them to learn about fraud methods and countermeasures. The crime prevention support department, for example, builds a system for providing crime prevention education programs for seniors. For example, it can provide online courses or video tutorials for learning about fraud methods and countermeasures. The crime prevention support department can also specify the specific content and format of the crime prevention education program. For example, it can provide online courses, workshops, video tutorials, etc. Furthermore, the crime prevention support department can also specify specific types and methods of fraud. For example, it can target phishing scams, telephone scams, investment scams, etc. This enables more appropriate crime prevention by providing crime prevention education programs for seniors and allowing them to learn about fraud methods and countermeasures.

[0041] The expenditure management unit can analyze the elderly person's past expenditure history and propose a budget plan based on their individual expenditure patterns. The expenditure management unit, for example, builds a system that analyzes the elderly person's past expenditure history and proposes a budget plan based on their individual expenditure patterns. For example, it proposes an optimal budget plan based on the past expenditure history. The expenditure management unit can also specify the specific content and scope of the expenditure history. For example, it targets past expenditure amounts, expenditure destinations, expenditure dates and times, etc. Furthermore, the expenditure management unit can also specify specific analysis methods and criteria for expenditure patterns. For example, it analyzes based on monthly expenditure trends, expenditures by category, etc. This enables more appropriate expenditure management by analyzing the elderly person's past expenditure history and proposing a budget plan based on their individual expenditure patterns.

[0042] The expenditure management unit can develop long-term expenditure plans taking into account the lifestyle and health condition of the elderly. The expenditure management unit, for example, analyzes the lifestyle and health condition of the elderly and builds a system that develops long-term expenditure plans. For example, it proposes an optimal expenditure plan based on the lifestyle and health condition. The expenditure management unit can also specify the specific content and scope of the lifestyle. For example, it can target daily routines, hobbies, diet, etc. Furthermore, the expenditure management unit can also specify specific evaluation criteria and methods for the health condition. For example, it can evaluate based on data from medical records and fitness trackers. This enables more appropriate expenditure management by developing long-term expenditure plans that take into account the lifestyle and health condition of the elderly.

[0043] The expenditure management unit can share the elderly person's expenditure information with family members or trusted third parties to jointly manage expenditures. The expenditure management unit, for example, builds a system for sharing the elderly person's expenditure information with family members or trusted third parties. For example, expenditure information can be shared in real time to jointly manage expenditures. The expenditure management unit can also specify the specific content and scope of the expenditure information. For example, expenditure history, expenditure patterns, expenditure forecasts, etc. are targeted. Furthermore, the expenditure management unit can also specify the specific scope and definition of third parties. For example, financial advisors, trust companies, legal representatives, etc. are targeted. This allows the elderly person's expenditure information to be shared with family members or trusted third parties to jointly manage expenditures, enabling more appropriate expenditure management.

[0044] The expenditure management unit can provide educational content related to elderly spending to improve consumer literacy. The expenditure management unit, for example, builds a system for providing educational content related to elderly spending. For example, it provides online courses and video tutorials to improve consumer literacy. The expenditure management unit can also specify the specific content and format of the educational content. For example, it can provide online courses, video tutorials, workshops, etc. The expenditure management unit can also specify specific evaluation criteria and improvement methods for consumer literacy. For example, it can evaluate basic consumer knowledge, understanding of contracts, risk management ability, etc. In this way, providing educational content related to elderly spending and improving consumer literacy enables more appropriate expenditure management.

[0045] The expenditure management unit can monitor the health status of elderly people in real time and propose measures to detect and prevent dementia early. The expenditure management unit, for example, builds a system that monitors the health status of elderly people in real time and proposes measures to detect and prevent dementia early. For example, it analyzes health status data and assesses the risk of dementia. The expenditure management unit can also specify specific evaluation criteria and methods for the health status. For example, it can evaluate based on medical records and data from fitness trackers. Furthermore, the expenditure management unit can specify specific evaluation criteria and detection methods for dementia. For example, it can use cognitive function tests, medical diagnosis, behavioral observation, etc. This enables the health status of elderly people to be monitored in real time and propose measures to detect and prevent dementia early, enabling more appropriate expenditure management.

[0046] The expenditure management unit can individually customize countermeasures for the onset of dementia, taking into account the elderly person's living environment and behavioral patterns. The expenditure management unit, for example, analyzes the elderly person's living environment and behavioral patterns and builds a system that individually customizes countermeasures for the onset of dementia. For example, it proposes optimal countermeasures based on the living environment and behavioral patterns. The expenditure management unit can also specify the specific content and scope of the living environment. For example, this can include the type of residence, surrounding environment, and lifestyle habits. Furthermore, the expenditure management unit can also specify specific countermeasures and standards for the onset of dementia. For example, medical response, nursing care response, adjustment of living environment, etc. are used. This allows for more appropriate expenditure management by individually customizing countermeasures for the onset of dementia, taking into account the elderly person's living environment and behavioral patterns.

[0047] The expenditure management unit can share the health information of an elderly person with family members or trusted third parties, and work together to respond when dementia develops. The expenditure management unit, for example, builds a system for sharing the health information of an elderly person with family members or trusted third parties. For example, the health information can be shared in real time, and a joint response can be made when dementia develops. The expenditure management unit can also specify the specific content and scope of the health information. For example, medical records, fitness tracker data, etc. are targeted. Furthermore, the expenditure management unit can also specify the specific scope and definition of third parties. For example, medical professionals, caregivers, legal representatives, etc. are targeted. This allows the health information of an elderly person to be shared with family members or trusted third parties, and a joint response can be made when dementia develops, enabling more appropriate expenditure management.

[0048] The expenditure management unit can provide a dementia prevention education program for the elderly and reduce the risk of dementia. The expenditure management unit, for example, builds a system for providing a dementia prevention education program for the elderly. For example, it can provide online courses and video tutorials for reducing the risk of dementia. The expenditure management unit can also specify the specific content and format of the dementia prevention education program. For example, it can provide online courses, workshops, video tutorials, etc. The expenditure management unit can also specify specific risk assessment criteria and management methods. For example, it can use risk assessment tests and risk management plans, etc. This enables more appropriate expenditure management by providing a dementia prevention education program for the elderly and reducing the risk of dementia.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The Self Trust System also includes a health management unit. The health management unit can collect health data from elderly people and monitor their health status. For example, it can collect data from fitness trackers and smartwatches and analyze daily activity levels and heart rates. The health management unit can also conduct regular health checks. For example, it can record blood pressure and blood sugar measurement results and issue alerts if abnormalities are detected. Furthermore, the health management unit can make suggestions for improving lifestyle habits based on the elderly's health status. For example, if a lack of exercise is detected, it can suggest an appropriate exercise plan. This allows for comprehensive management of the elderly's health status and improve their quality of life.

[0051] The Self Trust System also includes a hobby recommendation unit. The hobby recommendation unit analyzes the elderly's daily conversations and social media posts to suggest new activities based on their hobbies and interests. For example, it extracts hobbies and interests frequently mentioned in conversations and recommends related events and club activities. The hobby recommendation unit can also suggest local community activities and volunteer activities. For example, it provides information on local cultural events and volunteer activities. The hobby recommendation unit can also suggest hobby activities that can be participated in online. For example, it can recommend online painting classes or music lessons. This can provide new enjoyment to the elderly's lives and strengthen their social connections.

[0052] The Self Trust System also includes a reminder unit. The reminder unit can remind elderly people of important tasks and events in their daily lives. For example, it can remind them to take their medicine or make an appointment at a medical institution. The reminder unit can also set reminders in cooperation with family members or caregivers. For example, it can notify the elderly people of reminders set by family members. Furthermore, the reminder unit can provide reminders by voice or text message. For example, it can provide reminders through a voice assistant. This allows elderly people to live their daily lives smoothly without forgetting important tasks.

[0053] The Self Trust System also includes a travel support unit. The travel support unit can suggest travel plans based on the elderly person's hobbies and interests. For example, it can analyze everyday conversations and social media posts to recommend travel destinations and activities. The travel support unit can also create specific travel plans and schedules. For example, it can assist with booking accommodations and tourist spots. Furthermore, the travel support unit can support safety measures and health management during travel. For example, it can provide information on medical institutions at travel destinations. This allows elderly people to enjoy their trip with peace of mind.

[0054] The Self Trust System also includes a learning support unit. The learning support unit can provide learning content based on the elderly person's interests. For example, it can analyze everyday conversations and social media posts to recommend online courses and video tutorials in areas of interest. The learning support unit can also monitor learning progress and provide appropriate feedback. For example, it can provide additional learning resources according to learning progress. Furthermore, the learning support unit can share learning results with family members and caregivers. For example, it can provide learning results in the form of a report. This allows elderly people to continue enjoying learning.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The daily conversation collection unit collects daily conversations of elderly people. For example, the data is collected as voice data. The daily conversation collection unit can also collect the data as text data. For example, the content of the conversations is converted into text and collected. Step 2: The learning unit learns the everyday conversations collected by the everyday conversation collection unit. For example, learning is performed using a machine learning algorithm. The learning unit can also perform preprocessing of the data. For example, noise removal and data normalization are performed. Step 3: The asset management support department supports asset management based on the content learned by the learning department. For example, it provides investment advice. The asset management support department can also perform risk assessment. For example, it can conduct a risk assessment test. Step 4: The crime prevention support unit supports crime prevention based on the content learned by the learning unit. For example, it issues fraud prevention alerts. The crime prevention support unit can also provide security measures. For example, it can support the installation of security software. Step 5: The expenditure management unit manages expenditures based on the content learned by the learning unit. For example, it sets a budget. The expenditure management unit can also track expenditures. For example, it records and analyzes expenditure history.

[0057] (Example 2) The Self-Trust System according to an embodiment of the present invention is a system that creates an AI clone that learns from the everyday conversations of elderly people and supports appropriate asset management, crime prevention, and appropriate spending. As a result, the Self-Trust System can address issues such as the decline in cognitive ability of elderly people, the increasing sophistication of financial products, the sophistication of bank transfer fraud, and the increasing complexity of financial institution procedures, thereby realizing appropriate asset management, crime prevention, and appropriate spending.

[0058] The personal trust system according to the embodiment includes a daily conversation collection unit, a learning unit, an asset management support unit, a crime prevention support unit, and an expenditure management unit. The daily conversation collection unit collects daily conversations of elderly people. For example, it collects them as audio data. The daily conversation collection unit can also collect them as text data. For example, it converts the content of the conversations into text and collects them. The learning unit learns the daily conversations collected by the daily conversation collection unit. For example, it learns using a machine learning algorithm. The learning unit can also perform data preprocessing. For example, it performs noise removal and data normalization. The asset management support unit supports asset management based on the content learned by the learning unit. For example, it provides investment advice. The asset management support unit can also perform risk assessment. For example, it conducts a risk assessment test. The crime prevention support unit supports crime prevention based on the content learned by the learning unit. For example, it issues fraud prevention alerts. The crime prevention support unit can also provide security measures. For example, it supports the introduction of security software. The expenditure management unit manages expenditures based on the content learned by the learning unit. For example, it sets a budget. The expenditure management unit can also track expenditures. For example, it can record and analyze expenditure histories. As a result, the self-trust system according to the embodiment can address issues such as the decline in cognitive ability of the elderly, the increasing sophistication of financial products, the increasing sophistication of bank transfer fraud, and the increasing complexity of financial institution procedures, thereby achieving appropriate asset management, crime prevention, and appropriate expenditures.

[0059] The learning unit can collect not only everyday conversations but also the content of social media or emails, allowing it to learn a wider range of communication patterns. For example, the learning unit collects the content of social media and emails used by the elderly and analyzes it together with everyday conversations. For example, it analyzes the content of social media posts and email exchanges to learn communication patterns. The learning unit can also specify the type of social media platform to collect data from. For example, it can collect data from specific platforms such as Facebook, Twitter, and Instagram. Furthermore, the learning unit can specify the format and type of email to collect. For example, it can collect text emails, HTML emails, emails with attachments, etc. This allows it to learn the communication patterns of the elderly more broadly, enabling more accurate support.

[0060] The learning unit can analyze changes in tone of voice or speaking style in everyday conversation, detect changes in emotions, and reflect these in the learning. The learning unit, for example, analyzes audio data of everyday conversations of an elderly person and detects changes in tone of voice or speaking style. For example, it analyzes changes in voice pitch and speed to learn changes in emotions. The learning unit can also use specific analysis methods such as voice frequency, volume, and pitch. For example, it analyzes fluctuations in voice frequency to detect changes in emotions. Furthermore, the learning unit can also analyze changes in speaking style such as speaking speed, intonation, and word choice. For example, it analyzes changes in speaking speed to learn changes in emotions. This allows changes in the elderly person's emotions to be reflected in the learning, making it possible to provide more appropriate support.

[0061] The learning unit can use the emotion estimation function to analyze the emotional state of the elderly person in real time and learn behavioral patterns based on the emotions. The learning unit, for example, analyzes the elderly person's daily conversation in real time and detects the emotional state using the emotion estimation function. For example, it analyzes changes in emotions during conversation in real time and reflects them in behavioral patterns. The learning unit can also use specific technologies such as voice analysis, facial expression recognition, and text analysis. For example, it can detect changes in emotions using voice analysis and reflect them in behavioral patterns. Furthermore, the learning unit can analyze behavioral patterns such as daily routines, frequency of behavior, and type of behavior. For example, it can analyze daily routines and learn behavioral patterns based on emotions. This enables more appropriate support by analyzing the elderly person's emotional state in real time and reflecting them in behavioral patterns.

[0062] The learning unit can improve the quality of communication by feeding back what it has learned from everyday conversations to family members or caregivers. For example, the learning unit constructs a system that feeds back what it has learned from the elderly person's everyday conversations to family members or caregivers. For example, it notifies the family of the content of the conversation or changes in emotions. The learning unit can also specify the specific method and content of the feedback. For example, it provides feedback in the form of a report. The learning unit can also perform real-time notifications and periodic updates. For example, it can notify changes in emotions in real time and periodically update the content of the conversation. Furthermore, the learning unit can specify the scope and definition of family members and caregivers. For example, it can target relatives, family members living together, close relatives, etc. In this way, the quality of communication can be improved by feeding back what it has learned from the elderly person's everyday conversations to family members and caregivers.

[0063] The learning unit can analyze everyday conversations and suggest recreational activities based on hobbies or interests. The learning unit, for example, analyzes everyday conversations of elderly people and builds a system that suggests recreational activities based on their hobbies and interests. For example, it extracts hobbies and interests from the content of the conversations and suggests recreational activities. The learning unit can also specify the specific type and range of hobbies and interests. For example, it targets hobbies such as sports, music, and reading. Furthermore, the learning unit can also specify the specific type and content of recreational activities. For example, it suggests recreational activities such as games, travel, and crafts. In this way, the quality of life can be improved by analyzing everyday conversations of elderly people and suggesting recreational activities based on their hobbies and interests.

[0064] The learning unit can use the emotion estimation function to automatically recommend music or video content according to the emotions of the elderly. The learning unit, for example, analyzes the elderly's everyday conversations and detects their emotional state using the emotion estimation function. For example, it automatically recommends music or video content according to changes in emotions. The learning unit can also specify a specific type or range of music or video content. For example, it can target music such as classical, pop, and jazz. Furthermore, the learning unit can target video content such as movies, television programs, and documentaries. For example, it can recommend relaxing music or moving movies according to changes in emotions. This can improve the quality of life of the elderly by automatically recommending music and video content according to their emotions.

[0065] The asset management support unit can analyze the elderly person's past investment history and propose a customized investment plan based on their individual risk tolerance. The asset management support unit, for example, builds a system that analyzes the elderly person's past investment history and proposes a customized investment plan based on their individual risk tolerance. For example, the asset management support unit calculates risk tolerance based on the past investment history and proposes an optimal investment plan. The asset management support unit can also specify the specific content and scope of the investment history. For example, past investment amounts, investment destinations, investment periods, etc. are targeted. Furthermore, the asset management support unit can also specify specific evaluation criteria and methods for risk tolerance. For example, evaluation is based on risk assessment tests and past investment behavior. This enables more appropriate asset management by analyzing the elderly person's past investment history and proposing an investment plan based on their individual risk tolerance.

[0066] The asset management support department can develop long-term asset management plans that take into account the lifestyle and health condition of the elderly. The asset management support department, for example, analyzes the lifestyle and health condition of the elderly and builds a system that develops long-term asset management plans. For example, it proposes an optimal asset management plan based on the lifestyle and health condition. The asset management support department can also specify the specific content and scope of the lifestyle. For example, it can target daily routines, hobbies, diet, etc. Furthermore, the asset management support department can also specify specific evaluation criteria and methods for health condition. For example, it can evaluate based on medical records and fitness tracker data. This enables more appropriate asset management by developing long-term asset management plans that take into account the lifestyle and health condition of the elderly.

[0067] The asset management support unit can use the emotion estimation function to analyze the emotions of elderly people regarding investment and provide investment advice based on those emotions. The asset management support unit, for example, analyzes the emotions of elderly people regarding investment in real time and provides investment advice using the emotion estimation function. For example, it provides investment advice according to changes in emotions. The asset management support unit can also specify the specific type and range of investment. For example, it targets stock investment, real estate investment, bond investment, etc. Furthermore, the asset management support unit can also specify the specific type of emotion and evaluation criteria. For example, it evaluates emotions such as joy, sadness, and anger. This allows for more appropriate asset management by analyzing the emotions of elderly people regarding investment and providing investment advice based on emotions.

[0068] The asset management support department can share the asset management information of the elderly person with family members or trusted third parties and jointly manage assets. The asset management support department, for example, builds a system for sharing the asset management information of the elderly person with family members or trusted third parties. For example, asset management information is shared in real time and asset management is jointly carried out. The asset management support department can also specify the specific content and scope of the asset management information. For example, investment portfolios, risk assessments, investment histories, etc. are targeted. Furthermore, the asset management support department can also specify the specific scope and definition of third parties. For example, financial advisors, trust companies, legal representatives, etc. are targeted. This allows the asset management information of the elderly person to be shared with family members or trusted third parties and jointly manage assets, enabling more appropriate asset management.

[0069] The asset management support department can provide educational content related to asset management for the elderly, thereby improving their financial literacy. The asset management support department, for example, builds a system for providing educational content related to asset management for the elderly. For example, it provides online courses and video tutorials to improve financial literacy. The asset management support department can also specify the specific content and format of the educational content. For example, it can provide online courses, video tutorials, workshops, etc. Furthermore, the asset management support department can also specify specific evaluation criteria and methods for improving financial literacy. For example, it can evaluate basic financial knowledge, understanding of investments, risk management ability, etc. In this way, providing educational content related to asset management for the elderly and improving financial literacy can enable more appropriate asset management.

[0070] The asset management support unit can use the emotion estimation function to introduce relaxation techniques to reduce elderly people's anxiety about investing. The asset management support unit, for example, uses the emotion estimation function to introduce relaxation techniques to reduce elderly people's anxiety about investing. For example, relaxation music or meditation guides are provided in response to changes in emotions. The asset management support unit can also specify specific evaluation criteria and detection methods for anxiety. For example, voice analysis, facial expression recognition, text analysis, etc. are used. Furthermore, the asset management support unit can also specify specific content and methods of relaxation techniques. For example, meditation, deep breathing, music therapy, etc. are provided. This enables more appropriate asset management by introducing relaxation techniques to reduce elderly people's anxiety about investing.

[0071] The crime prevention support department can analyze the transaction history of elderly people and develop advanced algorithms to detect abnormal patterns. The crime prevention support department, for example, analyzes the transaction history of elderly people and develops advanced algorithms to detect abnormal patterns. For example, it analyzes fluctuations in transaction frequency and amounts to detect abnormal patterns. The crime prevention support department can also specify the specific content and scope of the transaction history. For example, it can target past transaction amounts, transaction partners, transaction dates and times, etc. Furthermore, the crime prevention support department can also specify specific detection methods and criteria for abnormal patterns. For example, it can detect abnormal patterns based on sudden increases in transaction frequency or the occurrence of large-amount transactions. In this way, by analyzing the transaction history of elderly people and developing advanced algorithms to detect abnormal patterns, more appropriate crime prevention becomes possible.

[0072] The crime prevention support department can propose individually customized crime prevention measures by taking into account the living environment and behavioral patterns of the elderly. For example, the crime prevention support department can analyze the living environment and behavioral patterns of the elderly and build a system that proposes individually customized crime prevention measures. For example, it can propose optimal crime prevention measures based on the living environment and behavioral patterns. The crime prevention support department can also specify the specific content and scope of the living environment. For example, it can target the type of residence, surrounding environment, lifestyle habits, etc. Furthermore, the crime prevention support department can also specify the specific content and method of crime prevention measures. For example, it can propose the introduction of a security system, community monitoring activities, etc. This allows for more appropriate crime prevention by proposing individually customized crime prevention measures by taking into account the living environment and behavioral patterns of the elderly.

[0073] The crime prevention support unit can use the emotion estimation function to build a system that automatically issues a warning when an elderly person feels anxious. The crime prevention support unit uses the emotion estimation function, for example, to build a system that automatically issues a warning when an elderly person feels anxious. For example, a system that issues a warning when an elderly person feels anxious is built. The crime prevention support unit can also specify specific evaluation criteria and detection methods for anxiety. For example, voice analysis, facial expression recognition, text analysis, etc. are used. Furthermore, the crime prevention support unit can also specify specific content and method of the warning. For example, voice alerts, text messages, visual alerts, etc. are used. This enables more appropriate crime prevention by automatically issuing a warning when an elderly person feels anxious.

[0074] The crime prevention support department can share the elderly person's transaction history with family members or trusted third parties and monitor it jointly. The crime prevention support department, for example, builds a system for sharing the elderly person's transaction history with family members or trusted third parties. For example, the transaction history is shared in real time and monitored jointly. The crime prevention support department can also specify the specific content and scope of the transaction history. For example, past transaction amounts, trading partners, transaction dates and times, etc. are targeted. Furthermore, the crime prevention support department can also specify the specific method and scope of monitoring. For example, real-time monitoring, periodic checks, anomaly detection alerts, etc. are used. In this way, by sharing the elderly person's transaction history with family members or trusted third parties and monitoring it jointly, more appropriate crime prevention is possible.

[0075] The crime prevention support department can provide crime prevention education programs for seniors, allowing them to learn about fraud methods and countermeasures. The crime prevention support department, for example, builds a system for providing crime prevention education programs for seniors. For example, it can provide online courses or video tutorials for learning about fraud methods and countermeasures. The crime prevention support department can also specify the specific content and format of the crime prevention education program. For example, it can provide online courses, workshops, video tutorials, etc. Furthermore, the crime prevention support department can also specify specific types and methods of fraud. For example, it can target phishing scams, telephone scams, investment scams, etc. This enables more appropriate crime prevention by providing crime prevention education programs for seniors and allowing them to learn about fraud methods and countermeasures.

[0076] The crime prevention support unit can use the emotion estimation function to introduce a system that provides immediate support when an elderly person suspects fraud. The crime prevention support unit uses the emotion estimation function, for example, to build a system that provides immediate support when an elderly person suspects fraud. For example, a system is built that provides support when an elderly person suspects fraud. The crime prevention support unit can also specify specific types and methods of fraud. For example, phishing scams, telephone scams, investment scams, etc. are targeted. Furthermore, the crime prevention support unit can also specify specific evaluation criteria and detection methods for suspicion. For example, voice analysis, facial expression recognition, text analysis, etc. are used. This enables more appropriate crime prevention by providing immediate support when an elderly person suspects fraud.

[0077] The expenditure management unit can analyze the elderly person's past expenditure history and propose a budget plan based on their individual expenditure patterns. The expenditure management unit, for example, builds a system that analyzes the elderly person's past expenditure history and proposes a budget plan based on their individual expenditure patterns. For example, it proposes an optimal budget plan based on the past expenditure history. The expenditure management unit can also specify the specific content and scope of the expenditure history. For example, it targets past expenditure amounts, expenditure destinations, expenditure dates and times, etc. Furthermore, the expenditure management unit can also specify specific analysis methods and criteria for expenditure patterns. For example, it analyzes based on monthly expenditure trends, expenditures by category, etc. This enables more appropriate expenditure management by analyzing the elderly person's past expenditure history and proposing a budget plan based on their individual expenditure patterns.

[0078] The expenditure management unit can develop long-term expenditure plans taking into account the lifestyle and health condition of the elderly. The expenditure management unit, for example, analyzes the lifestyle and health condition of the elderly and builds a system that develops long-term expenditure plans. For example, it proposes an optimal expenditure plan based on the lifestyle and health condition. The expenditure management unit can also specify the specific content and scope of the lifestyle. For example, it can target daily routines, hobbies, diet, etc. Furthermore, the expenditure management unit can also specify specific evaluation criteria and methods for the health condition. For example, it can evaluate based on data from medical records and fitness trackers. This enables more appropriate expenditure management by developing long-term expenditure plans that take into account the lifestyle and health condition of the elderly.

[0079] The expenditure management unit can use the emotion estimation function to analyze the elderly's emotions regarding spending and provide spending advice based on those emotions. The expenditure management unit, for example, analyzes the elderly's emotions regarding spending in real time and uses the emotion estimation function to provide spending advice. For example, spending advice is provided according to changes in emotions. The expenditure management unit can also specify specific types and ranges of expenditures. For example, it can target daily expenditures, large expenditures, regular expenditures, etc. Furthermore, the expenditure management unit can also specify specific types of emotions and evaluation criteria. For example, it can evaluate emotions such as joy, sadness, and anger. This enables more appropriate expenditure management by analyzing the elderly's emotions regarding spending and providing spending advice based on those emotions.

[0080] The expenditure management unit can share the elderly person's expenditure information with family members or trusted third parties to jointly manage expenditures. The expenditure management unit, for example, builds a system for sharing the elderly person's expenditure information with family members or trusted third parties. For example, expenditure information can be shared in real time to jointly manage expenditures. The expenditure management unit can also specify the specific content and scope of the expenditure information. For example, expenditure history, expenditure patterns, expenditure forecasts, etc. are targeted. Furthermore, the expenditure management unit can also specify the specific scope and definition of third parties. For example, financial advisors, trust companies, legal representatives, etc. are targeted. This allows the elderly person's expenditure information to be shared with family members or trusted third parties to jointly manage expenditures, enabling more appropriate expenditure management.

[0081] The expenditure management unit can provide educational content related to elderly spending to improve consumer literacy. The expenditure management unit, for example, builds a system for providing educational content related to elderly spending. For example, it provides online courses and video tutorials to improve consumer literacy. The expenditure management unit can also specify the specific content and format of the educational content. For example, it can provide online courses, video tutorials, workshops, etc. The expenditure management unit can also specify specific evaluation criteria and improvement methods for consumer literacy. For example, it can evaluate basic consumer knowledge, understanding of contracts, risk management ability, etc. In this way, providing educational content related to elderly spending and improving consumer literacy enables more appropriate expenditure management.

[0082] The expenditure management unit can use the emotion estimation function to introduce relaxation techniques to reduce the elderly's anxiety about spending. The expenditure management unit, for example, uses the emotion estimation function to introduce relaxation techniques to reduce the elderly's anxiety about spending. For example, relaxation music or meditation guides are provided in response to changes in emotions. The expenditure management unit can also specify specific evaluation criteria and detection methods for anxiety. For example, voice analysis, facial expression recognition, text analysis, etc. are used. The expenditure management unit can also specify specific content and methods of relaxation techniques. For example, meditation, deep breathing, music therapy, etc. are provided. This enables more appropriate expenditure management by introducing relaxation techniques to reduce the elderly's anxiety about spending.

[0083] The expenditure management unit can monitor the health status of elderly people in real time and propose measures to detect and prevent dementia early. The expenditure management unit, for example, builds a system that monitors the health status of elderly people in real time and proposes measures to detect and prevent dementia early. For example, it analyzes health status data and assesses the risk of dementia. The expenditure management unit can also specify specific evaluation criteria and methods for the health status. For example, it can evaluate based on medical records and data from fitness trackers. Furthermore, the expenditure management unit can specify specific evaluation criteria and detection methods for dementia. For example, it can use cognitive function tests, medical diagnosis, behavioral observation, etc. This enables the health status of elderly people to be monitored in real time and propose measures to detect and prevent dementia early, enabling more appropriate expenditure management.

[0084] The expenditure management unit can individually customize countermeasures for the onset of dementia, taking into account the elderly person's living environment and behavioral patterns. The expenditure management unit, for example, analyzes the elderly person's living environment and behavioral patterns and builds a system that individually customizes countermeasures for the onset of dementia. For example, it proposes optimal countermeasures based on the living environment and behavioral patterns. The expenditure management unit can also specify the specific content and scope of the living environment. For example, this can include the type of residence, surrounding environment, and lifestyle habits. Furthermore, the expenditure management unit can also specify specific countermeasures and standards for the onset of dementia. For example, medical response, nursing care response, adjustment of living environment, etc. are used. This allows for more appropriate expenditure management by individually customizing countermeasures for the onset of dementia, taking into account the elderly person's living environment and behavioral patterns.

[0085] The expenditure management unit can use the emotion estimation function to analyze the emotional state of the elderly and provide support to reduce stress when dementia develops. The expenditure management unit, for example, analyzes the emotional state of the elderly in real time and uses the emotion estimation function to provide support to reduce stress when dementia develops. For example, it provides relaxation techniques in response to changes in emotions. The expenditure management unit can also specify specific analysis methods and criteria for the emotional state. For example, it uses voice analysis, facial expression recognition, text analysis, etc. The expenditure management unit can also specify specific evaluation criteria and detection methods for stress. For example, it uses voice analysis, facial expression recognition, text analysis, etc. This enables more appropriate expenditure management by analyzing the emotional state of the elderly and providing support to reduce stress when dementia develops.

[0086] The expenditure management unit can share the health information of an elderly person with family members or trusted third parties, and work together to respond when dementia develops. The expenditure management unit, for example, builds a system for sharing the health information of an elderly person with family members or trusted third parties. For example, the health information can be shared in real time, and a joint response can be made when dementia develops. The expenditure management unit can also specify the specific content and scope of the health information. For example, medical records, fitness tracker data, etc. are targeted. Furthermore, the expenditure management unit can also specify the specific scope and definition of third parties. For example, medical professionals, caregivers, legal representatives, etc. are targeted. This allows the health information of an elderly person to be shared with family members or trusted third parties, and a joint response can be made when dementia develops, enabling more appropriate expenditure management.

[0087] The expenditure management unit can provide a dementia prevention education program for the elderly and reduce the risk of dementia. The expenditure management unit, for example, builds a system for providing a dementia prevention education program for the elderly. For example, it can provide online courses and video tutorials for reducing the risk of dementia. The expenditure management unit can also specify the specific content and format of the dementia prevention education program. For example, it can provide online courses, workshops, video tutorials, etc. The expenditure management unit can also specify specific risk assessment criteria and management methods. For example, it can use risk assessment tests and risk management plans, etc. This enables more appropriate expenditure management by providing a dementia prevention education program for the elderly and reducing the risk of dementia.

[0088] The expenditure management unit can use the emotion estimation function to introduce relaxation techniques according to the emotions of the elderly person, thereby reducing stress at the onset of dementia. The expenditure management unit, for example, analyzes the emotional state of the elderly person in real time and uses the emotion estimation function to provide relaxation techniques to reduce stress at the onset of dementia. For example, it provides relaxation music or meditation guides according to changes in emotions. The expenditure management unit can also specify specific types of emotions and evaluation criteria. For example, emotions such as joy, sadness, and anger can be evaluated. Furthermore, the expenditure management unit can also specify specific content and methods of relaxation techniques. For example, it can provide meditation, deep breathing, music therapy, etc. This enables more appropriate expenditure management by introducing relaxation techniques according to the emotions of the elderly person and reducing stress at the onset of dementia.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The Self Trust System also includes a health management unit. The health management unit can collect health data from elderly people and monitor their health status. For example, it can collect data from fitness trackers and smartwatches and analyze daily activity levels and heart rates. The health management unit can also conduct regular health checks. For example, it can record blood pressure and blood sugar measurement results and issue alerts if abnormalities are detected. Furthermore, the health management unit can make suggestions for improving lifestyle habits based on the elderly's health status. For example, if a lack of exercise is detected, it can suggest an appropriate exercise plan. This allows for comprehensive management of the elderly's health status and improve their quality of life.

[0091] The Self Trust System also includes a hobby recommendation unit. The hobby recommendation unit analyzes the elderly's daily conversations and social media posts to suggest new activities based on their hobbies and interests. For example, it extracts hobbies and interests frequently mentioned in conversations and recommends related events and club activities. The hobby recommendation unit can also suggest local community activities and volunteer activities. For example, it provides information on local cultural events and volunteer activities. The hobby recommendation unit can also suggest hobby activities that can be participated in online. For example, it can recommend online painting classes or music lessons. This can provide new enjoyment to the elderly's lives and strengthen their social connections.

[0092] The Self Trust System also includes a reminder unit. The reminder unit can remind elderly people of important tasks and events in their daily lives. For example, it can remind them to take their medicine or make an appointment at a medical institution. The reminder unit can also set reminders in cooperation with family members or caregivers. For example, it can notify the elderly people of reminders set by family members. Furthermore, the reminder unit can provide reminders by voice or text message. For example, it can provide reminders through a voice assistant. This allows elderly people to live their daily lives smoothly without forgetting important tasks.

[0093] The Self Trust System can also use an emotion estimation function to provide communication support based on the emotions of the elderly. For example, the emotion estimation function can be used to analyze the emotional state of the elderly and suggest conversation topics based on the emotion. The emotion estimation function can also be used to provide encouraging or comforting messages based on changes in emotions. For example, if the elderly is feeling depressed, an encouraging message can be sent. Furthermore, the emotion estimation function can also be used to suggest relaxation techniques based on emotions. For example, if the elderly is feeling excited, relaxation music can be recommended. This makes it possible to provide communication support that is sensitive to the emotions of the elderly.

[0094] The self-trust system can further use an emotion estimation function to manage health based on the emotions of the elderly. For example, the emotion estimation function can be used to analyze the emotional state of the elderly and provide health advice according to the emotion. The emotion estimation function can also be used to suggest stress management methods according to changes in emotions. For example, if the elderly is emotionally unstable, exercise or meditation to reduce stress can be suggested. Furthermore, the emotion estimation function can also be used to suggest a meal plan based on the emotions. For example, if the elderly is feeling depressed, meals to lift their spirits can be suggested. This makes it possible to manage health based on the emotions of the elderly.

[0095] The Self Trust System can further use the emotion estimation function to provide asset management advice based on the emotions of the elderly. For example, the emotion estimation function can be used to analyze the emotional state of the elderly and provide investment advice based on the emotions. The emotion estimation function can also be used to suggest risk management methods based on emotional changes. For example, if emotions are unstable, low-risk investments can be suggested. Furthermore, the emotion estimation function can also be used to suggest asset management plans based on emotions. For example, if emotions are high, advice is provided to encourage calm decision-making. In this way, asset management advice based on the emotions of the elderly can be provided.

[0096] The Self Trust System can further use its emotion estimation function to propose crime prevention measures based on the emotions of the elderly. For example, it can use the emotion estimation function to analyze the emotional state of the elderly and propose crime prevention measures according to the emotions. It can also use the emotion estimation function to propose security measures according to changes in emotions. For example, if the elderly person is emotionally unstable, it can provide advice on strengthening security. It can also use the emotion estimation function to propose fraud prevention measures based on emotions. For example, if the elderly person is emotionally excited, it can provide advice to encourage calm judgment. In this way, it can propose crime prevention measures based on the emotions of the elderly.

[0097] The self-trust system can further use an emotion estimation function to manage spending based on the emotions of the elderly. For example, the emotion estimation function can be used to analyze the emotional state of the elderly and provide spending advice based on the emotion. The emotion estimation function can also be used to suggest budget management methods that correspond to changes in emotions. For example, if the elderly are emotionally unstable, advice to curb spending can be provided. The emotion estimation function can also be used to suggest spending plans based on emotions. For example, if the elderly are emotionally charged, advice to encourage calm decision-making can be provided. This makes it possible to manage spending based on the emotions of the elderly.

[0098] The Self Trust System also includes a travel support unit. The travel support unit can suggest travel plans based on the elderly person's hobbies and interests. For example, it can analyze everyday conversations and social media posts to recommend travel destinations and activities. The travel support unit can also create specific travel plans and schedules. For example, it can assist with booking accommodations and tourist spots. Furthermore, the travel support unit can support safety measures and health management during travel. For example, it can provide information on medical institutions at travel destinations. This allows elderly people to enjoy their trip with peace of mind.

[0099] The Self Trust System also includes a learning support unit. The learning support unit can provide learning content based on the elderly person's interests. For example, it can analyze everyday conversations and social media posts to recommend online courses and video tutorials in areas of interest. The learning support unit can also monitor learning progress and provide appropriate feedback. For example, it can provide additional learning resources according to learning progress. Furthermore, the learning support unit can share learning results with family members and caregivers. For example, it can provide learning results in the form of a report. This allows elderly people to continue enjoying learning.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The daily conversation collection unit collects daily conversations of elderly people. For example, the data is collected as voice data. The daily conversation collection unit can also collect the data as text data. For example, the content of the conversations is converted into text and collected. Step 2: The learning unit learns the everyday conversations collected by the everyday conversation collection unit. For example, learning is performed using a machine learning algorithm. The learning unit can also perform preprocessing of the data. For example, noise removal and data normalization are performed. Step 3: The asset management support department supports asset management based on the content learned by the learning department. For example, it provides investment advice. The asset management support department can also perform risk assessment. For example, it can conduct a risk assessment test. Step 4: The crime prevention support unit supports crime prevention based on the content learned by the learning unit. For example, it issues fraud prevention alerts. The crime prevention support unit can also provide security measures. For example, it can support the installation of security software. Step 5: The expenditure management unit manages expenditures based on the content learned by the learning unit. For example, it sets a budget. The expenditure management unit can also track expenditures. For example, it records and analyzes expenditure history.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0104] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 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.

[0107] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0108] 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.

[0109] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0111] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0112] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0113] 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.

[0114] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0115] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0116] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 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.

[0122] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0123] 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.

[0124] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0127] 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.

[0128] 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.

[0129] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0130] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0131] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0132] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0133] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0134] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 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.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] 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.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0142] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0143] 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.

[0144] 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.

[0145] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0146] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0147] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0148] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0149] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0150] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0151] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0152] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0153] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0154] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0155] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0156] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0157] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0158] 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.

[0159] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0160] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0161] 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.

[0162] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0163] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0164] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0165] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0166] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0167] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0168] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0169] 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 department that collects everyday conversations among the elderly, a learning unit that learns the everyday conversations collected by the everyday conversation collection unit; an asset management support unit that supports asset management based on the content learned by the learning unit; a crime prevention support unit that supports crime prevention based on the content learned by the learning unit; an expenditure management unit that manages expenditures based on the content learned by the learning unit; A system characterized by:

2. The learning unit In addition to the daily conversations mentioned above, social media and email content will also be collected to learn a wider range of communication patterns.

2. The system of claim 1.

3. The asset management support department Analyzes seniors' past investment history and proposes customized investment plans based on their individual risk tolerance 2. The system of claim 1.

4. The Crime Prevention Support Department Developing advanced algorithms to analyze the transaction history of seniors and detect abnormal patterns 2. The system of claim 1.

5. The expenditure management unit Analyzes the elderly's past spending history and proposes budget plans based on their individual spending patterns 2. The system of claim 1.

6. The expenditure management unit Analyzing the emotional state of elderly people and providing support to reduce stress when dementia develops 2. The system of claim 1.

7. The learning unit Analyzing changes in tone of voice or speaking style in the everyday conversation, detecting changes in emotions, and reflecting them in learning.

2. The system of claim 1.

8. The asset management support department Analyzing seniors' investment sentiment and providing emotion-based investment advice 2. The system of claim 1.

Images