System

Abstract

To provide a system that learns a thinking pattern of a user and provides various supports on the basis of the thinking pattern.SOLUTION: A system includes a reception section, a learning section, a proxy section, an indication section, a simulation section, and a fellow finding section. The reception section receives an answer to a question from a user. The learning section analyzes the answer received by the reception section and learns a thinking pattern of the user. The proxy section performs work instead of the user on the basis of the thinking pattern learned by the learning section. The indication section points out good and bad points of the user on the basis of the thinking pattern learned by the learning section. The simulation section simulates a reaction of the other person on the basis of the thinking pattern learned by the learning section. The fellow finding section finds a fellow that suits the user, on the basis of the thinking pattern learned by the learning section.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional technologies have had a problem in that they have not adequately learned the user's thought patterns and provided various types of support based on those patterns.

[0005] The system according to the embodiment aims to learn the user's thought patterns and provide various types of support based on the learned thought patterns. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a learning unit, an agent unit, a suggestion unit, a simulation unit, and a companion discovery unit. The reception unit accepts answers to questions from a user. The learning unit analyzes the answers accepted by the reception unit and learns the user's thinking patterns. The agent unit performs work on behalf of the user based on the thinking patterns learned by the learning unit. The suggestion unit points out the strengths and weaknesses of the user based on the thinking patterns learned by the learning unit. The simulation unit simulates the other person's reaction based on the thinking patterns learned by the learning unit. The companion discovery unit finds a companion that suits the user based on the thinking patterns learned by the learning unit. Effect of the Invention

[0007] The system according to the embodiment can learn the user's thought patterns and provide various kinds of assistance based on the learned thought patterns. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The MY generation AI system according to the embodiment of the present invention is a system that accepts answers to questions from a user, learns the user's thought patterns, performs work on behalf of the user, points out the user's strengths and weaknesses, simulates the other party's reaction, and finds a companion that suits the user from among all of humanity. In the MY generation AI system, the user answers questions and provides a behavioral history, and the generation AI reproduces the user's thought circuit. Next, the generation AI performs work on behalf of the user, points out the user's strengths and weaknesses, and simulates the other party's reaction in advance. The generation AI can also find a companion that suits the user from among all of humanity. For example, the user answers questions. For example, by answering questions such as "What is your favorite food?" and "What are your recent hobbies?", the generation AI learns the user's thought pattern. The user's behavior history is also collected. For example, data such as which websites the user visited and which apps the user used is collected and analyzed by the generation AI. Next, the generation AI reproduces the user's thought circuit. The generation AI models the user's thought pattern based on the collected data, and becomes able to think in the same way as the user. This allows the generation AI to work on behalf of the user. For example, when a user is busy, the generation AI can reply to emails on behalf of the user. Furthermore, the generation AI can point out the user's strengths and weaknesses. The generation AI analyzes the user's actions and comments and gives feedback on the user's strengths and areas for improvement. For example, it can give specific suggestions such as, "You have good communication skills, but are not good at time management." The generation AI can also simulate the other person's reaction in advance. For example, before a user proposes a new idea, the generation AI can simulate the other person's reaction to the idea and feed it back to the user. This allows the user to predict the other person's reaction in advance and prepare an appropriate response. Furthermore, the generation AI can find a companion that suits the user from among all of humanity. The generation AI can share information with other users' generation AIs and find companions with common hobbies and interests. For example, it can introduce people with the same hobbies and provide opportunities for interaction.In this way, by using generative AI, users can have their own AI with their own thought processes and utilize it for various purposes. This makes the user's life more convenient and fulfilling. As a result, the MY generative AI system can learn the user's thought patterns, perform various tasks on behalf of the user, point out the user's strengths and weaknesses, simulate the reactions of others, and find companions.

[0029] The MY generation AI system according to the embodiment includes a reception unit, a learning unit, an agent unit, a suggestion unit, a simulation unit, and a companion discovery unit. The reception unit receives answers to questions from users. The user's questions include, but are not limited to, questions in text format, voice format, and questions about a specific topic. For example, when the user answers a question in text format, the reception unit stores the answer in a database. The reception unit can also convert answers to questions in voice format into text data using voice recognition technology and store the text data. Furthermore, the reception unit can present questions about a specific topic to the user and collect the answers. For example, when the user answers a question such as "What is your favorite food?", the reception unit stores the answer in a database. Answers to questions in voice format are converted into text data using voice recognition technology and stored. Questions about a specific topic are customized based on the user's interests and concerns. The learning unit analyzes the answers received by the reception unit and learns the user's thinking patterns. Learning of thought patterns includes, for example, behavior history, utterance contents, selection tendency, etc., but is not limited to such examples. For example, the learning unit analyzes the behavior history of the user and models the user's thought pattern. The learning unit can also analyze the contents of the user's utterances and learn the user's thought pattern. Furthermore, the learning unit can analyze the user's selection tendency and learn the thought pattern. For example, the learning unit analyzes the behavior history such as which websites the user visited and which apps he used, and models the thought pattern. The analysis of the utterance contents uses natural language processing technology to understand the meaning and intention of the user's utterance. The analysis of the selection tendency uses a machine learning algorithm to learn the user's selection pattern. The proxy unit performs work on behalf of the user based on the thought pattern learned by the learning unit. The tasks to be performed include, for example, replying to emails, schedule management, data entry, etc., but are not limited to such examples. For example, the proxy unit replies to emails on behalf of the user when the user is busy. The proxy unit can also manage the user's schedule and remind the user of important plans. Furthermore, the agent can also perform data entry tasks.For example, the proxy unit accesses the user's email account and responds appropriately to the received email. For schedule management, a calendar application is used to manage the user's schedule and set reminders. For data entry work, data specified by the user is entered and stored in a database. The pointing unit points out the strengths and weaknesses of the user based on the thought patterns learned by the learning unit. Examples of pointing out include, but are not limited to, performance evaluation and behavior analysis. For example, the pointing unit analyzes the user's behavior and remarks and provides feedback on the user's strengths and areas for improvement. The pointing unit can also evaluate the user's performance and point out specific areas for improvement. Furthermore, the pointing unit can analyze the user's behavioral patterns and point out the strengths and weaknesses. For example, the pointing unit evaluates the user's communication skills and provides specific feedback. For behavior analysis, the user's behavioral patterns are analyzed to identify strengths and areas for improvement. For performance evaluation, the user's ability to perform work is evaluated and specific areas for improvement are evaluated. The simulation unit simulates the other party's reaction based on the thought patterns learned by the learning unit. The simulation includes, for example, emotion analysis, past reaction data, etc., but is not limited to such examples. For example, the simulation unit simulates the other party's reaction to a new idea before the user proposes the idea. The simulation unit can also simulate the other party's reaction to the user's remarks. Furthermore, the simulation unit can simulate the other party's reaction to the user's actions. For example, the simulation unit simulates the other party's reaction to a new project before the user proposes the proposal. The emotion analysis involves analyzing the other party's emotions and predicting the reaction. For the past reaction data, a simulation is performed based on the other party's reaction in similar situations in the past. The companion discovery unit finds companions that suit the user from among all of humanity based on the thinking patterns learned by the learning unit. The companion discovery includes, for example, common hobbies, occupations, skills, etc., but is not limited to such examples. The companion discovery unit, for example, shares information with other users' generation AIs and finds companions with common hobbies and interests.The companion discovery unit can also suggest suitable companions based on the user's occupation and skills. Furthermore, the companion discovery unit can find companions based on the user's interests and concerns. For example, the companion discovery unit introduces people with the same hobbies and provides opportunities for interaction. Common hobbies include sports, music, reading, etc. For occupations and skills, it suggests people with the same occupations and skills. For interests and concerns, it finds suitable companions based on the user's interests. As a result, the MY generation AI system according to the embodiment can learn the user's thinking patterns, perform various tasks on behalf of the user, point out the user's strengths and weaknesses, simulate the other person's reactions, and find companions.

[0030] The reception unit receives answers to questions from users. The questions from users include, but are not limited to, for example, questions in text format, voice format, questions on specific topics, and the like. For example, when the user answers a question in text format, the reception unit stores the answer in a database. The reception unit can also convert answers to questions in voice format into text data using voice recognition technology and store the text data. Furthermore, the reception unit can present questions on specific topics to the user and collect the answers. For example, when the user answers a question such as "What is your favorite food?", the reception unit stores the answer in a database. Answers to questions in voice format are converted into text data using voice recognition technology and stored. Questions on specific topics are customized based on the user's interests and concerns. The reception unit has an efficient algorithm for quickly processing text data entered by the user and storing it in a database. The voice recognition technology uses the latest deep learning model, and can convert voice data into text with high accuracy. As a result, no matter what format the user asks a question in, the reception unit can accurately grasp the content and store it in a database. The reception unit also has a function of referring to the user's past question history and automatically suggesting related questions. This allows the user to ask questions efficiently, improving the usability of the entire system. Furthermore, the reception unit can perform initial filtering to provide appropriate answers according to the content of the user's question. For example, if there are many questions about a particular topic, information related to that topic is preferentially collected and stored in a database. This allows the reception unit to respond flexibly to the user's needs, improving the efficiency and accuracy of the entire system.

[0031] The learning unit analyzes the answer received by the reception unit and learns the user's thinking pattern. Learning of the thinking pattern includes, for example, behavior history, utterance content, and selection tendency, but is not limited to such examples. For example, the learning unit analyzes the user's behavior history and models the user's thinking pattern. The learning unit can also analyze the user's utterance content and learn the user's thinking pattern. Furthermore, the learning unit can analyze the user's selection tendency and learn the thinking pattern. For example, the learning unit analyzes the user's behavior history, such as which website the user visited and which app the user used, and models the thinking pattern. The utterance content is analyzed by using natural language processing technology to understand the meaning and intention of the user's utterance. The selection tendency is analyzed by using a machine learning algorithm to learn the user's selection pattern. The learning unit uses a complex algorithm to integrate these data and model the user's thinking pattern with high accuracy. Specifically, the deep learning technology is used to analyze the user's behavior history and utterance content with a multi-layer neural network and extract the user's thinking pattern. This allows the learning unit to deeply understand the intentions and emotions behind the user's actions and statements. The learning unit also uses a reinforcement learning algorithm to analyze the user's selection trends. This makes it possible to predict what choices the user will prefer and what choices they will make in what situations. Furthermore, the learning unit continuously updates the user's thought patterns and improves the model based on the latest information. This allows the learning unit to respond to the user's changing needs and interests and always provide optimal services.

[0032] The agent performs work on behalf of the user based on the thought patterns learned by the learning unit. Examples of tasks that are performed include, but are not limited to, replying to emails, managing schedules, and entering data. For example, the agent replies to emails when the user is busy. The agent can also manage the user's schedule and remind the user of important appointments. Furthermore, the agent can perform data entry work on behalf of the user. For example, the agent accesses the user's email account and responds appropriately to received emails. For schedule management, a calendar app is used to manage the user's schedule and set reminders. For data entry work, data specified by the user is entered and saved in a database. The agent utilizes advanced natural language processing technology and machine learning algorithms to efficiently perform these tasks. For example, for replying to emails, a generation AI is used to learn the user's past reply patterns and generate appropriate reply content. For schedule management, an algorithm is used to analyze the user's past schedule data and set optimal reminders. For data entry work, an automated tool is used to accurately enter data according to the format specified by the user and store it in the database. This allows the agent department to reduce the burden on the user and perform tasks efficiently. Furthermore, the agent department can collect user feedback and continuously improve the method of performing tasks. This allows the agent department to respond flexibly to user needs, improving the efficiency and accuracy of the entire system.

[0033] The pointing unit points out the strengths and weaknesses of the user based on the thought patterns learned by the learning unit. The pointing includes, but is not limited to, performance evaluation, behavior analysis, and the like. For example, the pointing unit analyzes the user's behavior and remarks, and feeds back the user's strengths and areas for improvement. The pointing unit can also evaluate the user's performance and point out specific areas for improvement. Furthermore, the pointing unit can analyze the user's behavioral patterns and point out strengths and weaknesses. For example, the pointing unit evaluates the user's communication skills and provides specific feedback. The behavioral analysis involves analyzing the user's behavioral patterns and identifying strengths and areas for improvement. The performance evaluation involves evaluating the user's ability to perform work and pointing out specific areas for improvement. The pointing unit utilizes machine learning algorithms and natural language processing technology to perform these evaluations. Specifically, an algorithm is used to analyze the user's behavioral data and build a performance evaluation model. This allows for a deep understanding of the intentions and emotions behind the user's behavior and remarks, and provides appropriate feedback. The pointing unit can also analyze long-term trends based on the user's past performance data and identify areas for future improvement. This allows the suggestion unit to support the user's growth and promote performance improvement. Furthermore, the suggestion unit can collect user feedback and continuously improve the evaluation model. This allows the suggestion unit to flexibly respond to the needs of the user, improving the efficiency and accuracy of the entire system.

[0034] The simulation unit simulates the other party's reaction based on the thought patterns learned by the learning unit. The simulation includes, for example, emotion analysis, past reaction data, and the like, but is not limited to such examples. For example, the simulation unit simulates the other party's reaction to a new idea before the user proposes the idea. The simulation unit can also simulate the other party's reaction to the user's remarks. Furthermore, the simulation unit can simulate the other party's reaction to the user's actions. For example, the simulation unit simulates the other party's reaction to a proposal before the user proposes a new project. The emotion analysis involves analyzing the other party's emotions and predicting the reaction. For the past reaction data, a simulation is performed based on the other party's reaction in similar situations in the past. The simulation unit uses a complex algorithm to integrate these data and predict the other party's reaction with high accuracy. Specifically, using deep learning technology, the other party's emotions and reactions are analyzed with a multi-layered neural network, and the other party's reaction is simulated. This allows the simulation unit to deeply understand the intentions and emotions behind the user's actions and remarks and provide an appropriate simulation. The simulation unit can also analyze long-term trends and predict future reactions based on the user's past behavioral data. This allows the simulation unit to respond flexibly to user needs, improving the efficiency and accuracy of the entire system. Furthermore, the simulation unit can collect user feedback and continuously improve the simulation model. This allows the simulation unit to respond flexibly to user needs, improving the efficiency and accuracy of the entire system.

[0035] The companion discovery unit finds companions suitable for the user from among all of humanity based on the thought patterns learned by the learning unit. Companion discovery includes, but is not limited to, common hobbies, occupations, skills, and the like. The companion discovery unit, for example, shares information with other users' generation AIs to find companions with common hobbies and interests. The companion discovery unit can also suggest suitable companions based on the user's occupation and skills. Furthermore, the companion discovery unit can find companions based on the user's interests and concerns. For example, the companion discovery unit introduces people with the same hobbies and provides opportunities for interaction. Common hobbies include sports, music, reading, and the like. For occupations and skills, it suggests people with the same occupations and skills. For interests and concerns, it finds suitable companions based on the user's interests. The companion discovery unit uses complex algorithms to integrate these data and suggest the most suitable companions to the user with high accuracy. Specifically, using deep learning technology, the user's hobbies, interests, occupations, and skills are analyzed with a multi-layered neural network to suggest the most suitable companions. This allows the companion discovery unit to respond flexibly to the needs of the user, improving the efficiency and accuracy of the entire system. The companion discovery unit can also analyze long-term trends based on the user's past behavioral data and predict future companions. This allows the companion discovery unit to respond flexibly to the needs of the user, improving the efficiency and accuracy of the entire system. Furthermore, the companion discovery unit can collect user feedback and continuously improve the proposed model. This allows the companion discovery unit to respond flexibly to the needs of the user, improving the efficiency and accuracy of the entire system.

[0036] The reception unit can collect the user's behavior history. The behavior history includes, for example, a website browsing history, an app usage history, and the like, but is not limited to such examples. For example, the reception unit records the URL of the website visited by the user and stores it in a database. The reception unit can also collect and analyze the usage history of the app used by the user. For example, the reception unit records the URL of the website visited by the user and stores it in a database. The app usage history records which app the user used and for how long. By collecting the user's behavior history, more accurate thinking patterns can be learned. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's behavior history data to the generation AI and cause the generation AI to execute the analysis of the behavior history.

[0037] The learning unit can analyze the behavior history collected by the reception unit and learn the user's thinking pattern. The analysis includes, for example, data mining, machine learning algorithms, and the like, but is not limited to such examples. The learning unit can analyze the user's behavior history using, for example, data mining technology, and model the thinking pattern. The learning unit can also analyze the user's behavior history using a machine learning algorithm and learn the thinking pattern. For example, the learning unit can use a data mining technology to extract a pattern from the user's behavior history and model the thinking pattern. The machine learning algorithm includes a neural network, a support vector machine, and the like. This makes it possible to more accurately learn the user's thinking pattern by analyzing the behavior history. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's behavior history data to the generation AI and cause the generation AI to model the thinking pattern.

[0038] The proxy unit can reply to an email on behalf of a user. The reply to an email includes, for example, the use of a template, natural language generation technology, and the like, but is not limited to such examples. For example, the proxy unit replies to an email received by a user using an appropriate template. The proxy unit can also generate a reply based on the user's intention using natural language generation technology. For example, the proxy unit swiftly replies to an email received by a user using a template prepared in advance. The natural language generation technology uses a text generation AI (for example, LLM) to generate a reply based on the user's intention. This makes it possible to reduce the burden on the user by replying to an email on behalf of the user. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit can input the received email data to a generation AI and have the generation AI execute the generation of the reply content.

[0039] The pointing unit can analyze the user's behavior and remarks and specifically point out the user's strengths and weaknesses. The analysis of behavior and remarks includes, but is not limited to, for example, behavior pattern analysis and emotion analysis of the remarks. For example, the pointing unit can analyze the user's behavior pattern and identify the user's strengths and areas for improvement. The pointing unit can also analyze the user's remarks using emotion analysis technology and provide specific feedback. For example, the pointing unit can analyze the user's behavior pattern and evaluate the user's communication ability and time management ability. For the emotion analysis of the remarks, natural language processing technology is used to analyze the emotion of the user's remarks. As a result, specific feedback can be provided by analyzing the user's behavior and remarks. A part or all of the above-mentioned processing in the pointing unit may be performed using, for example, AI, or may be performed without using AI. For example, the pointing unit can input the user's behavior data to the generation AI and cause the generation AI to identify the strengths and weaknesses.

[0040] The simulation unit can simulate the other party's reaction to the user's new idea. The simulation of the new idea includes, but is not limited to, for example, a creative proposal, a technical idea, and the like. For example, before the user proposes a new project, the simulation unit simulates the other party's reaction to the proposal. The simulation unit can also simulate the other party's reaction to the user's remarks. Furthermore, the simulation unit can simulate the other party's reaction to the user's actions. For example, the simulation unit simulates the other party's reaction to the proposal before the user proposes a new project. The emotion analysis involves analyzing the other party's emotions and predicting the reaction. For past reaction data, a simulation is performed based on the other party's reaction in similar situations in the past. This allows the other party's reaction to a new idea to be simulated in advance, allowing an appropriate response to be prepared. A part or all of the above-mentioned processing in the simulation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simulation unit can input the user's idea data into the generation AI and cause the generation AI to execute a simulation of the other party's reaction.

[0041] The companion discovery unit can share information with the generation AI of other users and specifically find companions who have common hobbies and interests. Common hobbies and interests include, but are not limited to, hobby categories, topics of interest, and the like. The companion discovery unit can share information with the generation AI of other users and find companions who have common hobbies and interests, for example. The companion discovery unit can also suggest appropriate companions based on the user's occupation and skills. Furthermore, the companion discovery unit can find companions based on the user's interests and concerns. For example, the companion discovery unit introduces people who have the same hobbies and provides opportunities for interaction. Common hobbies include sports, music, reading, and the like. For occupations and skills, people with the same occupations and skills are suggested. For interests and concerns, appropriate companions are found based on the user's interests. This allows the user to find companions who have common hobbies and interests, thereby providing opportunities for interaction. Some or all of the above-mentioned processing in the companion discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the companion discovery unit can input the user's hobby data into the generation AI and cause the generation AI to discover companions who share a common hobby.

[0042] The reception unit can analyze the user's past question history and select the optimal question format. The question formats include, for example, multiple choice and free description, but are not limited to such examples. The reception unit, for example, prioritizes the question format that the user has answered in the past. The reception unit can also avoid the question format that the user has avoided in the past. Furthermore, the reception unit can analyze the user's past answer patterns and propose the optimal question format. For example, the reception unit prioritizes the question format that the user has answered in the past. The multiple choice question format includes a format in which a user selects from multiple options. The free description question format includes a format in which a user freely writes an answer. In this way, the optimal question format can be provided to the user by analyzing the past question history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's question history data to the generation AI and cause the generation AI to select the optimal question format.

[0043] The reception unit can filter questions based on the user's current situation and field of interest when receiving a question. Examples of filtering include, but are not limited to, keyword matching and relevance score. For example, the reception unit preferentially issues questions related to topics in which the user is currently interested. The reception unit can also adjust questions according to the user's current situation (e.g., at work, on a break). Furthermore, the reception unit can customize questions based on the user's field of interest. For example, the reception unit preferentially issues questions related to topics in which the user is currently interested. For keyword matching, questions are filtered using keywords related to the user's interests. For relevance score, the relevance of questions is evaluated and scored based on the user's field of interest. As a result, questions can be filtered based on the user's current situation and field of interest, thereby providing more relevant questions. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's interest data to the generation AI and cause the generation AI to filter questions.

[0044] When receiving a question, the reception unit can preferentially receive a highly relevant question in consideration of the geographical location information of the user. The geographical location information includes, for example, GPS data, location information services, etc., but is not limited to such examples. For example, when the user is in a specific location, the reception unit prioritizes questions related to the location. In addition, the reception unit can also issue questions specific to the area based on the user's current location. Furthermore, the reception unit can also suggest optimal questions based on the user's geographical location information. For example, when the user is in a specific location, the reception unit prioritizes questions related to the location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. In this way, by considering the user's geographical location information, a highly relevant question can be provided. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's location information data to the generation AI and cause the generation AI to select a question.

[0045] The reception unit can analyze the user's social media activity when receiving a question and receive a related question. The social media activity includes, for example, the content of the post, the number of likes, and the like, but is not limited to such examples. The reception unit, for example, issues a question related to a topic in which the user has recently shown interest on social media. The reception unit can also suggest an optimal question based on the user's social media activity. Furthermore, the reception unit can analyze the user's social media remarks and issue a related question. For example, the reception unit issues a question related to a topic in which the user has recently shown interest on social media. The post content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. In this way, by analyzing the social media activity, a related question can be provided. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's social media data to the generation AI and cause the generation AI to select a question.

[0046] The learning unit can optimize the learning algorithm by referring to past learning data during learning. Examples of optimization of the learning algorithm include, but are not limited to, neural networks and support vector machines. The learning unit can set optimal learning parameters, for example, based on past learning data. The learning unit can also analyze past learning data and identify improvements to the learning algorithm. Furthermore, the learning unit can improve the accuracy of the learning algorithm by referring to past learning data. For example, the learning unit sets optimal learning parameters based on past learning data. The neural network includes a multilayer perceptron and a convolutional neural network. The support vector machine includes a linear SVM and a nonlinear SVM. As a result, the accuracy of the learning algorithm is improved by referring to the past learning data. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input past learning data to the generation AI and cause the generation AI to execute optimization of the learning algorithm.

[0047] During learning, the learning unit can analyze the user's behavior history in detail to improve the accuracy of the thought pattern. The detailed analysis includes, for example, the granularity of the data and the depth of the analysis, but is not limited to such examples. For example, the learning unit analyzes the user's behavior history in detail to extract the characteristics of the thought pattern. The learning unit can also refine the model of the thought pattern based on the user's behavior history. Furthermore, the learning unit can analyze the user's behavior history in detail to improve the accuracy of the thought pattern. For example, the learning unit analyzes the user's behavior history in detail to extract the characteristics of the thought pattern. The granularity of the data includes the fineness of the behavior data. The depth of the analysis includes a detailed analysis of the behavior data. As a result, the accuracy of the thought pattern is improved by analyzing the behavior history in detail. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's behavior history data to the generation AI and cause the generation AI to execute the improvement of the accuracy of the thought pattern.

[0048] During learning, the learning unit can weight the learning data based on the time of the question submitted by the user. The weighting includes, for example, weighting of time series data, weighting based on importance, and the like, but is not limited to such examples. For example, the learning unit learns by placing emphasis on data of a question recently submitted by the user. The learning unit can also learn by placing emphasis on data of a question submitted by the user at a specific time. Furthermore, the learning unit can weight the learning data based on the time of the question submitted by the user. For example, the learning unit learns by placing emphasis on data of a question recently submitted by the user. Weighting of time series data includes a method of weighting based on the chronological order of data. Weighting based on importance includes a method of weighting according to the importance of data. As a result, weighting of the learning data based on the time of the question improves the accuracy of learning. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's question data to the generation AI and cause the generation AI to perform weighting.

[0049] The learning unit can improve the accuracy of learning by referring to the user's related literature during learning. The related literature includes, for example, academic papers, technical reports, etc., but is not limited to such examples. The learning unit complements the learning data, for example, based on the related literature referred to by the user. The learning unit can also improve the accuracy of the learning algorithm by referring to the user's related literature. Furthermore, the learning unit can improve the quality of the learning data based on the user's related literature. For example, the learning unit complements the learning data based on the related literature referred to by the user. The academic papers include academic research results referred to by the user. The technical reports include technical reports referred to by the user. As a result, the accuracy of learning is improved by referring to the related literature. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's related literature data to the generation AI and cause the generation AI to execute the improvement of the learning accuracy.

[0050] The proxy unit can select an optimal proxy method by referring to the user's past task history during proxy operation. The task history includes, for example, past task records, task completion statuses, and the like, but is not limited to such examples. The proxy unit, for example, prioritizes a task method that the user has previously preferred. The proxy unit can also select an optimal proxy method based on the user's past task history. Furthermore, the proxy unit can also suggest an efficient proxy method by referring to the user's past task history. For example, the proxy unit prioritizes a task method that the user has previously preferred. The past task records include details of tasks that the user has previously performed. The task completion status includes the status of tasks that the user has previously completed. This allows the optimal proxy method to be selected by referring to the past task history. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit can input the user's task history data to the generation AI and cause the generation AI to select a proxy method.

[0051] The proxy unit can customize the contents of the task based on the current situation of the user when acting on behalf of the user. Customization includes, for example, adjustment based on the current situation of the user, settings according to individual needs, and the like, but is not limited to such examples. For example, when the user is busy, the proxy unit acts on behalf of the user with a simplified task. In addition, when the user is relaxed, the proxy unit can also act on behalf of the user with a detailed task. Furthermore, the proxy unit can customize the contents of the task based on the current situation of the user. For example, when the user is busy, the proxy unit acts on behalf of the user with a simplified task. The user's current situation includes the environment and state in which the user is currently placed. The individual needs include the user's specific requests and wishes. This allows for more appropriate acting on behalf of the user by customizing the contents of the task based on the current situation. Part or all of the above-mentioned processing in the proxy unit may be performed, for example, using AI, or may be performed without using AI. For example, the proxy unit can input the user's situation data to the generation AI and cause the generation AI to execute task customization.

[0052] The proxy unit can select the optimal proxy method in consideration of the geographical location information of the user at the time of proxy. The geographical location information includes, for example, GPS data, location information services, etc., but is not limited to such examples. For example, when the user is in a specific location, the proxy unit prioritizes a task related to the location. In addition, the proxy unit can also proxy a task specific to a region based on the user's current location. Furthermore, the proxy unit can select the optimal proxy method based on the user's geographical location information. For example, when the user is in a specific location, the proxy unit prioritizes a task related to the location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. As a result, the optimal proxy method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit can input the user's location information data to the generation AI and cause the generation AI to select the proxy method.

[0053] During the proxy operation, the proxy unit can analyze the user's social media activity and suggest a proxy task. The social media activity includes, for example, the content of the post, the number of likes, and the like, but is not limited to such examples. The proxy unit, for example, performs a task related to a topic in which the user has recently shown interest on social media. The proxy unit can also suggest an optimal proxy task based on the user's social media activity. Furthermore, the proxy unit can analyze the user's comments on social media and perform a related task on behalf of the user. For example, the proxy unit performs a task related to a topic in which the user has recently shown interest on social media. The post content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. This makes it possible to suggest a related task by analyzing the social media activity. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit can input the user's social media data to the generation AI and cause the generation AI to execute the proposal of a proxy task.

[0054] The indication unit can provide specific feedback by referring to the user's past behavior history when making an indication. The behavior history includes, for example, a record of past behavior, a frequency of behavior, and the like, but is not limited to such examples. The indication unit, for example, indicates specific improvements based on the user's past behavior history. The indication unit can also provide specific feedback by referring to the user's past behavior history. Furthermore, the indication unit can also indicate specific strengths based on the user's past behavior history. For example, the indication unit indicates specific improvements based on the user's past behavior history. The record of past behavior includes details of behaviors performed by the user in the past. The frequency of behavior includes the frequency of behaviors performed by the user in the past. Thereby, specific feedback can be provided by referring to the past behavior history. A part or all of the above-mentioned processing in the indication unit may be performed, for example, using AI, or may be performed without using AI. For example, the indication unit can input the user's behavior history data to the generation AI and cause the generation AI to provide feedback.

[0055] The indication unit can customize the indication contents based on the current situation of the user when making an indication. Customization includes, for example, adjustment based on the current situation of the user, settings according to individual needs, and the like, but is not limited to such examples. For example, when the user is busy, the indication unit makes a concise and to the point indication. In addition, when the user is relaxed, the indication unit can also make detailed indication. Furthermore, the indication unit can customize the indication contents based on the current situation of the user. For example, when the user is busy, the indication unit makes a concise and to the point indication. The current situation of the user includes the environment and state in which the user is currently placed. The individual needs include the specific requests and wishes of the user. As a result, by customizing the indication contents based on the current situation, more appropriate indication can be made. A part or all of the above-mentioned processing in the indication unit may be performed, for example, using AI, or may be performed without using AI. For example, the indication unit can input the user's situation data to the generation AI and cause the generation AI to execute customization of the indication contents.

[0056] The indication unit can select the optimal indication method in consideration of the geographical location information of the user at the time of indication. The geographical location information includes, for example, GPS data, location information services, etc., but is not limited to such examples. For example, when the user is in a specific location, the indication unit prioritizes indication related to the location. In addition, the indication unit can also perform area-specific indication based on the user's current location. Furthermore, the indication unit can select the optimal indication method based on the user's geographical location information. For example, when the user is in a specific location, the indication unit prioritizes indication related to the location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. As a result, the optimal indication method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the indication unit may be performed using, for example, AI, or may be performed without using AI. For example, the indication unit can input the user's location information data to the generation AI and cause the generation AI to select the indication method.

[0057] The pointing unit can analyze the user's social media activity at the time of pointing out and propose the content of the pointing out. The social media activity includes, for example, the content of the post, the number of likes, and the like, but is not limited to such examples. For example, the pointing unit makes a point related to a topic in which the user has recently shown interest on social media. The pointing unit can also propose optimal content of the pointing out based on the user's social media activity. Furthermore, the pointing unit can analyze the user's comments on social media and make related points. For example, the pointing unit makes a point related to a topic in which the user has recently shown interest on social media. The post content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. In this way, by analyzing the social media activity, related content of the pointing out can be proposed. A part or all of the above-mentioned processing in the pointing unit may be performed, for example, using AI, or may be performed without using AI. For example, the pointing unit can input the user's social media data to the generation AI and cause the generation AI to execute the suggestion of the content of the pointing out.

[0058] The simulation unit can improve the accuracy of the simulation by referring to the user's past idea history during the simulation. The idea history includes, for example, past idea records, idea evaluations, and the like, but is not limited to such examples. The simulation unit improves the accuracy of the simulation, for example, based on the user's past idea history. The simulation unit can also adjust the results of the simulation by referring to the user's past idea history. Furthermore, the simulation unit can analyze the user's past idea history and improve the accuracy of the simulation. For example, the simulation unit improves the accuracy of the simulation based on the user's past idea history. The past idea records include details of ideas proposed by the user in the past. The idea evaluations include evaluation results of ideas proposed by the user in the past. As a result, the accuracy of the simulation is improved by referring to the past idea history. A part or all of the above-mentioned processing in the simulation unit may be performed, for example, using AI, or may be performed without using AI. For example, the simulation unit can input the user's idea history data to the generation AI and cause the generation AI to execute improvement of the accuracy of the simulation.

[0059] The simulation unit can customize the simulation content based on the current situation of the user during the simulation. Customization includes, for example, adjustment based on the current situation of the user, settings according to individual needs, and the like, but is not limited to such examples. For example, when the user is busy, the simulation unit provides simplified simulation content. In addition, when the user is relaxed, the simulation unit can also provide detailed simulation content. Furthermore, the simulation unit can customize the simulation content based on the current situation of the user. For example, when the user is busy, the simulation unit provides simplified simulation content. The user's current situation includes the environment and state in which the user is currently placed. The individual needs include the user's specific requests and wishes. This allows a more appropriate simulation to be performed by customizing the simulation content based on the current situation. Part or all of the above-mentioned processing in the simulation unit may be performed, for example, using AI, or may be performed without using AI. For example, the simulation unit can input the user's situation data to the generation AI and cause the generation AI to customize the simulation content.

[0060] The simulation unit can select an optimal simulation method in consideration of the geographical location information of the user during the simulation. The geographical location information includes, for example, GPS data, location information services, etc., but is not limited to such examples. For example, when the user is in a specific location, the simulation unit prioritizes a simulation related to that location. In addition, the simulation unit can also perform a region-specific simulation based on the user's current location. Furthermore, the simulation unit can select an optimal simulation method based on the user's geographical location information. For example, when the user is in a specific location, the simulation unit prioritizes a simulation related to that location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. This allows the optimal simulation method to be selected by considering the geographical location information. A part or all of the above-mentioned processing in the simulation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simulation unit can input the user's location information data to the generation AI and cause the generation AI to select a simulation method.

[0061] The simulation unit can analyze the user's social media activity during the simulation to suggest simulation content. The social media activity includes, for example, the posting content, the number of likes, and the like, but is not limited to such examples. For example, the simulation unit performs a simulation related to a topic in which the user has recently shown interest on social media. The simulation unit can also suggest optimal simulation content based on the user's social media activity. Furthermore, the simulation unit can analyze the user's social media comments and perform a related simulation. For example, the simulation unit performs a simulation related to a topic in which the user has recently shown interest on social media. The posting content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. This makes it possible to suggest related simulation content by analyzing the social media activity. A part or all of the above-mentioned processing in the simulation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simulation unit can input the user's social media data to the generation AI and cause the generation AI to execute a proposal of simulation content.

[0062] When discovering a friend, the friend discovery unit can suggest an optimal friend by referring to the user's past interaction history. The interaction history includes, for example, records of past interactions, frequency of interactions, etc., but is not limited to such examples. The friend discovery unit, for example, suggests an optimal friend based on the user's past interaction history. The friend discovery unit can also suggest a friend who has a common hobby by referring to the user's past interaction history. Furthermore, the friend discovery unit can analyze the user's past interaction history and suggest an optimal friend. For example, the friend discovery unit suggests an optimal friend based on the user's past interaction history. The record of past interactions includes details of interactions that the user has performed in the past. The frequency of interactions includes the frequency of interactions that the user has performed in the past. As a result, the optimal friend can be suggested by referring to the past interaction history. A part or all of the above-mentioned processing in the friend discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the friend discovery unit can input the user's interaction history data to the generation AI and cause the generation AI to execute the suggestion of a friend.

[0063] The companion discovery unit can customize the companion discovery means based on the user's current situation when discovering a companion. Customization includes, for example, adjustment based on the user's current situation, settings according to individual needs, and the like, but is not limited to such examples. For example, the companion discovery unit provides a simplified companion discovery means when the user is busy. In addition, the companion discovery unit can also provide a detailed companion discovery means when the user is relaxed. Furthermore, the companion discovery unit can customize the companion discovery means based on the user's current situation. For example, the companion discovery unit provides a simplified companion discovery means when the user is busy. The user's current situation includes the environment and state in which the user is currently placed. The individual needs include the user's specific requests and wishes. This allows a more appropriate companion to be proposed by customizing the companion discovery means based on the current situation. Part or all of the above-mentioned processing in the companion discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the companion discovery unit can input the user's situation data into the generation AI and cause the generation AI to execute customization of the companion discovery means.

[0064] When discovering a friend, the friend discovery unit can propose the most suitable friend by considering the geographical location information of the user. The geographical location information includes, but is not limited to, for example, GPS data, location information services, and the like. For example, when the user is in a specific location, the friend discovery unit prioritizes a friend related to that location. In addition, the friend discovery unit can also propose a friend specific to the area based on the user's current location. Furthermore, the friend discovery unit can also propose the most suitable friend based on the user's geographical location information. For example, when the user is in a specific location, the friend discovery unit prioritizes a friend related to that location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. In this way, the most suitable friend can be proposed by considering the geographical location information. A part or all of the above-mentioned processing in the friend discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the friend discovery unit can input the user's location information data to the generation AI and cause the generation AI to execute the friend proposal.

[0065] When discovering a friend, the companion discovery unit can analyze the user's social media activity and suggest a means of discovering a friend. The social media activity includes, for example, the content of the post, the number of likes, and the like, but is not limited to such examples. The companion discovery unit, for example, suggests companions related to topics in which the user has recently shown interest on social media. The companion discovery unit can also suggest the optimal means of discovering a companion based on the user's social media activity. Furthermore, the companion discovery unit can analyze the user's comments on social media and suggest related companions. For example, the companion discovery unit suggests companions related to topics in which the user has recently shown interest on social media. The post content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. In this way, by analyzing the social media activity, a related means of discovering a companion can be suggested. A part or all of the above-mentioned processing in the companion discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the companion discovery unit can input the user's social media data to the generation AI and cause the generation AI to execute the suggestion of a means of discovering a companion.

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

[0067] The reception unit can collect and analyze the user's past purchase history. The purchase history includes, for example, online shopping history, in-store purchase history, and the like. The reception unit records what products the user has purchased and stores the records in a database. The reception unit can also analyze the user's purchase history and grasp the user's purchasing trends. For example, the reception unit can identify products and brands that the user frequently purchases and suggest products that suit the user. This can improve the user's purchasing experience.

[0068] The learning unit can customize the learning content based on the user's hobbies and interests. For example, if the user is interested in music, information related to music is given priority for learning. Also, if the user is interested in sports, information related to sports can be learned. Furthermore, the learning unit can dynamically adjust the learning content according to changes in the user's interests. For example, if the user starts a new hobby, information related to that hobby is learned. This allows learning to be done according to the user's interests.

[0069] The proxy unit can post on social media on behalf of the user. For example, when the user is busy, the proxy unit posts on behalf of the user. The proxy unit can also analyze the content of the user's past posts and generate posts that match the user's style. Furthermore, the proxy unit can analyze the reactions of the user's followers and suggest the optimal timing for posting. This allows the user to carry out social media activities efficiently.

[0070] The simulation unit can improve the accuracy of the simulation by referring to the user's past failure experiences. For example, the simulation unit can analyze data of projects that the user has failed in the past and perform a simulation to avoid similar failures. The simulation unit can also perform a simulation to increase the possibility of success by referring to the user's past successful experiences. Furthermore, the simulation unit can perform a simulation to minimize risk based on the user's past experiences. This allows the user to utilize past experiences to obtain better results.

[0071] The reception unit can analyze the user's past question history and select the most suitable question format. For example, the reception unit can give priority to question formats that the user has preferred to answer in the past. The reception unit can also avoid question formats that the user has avoided in the past. Furthermore, the reception unit can analyze the user's past answer patterns and suggest the most suitable question format. In this way, the most suitable question format can be provided to the user by analyzing the past question history.

[0072] The process flow of the first embodiment will be briefly described below.

[0073] Step 1: The reception unit receives answers to the user's questions. The user's questions may be in text format, voice format, or questions about a specific topic. The reception unit stores the answers in text format in a database, and converts the voice format answers into text data using voice recognition technology and stores them. Furthermore, the reception unit presents questions about a specific topic to the user and collects the answers. Step 2: The learning unit analyzes the answers received by the reception unit and learns the user's thought patterns. Learning of thought patterns includes behavioral history, utterance content, and selection tendencies. The learning unit analyzes the user's behavioral history and models the thought patterns. Natural language processing technology is used to analyze utterance content, and machine learning algorithms are used to analyze selection tendencies. Step 3: The agent performs tasks on behalf of the user based on the thought patterns learned by the learning unit. Tasks performed include replying to emails, managing schedules, and entering data. When the user is busy, the agent replies to emails, manages schedules, and reminds the user of important events. It also performs data entry tasks. Step 4: The suggestion unit suggests the user's strengths and weaknesses based on the thinking patterns learned by the learning unit. The suggestions include performance evaluation and behavior analysis. The suggestion unit analyzes the user's behavior and comments, and provides feedback on strengths and areas for improvement. Performance evaluation involves evaluating the user's ability to carry out work and suggesting specific areas for improvement. Step 5: The simulation unit simulates the other person's reaction based on the thought patterns learned by the learning unit. The simulation includes emotion analysis, past reaction data, etc. The simulation unit simulates the other person's reaction to a new idea before the user proposes the idea. The emotion analysis involves analyzing the other person's emotions and predicting the reaction. Step 6: The peer discovery unit finds peers that suit the user based on the thinking patterns learned by the learning unit. Peer discovery includes common hobbies, occupations, skills, etc. The peer discovery unit shares information with other users' generation AIs to find peers with common hobbies and interests. In addition, it suggests appropriate peers based on the user's occupation and skills.

[0074] (Example 2) The MY generation AI system according to the embodiment of the present invention is a system that accepts answers to questions from a user, learns the user's thought patterns, performs work on behalf of the user, points out the user's strengths and weaknesses, simulates the other party's reaction, and finds a companion that suits the user from among all of humanity. In the MY generation AI system, the user answers questions and provides a behavioral history, and the generation AI reproduces the user's thought circuit. Next, the generation AI performs work on behalf of the user, points out the user's strengths and weaknesses, and simulates the other party's reaction in advance. The generation AI can also find a companion that suits the user from among all of humanity. For example, the user answers questions. For example, by answering questions such as "What is your favorite food?" and "What are your recent hobbies?", the generation AI learns the user's thought pattern. The user's behavior history is also collected. For example, data such as which websites the user visited and which apps the user used is collected and analyzed by the generation AI. Next, the generation AI reproduces the user's thought circuit. The generation AI models the user's thought pattern based on the collected data, and becomes able to think in the same way as the user. This allows the generation AI to work on behalf of the user. For example, when a user is busy, the generation AI can reply to emails on behalf of the user. Furthermore, the generation AI can point out the user's strengths and weaknesses. The generation AI analyzes the user's actions and comments and gives feedback on the user's strengths and areas for improvement. For example, it can give specific suggestions such as, "You have good communication skills, but are not good at time management." The generation AI can also simulate the other person's reaction in advance. For example, before a user proposes a new idea, the generation AI can simulate the other person's reaction to the idea and feed it back to the user. This allows the user to predict the other person's reaction in advance and prepare an appropriate response. Furthermore, the generation AI can find a companion that suits the user from among all of humanity. The generation AI can share information with other users' generation AIs and find companions with common hobbies and interests. For example, it can introduce people with the same hobbies and provide opportunities for interaction.In this way, by using generative AI, users can have their own AI with their own thought processes and utilize it for various purposes. This makes the user's life more convenient and fulfilling. As a result, the MY generative AI system can learn the user's thought patterns, perform various tasks on behalf of the user, point out the user's strengths and weaknesses, simulate the reactions of others, and find companions.

[0075] The MY generation AI system according to the embodiment includes a reception unit, a learning unit, an agent unit, a suggestion unit, a simulation unit, and a companion discovery unit. The reception unit receives answers to questions from users. The user's questions include, but are not limited to, questions in text format, voice format, and questions about a specific topic. For example, when the user answers a question in text format, the reception unit stores the answer in a database. The reception unit can also convert answers to questions in voice format into text data using voice recognition technology and store the text data. Furthermore, the reception unit can present questions about a specific topic to the user and collect the answers. For example, when the user answers a question such as "What is your favorite food?", the reception unit stores the answer in a database. Answers to questions in voice format are converted into text data using voice recognition technology and stored. Questions about a specific topic are customized based on the user's interests and concerns. The learning unit analyzes the answers received by the reception unit and learns the user's thinking patterns. Learning of thought patterns includes, for example, behavior history, utterance contents, selection tendency, etc., but is not limited to such examples. For example, the learning unit analyzes the behavior history of the user and models the user's thought pattern. The learning unit can also analyze the contents of the user's utterances and learn the user's thought pattern. Furthermore, the learning unit can analyze the user's selection tendency and learn the thought pattern. For example, the learning unit analyzes the behavior history such as which websites the user visited and which apps he used, and models the thought pattern. The analysis of the utterance contents uses natural language processing technology to understand the meaning and intention of the user's utterance. The analysis of the selection tendency uses a machine learning algorithm to learn the user's selection pattern. The proxy unit performs work on behalf of the user based on the thought pattern learned by the learning unit. The tasks to be performed include, for example, replying to emails, schedule management, data entry, etc., but are not limited to such examples. For example, the proxy unit replies to emails on behalf of the user when the user is busy. The proxy unit can also manage the user's schedule and remind the user of important plans. Furthermore, the agent can also perform data entry tasks.For example, the proxy unit accesses the user's email account and responds appropriately to the received email. For schedule management, a calendar application is used to manage the user's schedule and set reminders. For data entry work, data specified by the user is entered and stored in a database. The pointing unit points out the strengths and weaknesses of the user based on the thought patterns learned by the learning unit. Examples of pointing out include, but are not limited to, performance evaluation and behavior analysis. For example, the pointing unit analyzes the user's behavior and remarks and provides feedback on the user's strengths and areas for improvement. The pointing unit can also evaluate the user's performance and point out specific areas for improvement. Furthermore, the pointing unit can analyze the user's behavioral patterns and point out the strengths and weaknesses. For example, the pointing unit evaluates the user's communication skills and provides specific feedback. For behavior analysis, the user's behavioral patterns are analyzed to identify strengths and areas for improvement. For performance evaluation, the user's ability to perform work is evaluated and specific areas for improvement are evaluated. The simulation unit simulates the other party's reaction based on the thought patterns learned by the learning unit. The simulation includes, for example, emotion analysis, past reaction data, etc., but is not limited to such examples. For example, the simulation unit simulates the other party's reaction to a new idea before the user proposes the idea. The simulation unit can also simulate the other party's reaction to the user's remarks. Furthermore, the simulation unit can simulate the other party's reaction to the user's actions. For example, the simulation unit simulates the other party's reaction to a new project before the user proposes the proposal. The emotion analysis involves analyzing the other party's emotions and predicting the reaction. For the past reaction data, a simulation is performed based on the other party's reaction in similar situations in the past. The companion discovery unit finds companions that suit the user from among all of humanity based on the thinking patterns learned by the learning unit. The companion discovery includes, for example, common hobbies, occupations, skills, etc., but is not limited to such examples. The companion discovery unit, for example, shares information with other users' generation AIs and finds companions with common hobbies and interests.The companion discovery unit can also suggest suitable companions based on the user's occupation and skills. Furthermore, the companion discovery unit can find companions based on the user's interests and concerns. For example, the companion discovery unit introduces people with the same hobbies and provides opportunities for interaction. Common hobbies include sports, music, reading, etc. For occupations and skills, it suggests people with the same occupations and skills. For interests and concerns, it finds suitable companions based on the user's interests. As a result, the MY generation AI system according to the embodiment can learn the user's thinking patterns, perform various tasks on behalf of the user, point out the user's strengths and weaknesses, simulate the other person's reactions, and find companions.

[0076] The reception unit receives answers to questions from users. The questions from users include, but are not limited to, for example, questions in text format, voice format, questions on specific topics, and the like. For example, when the user answers a question in text format, the reception unit stores the answer in a database. The reception unit can also convert answers to questions in voice format into text data using voice recognition technology and store the text data. Furthermore, the reception unit can present questions on specific topics to the user and collect the answers. For example, when the user answers a question such as "What is your favorite food?", the reception unit stores the answer in a database. Answers to questions in voice format are converted into text data using voice recognition technology and stored. Questions on specific topics are customized based on the user's interests and concerns. The reception unit has an efficient algorithm for quickly processing text data entered by the user and storing it in a database. The voice recognition technology uses the latest deep learning model, and can convert voice data into text with high accuracy. As a result, no matter what format the user asks a question in, the reception unit can accurately grasp the content and store it in a database. The reception unit also has a function of referring to the user's past question history and automatically suggesting related questions. This allows the user to ask questions efficiently, improving the usability of the entire system. Furthermore, the reception unit can perform initial filtering to provide appropriate answers according to the content of the user's question. For example, if there are many questions about a particular topic, information related to that topic is preferentially collected and stored in a database. This allows the reception unit to respond flexibly to the user's needs, improving the efficiency and accuracy of the entire system.

[0077] The learning unit analyzes the answer received by the reception unit and learns the user's thinking pattern. Learning of the thinking pattern includes, for example, behavior history, utterance content, and selection tendency, but is not limited to such examples. For example, the learning unit analyzes the user's behavior history and models the user's thinking pattern. The learning unit can also analyze the user's utterance content and learn the user's thinking pattern. Furthermore, the learning unit can analyze the user's selection tendency and learn the thinking pattern. For example, the learning unit analyzes the user's behavior history, such as which website the user visited and which app the user used, and models the thinking pattern. The utterance content is analyzed by using natural language processing technology to understand the meaning and intention of the user's utterance. The selection tendency is analyzed by using a machine learning algorithm to learn the user's selection pattern. The learning unit uses a complex algorithm to integrate these data and model the user's thinking pattern with high accuracy. Specifically, the deep learning technology is used to analyze the user's behavior history and utterance content with a multi-layer neural network and extract the user's thinking pattern. This allows the learning unit to deeply understand the intentions and emotions behind the user's actions and statements. The learning unit also uses a reinforcement learning algorithm to analyze the user's selection trends. This makes it possible to predict what choices the user will prefer and what choices they will make in what situations. Furthermore, the learning unit continuously updates the user's thought patterns and improves the model based on the latest information. This allows the learning unit to respond to the user's changing needs and interests and always provide optimal services.

[0078] The agent performs work on behalf of the user based on the thought patterns learned by the learning unit. Examples of tasks that are performed include, but are not limited to, replying to emails, managing schedules, and entering data. For example, the agent replies to emails when the user is busy. The agent can also manage the user's schedule and remind the user of important appointments. Furthermore, the agent can perform data entry work on behalf of the user. For example, the agent accesses the user's email account and responds appropriately to received emails. For schedule management, a calendar app is used to manage the user's schedule and set reminders. For data entry work, data specified by the user is entered and saved in a database. The agent utilizes advanced natural language processing technology and machine learning algorithms to efficiently perform these tasks. For example, for replying to emails, a generation AI is used to learn the user's past reply patterns and generate appropriate reply content. For schedule management, an algorithm is used to analyze the user's past schedule data and set optimal reminders. For data entry work, an automated tool is used to accurately enter data according to the format specified by the user and store it in the database. This allows the agent department to reduce the burden on the user and perform tasks efficiently. Furthermore, the agent department can collect user feedback and continuously improve the method of performing tasks. This allows the agent department to respond flexibly to user needs, improving the efficiency and accuracy of the entire system.

[0079] The pointing unit points out the strengths and weaknesses of the user based on the thought patterns learned by the learning unit. The pointing includes, but is not limited to, performance evaluation, behavior analysis, and the like. For example, the pointing unit analyzes the user's behavior and remarks, and feeds back the user's strengths and areas for improvement. The pointing unit can also evaluate the user's performance and point out specific areas for improvement. Furthermore, the pointing unit can analyze the user's behavioral patterns and point out strengths and weaknesses. For example, the pointing unit evaluates the user's communication skills and provides specific feedback. The behavioral analysis involves analyzing the user's behavioral patterns and identifying strengths and areas for improvement. The performance evaluation involves evaluating the user's ability to perform work and pointing out specific areas for improvement. The pointing unit utilizes machine learning algorithms and natural language processing technology to perform these evaluations. Specifically, an algorithm is used to analyze the user's behavioral data and build a performance evaluation model. This allows for a deep understanding of the intentions and emotions behind the user's behavior and remarks, and provides appropriate feedback. The pointing unit can also analyze long-term trends based on the user's past performance data and identify areas for future improvement. This allows the suggestion unit to support the user's growth and promote performance improvement. Furthermore, the suggestion unit can collect user feedback and continuously improve the evaluation model. This allows the suggestion unit to flexibly respond to the needs of the user, improving the efficiency and accuracy of the entire system.

[0080] The simulation unit simulates the other party's reaction based on the thought patterns learned by the learning unit. The simulation includes, for example, emotion analysis, past reaction data, and the like, but is not limited to such examples. For example, the simulation unit simulates the other party's reaction to a new idea before the user proposes the idea. The simulation unit can also simulate the other party's reaction to the user's remarks. Furthermore, the simulation unit can simulate the other party's reaction to the user's actions. For example, the simulation unit simulates the other party's reaction to a proposal before the user proposes a new project. The emotion analysis involves analyzing the other party's emotions and predicting the reaction. For the past reaction data, a simulation is performed based on the other party's reaction in similar situations in the past. The simulation unit uses a complex algorithm to integrate these data and predict the other party's reaction with high accuracy. Specifically, using deep learning technology, the other party's emotions and reactions are analyzed with a multi-layered neural network, and the other party's reaction is simulated. This allows the simulation unit to deeply understand the intentions and emotions behind the user's actions and remarks and provide an appropriate simulation. The simulation unit can also analyze long-term trends and predict future reactions based on the user's past behavioral data. This allows the simulation unit to respond flexibly to user needs, improving the efficiency and accuracy of the entire system. Furthermore, the simulation unit can collect user feedback and continuously improve the simulation model. This allows the simulation unit to respond flexibly to user needs, improving the efficiency and accuracy of the entire system.

[0081] The companion discovery unit finds companions suitable for the user from among all of humanity based on the thought patterns learned by the learning unit. Companion discovery includes, but is not limited to, common hobbies, occupations, skills, and the like. The companion discovery unit, for example, shares information with other users' generation AIs to find companions with common hobbies and interests. The companion discovery unit can also suggest suitable companions based on the user's occupation and skills. Furthermore, the companion discovery unit can find companions based on the user's interests and concerns. For example, the companion discovery unit introduces people with the same hobbies and provides opportunities for interaction. Common hobbies include sports, music, reading, and the like. For occupations and skills, it suggests people with the same occupations and skills. For interests and concerns, it finds suitable companions based on the user's interests. The companion discovery unit uses complex algorithms to integrate these data and suggest the most suitable companions to the user with high accuracy. Specifically, using deep learning technology, the user's hobbies, interests, occupations, and skills are analyzed with a multi-layered neural network to suggest the most suitable companions. This allows the companion discovery unit to respond flexibly to the needs of the user, improving the efficiency and accuracy of the entire system. The companion discovery unit can also analyze long-term trends based on the user's past behavioral data and predict future companions. This allows the companion discovery unit to respond flexibly to the needs of the user, improving the efficiency and accuracy of the entire system. Furthermore, the companion discovery unit can collect user feedback and continuously improve the proposed model. This allows the companion discovery unit to respond flexibly to the needs of the user, improving the efficiency and accuracy of the entire system.

[0082] The reception unit can collect the user's behavior history. The behavior history includes, for example, a website browsing history, an app usage history, and the like, but is not limited to such examples. For example, the reception unit records the URL of the website visited by the user and stores it in a database. The reception unit can also collect and analyze the usage history of the app used by the user. For example, the reception unit records the URL of the website visited by the user and stores it in a database. The app usage history records which app the user used and for how long. By collecting the user's behavior history, more accurate thinking patterns can be learned. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's behavior history data to the generation AI and cause the generation AI to execute the analysis of the behavior history.

[0083] The learning unit can analyze the behavior history collected by the reception unit and learn the user's thinking pattern. The analysis includes, for example, data mining, machine learning algorithms, and the like, but is not limited to such examples. The learning unit can analyze the user's behavior history using, for example, data mining technology, and model the thinking pattern. The learning unit can also analyze the user's behavior history using a machine learning algorithm and learn the thinking pattern. For example, the learning unit can use a data mining technology to extract a pattern from the user's behavior history and model the thinking pattern. The machine learning algorithm includes a neural network, a support vector machine, and the like. This makes it possible to more accurately learn the user's thinking pattern by analyzing the behavior history. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's behavior history data to the generation AI and cause the generation AI to model the thinking pattern.

[0084] The proxy unit can reply to an email on behalf of a user. The reply to an email includes, for example, the use of a template, natural language generation technology, and the like, but is not limited to such examples. For example, the proxy unit replies to an email received by a user using an appropriate template. The proxy unit can also generate a reply based on the user's intention using natural language generation technology. For example, the proxy unit swiftly replies to an email received by a user using a template prepared in advance. The natural language generation technology uses a text generation AI (for example, LLM) to generate a reply based on the user's intention. This makes it possible to reduce the burden on the user by replying to an email on behalf of the user. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit can input the received email data to a generation AI and have the generation AI execute the generation of the reply content.

[0085] The pointing unit can analyze the user's behavior and remarks and specifically point out the user's strengths and weaknesses. The analysis of behavior and remarks includes, but is not limited to, for example, behavior pattern analysis and emotion analysis of the remarks. For example, the pointing unit can analyze the user's behavior pattern and identify the user's strengths and areas for improvement. The pointing unit can also analyze the user's remarks using emotion analysis technology and provide specific feedback. For example, the pointing unit can analyze the user's behavior pattern and evaluate the user's communication ability and time management ability. For the emotion analysis of the remarks, natural language processing technology is used to analyze the emotion of the user's remarks. As a result, specific feedback can be provided by analyzing the user's behavior and remarks. A part or all of the above-mentioned processing in the pointing unit may be performed using, for example, AI, or may be performed without using AI. For example, the pointing unit can input the user's behavior data to the generation AI and cause the generation AI to identify the strengths and weaknesses.

[0086] The simulation unit can simulate the other party's reaction to the user's new idea. The simulation of the new idea includes, but is not limited to, for example, a creative proposal, a technical idea, and the like. For example, before the user proposes a new project, the simulation unit simulates the other party's reaction to the proposal. The simulation unit can also simulate the other party's reaction to the user's remarks. Furthermore, the simulation unit can simulate the other party's reaction to the user's actions. For example, the simulation unit simulates the other party's reaction to the proposal before the user proposes a new project. The emotion analysis involves analyzing the other party's emotions and predicting the reaction. For past reaction data, a simulation is performed based on the other party's reaction in similar situations in the past. This allows the other party's reaction to a new idea to be simulated in advance, allowing an appropriate response to be prepared. A part or all of the above-mentioned processing in the simulation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simulation unit can input the user's idea data into the generation AI and cause the generation AI to execute a simulation of the other party's reaction.

[0087] The companion discovery unit can share information with the generation AI of other users and specifically find companions who have common hobbies and interests. Common hobbies and interests include, but are not limited to, hobby categories, topics of interest, and the like. The companion discovery unit can share information with the generation AI of other users and find companions who have common hobbies and interests, for example. The companion discovery unit can also suggest appropriate companions based on the user's occupation and skills. Furthermore, the companion discovery unit can find companions based on the user's interests and concerns. For example, the companion discovery unit introduces people who have the same hobbies and provides opportunities for interaction. Common hobbies include sports, music, reading, and the like. For occupations and skills, people with the same occupations and skills are suggested. For interests and concerns, appropriate companions are found based on the user's interests. This allows the user to find companions who have common hobbies and interests, thereby providing opportunities for interaction. Some or all of the above-mentioned processing in the companion discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the companion discovery unit can input the user's hobby data into the generation AI and cause the generation AI to discover companions who share a common hobby.

[0088] The reception unit can estimate the user's emotion and adjust the content and timing of the question based on the estimated user's emotion. The estimation of emotion includes, for example, facial expression recognition, voice tone analysis, etc., but is not limited to such examples. For example, when the user is stressed, the reception unit prioritizes simple questions that can relax the user. In addition, when the user is relaxed, the reception unit can also ask questions that encourage deep thinking. Furthermore, when the user is in a hurry, the reception unit can also ask questions that can be answered in a short time. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The voice tone analysis involves analyzing the tone and speed of the user's voice to estimate the emotion. As a result, the content and timing of the question can be adjusted according to the user's emotion, so that more appropriate questions can be provided. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotional data into the generation AI and have the generation AI adjust the content and timing of the questions.

[0089] The reception unit can analyze the user's past question history and select the optimal question format. The question formats include, for example, multiple choice and free description, but are not limited to such examples. The reception unit, for example, prioritizes the question format that the user has answered in the past. The reception unit can also avoid the question format that the user has avoided in the past. Furthermore, the reception unit can analyze the user's past answer patterns and propose the optimal question format. For example, the reception unit prioritizes the question format that the user has answered in the past. The multiple choice question format includes a format in which a user selects from multiple options. The free description question format includes a format in which a user freely writes an answer. In this way, the optimal question format can be provided to the user by analyzing the past question history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's question history data to the generation AI and cause the generation AI to select the optimal question format.

[0090] The reception unit can filter questions based on the user's current situation and field of interest when receiving a question. Examples of filtering include, but are not limited to, keyword matching and relevance score. For example, the reception unit preferentially issues questions related to topics in which the user is currently interested. The reception unit can also adjust questions according to the user's current situation (e.g., at work, on a break). Furthermore, the reception unit can customize questions based on the user's field of interest. For example, the reception unit preferentially issues questions related to topics in which the user is currently interested. For keyword matching, questions are filtered using keywords related to the user's interests. For relevance score, the relevance of questions is evaluated and scored based on the user's field of interest. As a result, questions can be filtered based on the user's current situation and field of interest, thereby providing more relevant questions. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's interest data to the generation AI and cause the generation AI to filter questions.

[0091] The reception unit can estimate the user's emotion and determine the priority of questions based on the estimated user's emotion. The determination of the priority includes, for example, urgency, importance, etc., but is not limited to such examples. For example, when the user is stressed, the reception unit prioritizes questions that can relax the user. Also, when the user is relaxed, the reception unit can prioritize questions that encourage deep thinking. Furthermore, when the user is in a hurry, the reception unit can prioritize questions that can be answered in a short time. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For voice tone analysis, the tone and speed of the user's voice are analyzed to estimate the emotion. As a result, the priority of questions can be determined based on the user's emotion, and more appropriate questions can be provided. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotional data into the generation AI and have the generation AI determine the priority of questions.

[0092] When receiving a question, the reception unit can preferentially receive a highly relevant question in consideration of the geographical location information of the user. The geographical location information includes, for example, GPS data, location information services, etc., but is not limited to such examples. For example, when the user is in a specific location, the reception unit prioritizes questions related to the location. In addition, the reception unit can also issue questions specific to the area based on the user's current location. Furthermore, the reception unit can also suggest optimal questions based on the user's geographical location information. For example, when the user is in a specific location, the reception unit prioritizes questions related to the location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. In this way, by considering the user's geographical location information, a highly relevant question can be provided. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's location information data to the generation AI and cause the generation AI to select a question.

[0093] The reception unit can analyze the user's social media activity when receiving a question and receive a related question. The social media activity includes, for example, the content of the post, the number of likes, and the like, but is not limited to such examples. The reception unit, for example, issues a question related to a topic in which the user has recently shown interest on social media. The reception unit can also suggest an optimal question based on the user's social media activity. Furthermore, the reception unit can analyze the user's social media remarks and issue a related question. For example, the reception unit issues a question related to a topic in which the user has recently shown interest on social media. The post content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. In this way, by analyzing the social media activity, a related question can be provided. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's social media data to the generation AI and cause the generation AI to select a question.

[0094] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. The selection of learning data includes, for example, the type of data and the quality of data, but is not limited to such examples. For example, when the user is relaxed, the learning unit preferentially learns behavioral data in a relaxed state. In addition, when the user is stressed, the learning unit can also preferentially learn behavioral data under stress. Furthermore, when the user is excited, the learning unit can also preferentially learn behavioral data in an excited state. For example, the learning unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For voice tone analysis, the tone and speed of the user's voice are analyzed to estimate the emotion. As a result, more appropriate learning can be performed by selecting learning data based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input a user's emotional data into the generation AI and have the generation AI select the learning data.

[0095] The learning unit can optimize the learning algorithm by referring to past learning data during learning. Examples of optimization of the learning algorithm include, but are not limited to, neural networks and support vector machines. The learning unit can set optimal learning parameters, for example, based on past learning data. The learning unit can also analyze past learning data and identify improvements to the learning algorithm. Furthermore, the learning unit can improve the accuracy of the learning algorithm by referring to past learning data. For example, the learning unit sets optimal learning parameters based on past learning data. The neural network includes a multilayer perceptron and a convolutional neural network. The support vector machine includes a linear SVM and a nonlinear SVM. As a result, the accuracy of the learning algorithm is improved by referring to the past learning data. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input past learning data to the generation AI and cause the generation AI to execute optimization of the learning algorithm.

[0096] During learning, the learning unit can analyze the user's behavior history in detail to improve the accuracy of the thought pattern. The detailed analysis includes, for example, the granularity of the data and the depth of the analysis, but is not limited to such examples. For example, the learning unit analyzes the user's behavior history in detail to extract the characteristics of the thought pattern. The learning unit can also refine the model of the thought pattern based on the user's behavior history. Furthermore, the learning unit can analyze the user's behavior history in detail to improve the accuracy of the thought pattern. For example, the learning unit analyzes the user's behavior history in detail to extract the characteristics of the thought pattern. The granularity of the data includes the fineness of the behavior data. The depth of the analysis includes a detailed analysis of the behavior data. As a result, the accuracy of the thought pattern is improved by analyzing the behavior history in detail. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's behavior history data to the generation AI and cause the generation AI to execute the improvement of the accuracy of the thought pattern.

[0097] The learning unit can estimate the user's emotion and adjust the frequency of learning based on the estimated user's emotion. The adjustment of the frequency of learning includes, for example, periodic learning, event-driven learning, and the like, but is not limited to such examples. For example, the learning unit increases the frequency of learning when the user is relaxed. Also, the learning unit can reduce the frequency of learning when the user is stressed. Furthermore, the learning unit can adjust the frequency of learning when the user is excited. For example, the learning unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For voice tone analysis, the tone and speed of the user's voice are analyzed and the emotion is estimated. As a result, more appropriate learning can be performed by adjusting the frequency of learning based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input a user's emotional data into the generation AI and cause the generation AI to adjust the frequency of learning.

[0098] During learning, the learning unit can weight the learning data based on the time of the question submitted by the user. The weighting includes, for example, weighting of time series data, weighting based on importance, and the like, but is not limited to such examples. For example, the learning unit learns by placing emphasis on data of a question recently submitted by the user. The learning unit can also learn by placing emphasis on data of a question submitted by the user at a specific time. Furthermore, the learning unit can weight the learning data based on the time of the question submitted by the user. For example, the learning unit learns by placing emphasis on data of a question recently submitted by the user. Weighting of time series data includes a method of weighting based on the chronological order of data. Weighting based on importance includes a method of weighting according to the importance of data. As a result, weighting of the learning data based on the time of the question improves the accuracy of learning. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's question data to the generation AI and cause the generation AI to perform weighting.

[0099] The learning unit can improve the accuracy of learning by referring to the user's related literature during learning. The related literature includes, for example, academic papers, technical reports, etc., but is not limited to such examples. The learning unit complements the learning data, for example, based on the related literature referred to by the user. The learning unit can also improve the accuracy of the learning algorithm by referring to the user's related literature. Furthermore, the learning unit can improve the quality of the learning data based on the user's related literature. For example, the learning unit complements the learning data based on the related literature referred to by the user. The academic papers include academic research results referred to by the user. The technical reports include technical reports referred to by the user. As a result, the accuracy of learning is improved by referring to the related literature. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's related literature data to the generation AI and cause the generation AI to execute the improvement of the learning accuracy.

[0100] The proxy unit can estimate the user's emotion and determine the priority of the task to be performed on behalf of the user based on the estimated emotion of the user. The determination of the priority of the task includes, for example, urgency, importance, etc., but is not limited to such examples. For example, when the user is feeling stressed, the proxy unit prioritizes a task that reduces stress. In addition, when the user is relaxed, the proxy unit can also prioritize an important task. Furthermore, when the user is in a hurry, the proxy unit can also prioritize a task that can be completed quickly. For example, the proxy unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For voice tone analysis, the tone and speed of the user's voice are analyzed to estimate the emotion. As a result, by determining the priority of the task based on the user's emotion, it is possible to perform a more appropriate task on behalf of the user. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit may input the user's emotion data to the generation AI and have the generation AI determine the priority order of tasks.

[0101] The proxy unit can select an optimal proxy method by referring to the user's past task history during proxy operation. The task history includes, for example, past task records, task completion statuses, and the like, but is not limited to such examples. The proxy unit, for example, prioritizes a task method that the user has previously preferred. The proxy unit can also select an optimal proxy method based on the user's past task history. Furthermore, the proxy unit can also suggest an efficient proxy method by referring to the user's past task history. For example, the proxy unit prioritizes a task method that the user has previously preferred. The past task records include details of tasks that the user has previously performed. The task completion status includes the status of tasks that the user has previously completed. This allows the optimal proxy method to be selected by referring to the past task history. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit can input the user's task history data to the generation AI and cause the generation AI to select a proxy method.

[0102] The proxy unit can customize the contents of the task based on the current situation of the user when acting on behalf of the user. Customization includes, for example, adjustment based on the current situation of the user, settings according to individual needs, and the like, but is not limited to such examples. For example, when the user is busy, the proxy unit acts on behalf of the user with a simplified task. In addition, when the user is relaxed, the proxy unit can also act on behalf of the user with a detailed task. Furthermore, the proxy unit can customize the contents of the task based on the current situation of the user. For example, when the user is busy, the proxy unit acts on behalf of the user with a simplified task. The user's current situation includes the environment and state in which the user is currently placed. The individual needs include the user's specific requests and wishes. This allows for more appropriate acting on behalf of the user by customizing the contents of the task based on the current situation. Part or all of the above-mentioned processing in the proxy unit may be performed, for example, using AI, or may be performed without using AI. For example, the proxy unit can input the user's situation data to the generation AI and cause the generation AI to execute task customization.

[0103] The proxy unit can estimate the user's emotion and adjust the display method of the task to be performed on behalf of the user based on the estimated emotion of the user. The adjustment of the display method includes, for example, UI design, priority of information, and the like, but is not limited to such examples. For example, when the user is stressed, the proxy unit provides a display method that is simple and highly visible. In addition, when the user is relaxed, the proxy unit can also provide a display method that includes detailed information. Furthermore, when the user is in a hurry, the proxy unit can also provide a display method that focuses on the main points. For example, the proxy unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For voice tone analysis, the tone and speed of the user's voice are analyzed to estimate the emotion. As a result, the display method can be adjusted based on the user's emotion, thereby enabling more appropriate task display. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, AI, or may be performed without using AI. For example, the proxy unit may input the user's emotion data to the generation AI and cause the generation AI to adjust the display method.

[0104] The proxy unit can select the optimal proxy method in consideration of the geographical location information of the user at the time of proxy. The geographical location information includes, for example, GPS data, location information services, etc., but is not limited to such examples. For example, when the user is in a specific location, the proxy unit prioritizes a task related to the location. In addition, the proxy unit can also proxy a task specific to a region based on the user's current location. Furthermore, the proxy unit can select the optimal proxy method based on the user's geographical location information. For example, when the user is in a specific location, the proxy unit prioritizes a task related to the location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. As a result, the optimal proxy method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit can input the user's location information data to the generation AI and cause the generation AI to select the proxy method.

[0105] During the proxy operation, the proxy unit can analyze the user's social media activity and suggest a proxy task. The social media activity includes, for example, the content of the post, the number of likes, and the like, but is not limited to such examples. The proxy unit, for example, performs a task related to a topic in which the user has recently shown interest on social media. The proxy unit can also suggest an optimal proxy task based on the user's social media activity. Furthermore, the proxy unit can analyze the user's comments on social media and perform a related task on behalf of the user. For example, the proxy unit performs a task related to a topic in which the user has recently shown interest on social media. The post content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. This makes it possible to suggest a related task by analyzing the social media activity. A part or all of the above-mentioned processing in the proxy unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the proxy unit can input the user's social media data to the generation AI and cause the generation AI to execute the proposal of a proxy task.

[0106] The indication unit can estimate the user's emotion and adjust the expression method of the indication based on the estimated user's emotion. The adjustment of the expression method includes, for example, but is not limited to, the wording, tone, and form of feedback. For example, when the user is stressed, the indication unit makes an indication in a gentle expression. Furthermore, when the user is relaxed, the indication unit can also make specific and detailed indication. Furthermore, when the user is in a hurry, the indication unit can make a concise and to the point indication. For example, the indication unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In the voice tone analysis, the tone and speed of the user's voice are analyzed and the emotion is estimated. As a result, by adjusting the expression method based on the user's emotion, more appropriate indication can be made. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the indication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the expression method.

[0107] The indication unit can provide specific feedback by referring to the user's past behavior history when making an indication. The behavior history includes, for example, a record of past behavior, a frequency of behavior, and the like, but is not limited to such examples. The indication unit, for example, indicates specific improvements based on the user's past behavior history. The indication unit can also provide specific feedback by referring to the user's past behavior history. Furthermore, the indication unit can also indicate specific strengths based on the user's past behavior history. For example, the indication unit indicates specific improvements based on the user's past behavior history. The record of past behavior includes details of behaviors performed by the user in the past. The frequency of behavior includes the frequency of behaviors performed by the user in the past. Thereby, specific feedback can be provided by referring to the past behavior history. A part or all of the above-mentioned processing in the indication unit may be performed, for example, using AI, or may be performed without using AI. For example, the indication unit can input the user's behavior history data to the generation AI and cause the generation AI to provide feedback.

[0108] The indication unit can customize the indication contents based on the current situation of the user when making an indication. Customization includes, for example, adjustment based on the current situation of the user, settings according to individual needs, and the like, but is not limited to such examples. For example, when the user is busy, the indication unit makes a concise and to the point indication. In addition, when the user is relaxed, the indication unit can also make detailed indication. Furthermore, the indication unit can customize the indication contents based on the current situation of the user. For example, when the user is busy, the indication unit makes a concise and to the point indication. The current situation of the user includes the environment and state in which the user is currently placed. The individual needs include the specific requests and wishes of the user. As a result, by customizing the indication contents based on the current situation, more appropriate indication can be made. A part or all of the above-mentioned processing in the indication unit may be performed, for example, using AI, or may be performed without using AI. For example, the indication unit can input the user's situation data to the generation AI and cause the generation AI to execute customization of the indication contents.

[0109] The indication unit can estimate the user's emotion and determine the priority of indications based on the estimated user's emotion. The determination of the priority includes, for example, urgency, importance, etc., but is not limited to such examples. For example, when the user is stressed, the indication unit prioritizes indications that reduce stress. Also, when the user is relaxed, the indication unit can prioritize important indications. Furthermore, when the user is in a hurry, the indication unit can prioritize indications that can be quickly responded to. For example, the indication unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In the voice tone analysis, the tone and speed of the user's voice are analyzed and the emotion is estimated. As a result, more appropriate indications can be made by determining the priority of indications based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the indication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the user's emotional data to the generation AI and have the generation AI determine the priority of the suggestions.

[0110] The indication unit can select the optimal indication method in consideration of the geographical location information of the user at the time of indication. The geographical location information includes, for example, GPS data, location information services, etc., but is not limited to such examples. For example, when the user is in a specific location, the indication unit prioritizes indication related to the location. In addition, the indication unit can also perform area-specific indication based on the user's current location. Furthermore, the indication unit can select the optimal indication method based on the user's geographical location information. For example, when the user is in a specific location, the indication unit prioritizes indication related to the location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. As a result, the optimal indication method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the indication unit may be performed using, for example, AI, or may be performed without using AI. For example, the indication unit can input the user's location information data to the generation AI and cause the generation AI to select the indication method.

[0111] The pointing unit can analyze the user's social media activity at the time of pointing out and propose the content of the pointing out. The social media activity includes, for example, the content of the post, the number of likes, and the like, but is not limited to such examples. For example, the pointing unit makes a point related to a topic in which the user has recently shown interest on social media. The pointing unit can also propose optimal content of the pointing out based on the user's social media activity. Furthermore, the pointing unit can analyze the user's comments on social media and make related points. For example, the pointing unit makes a point related to a topic in which the user has recently shown interest on social media. The post content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. In this way, by analyzing the social media activity, related content of the pointing out can be proposed. A part or all of the above-mentioned processing in the pointing unit may be performed, for example, using AI, or may be performed without using AI. For example, the pointing unit can input the user's social media data to the generation AI and cause the generation AI to execute the suggestion of the content of the pointing out.

[0112] The simulation unit can estimate the user's emotion and adjust the result of the simulation based on the estimated user's emotion. The adjustment of the simulation result includes, for example, the display format of the result, the evaluation criteria of the result, and the like, but is not limited to such examples. For example, when the user is relaxed, the simulation unit provides a detailed simulation result. In addition, when the user is stressed, the simulation unit can also provide a concise simulation result. Furthermore, when the user is excited, the simulation unit can also provide a visually stimulating simulation result. For example, the simulation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For voice tone analysis, the tone and speed of the user's voice are analyzed and the emotion is estimated. As a result, a more appropriate simulation can be performed by adjusting the simulation result based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the simulation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simulation unit can input user emotion data to the generation AI and have the generation AI adjust the simulation results.

[0113] The simulation unit can improve the accuracy of the simulation by referring to the user's past idea history during the simulation. The idea history includes, for example, past idea records, idea evaluations, and the like, but is not limited to such examples. The simulation unit improves the accuracy of the simulation, for example, based on the user's past idea history. The simulation unit can also adjust the results of the simulation by referring to the user's past idea history. Furthermore, the simulation unit can analyze the user's past idea history and improve the accuracy of the simulation. For example, the simulation unit improves the accuracy of the simulation based on the user's past idea history. The past idea records include details of ideas proposed by the user in the past. The idea evaluations include evaluation results of ideas proposed by the user in the past. As a result, the accuracy of the simulation is improved by referring to the past idea history. A part or all of the above-mentioned processing in the simulation unit may be performed, for example, using AI, or may be performed without using AI. For example, the simulation unit can input the user's idea history data to the generation AI and cause the generation AI to execute improvement of the accuracy of the simulation.

[0114] The simulation unit can customize the simulation content based on the current situation of the user during the simulation. Customization includes, for example, adjustment based on the current situation of the user, settings according to individual needs, and the like, but is not limited to such examples. For example, when the user is busy, the simulation unit provides simplified simulation content. In addition, when the user is relaxed, the simulation unit can also provide detailed simulation content. Furthermore, the simulation unit can customize the simulation content based on the current situation of the user. For example, when the user is busy, the simulation unit provides simplified simulation content. The user's current situation includes the environment and state in which the user is currently placed. The individual needs include the user's specific requests and wishes. This allows a more appropriate simulation to be performed by customizing the simulation content based on the current situation. Part or all of the above-mentioned processing in the simulation unit may be performed, for example, using AI, or may be performed without using AI. For example, the simulation unit can input the user's situation data to the generation AI and cause the generation AI to customize the simulation content.

[0115] The simulation unit can estimate the user's emotion and adjust the display method of the simulation based on the estimated user's emotion. The adjustment of the display method includes, for example, UI design, priority of information, etc., but is not limited to such examples. For example, when the user is stressed, the simulation unit provides a simple and highly visible display method. In addition, when the user is relaxed, the simulation unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the simulation unit can also provide a display method that focuses on the main points. For example, the simulation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For voice tone analysis, the tone and speed of the user's voice are analyzed and the emotion is estimated. As a result, a more appropriate simulation display can be performed by adjusting the display method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the simulation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simulation unit can input a user's emotional data into the generation AI and have the generation AI adjust the display method.

[0116] The simulation unit can select an optimal simulation method in consideration of the geographical location information of the user during the simulation. The geographical location information includes, for example, GPS data, location information services, etc., but is not limited to such examples. For example, when the user is in a specific location, the simulation unit prioritizes a simulation related to that location. In addition, the simulation unit can also perform a region-specific simulation based on the user's current location. Furthermore, the simulation unit can select an optimal simulation method based on the user's geographical location information. For example, when the user is in a specific location, the simulation unit prioritizes a simulation related to that location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. This allows the optimal simulation method to be selected by considering the geographical location information. A part or all of the above-mentioned processing in the simulation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simulation unit can input the user's location information data to the generation AI and cause the generation AI to select a simulation method.

[0117] The simulation unit can analyze the user's social media activity during the simulation to suggest simulation content. The social media activity includes, for example, the posting content, the number of likes, and the like, but is not limited to such examples. For example, the simulation unit performs a simulation related to a topic in which the user has recently shown interest on social media. The simulation unit can also suggest optimal simulation content based on the user's social media activity. Furthermore, the simulation unit can analyze the user's social media comments and perform a related simulation. For example, the simulation unit performs a simulation related to a topic in which the user has recently shown interest on social media. The posting content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. This makes it possible to suggest related simulation content by analyzing the social media activity. A part or all of the above-mentioned processing in the simulation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simulation unit can input the user's social media data to the generation AI and cause the generation AI to execute a proposal of simulation content.

[0118] The companion discovery unit can estimate the user's emotions and adjust the companion discovery method based on the estimated user's emotions. The companion discovery method includes, for example, common hobbies, occupations, skills, etc., but is not limited to such examples. For example, when the user is relaxed, the companion discovery unit proposes companions with detailed profiles. In addition, when the user is stressed, the companion discovery unit can also propose companions with simple profiles. In addition, when the user is excited, the companion discovery unit can also propose companions with common hobbies. For example, the companion discovery unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In the voice tone analysis, the tone and speed of the user's voice are analyzed to estimate the emotion. In this way, by adjusting the companion discovery method based on the user's emotions, it is possible to propose more appropriate companions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the companion discovery unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the companion discovery unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the companion discovery method.

[0119] When discovering a friend, the friend discovery unit can suggest an optimal friend by referring to the user's past interaction history. The interaction history includes, for example, records of past interactions, frequency of interactions, etc., but is not limited to such examples. The friend discovery unit, for example, suggests an optimal friend based on the user's past interaction history. The friend discovery unit can also suggest a friend who has a common hobby by referring to the user's past interaction history. Furthermore, the friend discovery unit can analyze the user's past interaction history and suggest an optimal friend. For example, the friend discovery unit suggests an optimal friend based on the user's past interaction history. The record of past interactions includes details of interactions that the user has performed in the past. The frequency of interactions includes the frequency of interactions that the user has performed in the past. As a result, the optimal friend can be suggested by referring to the past interaction history. A part or all of the above-mentioned processing in the friend discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the friend discovery unit can input the user's interaction history data to the generation AI and cause the generation AI to execute the suggestion of a friend.

[0120] The companion discovery unit can customize the companion discovery means based on the user's current situation when discovering a companion. Customization includes, for example, adjustment based on the user's current situation, settings according to individual needs, and the like, but is not limited to such examples. For example, the companion discovery unit provides a simplified companion discovery means when the user is busy. In addition, the companion discovery unit can also provide a detailed companion discovery means when the user is relaxed. Furthermore, the companion discovery unit can customize the companion discovery means based on the user's current situation. For example, the companion discovery unit provides a simplified companion discovery means when the user is busy. The user's current situation includes the environment and state in which the user is currently placed. The individual needs include the user's specific requests and wishes. This allows a more appropriate companion to be proposed by customizing the companion discovery means based on the current situation. Part or all of the above-mentioned processing in the companion discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the companion discovery unit can input the user's situation data into the generation AI and cause the generation AI to execute customization of the companion discovery means.

[0121] The companion discovery unit can estimate the user's emotions and determine the priority of companion discovery based on the estimated user's emotions. The priority determination includes, for example, urgency, importance, and the like, but is not limited to such examples. For example, when the user is feeling stressed, the companion discovery unit prioritizes companions who can reduce stress. In addition, when the user is relaxed, the companion discovery unit can also prioritize companions who have a common hobby. Furthermore, when the user is in a hurry, the companion discovery unit can also prioritize companions who can quickly interact. For example, the companion discovery unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For voice tone analysis, the tone and speed of the user's voice are analyzed to estimate the emotion. As a result, by determining the priority of companion discovery based on the user's emotions, more appropriate companions can be proposed. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the companion discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the companion discovery unit may input the user's emotion data to the generation AI and cause the generation AI to determine the priority order for companion discovery.

[0122] When discovering a friend, the friend discovery unit can propose the most suitable friend by considering the geographical location information of the user. The geographical location information includes, but is not limited to, for example, GPS data, location information services, and the like. For example, when the user is in a specific location, the friend discovery unit prioritizes a friend related to that location. In addition, the friend discovery unit can also propose a friend specific to the area based on the user's current location. Furthermore, the friend discovery unit can also propose the most suitable friend based on the user's geographical location information. For example, when the user is in a specific location, the friend discovery unit prioritizes a friend related to that location. The GPS data includes location information for identifying the user's current location. The location information service includes a service that provides the user's location information. In this way, the most suitable friend can be proposed by considering the geographical location information. A part or all of the above-mentioned processing in the friend discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the friend discovery unit can input the user's location information data to the generation AI and cause the generation AI to execute the friend proposal.

[0123] When discovering a friend, the companion discovery unit can analyze the user's social media activity and suggest a means of discovering a friend. The social media activity includes, for example, the content of the post, the number of likes, and the like, but is not limited to such examples. The companion discovery unit, for example, suggests companions related to topics in which the user has recently shown interest on social media. The companion discovery unit can also suggest the optimal means of discovering a companion based on the user's social media activity. Furthermore, the companion discovery unit can analyze the user's comments on social media and suggest related companions. For example, the companion discovery unit suggests companions related to topics in which the user has recently shown interest on social media. The post content includes the content posted by the user on social media. The number of likes includes the number of likes given by the user to other posts. In this way, by analyzing the social media activity, a related means of discovering a companion can be suggested. A part or all of the above-mentioned processing in the companion discovery unit may be performed, for example, using AI, or may be performed without using AI. For example, the companion discovery unit can input the user's social media data to the generation AI and cause the generation AI to execute the suggestion of a means of discovering a companion.

[0124] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0125] The MY generation AI system can also be equipped with a health management unit that monitors the user's health condition and provides health advice. The health management unit collects and analyzes data such as the user's heart rate, blood pressure, and sleep patterns. For example, if the user feels stressed, it can provide advice on how to relax. It can also analyze the user's sleep patterns and make suggestions on how to get better sleep. Furthermore, the health management unit can provide advice on maintaining a healthy lifestyle based on the user's diet and exercise history. This allows the user to always be aware of their health condition and take appropriate measures.

[0126] The reception unit can collect and analyze the user's past purchase history. The purchase history includes, for example, online shopping history, in-store purchase history, and the like. The reception unit records what products the user has purchased and stores the records in a database. The reception unit can also analyze the user's purchase history and grasp the user's purchasing trends. For example, the reception unit can identify products and brands that the user frequently purchases and suggest products that suit the user. This can improve the user's purchasing experience.

[0127] The learning unit can customize the learning content based on the user's hobbies and interests. For example, if the user is interested in music, information related to music is given priority for learning. Also, if the user is interested in sports, information related to sports can be learned. Furthermore, the learning unit can dynamically adjust the learning content according to changes in the user's interests. For example, if the user starts a new hobby, information related to that hobby is learned. This allows learning to be done according to the user's interests.

[0128] The proxy unit can post on social media on behalf of the user. For example, when the user is busy, the proxy unit posts on behalf of the user. The proxy unit can also analyze the content of the user's past posts and generate posts that match the user's style. Furthermore, the proxy unit can analyze the reactions of the user's followers and suggest the optimal timing for posting. This allows the user to carry out social media activities efficiently.

[0129] The indication unit can estimate the user's emotion and adjust the timing of the feedback based on the estimated user's emotion. For example, if the user is stressed, the feedback can be delayed. Also, if the user is relaxed, the feedback can be provided immediately. Furthermore, if the user is in a hurry, the indication unit can provide brief feedback. This makes it possible to provide feedback at an appropriate timing according to the user's emotion.

[0130] The simulation unit can improve the accuracy of the simulation by referring to the user's past failure experiences. For example, the simulation unit can analyze data of projects that the user has failed in the past and perform a simulation to avoid similar failures. The simulation unit can also perform a simulation to increase the possibility of success by referring to the user's past successful experiences. Furthermore, the simulation unit can perform a simulation to minimize risk based on the user's past experiences. This allows the user to utilize past experiences to obtain better results.

[0131] The companion discovering unit can estimate the user's emotions and adjust the method of interaction based on the estimated user's emotions. For example, when the user is relaxed, companions with detailed profiles can be suggested. Also, when the user is stressed, companions with simple profiles can be suggested. Furthermore, when the user is excited, the companion discovering unit can suggest companions with common hobbies. This makes it possible to provide an appropriate interaction method according to the user's emotions.

[0132] The reception unit can analyze the user's past question history and select the most suitable question format. For example, the reception unit can give priority to question formats that the user has preferred to answer in the past. The reception unit can also avoid question formats that the user has avoided in the past. Furthermore, the reception unit can analyze the user's past answer patterns and suggest the most suitable question format. In this way, the most suitable question format can be provided to the user by analyzing the past question history.

[0133] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user's emotions. For example, if the user is relaxed, the frequency of learning can be increased. Also, if the user is stressed, the frequency of learning can be decreased. Furthermore, the learning unit can adjust the frequency of learning when the user is excited. In this way, more appropriate learning can be performed by adjusting the frequency of learning based on the user's emotions.

[0134] The proxy unit can estimate the user's emotions and determine the priority of tasks to be performed on behalf of the user based on the estimated user's emotions. For example, if the user is feeling stressed, a task that reduces stress can be given priority. Also, if the user is relaxed, an important task can be given priority. Furthermore, if the user is in a hurry, the proxy unit can give priority to a task that can be completed quickly. In this way, by determining the priority of tasks based on the user's emotions, more appropriate tasks can be performed on behalf of the user.

[0135] The process flow of the second embodiment will be briefly described below.

[0136] Step 1: The reception unit receives answers to the user's questions. The user's questions may be in text format, voice format, or questions about a specific topic. The reception unit stores the answers in text format in a database, and converts the voice format answers into text data using voice recognition technology and stores them. Furthermore, the reception unit presents questions about a specific topic to the user and collects the answers. Step 2: The learning unit analyzes the answers received by the reception unit and learns the user's thought patterns. Learning of thought patterns includes behavioral history, utterance content, and selection tendencies. The learning unit analyzes the user's behavioral history and models the thought patterns. Natural language processing technology is used to analyze utterance content, and machine learning algorithms are used to analyze selection tendencies. Step 3: The agent performs tasks on behalf of the user based on the thought patterns learned by the learning unit. Tasks performed include replying to emails, managing schedules, and entering data. When the user is busy, the agent replies to emails, manages schedules, and reminds the user of important events. It also performs data entry tasks. Step 4: The suggestion unit suggests the user's strengths and weaknesses based on the thinking patterns learned by the learning unit. The suggestions include performance evaluation and behavior analysis. The suggestion unit analyzes the user's behavior and comments, and provides feedback on strengths and areas for improvement. Performance evaluation involves evaluating the user's ability to carry out work and suggesting specific areas for improvement. Step 5: The simulation unit simulates the other person's reaction based on the thought patterns learned by the learning unit. The simulation includes emotion analysis, past reaction data, etc. The simulation unit simulates the other person's reaction to a new idea before the user proposes the idea. The emotion analysis involves analyzing the other person's emotions and predicting the reaction. Step 6: The peer discovery unit finds peers that suit the user based on the thinking patterns learned by the learning unit. Peer discovery includes common hobbies, occupations, skills, etc. The peer discovery unit shares information with other users' generation AIs to find peers with common hobbies and interests. In addition, it suggests appropriate peers based on the user's occupation and skills.

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0139] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements including the above-mentioned reception unit, learning unit, proxy unit, indication unit, simulation unit, and companion discovery unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives answers to questions from the user. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the user's thinking pattern. The proxy unit is realized by the specific processing unit 290 of the data processing device 12 and performs work on behalf of the user. The indication unit is realized by the specific processing unit 290 of the data processing device 12 and indicates the strengths and weaknesses of the user. The simulation unit is realized by the specific processing unit 290 of the data processing device 12 and simulates the reaction of the other party. The companion discovery unit is realized by the specific processing unit 290 of the data processing device 12 and finds a companion that suits the user from among all of humanity. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0141] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0142] 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.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The 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.

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

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

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

[0148] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0151] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0153] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements including the above-mentioned reception unit, learning unit, proxy unit, indication unit, simulation unit, and companion discovery unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives answers to questions from the user. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the user's thinking patterns. The proxy unit is realized by the specific processing unit 290 of the data processing device 12 and performs work on behalf of the user. The indication unit is realized by the specific processing unit 290 of the data processing device 12 and indicates the strengths and weaknesses of the user. The simulation unit is realized by the specific processing unit 290 of the data processing device 12 and simulates the reaction of the other party. The companion discovery unit is realized by the specific processing unit 290 of the data processing device 12 and finds a companion that suits the user from among all of humanity. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0157] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0158] 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.

[0159] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] The 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.

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

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

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

[0164] 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.

[0165] 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.

[0166] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0167] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0172] Each of the multiple elements including the above-mentioned reception unit, learning unit, proxy unit, indication unit, simulation unit, and companion discovery unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives answers to questions from the user. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the user's thinking patterns. The proxy unit is realized by the specific processing unit 290 of the data processing device 12 and performs work on behalf of the user. The indication unit is realized by the specific processing unit 290 of the data processing device 12 and indicates the strengths and weaknesses of the user. The simulation unit is realized by the specific processing unit 290 of the data processing device 12 and simulates the reaction of the other party. The companion discovery unit is realized by the specific processing unit 290 of the data processing device 12 and finds a companion that suits the user from among all of humanity. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0173] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0176] 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.

[0177] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0179] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0180] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0181] 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.

[0182] 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.

[0183] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0184] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0185] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0186] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0187] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0189] Each of the multiple elements including the above-mentioned reception unit, learning unit, proxy unit, indication unit, simulation unit, and companion discovery unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives answers to questions from the user. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the user's thinking patterns. The proxy unit is realized by the specific processing unit 290 of the data processing device 12 and performs work on behalf of the user. The indication unit is realized by the specific processing unit 290 of the data processing device 12 and indicates the strengths and weaknesses of the user. The simulation unit is realized by the specific processing unit 290 of the data processing device 12 and simulates the reaction of the other party. The companion discovery unit is realized by the specific processing unit 290 of the data processing device 12 and finds a companion that suits the user from among all of humanity. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0190] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0191] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0192] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0193] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0194] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0195] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0196] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0197] 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.

[0198] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0199] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0200] 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.

[0201] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0202] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0203] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0204] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The above specific processes are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0205] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0206] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0207] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0208] (Appendix 1) A reception unit that receives answers to questions from users; a learning unit that analyzes the answers received by the receiving unit and learns the user's thought pattern; a proxy unit that performs work on behalf of a user based on the thought pattern learned by the learning unit; A pointing out unit that points out the strengths and weaknesses of a user based on the thought patterns learned by the learning unit; a simulation unit that simulates a reaction of a person on the basis of the thought pattern learned by the learning unit; A companion discovery unit that finds companions that match the user based on the thought patterns learned by the learning unit. A system characterized by: (Appendix 2) The reception unit is Collect user behavior history 2. The system of claim 1, (Appendix 3) The learning unit is The behavioral history collected by the reception unit is analyzed to learn the user's thought patterns. 2. The system of claim 1, (Appendix 4) The agent unit is Replying to emails on behalf of users 2. The system of claim 1, (Appendix 5) The indication unit is Analyze user behavior and comments to specifically point out the user's strengths and weaknesses 2. The system of claim 1, (Appendix 6) The simulation unit is Simulate other people's reactions to your new ideas 2. The system of claim 1, (Appendix 7) The fellow discovery unit is Share information with other users' generated AI to find specific people with common hobbies and interests 2. The system of claim 1, (Appendix 8) The reception unit is Estimate the user's emotions and adjust the content and timing of questions based on the estimated user emotions 2. The system of claim 1, (Appendix 9) The reception unit is Analyze the user's past question history and select the most appropriate question format 2. The system of claim 1, (Appendix 10) The reception unit is As questions are submitted, filter them based on the user's current situation and areas of interest 2. The system of claim 1, (Appendix 11) The reception unit is Estimate user sentiment and prioritize questions based on the estimated user sentiment 2. The system of claim 1, (Appendix 12) The reception unit is When accepting questions, the system takes into account the user's geographic location information to prioritize questions that are more relevant to the user. 2. The system of claim 1, (Appendix 13) The reception unit is When a question is received, the user's social media activity is analyzed to receive related questions. 2. The system of claim 1, (Appendix 14) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 2. The system of claim 1, (Appendix 15) The learning unit is During training, the learning algorithm is optimized by referencing past training data. 2. The system of claim 1, (Appendix 16) The learning unit is During learning, the user's behavioral history is analyzed in detail to improve the accuracy of thought patterns. 2. The system of claim 1, (Appendix 17) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1, (Appendix 18) The learning unit is During training, the training data is weighted based on the timing of the user's questions. 2. The system of claim 1, (Appendix 19) The learning unit is When learning, the accuracy of learning is improved by referring to the user's related literature. 2. The system of claim 1, (Appendix 20) The agent unit is Estimate the user's emotions and prioritize tasks based on the estimated user's emotions. 2. The system of claim 1, (Appendix 21) The agent unit is When delegating, refer to the user's past task history to select the optimal delegation method 2. The system of claim 1, (Appendix 22) The agent unit is When delegating, customize the task content based on the user's current situation 2. The system of claim 1, (Appendix 23) The agent unit is Estimate the user's emotions and adjust the way the tasks are displayed based on the estimated user's emotions. 2. The system of claim 1, (Appendix 24) The agent unit is When proxying, the optimal proxy method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 25) The agent unit is When acting on behalf of a user, the system analyzes the user's social media activity and suggests tasks to be performed on their behalf. 2. The system of claim 1, (Appendix 26) The indication unit is Infer the user's emotions and adjust the way the comment is expressed based on the estimated user's emotions 2. The system of claim 1, (Appendix 27) The indication unit is When a problem is pointed out, specific feedback is provided by referencing the user's past behavior history. 2. The system of claim 1, (Appendix 28) The indication unit is When issuing an issue, customize the issue based on the user's current situation 2. The system of claim 1, (Appendix 29) The indication unit is Infer user sentiment and prioritize issues based on the estimated user sentiment 2. The system of claim 1, (Appendix 30) The indication unit is When reporting, the most appropriate reporting method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 31) The indication unit is When a problem is reported, the system analyzes the user's social media activity to provide suggestions. 2. The system of claim 1, (Appendix 32) The simulation unit is Estimating a user's emotions and adjusting the results of a simulation based on the estimated user's emotions 2. The system of claim 1, (Appendix 33) The simulation unit is During simulation, the accuracy of the simulation can be improved by referring to the user's past idea history. 2. The system of claim 1, (Appendix 34) The simulation unit is Customize simulation content based on the user's current situation during simulation 2. The system of claim 1, (Appendix 35) The simulation unit is Inferring a user's emotions and adjusting the way the simulation is displayed based on the inferred user's emotions 2. The system of claim 1, (Appendix 36) The simulation unit is During simulation, the optimal simulation method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 37) The simulation unit is During the simulation, the system analyzes users' social media activity and suggests simulation content. 2. The system of claim 1, (Appendix 38) The fellow discovery unit is Estimate the user's emotions and adjust the companion discovery method based on the estimated user's emotions. 2. The system of claim 1, (Appendix 39) The fellow discovery unit is When discovering companions, the system suggests suitable companions by referring to the user's past interaction history. 2. The system of claim 1, (Appendix 40) The fellow discovery unit is When discovering friends, customize the means of discovery based on the user's current situation 2. The system of claim 1, (Appendix 41) The fellow discovery unit is Estimate the user's emotions and determine the priority of companion discovery based on the estimated user's emotions. 2. The system of claim 1, (Appendix 42) The fellow discovery unit is When discovering companions, the system considers the user's geographic location to suggest the most suitable companions. 2. The system of claim 1, (Appendix 43) The fellow discovery unit is When searching for peers, the system analyzes the user's social media activity to suggest ways to find peers. 2. The system of claim 1, [Explanation of symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit that receives answers to questions from users; a learning unit that analyzes the answers received by the receiving unit and learns the user's thought pattern; a proxy unit that performs work on behalf of a user based on the thought pattern learned by the learning unit; A pointing out unit that points out the strengths and weaknesses of a user based on the thought patterns learned by the learning unit; a simulation unit that simulates a reaction of a person on the basis of the thought pattern learned by the learning unit; A companion discovery unit that finds companions that match the user based on the thought patterns learned by the learning unit. A system characterized by:

2. The reception unit is Collect user behavior history 2. The system of claim 1 .

3. The learning unit is The behavioral history collected by the reception unit is analyzed to learn the user's thought patterns.

3. The system of claim 2.

4. The agent unit is Replying to emails on behalf of users 2. The system of claim 1 .

5. The indication unit is Analyze user behavior and comments to specifically point out the user's strengths and weaknesses 2. The system of claim 1 .

6. The simulation unit is Simulate other people's reactions to your new ideas 2. The system of claim 1 .

7. The fellow discovery unit is Share information with other users' generative AI to specifically find people with common hobbies and interests 2. The system of claim 1 .

8. The reception unit is Infer the user's emotions and adjust the content and timing of questions based on the inferred user emotions 2. The system of claim 1 .

9. The reception unit is Analyze the user's past question history and select the most appropriate question format 2. The system of claim 1 .

Images