System

Abstract

To provide a system that allows a user to feel a sense of consultation by reproducing thought patterns of a respected deceased person.SOLUTION: A system according to an embodiment comprises a collection unit, a learning unit, a reception unit and a generation unit. The collection unit collects questions. The learning unit learns thought patterns on the basis of the questions collected by the collection unit. The reception unit receives questions from a user. The generation unit generates answers on the basis of the questions received by the reception unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] With conventional technology, if you want to consult with a respected person who has passed away, it is difficult to reproduce their thought patterns.

[0005] The system of the embodiment aims to reproduce the thought patterns of a respected person who has passed away, giving the user the feeling of consulting with them. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, a reception unit, and a generation unit. The collection unit collects questions. The learning unit learns a thought pattern based on the questions collected by the collection unit. The reception unit receives questions from a user. The generation unit generates an answer based on the question received by the reception unit. Effect of the Invention

[0007] The system according to the embodiment reproduces the thought patterns of a respected person who has passed away, giving the user the feeling of consulting with them. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a 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 consultation support system according to the embodiment of the present invention is a system that uses a generation AI to resolve issues that users would like to discuss with their respected father when the father passes away. This consultation support system asks 100 questions to the person they respect, learns their thinking patterns, and when the user inputs the issues that the user would like to discuss with the father, the generation AI generates an answer based on the father's thinking patterns. For example, when the user inputs a question such as "I'm thinking of trying a new job. What do you think?", the generation AI generates an answer based on the father's thinking patterns. This allows the user to get the feeling of consulting with their father even after the father passes away. First, the user asks 100 questions to the person they respect. For example, questions such as "What values ​​do you value most in your life?" and "How do you deal with difficult situations?". Answers to these questions are collected and the thinking patterns are learned. Next, the learned thinking patterns are applied to the generation AI. Specifically, the collected answer data is input to the generation AI, and the generation AI learns based on the data. This allows the generation AI to understand the thinking patterns of the person they respect and generate answers based on those patterns. When a user inputs what they want to consult or talk about with their father, the generation AI generates an answer based on the father's thought patterns. For example, in response to a question such as, "I'm thinking of trying a new job. What do you think?", the generation AI generates an answer based on the father's thought patterns. This allows the user to get the feeling of consulting with their father. With this system, it is possible to resolve the things that users want to consult or talk about with their father even after their father has passed away. By receiving an answer based on the father's thought patterns, the user can get the feeling of consulting with their father and achieve peace of mind. In this way, the consultation support system allows the user to get the feeling of consulting with their father even after their father has passed away.

[0029] The consultation support system according to the embodiment includes a collection unit, a learning unit, a reception unit, and a generation unit. The collection unit asks 100 questions to a person the user respects and collects the answers. For example, the collection unit can ask the user questions such as "What values ​​do you value most in your life?" and "How do you deal with a difficult situation?" and collect the answers. The collection unit can collect questions in various formats, such as text format, audio format, and questions about a specific topic. The learning unit learns a thinking pattern based on the questions collected by the collection unit. For example, the learning unit learns thinking patterns such as logical thinking, creative thinking, and problem-solving approaches based on the collected answer data. The learning unit can preprocess the collected data and learn the thinking pattern using a machine learning algorithm. The reception unit accepts a question from the user. For example, the reception unit provides an interface for the user to input what he or she wants to consult or talk about with his or her father. The reception unit can accept questions in various formats, such as text format and audio format. The generating unit generates an answer based on the question received by the receiving unit. For example, when the user inputs a question such as "I'm thinking of trying a new job. What do you think?", the generating unit uses the generating AI to generate an answer based on the father's thinking pattern. The generating unit can use the generating AI to apply the thinking pattern learned based on the collected data to generate an appropriate answer to the user's question. As a result, the consultation support system according to the embodiment can provide an appropriate answer to the user's question through each process of collection, learning, reception, and generation. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit inputs the user's question to the generating AI, and the generating AI can generate an answer based on the question. As a result, the consultation support system can provide an appropriate answer to the user's question.

[0030] The collection unit asks 100 questions to people the user respects and collects their answers. For example, the collection unit can ask the user questions such as "What values ​​do you value most in your life?" and "How do you deal with difficult situations?" and collect the answers. The collection unit can collect questions in various formats, such as text format, audio format, and questions on specific topics. Specifically, the collection unit interviews people the user respects using a pre-set list of questions. This interview may be conducted face-to-face or online. In the case of an online interview, questions are asked through a video call or audio call, and the answers are recorded or converted into text. The collection unit stores these answers in a database and uses them for subsequent processing. Furthermore, the collection unit can flexibly change the format and content of the questions. For example, if a user is interested in a particular topic, questions related to that topic can be added. The collection unit can also devise the order and expression of the questions to improve the quality of the answers. For example, by asking simple questions first and gradually moving to questions with deeper content, the respondent can relax and answer more easily. This enables the collection unit to efficiently collect data that allows the user to get a detailed understanding of the thoughts and values ​​of people the user respects.

[0031] The learning unit learns thinking patterns based on the questions collected by the collection unit. For example, the learning unit learns thinking patterns such as logical thinking, creative thinking, and problem-solving approaches based on the collected answer data. The learning unit can preprocess the collected data using a machine learning algorithm to learn thinking patterns. Specifically, the learning unit preprocesses the collected answer data using a text analysis tool. Preprocessing includes text normalization, tokenization, stop word removal, stemming, and the like. This reduces data noise and improves analysis accuracy. Next, the learning unit trains a machine learning model using the preprocessed data. For example, natural language processing technology is used to extract features from the answer data, and clustering and classification algorithms are applied to identify thinking patterns. Furthermore, the learning unit analyzes the respondent's thinking patterns and values ​​trends based on the collected data. For example, it clarifies what kind of judgments the respondent makes in what situations and what values ​​he or she values. This allows the learning unit to build a foundation for learning in detail the thinking patterns of people the user respects and using them in subsequent processes.

[0032] The reception unit receives questions from the user. For example, the reception unit provides an interface for the user to input what the user wants to consult or talk about with his / her father. The reception unit can receive questions in various formats, such as text format and voice format. Specifically, the reception unit provides an intuitive user interface so that the user can easily input questions. For example, a text input field and a voice input button are provided so that the user can input or record questions. Furthermore, the reception unit provides a function that allows the user to refer to questions and answers that have been asked in the past. This allows the user to check the contents of past consultations and avoid duplicate questions. In addition, the reception unit organizes the user's questions by category and efficiently manages them. For example, the reception unit classifies questions into categories such as work, family, and human relationships, so that the user can easily find questions related to a specific category. This allows the reception unit to efficiently receive the user's questions and smoothly hand them over to the subsequent process.

[0033] The generation unit generates an answer based on the question received by the reception unit. For example, when the user inputs a question such as "I'm thinking of trying a new job. What do you think?", the generation unit uses the generation AI to generate an answer based on the father's thinking pattern. The generation unit can use the generation AI to apply the thinking pattern learned based on the collected data to generate an appropriate answer to the user's question. Specifically, the generation unit analyzes the user's question using natural language processing technology and understands the intention and content of the question. Next, the generation AI generates an appropriate answer based on the thinking pattern learned by the learning unit. For example, the generation AI simulates how the father would answer the user's question and generates the answer. The generated answer is provided to the user in text or audio format. Furthermore, the generation unit evaluates the quality of the generated answer and makes corrections as necessary. For example, if the generated answer is inappropriate, the generation AI generates an answer again to provide an optimal answer. In addition, the generation unit collects user feedback and continuously improves the performance of the generation AI. This allows the generation unit to provide high-quality answers to the user's questions and improve user satisfaction.

[0034] The collection unit can collect other data such as diaries and letters. The collection unit can collect diaries and letters in various formats, such as handwritten diaries and letters in e-mail format. For example, the collection unit can scan a diary written by a user, convert it into digital data, and collect the data. The collection unit can also collect e-mails sent and received by a user and save the contents of the e-mails as data. This allows the collection unit to learn thinking patterns based on more diverse information by collecting other data such as diaries and letters. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input diary and letter data into a generation AI, and the generation AI can analyze and collect the data.

[0035] The evaluation unit allows the user to evaluate the generated answer. The evaluation unit provides, for example, an interface for the user to evaluate the satisfaction level for the generated answer. For example, the evaluation unit can provide evaluation criteria for the user to evaluate the accuracy and detail of the answer. The evaluation unit also has a function for the user to provide feedback to the generated answer. For example, the evaluation unit allows the user to input a comment on the answer and store the comment as evaluation data. In this way, the evaluation unit can improve the accuracy of the system by evaluating the generated answer by the user. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the user's evaluation data to the generation AI, and the generation AI can analyze the data to generate an evaluation result.

[0036] The feedback unit can use the evaluation data as feedback. For example, the feedback unit collects evaluation data provided by the user in the evaluation unit, and provides feedback to improve the accuracy of the system based on the data. For example, the feedback unit can adjust the algorithm of the generation unit based on the user's satisfaction and the accuracy of the answer. The feedback unit can also identify improvements to improve the quality of the answer generated by the generation unit based on the user's feedback. In this way, the feedback unit can continuously improve the accuracy of the system by using the evaluation data as feedback. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the evaluation data to the generation AI, and the generation AI can analyze the data to generate a feedback result.

[0037] The analysis unit can perform context analysis. The analysis unit has a function for analyzing the context of a question input by a user to the reception unit, for example. For example, the analysis unit can use natural language processing technology to extract context information of the question and perform analysis to generate an appropriate answer based on the information. The analysis unit also has an algorithm for analyzing the user's intention and background information of the question. For example, the analysis unit can analyze sentences before and after the question input by the user and related topics to understand the intention of the question. As a result, the analysis unit can generate a more appropriate answer to the user's question by performing context analysis. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's question data to the generation AI, and the generation AI can analyze the data to extract context information.

[0038] The collection unit can also collect data on diaries and letters, which the learning unit can use. The collection unit can collect diaries and letters in various formats, such as handwritten diaries and letters in e-mail format. For example, the collection unit can scan diaries written by the user, convert them into digital data, and collect the data. The collection unit can also collect e-mails sent and received by the user and save the contents of the e-mails as data. The learning unit learns thinking patterns based on the diary and letter data collected by the collection unit. For example, the learning unit learns thinking patterns such as logical thinking, creative thinking, and problem-solving approaches based on the collected diary and letter data. The learning unit can preprocess the collected data and learn thinking patterns using a machine learning algorithm. This allows the collection unit to collect data such as diaries and letters and use it for learning, thereby improving the accuracy of the thinking patterns. Some or all of the above-mentioned processing in the collection unit and the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input diary and letter data into a generation AI, which can analyze and collect the data. In addition, the learning unit inputs the collected data into the generation AI, allowing the generation AI to learn thinking patterns based on that data.

[0039] The evaluation unit evaluates the answer generated by the generation unit, and the feedback unit can improve the accuracy of the generation unit by using the evaluation data. The evaluation unit, for example, provides an interface for the user to evaluate the satisfaction with the generated answer. For example, the evaluation unit can provide evaluation criteria for the user to evaluate the accuracy and detail of the answer. The evaluation unit also has a function for the user to provide feedback to the generated answer. For example, the evaluation unit can allow the user to input a comment on the answer and store the comment as evaluation data. The feedback unit collects evaluation data provided by the evaluation unit and adjusts the algorithm of the generation unit based on the data. For example, the feedback unit can adjust the algorithm of the generation unit based on the user's satisfaction and the accuracy of the answer. The feedback unit can also identify improvements for improving the quality of the answer generated by the generation unit based on the user's feedback. As a result, the evaluation unit and the feedback unit can provide a more appropriate answer by improving the accuracy of the generation unit by using the evaluation data. Part or all of the above-mentioned processing in the evaluation unit and the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the user's evaluation data to the generation AI, and the generation AI can analyze the data to generate an evaluation result. The feedback unit can also input evaluation data to the generation AI, which can then analyze the data and generate feedback results.

[0040] The analysis unit can analyze the context of the question received by the reception unit and help the generation unit generate an appropriate answer. The analysis unit has, for example, a function for analyzing the context of the question input by the user to the reception unit. For example, the analysis unit can use natural language processing technology to extract context information of the question and perform analysis to generate an appropriate answer based on the information. The analysis unit also has an algorithm for analyzing the user's intention and background information of the question. For example, the analysis unit can analyze sentences before and after the question input by the user and related topics to understand the intention of the question. As a result, the analysis unit can perform context analysis to enable the generation unit to generate a more appropriate answer. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's question data to the generation AI, and the generation AI can analyze the data to extract context information.

[0041] When collecting questions, the collection unit can analyze the user's past question history and select the most appropriate question. For example, the collection unit can preferentially collect questions related to topics in which the user has shown interest in the past. The collection unit can also analyze the pattern of questions answered by the user in the past and collect similar questions. Furthermore, the collection unit can avoid questions that the user has avoided in the past and collect questions that the user can easily answer. This allows the collection unit to select the most appropriate question by analyzing the user's past question history and efficiently collect questions. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's past question history data to the generation AI, and the generation AI can analyze the data to select the most appropriate question.

[0042] The collection unit can filter questions based on the user's current interests and life situation when collecting questions. The collection unit can collect questions related to a project the user is currently working on, for example. The collection unit can also collect questions related to the user's life situation (for example, moving or a new job). Furthermore, the collection unit can filter and collect questions based on the user's current hobbies and interests. This allows the collection unit to collect highly relevant questions by filtering questions based on the user's current interests and life situation. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's current interests and life situation data to the generation AI, and the generation AI can analyze the data to filter questions.

[0043] When collecting questions, the collection unit can preferentially collect questions that are highly relevant by taking into account the geographical location information of the user. For example, when the user is traveling, the collection unit can collect questions related to the area. Also, when the user is in a specific location, the collection unit can collect questions related to the location. Furthermore, the collection unit can preferentially collect questions related to the area in which the user lives. Thereby, the collection unit can preferentially collect questions that are highly relevant by taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data to select questions that are highly relevant.

[0044] When collecting questions, the collection unit can analyze the user's social media activity and collect related questions. For example, the collection unit can collect questions related to topics that the user frequently mentions on social media. The collection unit can also analyze the content of the user's social media posts and collect questions that the user is likely to be interested in. Furthermore, the collection unit can collect questions based on the content of accounts that the user follows. In this way, the collection unit can efficiently collect related questions by analyzing the user's social media activity. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's social media activity data to the generation AI, and the generation AI can analyze the data to select related questions.

[0045] The learning unit can adjust the learning algorithm by referring to past learning data during learning. The learning unit can, for example, analyze past learning data and select the most effective algorithm. The learning unit can also select an algorithm with a low error rate from the past learning data. Furthermore, the learning unit can adjust the parameters of the learning algorithm based on the past learning data. As a result, the learning unit can optimize the learning algorithm and improve the accuracy of the thinking pattern 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 a generation AI, and the generation AI can analyze the data and select the optimal algorithm.

[0046] The learning unit can apply different learning algorithms to each category of question during learning. For example, the learning unit can apply a deep learning algorithm to questions about values ​​in life. Also, the learning unit can apply a decision tree algorithm to questions about solving everyday problems. Furthermore, the learning unit can apply a natural language processing algorithm to questions about emotions. In this way, the learning unit can learn more appropriate thinking patterns by applying different learning algorithms to each category of question. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data for each category of question to a generation AI, which can analyze the data and apply an optimal algorithm.

[0047] During learning, the learning unit can weight the learning data based on the time of question submission. For example, the learning unit can learn by weighting data of questions submitted recently. In addition, the learning unit can learn by weighting data of questions submitted frequently in the past. Furthermore, the learning unit can learn by weighting data of questions submitted intensively in a specific period. In this way, the learning unit can learn a more appropriate thinking pattern by weighting the learning data based on the time of question submission. 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 data on the time of question submission to a generation AI, and the generation AI can analyze the data and perform weighting.

[0048] The learning unit can determine the priority of the learning data based on the relevance of the question during learning. For example, the learning unit can preferentially learn data with high relevance to the question. Also, the learning unit can postpone learning data with low relevance to the question. Furthermore, the learning unit can dynamically adjust the priority of the learning data based on the relevance of the question. Thereby, the learning unit can learn a more appropriate thinking pattern by determining the priority of the learning data based on the relevance of the question. 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 question relevance data to a generation AI, and the generation AI can analyze the data and determine the priority.

[0049] The reception unit can select the optimal reception method by referring to the user's past question history when receiving a question. For example, the reception unit can preferentially receive a question format that the user has frequently used in the past. The reception unit can also analyze a specific pattern from the user's past question history and suggest the optimal reception method. Furthermore, the reception unit can avoid question formats that the user has avoided in the past and receive formats that the user can easily answer. As a result, the reception unit can select the optimal reception method by referring to the user's past question history and efficiently receive questions. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's past question history data to the generation AI, and the generation AI can analyze the data to select the optimal reception method.

[0050] The reception unit can perform filtering based on the user's current interests and living situation when receiving a question. For example, the reception unit can preferentially receive questions related to a project that the user is currently working on. The reception unit can also preferentially receive questions related to the user's living situation (for example, moving or a new job). Furthermore, the reception unit can filter and receive questions based on the user's current hobbies and interests. This allows the reception unit to receive highly relevant questions by filtering questions based on the user's current interests and living situation. 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 current interests and living situation data to the generation AI, and the generation AI can analyze the data to filter the questions.

[0051] When receiving a question, the reception unit can preferentially receive a highly relevant question by taking into account the geographical location information of the user. For example, when the user is traveling, the reception unit can preferentially receive a question related to the area. Furthermore, when the user is in a specific location, the reception unit can preferentially receive a question related to the location. Furthermore, the reception unit can preferentially receive a question related to the area where the user lives. Thereby, the reception unit can preferentially receive a highly relevant question by taking into account the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data and select a highly relevant question.

[0052] The reception unit can analyze the user's social media activity and receive related questions when receiving a question. For example, the reception unit can preferentially receive questions related to topics that the user frequently mentions on social media. The reception unit can also analyze the content of the user's social media posts and receive questions that the user is likely to be interested in. Furthermore, the reception unit can receive questions based on the content of accounts the user follows. In this way, the reception unit can efficiently receive related questions by analyzing the user's social media activity. 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 social media activity data to the generation AI, and the generation AI can analyze the data and select related questions.

[0053] The generation unit can adjust the level of detail of the answer based on the importance of the question when generating the answer. For example, the generation unit can generate a detailed answer for a question with a high level of importance. Also, the generation unit can generate a concise answer for a question with a low level of importance. Furthermore, the generation unit can dynamically adjust the level of detail of the answer according to the importance of the question. As a result, the generation unit can provide a more appropriate answer by adjusting the level of detail of the answer based on the importance of the question. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the importance data of the question to the generation AI, and the generation AI can analyze the data and adjust the level of detail of the answer.

[0054] The generation unit can apply different generation algorithms depending on the category of the question when generating an answer. For example, the generation unit can apply a deep learning algorithm to a question about values ​​in life. The generation unit can also apply a decision tree algorithm to a question about solving everyday problems. The generation unit can also apply a natural language processing algorithm to a question about emotions. This allows the generation unit to provide a more appropriate answer by applying different generation algorithms depending on the category of the question. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data for each category of questions to the generation AI, which can then analyze the data and apply the optimal algorithm.

[0055] The generation unit can determine the priority of the answers based on the submission time of the questions when generating the answers. For example, the generation unit can generate answers preferentially for questions submitted recently. The generation unit can also generate answers preferentially for questions submitted frequently in the past. Furthermore, the generation unit can generate answers preferentially for questions submitted in a concentrated manner in a specific period. In this way, the generation unit can provide more appropriate answers by determining the priority of the answers based on the submission time of the questions. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input data on the submission time of the questions to the generation AI, and the generation AI can analyze the data to determine the priority.

[0056] The generation unit can adjust the order of answers based on the relevance of the questions when generating answers. For example, the generation unit can give priority to answers with high relevance to questions. Also, the generation unit can give answers with low relevance to questions later. Furthermore, the generation unit can dynamically adjust the order of answers based on the relevance of the questions. This allows the generation unit to provide more appropriate answers by adjusting the order of answers based on the relevance of the questions. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input question relevance data to the generation AI, and the generation AI can analyze the data and adjust the order of answers.

[0057] The collection unit can analyze the user's past data collection history and select the optimal collection method when collecting a diary or a letter. The collection unit can, for example, preferentially collect data formats that the user has frequently collected in the past. The collection unit can also analyze a specific pattern from the user's past data collection history and suggest the optimal collection method. Furthermore, the collection unit can avoid data formats that the user has avoided in the past and collect formats that the user can easily collect. As a result, the collection unit can select the optimal collection method and efficiently collect data by analyzing the user's past data collection history. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's past data collection history data to the generation AI, and the generation AI can analyze the data and select the optimal collection method.

[0058] When collecting diaries and letters, the collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user. For example, when the user is traveling, the collection unit can preferentially collect diaries and letters related to the area. In addition, when the user is in a specific location, the collection unit can preferentially collect diaries and letters related to the location. Furthermore, the collection unit can preferentially collect diaries and letters related to the area where the user lives. In this way, the collection unit can preferentially collect highly relevant data by considering the geographical location information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data and select highly relevant data.

[0059] The evaluation unit can select the optimal evaluation method by referring to the user's past evaluation history at the time of evaluation. The evaluation unit can, for example, preferentially provide an evaluation format that the user has frequently used in the past. The evaluation unit can also analyze a specific pattern from the user's past evaluation history and suggest the optimal evaluation method. Furthermore, the evaluation unit can avoid evaluation formats that the user has avoided in the past and provide a format that the user can easily evaluate. Thereby, the evaluation unit can select the optimal evaluation method by referring to the user's past evaluation history and perform evaluation efficiently. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the user's past evaluation history data to the generation AI, and the generation AI can analyze the data to select the optimal evaluation method.

[0060] The evaluation unit can prioritize highly relevant evaluations during evaluation, taking into account the geographical location information of the user. For example, when the user is traveling, the evaluation unit can prioritize evaluations related to the area. Also, when the user is in a specific location, the evaluation unit can prioritize evaluations related to the location. Furthermore, the evaluation unit can prioritize evaluations related to the area in which the user lives. As a result, the evaluation unit can prioritize highly relevant evaluations by taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data and select a highly relevant evaluation.

[0061] The feedback unit can select the optimal feedback method by referring to the user's past feedback history at the time of feedback. The feedback unit can, for example, preferentially provide a feedback format that the user has frequently used in the past. The feedback unit can also analyze a specific pattern from the user's past feedback history and suggest the optimal feedback method. Furthermore, the feedback unit can avoid feedback formats that the user has avoided in the past and provide a format that is easy for the user to give feedback. Thereby, the feedback unit can select the optimal feedback method by referring to the user's past feedback history and provide feedback efficiently. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can input the user's past feedback history data to the generation AI, and the generation AI can analyze the data to select the optimal feedback method.

[0062] The feedback unit can give priority to highly relevant feedback in consideration of the geographical location information of the user when providing feedback. For example, when the user is traveling, the feedback unit can give priority to feedback related to the area. Also, when the user is in a specific location, the feedback unit can give priority to feedback related to the location. Furthermore, the feedback unit can give priority to feedback related to the area where the user lives. As a result, the feedback unit can give priority to highly relevant feedback by considering the geographical location information of the user. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data to select highly relevant feedback.

[0063] The analysis unit can select the optimal analysis method by referring to the user's past question history when analyzing the context. The analysis unit can select the analysis method based on, for example, a question format that the user frequently used in the past. The analysis unit can also analyze a specific pattern from the user's past question history and propose the optimal analysis method. Furthermore, the analysis unit can avoid question formats that the user has avoided in the past and analyze based on a format that the user can easily answer. This allows the analysis unit to select the optimal analysis method by referring to the user's past question history and perform analysis efficiently. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can input the user's past question history data to the generation AI, and the generation AI can analyze the data to select the optimal analysis method.

[0064] The analysis unit can apply different analysis algorithms to each category of question during context analysis. For example, the analysis unit can apply a deep learning algorithm to questions about values ​​in life. The analysis unit can also apply a decision tree algorithm to questions about solving everyday problems. The analysis unit can also apply a natural language processing algorithm to questions about emotions. This allows the analysis unit to perform more appropriate analysis by applying different analysis algorithms to each category of question. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data for each category of question to a generation AI, which can then analyze the data and apply an optimal algorithm.

[0065] The analysis unit can determine the priority of the analysis based on the time of question submission during the context analysis. For example, the analysis unit can preferentially analyze the context of a question submitted recently. Furthermore, the analysis unit can preferentially analyze the context of a question submitted frequently in the past. Furthermore, the analysis unit can preferentially analyze the context of a question submitted in a specific period. This allows the analysis unit to perform a more appropriate analysis by determining the priority of the analysis based on the time of question submission. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input question submission time data to a generation AI, and the generation AI can analyze the data to determine the priority.

[0066] The analysis unit can adjust the order of analysis based on the relevance of the question during context analysis. For example, the analysis unit can prioritize analysis of a context with high relevance of the question. Also, the analysis unit can analyze a context with low relevance of the question later. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the question. As a result, the analysis unit can perform a more appropriate analysis by adjusting the order of analysis based on the relevance of the question. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input question relevance data to the generation AI, and the generation AI can analyze the data and adjust the order of analysis.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The consultation support system may further include a history analysis unit that analyzes the user's past consultation history. The history analysis unit may analyze the content of consultations the user has had in the past and grasp the user's consultation patterns and tendencies. For example, the history analysis unit may identify topics the user frequently consults about and the content the user frequently consults about at a particular time. The history analysis unit may also analyze the user's satisfaction with answers he or she has received in the past and extract the characteristics of answers that have satisfied the user. Furthermore, the history analysis unit may predict future consultation contents based on the user's consultation history and provide related information at an appropriate time. This allows the history analysis unit to provide more personalized consultation support by utilizing the user's past consultation history.

[0069] The collection unit can analyze the user's social media activity and collect questions related to topics in which the user is interested. For example, the collection unit can analyze the content frequently posted by the user and the topics of accounts followed by the user, and generate questions based on the analysis. The collection unit can also analyze comments and reactions received by the user on social media, and identify themes in which the user is interested. Furthermore, the collection unit can collect questions at optimal timing, taking into account the time period during which the user is active on social media. This allows the collection unit to collect more relevant questions by utilizing the user's social media activity.

[0070] The evaluation unit can collect user feedback in real time and immediately reflect it in improvements to the system. For example, the evaluation unit can request an evaluation immediately after the user receives an answer, and immediately analyze the evaluation result to adjust the system's algorithm. The evaluation unit can also reflect the feedback provided by the user when generating the next answer. Furthermore, the evaluation unit can accumulate user feedback and use it to improve the system over the long term. In this way, the evaluation unit can provide a system that always meets the latest user needs by quickly reflecting user feedback.

[0071] The feedback unit can make adjustments to improve the degree of personalization of the system based on the user's feedback. For example, the feedback unit can analyze the feedback provided by the user and customize the system settings to suit the user's preferences and needs. The feedback unit can also improve the system's interface and functions based on the user's feedback. Furthermore, the feedback unit can utilize the user's feedback to suggest new functions and services. In this way, the feedback unit can provide a more personalized system by utilizing the user's feedback.

[0072] The analysis unit can utilize external data sources to improve the accuracy of answers to user questions. For example, the analysis unit can collect public databases on the Internet and expert opinions and generate answers based on them. The analysis unit can also analyze additional information provided by the user to provide a more detailed answer. Furthermore, the analysis unit can refer to questions and answers from other users to generate optimal answers to similar questions. This allows the analysis unit to utilize external data sources to provide more accurate answers.

[0073] The process flow of the first embodiment will be briefly described below.

[0074] Step 1: The collection unit asks 100 questions to people the user respects and collects their answers. For example, the collection unit can ask the user questions such as "What values ​​do you value most in your life?" and "When you are faced with a difficult situation, how do you deal with it?" and collect the answers. The collection unit can collect questions in various formats, such as text format, audio format, and questions about a specific topic. Step 2: The learning unit learns thinking patterns based on the questions collected by the collection unit. For example, the learning unit learns thinking patterns such as logical thinking, creative thinking, and problem-solving approaches based on the collected answer data. The learning unit can use a machine learning algorithm to preprocess the collected data and learn thinking patterns. Step 3: The reception unit receives a question from the user. For example, the reception unit provides an interface for the user to input what he or she wants to discuss with his or her father. The reception unit can receive questions in various formats, such as text format and voice format. Step 4: The generation unit generates an answer based on the question received by the reception unit. For example, when a user inputs a question such as "I'm thinking of trying a new job. What do you think?", the generation unit uses the generation AI to generate an answer based on the father's thought patterns. The generation unit can use the generation AI to apply the thought patterns learned from the collected data and generate an appropriate answer to the user's question.

[0075] (Example 2) The consultation support system according to the embodiment of the present invention is a system that uses a generation AI to resolve issues that users would like to discuss with their respected father when the father passes away. This consultation support system asks 100 questions to the person they respect, learns their thinking patterns, and when the user inputs the issues that the user would like to discuss with the father, the generation AI generates an answer based on the father's thinking patterns. For example, when the user inputs a question such as "I'm thinking of trying a new job. What do you think?", the generation AI generates an answer based on the father's thinking patterns. This allows the user to get the feeling of consulting with their father even after the father passes away. First, the user asks 100 questions to the person they respect. For example, questions such as "What values ​​do you value most in your life?" and "How do you deal with difficult situations?". Answers to these questions are collected and the thinking patterns are learned. Next, the learned thinking patterns are applied to the generation AI. Specifically, the collected answer data is input to the generation AI, and the generation AI learns based on the data. This allows the generation AI to understand the thinking patterns of the person they respect and generate answers based on those patterns. When a user inputs what they want to consult or talk about with their father, the generation AI generates an answer based on the father's thought patterns. For example, in response to a question such as, "I'm thinking of trying a new job. What do you think?", the generation AI generates an answer based on the father's thought patterns. This allows the user to get the feeling of consulting with their father. With this system, it is possible to resolve the things that users want to consult or talk about with their father even after their father has passed away. By receiving an answer based on the father's thought patterns, the user can get the feeling of consulting with their father and achieve peace of mind. In this way, the consultation support system allows the user to get the feeling of consulting with their father even after their father has passed away.

[0076] The consultation support system according to the embodiment includes a collection unit, a learning unit, a reception unit, and a generation unit. The collection unit asks 100 questions to a person the user respects and collects the answers. For example, the collection unit can ask the user questions such as "What values ​​do you value most in your life?" and "How do you deal with a difficult situation?" and collect the answers. The collection unit can collect questions in various formats, such as text format, audio format, and questions about a specific topic. The learning unit learns a thinking pattern based on the questions collected by the collection unit. For example, the learning unit learns thinking patterns such as logical thinking, creative thinking, and problem-solving approaches based on the collected answer data. The learning unit can preprocess the collected data and learn the thinking pattern using a machine learning algorithm. The reception unit accepts a question from the user. For example, the reception unit provides an interface for the user to input what he or she wants to consult or talk about with his or her father. The reception unit can accept questions in various formats, such as text format and audio format. The generating unit generates an answer based on the question received by the receiving unit. For example, when the user inputs a question such as "I'm thinking of trying a new job. What do you think?", the generating unit uses the generating AI to generate an answer based on the father's thinking pattern. The generating unit can use the generating AI to apply the thinking pattern learned based on the collected data to generate an appropriate answer to the user's question. As a result, the consultation support system according to the embodiment can provide an appropriate answer to the user's question through each process of collection, learning, reception, and generation. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit inputs the user's question to the generating AI, and the generating AI can generate an answer based on the question. As a result, the consultation support system can provide an appropriate answer to the user's question.

[0077] The collection unit asks 100 questions to people the user respects and collects their answers. For example, the collection unit can ask the user questions such as "What values ​​do you value most in your life?" and "How do you deal with difficult situations?" and collect the answers. The collection unit can collect questions in various formats, such as text format, audio format, and questions on specific topics. Specifically, the collection unit interviews people the user respects using a pre-set list of questions. This interview may be conducted face-to-face or online. In the case of an online interview, questions are asked through a video call or audio call, and the answers are recorded or converted into text. The collection unit stores these answers in a database and uses them for subsequent processing. Furthermore, the collection unit can flexibly change the format and content of the questions. For example, if a user is interested in a particular topic, questions related to that topic can be added. The collection unit can also devise the order and expression of the questions to improve the quality of the answers. For example, by asking simple questions first and gradually moving to questions with deeper content, the respondent can relax and answer more easily. This enables the collection unit to efficiently collect data that allows the user to get a detailed understanding of the thoughts and values ​​of people the user respects.

[0078] The learning unit learns thinking patterns based on the questions collected by the collection unit. For example, the learning unit learns thinking patterns such as logical thinking, creative thinking, and problem-solving approaches based on the collected answer data. The learning unit can preprocess the collected data using a machine learning algorithm to learn thinking patterns. Specifically, the learning unit preprocesses the collected answer data using a text analysis tool. Preprocessing includes text normalization, tokenization, stop word removal, stemming, and the like. This reduces data noise and improves analysis accuracy. Next, the learning unit trains a machine learning model using the preprocessed data. For example, natural language processing technology is used to extract features from the answer data, and clustering and classification algorithms are applied to identify thinking patterns. Furthermore, the learning unit analyzes the respondent's thinking patterns and values ​​trends based on the collected data. For example, it clarifies what kind of judgments the respondent makes in what situations and what values ​​he or she values. This allows the learning unit to build a foundation for learning in detail the thinking patterns of people the user respects and using them in subsequent processes.

[0079] The reception unit receives questions from the user. For example, the reception unit provides an interface for the user to input what the user wants to consult or talk about with his / her father. The reception unit can receive questions in various formats, such as text format and voice format. Specifically, the reception unit provides an intuitive user interface so that the user can easily input questions. For example, a text input field and a voice input button are provided so that the user can input or record questions. Furthermore, the reception unit provides a function that allows the user to refer to questions and answers that have been asked in the past. This allows the user to check the contents of past consultations and avoid duplicate questions. In addition, the reception unit organizes the user's questions by category and efficiently manages them. For example, the reception unit classifies questions into categories such as work, family, and human relationships, so that the user can easily find questions related to a specific category. This allows the reception unit to efficiently receive the user's questions and smoothly hand them over to the subsequent process.

[0080] The generation unit generates an answer based on the question received by the reception unit. For example, when the user inputs a question such as "I'm thinking of trying a new job. What do you think?", the generation unit uses the generation AI to generate an answer based on the father's thinking pattern. The generation unit can use the generation AI to apply the thinking pattern learned based on the collected data to generate an appropriate answer to the user's question. Specifically, the generation unit analyzes the user's question using natural language processing technology and understands the intention and content of the question. Next, the generation AI generates an appropriate answer based on the thinking pattern learned by the learning unit. For example, the generation AI simulates how the father would answer the user's question and generates the answer. The generated answer is provided to the user in text or audio format. Furthermore, the generation unit evaluates the quality of the generated answer and makes corrections as necessary. For example, if the generated answer is inappropriate, the generation AI generates an answer again to provide an optimal answer. In addition, the generation unit collects user feedback and continuously improves the performance of the generation AI. This allows the generation unit to provide high-quality answers to the user's questions and improve user satisfaction.

[0081] The collection unit can collect other data such as diaries and letters. The collection unit can collect diaries and letters in various formats, such as handwritten diaries and letters in e-mail format. For example, the collection unit can scan a diary written by a user, convert it into digital data, and collect the data. The collection unit can also collect e-mails sent and received by a user and save the contents of the e-mails as data. This allows the collection unit to learn thinking patterns based on more diverse information by collecting other data such as diaries and letters. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input diary and letter data into a generation AI, and the generation AI can analyze and collect the data.

[0082] The evaluation unit allows the user to evaluate the generated answer. The evaluation unit provides, for example, an interface for the user to evaluate the satisfaction level for the generated answer. For example, the evaluation unit can provide evaluation criteria for the user to evaluate the accuracy and detail of the answer. The evaluation unit also has a function for the user to provide feedback to the generated answer. For example, the evaluation unit allows the user to input a comment on the answer and store the comment as evaluation data. In this way, the evaluation unit can improve the accuracy of the system by evaluating the generated answer by the user. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the user's evaluation data to the generation AI, and the generation AI can analyze the data to generate an evaluation result.

[0083] The feedback unit can use the evaluation data as feedback. For example, the feedback unit collects evaluation data provided by the user in the evaluation unit, and provides feedback to improve the accuracy of the system based on the data. For example, the feedback unit can adjust the algorithm of the generation unit based on the user's satisfaction and the accuracy of the answer. The feedback unit can also identify improvements to improve the quality of the answer generated by the generation unit based on the user's feedback. In this way, the feedback unit can continuously improve the accuracy of the system by using the evaluation data as feedback. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the evaluation data to the generation AI, and the generation AI can analyze the data to generate a feedback result.

[0084] The analysis unit can perform context analysis. The analysis unit has a function for analyzing the context of a question input by a user to the reception unit, for example. For example, the analysis unit can use natural language processing technology to extract context information of the question and perform analysis to generate an appropriate answer based on the information. The analysis unit also has an algorithm for analyzing the user's intention and background information of the question. For example, the analysis unit can analyze sentences before and after the question input by the user and related topics to understand the intention of the question. As a result, the analysis unit can generate a more appropriate answer to the user's question by performing context analysis. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's question data to the generation AI, and the generation AI can analyze the data to extract context information.

[0085] The collection unit can also collect data on diaries and letters, which the learning unit can use. The collection unit can collect diaries and letters in various formats, such as handwritten diaries and letters in e-mail format. For example, the collection unit can scan diaries written by the user, convert them into digital data, and collect the data. The collection unit can also collect e-mails sent and received by the user and save the contents of the e-mails as data. The learning unit learns thinking patterns based on the diary and letter data collected by the collection unit. For example, the learning unit learns thinking patterns such as logical thinking, creative thinking, and problem-solving approaches based on the collected diary and letter data. The learning unit can preprocess the collected data and learn thinking patterns using a machine learning algorithm. This allows the collection unit to collect data such as diaries and letters and use it for learning, thereby improving the accuracy of the thinking patterns. Some or all of the above-mentioned processing in the collection unit and the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input diary and letter data into a generation AI, which can analyze and collect the data. In addition, the learning unit inputs the collected data into the generation AI, allowing the generation AI to learn thinking patterns based on that data.

[0086] The evaluation unit evaluates the answer generated by the generation unit, and the feedback unit can improve the accuracy of the generation unit by using the evaluation data. The evaluation unit, for example, provides an interface for the user to evaluate the satisfaction with the generated answer. For example, the evaluation unit can provide evaluation criteria for the user to evaluate the accuracy and detail of the answer. The evaluation unit also has a function for the user to provide feedback to the generated answer. For example, the evaluation unit can allow the user to input a comment on the answer and store the comment as evaluation data. The feedback unit collects evaluation data provided by the evaluation unit and adjusts the algorithm of the generation unit based on the data. For example, the feedback unit can adjust the algorithm of the generation unit based on the user's satisfaction and the accuracy of the answer. The feedback unit can also identify improvements for improving the quality of the answer generated by the generation unit based on the user's feedback. As a result, the evaluation unit and the feedback unit can provide a more appropriate answer by improving the accuracy of the generation unit by using the evaluation data. Part or all of the above-mentioned processing in the evaluation unit and the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the user's evaluation data to the generation AI, and the generation AI can analyze the data to generate an evaluation result. The feedback unit can also input evaluation data to the generation AI, which can then analyze the data and generate feedback results.

[0087] The analysis unit can analyze the context of the question received by the reception unit and help the generation unit generate an appropriate answer. The analysis unit has, for example, a function for analyzing the context of the question input by the user to the reception unit. For example, the analysis unit can use natural language processing technology to extract context information of the question and perform analysis to generate an appropriate answer based on the information. The analysis unit also has an algorithm for analyzing the user's intention and background information of the question. For example, the analysis unit can analyze sentences before and after the question input by the user and related topics to understand the intention of the question. As a result, the analysis unit can perform context analysis to enable the generation unit to generate a more appropriate answer. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's question data to the generation AI, and the generation AI can analyze the data to extract context information.

[0088] The collection unit can estimate the user's emotions and adjust the timing of collecting questions based on the estimated user's emotions. For example, when the user is sad, the collection unit can temporarily stop collecting questions and resume when the user calms down. In addition, when the user is relaxed, the collection unit can proactively collect questions and provide an environment in which the user can easily answer questions. Furthermore, when the user is busy, the collection unit can postpone collecting questions and collect them when the user has time. In this way, the collection unit can provide an environment in which the user can easily answer questions by adjusting the timing of collecting questions based on the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate emotions, and adjust the timing of collecting questions based on the results.

[0089] When collecting questions, the collection unit can analyze the user's past question history and select the most appropriate question. For example, the collection unit can preferentially collect questions related to topics in which the user has shown interest in the past. The collection unit can also analyze the pattern of questions answered by the user in the past and collect similar questions. Furthermore, the collection unit can avoid questions that the user has avoided in the past and collect questions that the user can easily answer. This allows the collection unit to select the most appropriate question by analyzing the user's past question history and efficiently collect questions. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's past question history data to the generation AI, and the generation AI can analyze the data to select the most appropriate question.

[0090] The collection unit can filter questions based on the user's current interests and life situation when collecting questions. The collection unit can collect questions related to a project the user is currently working on, for example. The collection unit can also collect questions related to the user's life situation (for example, moving or a new job). Furthermore, the collection unit can filter and collect questions based on the user's current hobbies and interests. This allows the collection unit to collect highly relevant questions by filtering questions based on the user's current interests and life situation. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's current interests and life situation data to the generation AI, and the generation AI can analyze the data to filter questions.

[0091] The collection unit can estimate the user's emotion and determine the priority of questions to be collected based on the estimated user's emotion. For example, when the user is sad, the collection unit can preferentially collect questions that are in tune with the emotion. In addition, when the user is excited, the collection unit can preferentially collect positive questions. Furthermore, when the user is tired, the collection unit can preferentially collect questions that are easy to answer. In this way, the collection unit can collect questions according to the user's situation by determining the priority of questions 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 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 collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and determine the priority of questions based on the result.

[0092] When collecting questions, the collection unit can preferentially collect questions that are highly relevant by taking into account the geographical location information of the user. For example, when the user is traveling, the collection unit can collect questions related to the area. Also, when the user is in a specific location, the collection unit can collect questions related to the location. Furthermore, the collection unit can preferentially collect questions related to the area in which the user lives. Thereby, the collection unit can preferentially collect questions that are highly relevant by taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data to select questions that are highly relevant.

[0093] When collecting questions, the collection unit can analyze the user's social media activity and collect related questions. For example, the collection unit can collect questions related to topics that the user frequently mentions on social media. The collection unit can also analyze the content of the user's social media posts and collect questions that the user is likely to be interested in. Furthermore, the collection unit can collect questions based on the content of accounts that the user follows. In this way, the collection unit can efficiently collect related questions by analyzing the user's social media activity. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's social media activity data to the generation AI, and the generation AI can analyze the data to select related questions.

[0094] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. For example, when the user is sad, the learning unit can preferentially learn data including answers that are in tune with the emotion. Furthermore, when the user is relaxed, the learning unit can preferentially learn data including detailed explanations. Furthermore, when the user is excited, the learning unit can preferentially learn data including positive answers. This allows the learning unit to learn a more appropriate thought pattern 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 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 the user's emotion data to the generation AI, which analyzes the data to estimate the emotion, and select learning data based on the result.

[0095] The learning unit can adjust the learning algorithm by referring to past learning data during learning. The learning unit can, for example, analyze past learning data and select the most effective algorithm. The learning unit can also select an algorithm with a low error rate from the past learning data. Furthermore, the learning unit can adjust the parameters of the learning algorithm based on the past learning data. As a result, the learning unit can optimize the learning algorithm and improve the accuracy of the thinking pattern 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 a generation AI, and the generation AI can analyze the data and select the optimal algorithm.

[0096] The learning unit can apply different learning algorithms to each category of question during learning. For example, the learning unit can apply a deep learning algorithm to questions about values ​​in life. Also, the learning unit can apply a decision tree algorithm to questions about solving everyday problems. Furthermore, the learning unit can apply a natural language processing algorithm to questions about emotions. In this way, the learning unit can learn more appropriate thinking patterns by applying different learning algorithms to each category of question. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data for each category of question to a generation AI, which can analyze the data and apply an optimal algorithm.

[0097] The learning unit can estimate the user's emotion and adjust the frequency of learning based on the estimated user's emotion. For example, when the user is sad, the learning unit can reduce the frequency of learning and resume when the user is calm. Also, when the user is relaxed, the learning unit can increase the frequency of learning and learn detailed data. Furthermore, when the user is busy, the learning unit can adjust the frequency of learning and learn when the user has time. In this way, the learning unit can adjust the frequency of learning based on the user's emotion, thereby performing learning according to the user's situation. 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 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 the user's emotion data to the generation AI, which analyzes the data to estimate the emotion, and adjust the frequency of learning based on the result.

[0098] During learning, the learning unit can weight the learning data based on the time of question submission. For example, the learning unit can learn by weighting data of questions submitted recently. In addition, the learning unit can learn by weighting data of questions submitted frequently in the past. Furthermore, the learning unit can learn by weighting data of questions submitted intensively in a specific period. In this way, the learning unit can learn a more appropriate thinking pattern by weighting the learning data based on the time of question submission. 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 data on the time of question submission to a generation AI, and the generation AI can analyze the data and perform weighting.

[0099] The learning unit can determine the priority of the learning data based on the relevance of the question during learning. For example, the learning unit can preferentially learn data with high relevance to the question. Also, the learning unit can postpone learning data with low relevance to the question. Furthermore, the learning unit can dynamically adjust the priority of the learning data based on the relevance of the question. Thereby, the learning unit can learn a more appropriate thinking pattern by determining the priority of the learning data based on the relevance of the question. 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 question relevance data to a generation AI, and the generation AI can analyze the data and determine the priority.

[0100] The reception unit can estimate the user's emotion and adjust the method of receiving a question based on the estimated user's emotion. For example, when the user is sad, the reception unit can provide a simple interface and minimize input procedures. Also, when the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the user is in a hurry, the reception unit can prioritize voice input and quickly receive questions. In this way, the reception unit can provide an environment in which the user can easily ask questions by adjusting the method of receiving a question 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 reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI, which can analyze the data to estimate the emotion, and adjust the method of receiving a question based on the result.

[0101] The reception unit can select the optimal reception method by referring to the user's past question history when receiving a question. For example, the reception unit can preferentially receive a question format that the user has frequently used in the past. The reception unit can also analyze a specific pattern from the user's past question history and suggest the optimal reception method. Furthermore, the reception unit can avoid question formats that the user has avoided in the past and receive formats that the user can easily answer. As a result, the reception unit can select the optimal reception method by referring to the user's past question history and efficiently receive questions. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's past question history data to the generation AI, and the generation AI can analyze the data to select the optimal reception method.

[0102] The reception unit can perform filtering based on the user's current interests and living situation when receiving a question. For example, the reception unit can preferentially receive questions related to a project that the user is currently working on. The reception unit can also preferentially receive questions related to the user's living situation (for example, moving or a new job). Furthermore, the reception unit can filter and receive questions based on the user's current hobbies and interests. This allows the reception unit to receive highly relevant questions by filtering questions based on the user's current interests and living situation. 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 current interests and living situation data to the generation AI, and the generation AI can analyze the data to filter the questions.

[0103] The reception unit can estimate the user's emotion and determine the priority of questions to be received based on the estimated user's emotion. For example, when the user is sad, the reception unit can preferentially receive questions that are sympathetic to the emotion. Furthermore, when the user is excited, the reception unit can preferentially receive positive questions. Furthermore, when the user is tired, the reception unit can preferentially receive questions that are simple and easy to answer. In this way, the reception unit can receive questions according to the user's situation by determining the priority of questions 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 a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and determine the priority of questions based on the result.

[0104] When receiving a question, the reception unit can preferentially receive a highly relevant question by taking into account the geographical location information of the user. For example, when the user is traveling, the reception unit can preferentially receive a question related to the area. Furthermore, when the user is in a specific location, the reception unit can preferentially receive a question related to the location. Furthermore, the reception unit can preferentially receive a question related to the area where the user lives. Thereby, the reception unit can preferentially receive a highly relevant question by taking into account the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data and select a highly relevant question.

[0105] The reception unit can analyze the user's social media activity and receive related questions when receiving a question. For example, the reception unit can preferentially receive questions related to topics that the user frequently mentions on social media. The reception unit can also analyze the content of the user's social media posts and receive questions that the user is likely to be interested in. Furthermore, the reception unit can receive questions based on the content of accounts the user follows. In this way, the reception unit can efficiently receive related questions by analyzing the user's social media activity. 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 social media activity data to the generation AI, and the generation AI can analyze the data and select related questions.

[0106] The generation unit can estimate the user's emotion and adjust the way of expressing the answer based on the estimated emotion of the user. For example, when the user is sad, the generation unit can generate an answer in gentle language. Furthermore, when the user is relaxed, the generation unit can generate an answer including a detailed explanation. Furthermore, when the user is excited, the generation unit can generate an answer that uses a lot of positive expressions. In this way, the generation unit can provide a more appropriate answer for the user by adjusting the way of expressing the answer based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and adjust the way of expressing the answer based on the result.

[0107] The generation unit can adjust the level of detail of the answer based on the importance of the question when generating the answer. For example, the generation unit can generate a detailed answer for a question with a high level of importance. Also, the generation unit can generate a concise answer for a question with a low level of importance. Furthermore, the generation unit can dynamically adjust the level of detail of the answer according to the importance of the question. As a result, the generation unit can provide a more appropriate answer by adjusting the level of detail of the answer based on the importance of the question. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the importance data of the question to the generation AI, and the generation AI can analyze the data and adjust the level of detail of the answer.

[0108] The generation unit can apply different generation algorithms depending on the category of the question when generating an answer. For example, the generation unit can apply a deep learning algorithm to a question about values ​​in life. The generation unit can also apply a decision tree algorithm to a question about solving everyday problems. The generation unit can also apply a natural language processing algorithm to a question about emotions. This allows the generation unit to provide a more appropriate answer by applying different generation algorithms depending on the category of the question. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data for each category of questions to the generation AI, which can then analyze the data and apply the optimal algorithm.

[0109] The generation unit can estimate the user's emotion and adjust the length of the answer based on the estimated user's emotion. For example, when the user is in a hurry, the generation unit can generate a short answer that is to the point. Furthermore, when the user is relaxed, the generation unit can generate a longer answer that includes a detailed explanation. Furthermore, when the user is excited, the generation unit can generate an answer with a visually stimulating effect. In this way, the generation unit can provide a more appropriate answer for the user by adjusting the length of the answer 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 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 generation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and adjust the length of the answer based on the result.

[0110] The generation unit can determine the priority of the answers based on the submission time of the questions when generating the answers. For example, the generation unit can generate answers preferentially for questions submitted recently. The generation unit can also generate answers preferentially for questions submitted frequently in the past. Furthermore, the generation unit can generate answers preferentially for questions submitted in a concentrated manner in a specific period. In this way, the generation unit can provide more appropriate answers by determining the priority of the answers based on the submission time of the questions. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input data on the submission time of the questions to the generation AI, and the generation AI can analyze the data to determine the priority.

[0111] The generation unit can adjust the order of answers based on the relevance of the questions when generating answers. For example, the generation unit can give priority to answers with high relevance to questions. Also, the generation unit can give answers with low relevance to questions later. Furthermore, the generation unit can dynamically adjust the order of answers based on the relevance of the questions. This allows the generation unit to provide more appropriate answers by adjusting the order of answers based on the relevance of the questions. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input question relevance data to the generation AI, and the generation AI can analyze the data and adjust the order of answers.

[0112] The collection unit can estimate the user's emotions and adjust the timing of collecting diaries and letters based on the estimated user's emotions. For example, when the user is sad, the collection unit can temporarily stop collecting diaries and letters and resume when the user calms down. In addition, when the user is relaxed, the collection unit can proactively collect diaries and letters to provide an environment in which the user can easily respond. Furthermore, when the user is busy, the collection unit can postpone collecting diaries and letters and collect them when the user has time. In this way, the collection unit can provide an environment in which the user can easily respond by adjusting the timing of collecting diaries and letters based on the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input a user's emotional data into the generation AI, which can then analyze the data to infer the emotions, and adjust the timing of diary or letter collection based on the results.

[0113] The collection unit can analyze the user's past data collection history and select the optimal collection method when collecting a diary or a letter. The collection unit can, for example, preferentially collect data formats that the user has frequently collected in the past. The collection unit can also analyze a specific pattern from the user's past data collection history and suggest the optimal collection method. Furthermore, the collection unit can avoid data formats that the user has avoided in the past and collect formats that the user can easily collect. As a result, the collection unit can select the optimal collection method and efficiently collect data by analyzing the user's past data collection history. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's past data collection history data to the generation AI, and the generation AI can analyze the data and select the optimal collection method.

[0114] The collection unit can estimate the user's emotion and determine the priority of data to be collected based on the estimated user's emotion. For example, when the user is sad, the collection unit can preferentially collect data that is close to the emotion. In addition, when the user is excited, the collection unit can preferentially collect positive data. Furthermore, when the user is tired, the collection unit can preferentially collect data that is simple and easy to collect. In this way, the collection unit can collect data according to the user's situation by determining the priority of data 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 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 collection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and determine the priority of the data based on the result.

[0115] When collecting diaries and letters, the collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user. For example, when the user is traveling, the collection unit can preferentially collect diaries and letters related to the area. In addition, when the user is in a specific location, the collection unit can preferentially collect diaries and letters related to the location. Furthermore, the collection unit can preferentially collect diaries and letters related to the area where the user lives. In this way, the collection unit can preferentially collect highly relevant data by considering the geographical location information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data and select highly relevant data.

[0116] The evaluation unit can estimate the user's emotion and adjust the evaluation method based on the estimated user's emotion. For example, when the user is sad, the evaluation unit can provide a simple evaluation method and minimize the evaluation procedure. Also, when the user is relaxed, the evaluation unit can provide detailed evaluation options and suggest a customizable evaluation method. Furthermore, when the user is in a hurry, the evaluation unit can prioritize voice input and enable quick evaluation. In this way, the evaluation unit can provide an environment in which the user can easily evaluate by adjusting the evaluation 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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and adjust the evaluation method based on the result.

[0117] The evaluation unit can select the optimal evaluation method by referring to the user's past evaluation history at the time of evaluation. The evaluation unit can, for example, preferentially provide an evaluation format that the user has frequently used in the past. The evaluation unit can also analyze a specific pattern from the user's past evaluation history and suggest the optimal evaluation method. Furthermore, the evaluation unit can avoid evaluation formats that the user has avoided in the past and provide a format that the user can easily evaluate. Thereby, the evaluation unit can select the optimal evaluation method by referring to the user's past evaluation history and perform evaluation efficiently. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the user's past evaluation history data to the generation AI, and the generation AI can analyze the data to select the optimal evaluation method.

[0118] The evaluation unit can estimate the user's emotion and determine the priority of the evaluation based on the estimated user's emotion. For example, when the user is sad, the evaluation unit can give priority to an evaluation that is in line with the emotion. In addition, when the user is excited, the evaluation unit can give priority to a positive evaluation. Furthermore, when the user is tired, the evaluation unit can give priority to evaluating items that are easy to evaluate. In this way, the evaluation unit can perform evaluation according to the user's situation by determining the priority of the evaluation based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and determine the priority of the evaluation based on the result.

[0119] The evaluation unit can prioritize highly relevant evaluations during evaluation, taking into account the geographical location information of the user. For example, when the user is traveling, the evaluation unit can prioritize evaluations related to the area. Also, when the user is in a specific location, the evaluation unit can prioritize evaluations related to the location. Furthermore, the evaluation unit can prioritize evaluations related to the area in which the user lives. As a result, the evaluation unit can prioritize highly relevant evaluations by taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data and select a highly relevant evaluation.

[0120] The feedback unit can estimate the user's emotion and adjust the feedback method based on the estimated user's emotion. For example, when the user is sad, the feedback unit can provide a simple feedback method and minimize the feedback procedure. Also, when the user is relaxed, the feedback unit can provide detailed feedback options and suggest a customizable feedback method. Furthermore, when the user is in a hurry, the feedback unit can prioritize voice input and provide quick feedback. In this way, the feedback unit can provide an environment in which the user can easily give feedback by adjusting the feedback 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 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 feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and adjust the feedback method based on the result.

[0121] The feedback unit can select the optimal feedback method by referring to the user's past feedback history at the time of feedback. The feedback unit can, for example, preferentially provide a feedback format that the user has frequently used in the past. The feedback unit can also analyze a specific pattern from the user's past feedback history and suggest the optimal feedback method. Furthermore, the feedback unit can avoid feedback formats that the user has avoided in the past and provide a format that is easy for the user to give feedback. Thereby, the feedback unit can select the optimal feedback method by referring to the user's past feedback history and provide feedback efficiently. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can input the user's past feedback history data to the generation AI, and the generation AI can analyze the data to select the optimal feedback method.

[0122] The feedback unit can estimate the user's emotion and determine the priority of feedback based on the estimated user's emotion. For example, when the user is sad, the feedback unit can give priority to feedback that is in tune with the emotion. Also, when the user is excited, the feedback unit can give priority to positive feedback. Furthermore, when the user is tired, the feedback unit can give priority to items that are easy to provide feedback on. In this way, the feedback unit can provide feedback according to the user's situation by determining the priority of feedback 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 feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and determine the priority of feedback based on the result.

[0123] The feedback unit can give priority to highly relevant feedback in consideration of the geographical location information of the user when providing feedback. For example, when the user is traveling, the feedback unit can give priority to feedback related to the area. Also, when the user is in a specific location, the feedback unit can give priority to feedback related to the location. Furthermore, the feedback unit can give priority to feedback related to the area where the user lives. As a result, the feedback unit can give priority to highly relevant feedback by considering the geographical location information of the user. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the geographical location information data of the user to the generation AI, and the generation AI can analyze the data to select highly relevant feedback.

[0124] The analysis unit can estimate the user's emotion and adjust the context analysis method based on the estimated user's emotion. For example, if the user is sad, the analysis unit can apply an analysis method that is sympathetic to the emotion. Also, if the user is relaxed, the analysis unit can apply a detailed analysis method. Furthermore, if the user is excited, the analysis unit can apply a positive analysis method. This allows the analysis unit to adjust the context analysis method based on the user's emotion, thereby performing an analysis that is more appropriate for 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 a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI, which analyzes the data to estimate the emotion, and adjust the context analysis method based on the result.

[0125] The analysis unit can select the optimal analysis method by referring to the user's past question history when analyzing the context. The analysis unit can select the analysis method based on, for example, a question format that the user frequently used in the past. The analysis unit can also analyze a specific pattern from the user's past question history and propose the optimal analysis method. Furthermore, the analysis unit can avoid question formats that the user has avoided in the past and analyze based on a format that the user can easily answer. This allows the analysis unit to select the optimal analysis method by referring to the user's past question history and perform analysis efficiently. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can input the user's past question history data to the generation AI, and the generation AI can analyze the data to select the optimal analysis method.

[0126] The analysis unit can apply different analysis algorithms to each category of question during context analysis. For example, the analysis unit can apply a deep learning algorithm to questions about values ​​in life. The analysis unit can also apply a decision tree algorithm to questions about solving everyday problems. The analysis unit can also apply a natural language processing algorithm to questions about emotions. This allows the analysis unit to perform more appropriate analysis by applying different analysis algorithms to each category of question. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data for each category of question to a generation AI, which can then analyze the data and apply an optimal algorithm.

[0127] The analysis unit can estimate the user's emotion and determine the priority of the context analysis based on the estimated user's emotion. For example, when the user is sad, the analysis unit can preferentially analyze a context that is close to the emotion. In addition, when the user is excited, the analysis unit can preferentially analyze a positive context. Furthermore, when the user is tired, the analysis unit can preferentially analyze a simple and easy-to-analyze context. In this way, the analysis unit can perform analysis according to the user's situation by determining the priority of the context analysis based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to estimate the emotion, and determine the priority of the context analysis based on the result.

[0128] The analysis unit can determine the priority of the analysis based on the time of question submission during the context analysis. For example, the analysis unit can preferentially analyze the context of a question submitted recently. Furthermore, the analysis unit can preferentially analyze the context of a question submitted frequently in the past. Furthermore, the analysis unit can preferentially analyze the context of a question submitted in a specific period. This allows the analysis unit to perform a more appropriate analysis by determining the priority of the analysis based on the time of question submission. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input question submission time data to a generation AI, and the generation AI can analyze the data to determine the priority.

[0129] The analysis unit can adjust the order of analysis based on the relevance of the question during context analysis. For example, the analysis unit can prioritize analysis of a context with high relevance of the question. Also, the analysis unit can analyze a context with low relevance of the question later. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the question. As a result, the analysis unit can perform a more appropriate analysis by adjusting the order of analysis based on the relevance of the question. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input question relevance data to the generation AI, and the generation AI can analyze the data and adjust the order of analysis.

[0130] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0131] The consultation support system may further include a history analysis unit that analyzes the user's past consultation history. The history analysis unit may analyze the content of consultations the user has had in the past and grasp the user's consultation patterns and tendencies. For example, the history analysis unit may identify topics the user frequently consults about and the content the user frequently consults about at a particular time. The history analysis unit may also analyze the user's satisfaction with answers he or she has received in the past and extract the characteristics of answers that have satisfied the user. Furthermore, the history analysis unit may predict future consultation contents based on the user's consultation history and provide related information at an appropriate time. This allows the history analysis unit to provide more personalized consultation support by utilizing the user's past consultation history.

[0132] The collection unit can analyze the user's social media activity and collect questions related to topics in which the user is interested. For example, the collection unit can analyze the content frequently posted by the user and the topics of accounts followed by the user, and generate questions based on the analysis. The collection unit can also analyze comments and reactions received by the user on social media, and identify themes in which the user is interested. Furthermore, the collection unit can collect questions at optimal timing, taking into account the time period during which the user is active on social media. This allows the collection unit to collect more relevant questions by utilizing the user's social media activity.

[0133] The evaluation unit can collect user feedback in real time and immediately reflect it in improvements to the system. For example, the evaluation unit can request an evaluation immediately after the user receives an answer, and immediately analyze the evaluation result to adjust the system's algorithm. The evaluation unit can also reflect the feedback provided by the user when generating the next answer. Furthermore, the evaluation unit can accumulate user feedback and use it to improve the system over the long term. In this way, the evaluation unit can provide a system that always meets the latest user needs by quickly reflecting user feedback.

[0134] The feedback unit can make adjustments to improve the degree of personalization of the system based on the user's feedback. For example, the feedback unit can analyze the feedback provided by the user and customize the system settings to suit the user's preferences and needs. The feedback unit can also improve the system's interface and functions based on the user's feedback. Furthermore, the feedback unit can utilize the user's feedback to suggest new functions and services. In this way, the feedback unit can provide a more personalized system by utilizing the user's feedback.

[0135] The analysis unit can utilize external data sources to improve the accuracy of answers to user questions. For example, the analysis unit can collect public databases on the Internet and expert opinions and generate answers based on them. The analysis unit can also analyze additional information provided by the user to provide a more detailed answer. Furthermore, the analysis unit can refer to questions and answers from other users to generate optimal answers to similar questions. This allows the analysis unit to utilize external data sources to provide more accurate answers.

[0136] The collection unit can estimate the user's emotions and adjust the content of the questions based on the estimated emotions. For example, when the user is sad, the collection unit can collect kind questions that are sympathetic to the user's emotions. When the user is excited, positive questions can be collected. When the user is tired, simple and easy-to-answer questions can be collected. In this way, the collection unit can provide an environment in which the user can easily answer questions by adjusting the content of the questions based on the user's emotions.

[0137] The learning unit can estimate the user's emotions and select learning data based on the estimated emotions. For example, if the user is sad, data including answers that empathize with the user's emotions can be preferentially learned. Also, if the user is relaxed, data including detailed explanations can be preferentially learned. Furthermore, if the user is excited, data including positive answers can be preferentially learned. In this way, the learning unit can learn more appropriate thinking patterns by selecting learning data based on the user's emotions.

[0138] The reception unit can estimate the user's emotion and adjust the method of receiving a question based on the estimated emotion. For example, if the user is sad, a simple interface can be provided and input procedures can be minimized. Also, if the user is relaxed, detailed input options can be provided and a customizable input method can be suggested. Furthermore, if the user is in a hurry, voice input can be prioritized so that questions can be quickly received. In this way, the reception unit can provide an environment in which the user can easily ask questions by adjusting the method of receiving a question based on the user's emotion.

[0139] The generation unit can estimate the user's emotion and adjust the way the answer is expressed based on the estimated emotion. For example, if the user is sad, an answer can be generated using gentle language. If the user is relaxed, an answer including detailed explanations can be generated. If the user is excited, an answer using a lot of positive expressions can be generated. In this way, the generation unit can provide a more appropriate answer for the user by adjusting the way the answer is expressed based on the user's emotion.

[0140] The collection unit can estimate the user's emotions and adjust the timing of collecting diaries and letters based on the estimated emotions. For example, if the user is sad, collection of diaries and letters can be temporarily stopped and resumed when the user has calmed down. Also, if the user is relaxed, collection of diaries and letters can be proactively performed to provide an environment in which the user can easily respond. Furthermore, if the user is busy, collection of diaries and letters can be postponed and collected when the user has time. In this way, the collection unit can provide an environment in which the user can easily respond by adjusting the timing of collecting diaries and letters based on the user's emotions.

[0141] The process flow of the second embodiment will be briefly described below.

[0142] Step 1: The collection unit asks 100 questions to people the user respects and collects their answers. For example, the collection unit can ask the user questions such as "What values ​​do you value most in your life?" and "When you are faced with a difficult situation, how do you deal with it?" and collect the answers. The collection unit can collect questions in various formats, such as text format, audio format, and questions about a specific topic. Step 2: The learning unit learns thinking patterns based on the questions collected by the collection unit. For example, the learning unit learns thinking patterns such as logical thinking, creative thinking, and problem-solving approaches based on the collected answer data. The learning unit can use a machine learning algorithm to preprocess the collected data and learn thinking patterns. Step 3: The reception unit receives a question from the user. For example, the reception unit provides an interface for the user to input what he or she wants to discuss with his or her father. The reception unit can receive questions in various formats, such as text format and voice format. Step 4: The generation unit generates an answer based on the question received by the reception unit. For example, when a user inputs a question such as "I'm thinking of trying a new job. What do you think?", the generation unit uses the generation AI to generate an answer based on the father's thought patterns. The generation unit can use the generation AI to apply the thought patterns learned from the collected data and generate an appropriate answer to the user's question.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements including the above-mentioned collection unit, learning unit, reception unit, generation unit, evaluation unit, feedback unit, analysis unit, and emotion estimation function is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart device 14, and asks questions to people the user respects and collects their answers. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns a thought pattern based on the collected answer data. The reception unit is realized, for example, by the control unit 46A of the smart device 14, and receives a question from the user. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an answer to the user's question. The evaluation unit is realized, for example, by the control unit 46A of the smart device 14, and evaluates the answer generated by the user. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and improves the accuracy of the system based on the evaluation data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the context of the user's question. The emotion estimation function is realized, for example, by the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the collection timing. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0147] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements including the above-mentioned collection unit, learning unit, reception unit, generation unit, evaluation unit, feedback unit, analysis unit, and emotion estimation function is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart glasses 214, and asks questions to people the user respects and collects their answers. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns a thought pattern based on the collected answer data. The reception unit is realized, for example, by the control unit 46A of the smart glasses 214, and receives a question from the user. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an answer to the user's question. The evaluation unit is realized, for example, by the control unit 46A of the smart glasses 214, and evaluates the answer generated by the user. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and improves the accuracy of the system based on the evaluation data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the context of the user's question. The emotion estimation function is realized, for example, by the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the collection timing. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0163] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements including the above-mentioned collection unit, learning unit, reception unit, generation unit, evaluation unit, feedback unit, analysis unit, and emotion estimation function is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the headset type terminal 314, and asks questions to people the user respects and collects their answers. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns a thought pattern based on the collected answer data. The reception unit is realized, for example, by the control unit 46A of the headset type terminal 314, and receives a question from the user. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an answer to the user's question. The evaluation unit is realized, for example, by the control unit 46A of the headset type terminal 314, and evaluates the answer generated by the user. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and improves the accuracy of the system based on the evaluation data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the context of the user's question. The emotion estimation function is realized, for example, by the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the collection timing. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0179] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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).

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] Each of the multiple elements including the above-mentioned collection unit, learning unit, reception unit, generation unit, evaluation unit, feedback unit, analysis unit, and emotion estimation function is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the robot 414, and asks questions to people the user respects and collects their answers. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns a thought pattern based on the collected answer data. The reception unit is realized, for example, by the control unit 46A of the robot 414, and receives a question from the user. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an answer to the user's question. The evaluation unit is realized, for example, by the control unit 46A of the robot 414, and evaluates the answer generated by the user. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and improves the accuracy of the system based on the evaluation data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the context of the user's question. The emotion estimation function is realized, for example, by the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the collection timing. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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."

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] (Appendix 1) A collection unit that collects questions; a learning unit that learns a thought pattern based on the questions collected by the collection unit; a reception unit for receiving a question from a user; A generating unit that generates an answer based on the question received by the receiving unit. A system characterized by: (Appendix 2) Have a collection department to collect diary entries, letters and other data 2. The system of claim 1, (Appendix 3) An evaluation section is provided whereby the user evaluates the answers. 2. The system of claim 1, (Appendix 4) Equipped with a feedback section that uses evaluation data as feedback 2. The system of claim 1, (Appendix 5) Equipped with an analysis section that performs context analysis 2. The system of claim 1, (Appendix 6) The collecting unit includes: We also collected data from diaries and letters. The learning unit uses it. 2. The system of claim 1, (Appendix 7) The evaluation unit is Evaluating the answer generated by the generation unit; The feedback unit utilizes the evaluation data to improve the accuracy of the generator. 2. The system of claim 1, (Appendix 8) The analysis unit is Analyzing a context of the question received by the reception unit; The generator helps generate appropriate answers. 2. The system of claim 1, (Appendix 9) The collecting unit includes: Estimate the user's emotions, Adjust the timing of question collection based on estimated user sentiment 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting questions, analyze the user's past question history and select appropriate questions. 2. The system of claim 1, (Appendix 11) The collecting unit includes: As questions are collected, they are filtered based on the user's current interests and life situation. 2. The system of claim 1, (Appendix 12) The collecting unit includes: Estimate the user's emotions, Prioritize questions to collect based on estimated user sentiment 2. The system of claim 1, (Appendix 13) The collecting unit includes: When collecting questions, the system takes into account the user's geographic location to prioritize collecting the most relevant questions. 2. The system of claim 1, (Appendix 14) The collecting unit includes: When collecting questions, analyze users' social media activity to collect related questions. 2. The system of claim 1, (Appendix 15) The learning unit is Estimate the user's emotions, Select learning data based on estimated user emotions 2. The system of claim 1, (Appendix 16) The learning unit is During training, the learning algorithm is adjusted by referencing past training data. 2. The system of claim 1, (Appendix 17) The learning unit is During training, different learning algorithms are applied to different categories of questions. 2. The system of claim 1, (Appendix 18) The learning unit is Estimate the user's emotions, Adjust the frequency of learning based on estimated user sentiment 2. The system of claim 1, (Appendix 19) The learning unit is During training, the training data is weighted based on when the question was submitted 2. The system of claim 1, (Appendix 20) The learning unit is During training, prioritize training data based on question relevance 2. The system of claim 1, (Appendix 21) The reception unit is Estimate the user's emotions, Adjust how questions are accepted based on estimated user sentiment 2. The system of claim 1, (Appendix 22) The reception unit is When accepting a question, the system selects the most appropriate method of acceptance by referring to the user's past question history. 2. The system of claim 1, (Appendix 23) The reception unit is As questions are submitted, they are filtered based on the user's current interests and life situation. 2. The system of claim 1, (Appendix 24) The reception unit is Estimate the user's emotions, Prioritize questions to be accepted based on estimated user sentiment 2. The system of claim 1, (Appendix 25) 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 26) The reception unit is When a question is submitted, we analyze the user's social media activity and submit related questions. 2. The system of claim 1, (Appendix 27) The generation unit is Estimate the user's emotions, Adjust the way you phrase your answers based on the estimated user sentiment 2. The system of claim 1, (Appendix 28) The generation unit is When generating answers, adjust the detail of the answer based on the importance of the question 2. The system of claim 1, (Appendix 29) The generation unit is When generating answers, different generation algorithms are applied depending on the question category. 2. The system of claim 1, (Appendix 30) The generation unit is Estimate the user's emotions, Adjust the length of answers based on estimated user sentiment 2. The system of claim 1, (Appendix 31) The generation unit is When generating answers, prioritize answers based on when the question was submitted 2. The system of claim 1, (Appendix 32) The generation unit is During answer generation, adjust the order of answers based on the relevance of the question 2. The system of claim 1, (Appendix 33) The collecting unit includes: Estimate the user's emotions, Adjusting the timing of diary and letter collection based on estimated user emotions 3. The system of claim 2, (Appendix 34) The collecting unit includes: When collecting diaries or letters, the system analyzes the user's past data collection history and selects the appropriate collection method. 3. The system of claim 2, (Appendix 35) The collecting unit includes: Estimate the user's emotions, Prioritize data collection based on estimated user sentiment 3. The system of claim 2, (Appendix 36) The collecting unit includes: When collecting diaries and letters, the system prioritizes the collection of relevant data by taking into account the user's geographic location information. 3. The system of claim 2, (Appendix 37) The evaluation unit is Estimate the user's emotions, Adjust the rating method based on estimated user sentiment 4. The system of claim 3. (Appendix 38) The evaluation unit is When evaluating, the appropriate evaluation method is selected by referring to the user's past evaluation history. 4. The system of claim 3. (Appendix 39) The evaluation unit is Estimate the user's emotions, Prioritize ratings based on estimated user sentiment 4. The system of claim 3. (Appendix 40) The evaluation unit is When rating, the app takes into account the user's geographic location to prioritize more relevant ratings 4. The system of claim 3. (Appendix 41) The feedback unit is Estimate the user's emotions, Adjusting feedback methods based on estimated user emotions 5. The system of claim 4. (Appendix 42) The feedback unit is When providing feedback, select the appropriate feedback method by referring to the user's past feedback history. 5. The system of claim 4. (Appendix 43) The feedback unit is Estimate the user's emotions, Prioritize feedback based on estimated user sentiment 5. The system of claim 4. (Appendix 44) The feedback unit is When providing feedback, the geographic location of the user is taken into consideration to prioritize the most relevant feedback. 5. The system of claim 4. (Appendix 45) The analysis unit is Estimate the user's emotions, Adjusting the context analysis method based on estimated user sentiment 6. The system of claim 5, (Appendix 46) The analysis unit is When analyzing the context, the appropriate analysis method is selected by referring to the user's past question history. 6. The system of claim 5, (Appendix 47) The analysis unit is During context analysis, different analysis algorithms are applied to different categories of questions 6. The system of claim 5, (Appendix 48) The analysis unit is Estimate the user's emotions, Prioritizing context analysis based on estimated user sentiment 6. The system of claim 5, (Appendix 49) The analysis unit is During context analysis, prioritize analysis based on when the question was submitted 6. The system of claim 5, (Appendix 50) The analysis unit is During context analysis, adjust the order of analysis based on question relevance 6. The system of claim 5, [Explanation of symbols]

[0215] 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 collection unit that collects questions; a learning unit that learns a thought pattern based on the questions collected by the collection unit; a reception unit for receiving a question from a user; A generating unit that generates an answer based on the question received by the receiving unit. A system characterized by:

2. The collecting unit includes: The user's emotions are estimated, and the timing of collecting questions is adjusted based on the estimated user's emotions.

2. The system of claim 1 .

3. an evaluation unit in which the user evaluates the answers; A feedback unit that uses the evaluation data as feedback.

2. The system of claim 1 .

4. Equipped with an analysis section that performs context analysis 2. The system of claim 1 .

5. The collecting unit includes: We also collected data from diaries and letters. The learning unit uses it.

2. The system of claim 1 .

6. The evaluation unit is Evaluating the answer generated by the generation unit; The feedback unit utilizes the evaluation data to improve the accuracy of the generator.

4. The system of claim 3.

7. The analysis unit is Analyzing a context of the question received by the reception unit; The generator helps generate appropriate answers.

5. The system of claim 4.

Images