System

Abstract

An object of the system according to the embodiment is to grow based on knowledge and experience of the owner and to actively talk to the owner.SOLUTION: A system according to an embodiment includes a knowledge growing unit, a dialog starting unit, and a knowledge updating unit. The knowledge growth portion grows based on the knowledge and experience of the owner. The dialog starter actively talks to the owner based on the knowledge grown by the knowledge grower. The knowledge updating unit periodically updates the knowledge grown by the knowledge growing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the generated AI did not grow based on the owner's knowledge and experience, and had the problem of not being able to actively talk to the owner.

[0005] The system according to the embodiment aims to grow based on the knowledge and experience of the owner and to actively talk to the owner. [Means for solving the problem]

[0006] The system according to the embodiment includes a knowledge growth unit, a dialogue initiation unit, and a knowledge update unit. The knowledge growth unit grows based on the knowledge and experience of the knowledge owner. The dialogue initiation unit actively speaks to the knowledge owner based on the knowledge grown by the knowledge growth unit. The knowledge update unit periodically updates the knowledge grown by the knowledge growth unit. [Effects of the Invention]

[0007] The system according to the embodiment grows based on the knowledge and experience of the owner and can actively talk to the owner. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The generative AI service according to the embodiment of the present invention is a service that grows in accordance with the knowledge and experience of its owner and actively engages with the owner. This allows the generative AI service to update its knowledge base in accordance with the owner's growth, and is the first step towards creating a human-like artificial general intelligence (AGI).

[0029] A generative AI service according to an embodiment includes a knowledge growth unit, a dialogue initiation unit, and a knowledge update unit. The knowledge growth unit grows based on the knowledge and experience of the user. For example, if the user learns a new language, the knowledge growth unit learns that language and becomes able to converse at the same level as the user. The knowledge growth unit also learns based on prompts including the content and experience of the user. The dialogue initiation unit actively speaks to the user based on the knowledge grown by the knowledge growth unit. For example, the dialogue initiation unit spontaneously provides advice and information in response to problems and questions the user faces in daily life. The dialogue initiation unit also generates appropriate dialogue based on prompts that reflect the user's situation and emotions. The knowledge update unit regularly updates the knowledge grown by the knowledge growth unit. For example, if the user acquires knowledge in a new field, the knowledge update unit learns the knowledge in that field and provides appropriate advice to the user. The knowledge update unit also regularly updates its own knowledge base as the user grows. As a result, the generative AI service of the embodiment grows based on the owner's knowledge and experience, and by actively talking to it, it can update its knowledge base in line with the owner's growth.

[0030] The knowledge growth unit can analyze learning history in real time and predict and suggest the next piece of knowledge to learn. For example, if the user is taking an online course, the knowledge growth unit analyzes the progress data in real time and uses a generation AI to suggest the next topic to learn. For example, if the user is learning the basics of programming, the unit suggests the algorithm or data structure to learn next. The knowledge growth unit also uses an algorithm to predict the next piece of knowledge to learn based on the user's learning history. For example, it predicts the next piece of knowledge to learn based on the topics the user has learned in the past and their learning outcomes. The knowledge growth unit also takes into account the format and timing of the suggestion when suggesting predicted knowledge. For example, it makes suggestions during times when the user is concentrating on studying. In this way, learning efficiency can be improved by analyzing the user's learning history and suggesting the next piece of knowledge to learn.

[0031] The knowledge growth unit can analyze a user's learning style and automatically generate learning content optimized for that style. For example, if the user has a visual learning style, the generation AI in the knowledge growth unit automatically generates visual learning materials (videos, infographics, etc.). For example, if the user is studying history, the generation AI can generate videos that visually explain historical events. The knowledge growth unit also analyzes the user's learning style based on styles such as visual, auditory, and tactile. For example, if the user has an auditory learning style, the generation AI can generate audio learning materials. The knowledge growth unit also takes into account optimization criteria and algorithms when generating learning content optimized for a user's learning style. For example, the generation AI can generate content tailored to the user's learning pace and level of understanding. This maximizes learning effectiveness by providing learning content optimized for the user's learning style.

[0032] The dialogue initiation unit analyzes the dialogue history, predicts the next topic to discuss, and can start the dialogue at an appropriate time. For example, the dialogue initiation unit analyzes the owner's past dialogue history, and the generation AI predicts the next topic to discuss. For example, it suggests related topics based on topics that the owner has recently been interested in. The dialogue initiation unit also uses an algorithm to predict the next topic to discuss based on the owner's dialogue history. For example, it predicts the next topic to discuss based on what the owner has previously said and the results of the dialogue. The dialogue initiation unit also takes into account the owner's schedule and frequency of dialogue to determine the appropriate time to start the dialogue. For example, it can start the dialogue when the owner is relaxed. In this way, by analyzing the owner's dialogue history and starting the dialogue at an appropriate time, it is possible to provide a dialogue that will interest the owner.

[0033] The dialogue initiation unit can analyze the owner's lifestyle and automatically adjust the schedule so that the generation AI speaks at the optimal timing. The dialogue initiation unit, for example, analyzes the owner's lifestyle and automatically adjusts the schedule so that the generation AI speaks at the optimal timing. For example, if the owner is most relaxed in the morning, the generation AI will speak at that time. The dialogue initiation unit also analyzes the owner's lifestyle based on their sleep patterns and activity levels to analyze the owner's lifestyle. For example, if the owner has a nocturnal lifestyle, the generation AI will speak to them in the evening. The dialogue initiation unit also takes into account the algorithms and adjustment criteria used when automatically adjusting the schedule. For example, the dialogue timing is adjusted to match the owner's schedule. This makes it possible to provide more effective dialogue by adjusting the dialogue timing to match the owner's lifestyle.

[0034] The knowledge update unit can periodically evaluate the learning progress and automatically update the knowledge base based on that evaluation. For example, the knowledge update unit periodically evaluates the learning progress of the owner, and builds a system in which the generation AI automatically updates the knowledge base based on that evaluation. For example, when the owner acquires a new skill, information related to that skill is added to the knowledge base. In addition, to evaluate the learning progress, the knowledge update unit performs an evaluation based on the learning achievement level and learning speed. For example, when the owner achieves a certain learning goal, the progress is evaluated. In addition, when automatically updating the knowledge base, the knowledge update unit takes into account the algorithm to be used and the timing of the update. For example, the knowledge base is updated to match the owner's learning pace. In this way, by evaluating the owner's learning progress and automatically updating the knowledge base, it is possible to always provide the latest knowledge.

[0035] The knowledge updating unit can analyze the learning content and automatically collect the latest research papers and articles related to that content and add them to the knowledge base. For example, the knowledge updating unit analyzes the learning content of the owner, and the generation AI automatically collects the latest research papers related to that content and adds them to the knowledge base. For example, if the owner is studying machine learning, the knowledge updating unit collects the latest papers on machine learning. In addition, to analyze the learning content, the knowledge updating unit performs an analysis based on the learning topic and depth of learning. For example, if the owner is deepening their knowledge in a particular field, the knowledge updating unit collects the latest information related to that field. In addition, when collecting research papers and articles, the knowledge updating unit takes into account the database used and the frequency of collection. For example, the knowledge updating unit periodically searches a database to collect the latest information. In this way, the latest information related to the owner's learning content is automatically collected and added to the knowledge base, thereby always providing the latest knowledge.

[0036] The knowledge update unit can build a platform for sharing the knowledge base with other generation AI users and collaboratively updating knowledge. For example, the knowledge update unit builds an online platform for sharing the owner's knowledge base with other generation AI users and collaboratively updating knowledge. For example, the owner can share what they have learned with other users and collaboratively deepen their knowledge. In addition, the knowledge update unit takes into account the attributes of the generation AI users and the type of AI used to share the knowledge base. For example, it matches users with knowledge in the same field. In addition, the knowledge update unit takes into account the technology to be used and the functions to be provided when building the platform. For example, it provides online forums and chat functions. This allows the owner's knowledge base to be shared with other users and collaboratively updating knowledge, thereby promoting the deepening and expansion of knowledge.

[0037] The knowledge updating unit can visualize the knowledge base, identify knowledge gaps, and suggest learning content to fill those gaps. The knowledge updating unit, for example, builds a system that visualizes the user's knowledge base and identifies knowledge gaps. For example, it displays topics learned by the user in mind map format and identifies unstudied topics. The knowledge updating unit also performs analysis based on learning achievement and unstudied topics to identify knowledge gaps. For example, if the user is deepening their knowledge in a particular field, it identifies unstudied topics related to that field. The knowledge updating unit also takes into account the tools to be used and the format of the suggestion when suggesting learning content to fill knowledge gaps. For example, it suggests visual teaching materials or interactive learning content. This makes it possible to improve learning efficiency by visualizing the user's knowledge base, identifying knowledge gaps, and suggesting learning content to fill them.

[0038] The dialogue initiation unit can provide a function for sharing the content of the dialogue with other generated AI users and connecting users with common interests. For example, the dialogue initiation unit shares the content of the owner's dialogue with other generated AI users to build an online community that connects users with common interests. For example, it matches users with the same hobbies. The dialogue initiation unit also considers how to analyze the content of the dialogue and match users in order to connect users with common interests. For example, it identifies common interests based on the content of the owner's dialogue. The dialogue initiation unit also considers the technology to be used and the functions to be provided when building a platform for connection. For example, it provides an online forum or chat function. This allows the content of the owner's dialogue to be shared and connects users with common interests, thereby promoting the formation of a community.

[0039] The dialogue initiation unit can automatically suggest events and news related to the owner's hobbies and interests based on the dialogue history. For example, the dialogue initiation unit analyzes the owner's dialogue history, and the generation AI automatically suggests events related to the owner's hobbies and interests. For example, if the owner is interested in music, it suggests nearby concerts. The dialogue initiation unit also considers how to analyze the dialogue content and how to classify hobbies and interests in order to identify the owner's hobbies and interests based on the owner's dialogue history. For example, it identifies hobbies and interests based on content that the owner has previously spoken about. The dialogue initiation unit also considers the timing and format of the suggestion when suggesting events and news. For example, it makes suggestions during times when the owner is relaxing. This makes it possible to continue to attract the owner's interest by suggesting related events and news based on the owner's dialogue history.

[0040] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0041] The generative AI service can also monitor the owner's health and provide health advice. For example, it can collect the owner's dietary and exercise data and suggest a balanced diet and appropriate exercise plan. It can also analyze the owner's sleep patterns and provide advice on how to get better quality sleep. Furthermore, if the owner is feeling stressed, it can suggest relaxation techniques and stress management methods. This allows it to provide comprehensive support for the owner's health and provide advice on how to live a healthier life.

[0042] The generative AI service can also suggest new hobbies and activities based on the owner's hobbies and interests. For example, if the owner is interested in music, it can suggest new ways to play instruments or create music. If the owner is interested in outdoor activities, it can provide ideas for new hiking trails and camping trips. Furthermore, if the owner is interested in art, it can suggest new art projects and techniques. This allows the service to provide suggestions for expanding the owner's hobbies and interests and enjoying new activities.

[0043] The generative AI service can also provide a platform for sharing the owner's learning progress with other users and for collaborative learning. For example, if the owner is learning about a particular topic, they can form a study group with other users who are interested in that topic and work together to advance their learning. The owner can also share with other users any problems or questions they encounter while studying and hold discussions to find solutions. Furthermore, by sharing what they have learned with other users and receiving feedback, the effectiveness of their learning can be improved. This can support the owner's learning and provide a platform for collaborative learning.

[0044] The generative AI service can analyze the user's learning history and provide a customized learning plan to maximize the effectiveness of their learning. For example, it can suggest the next topic to study and the learning method based on the content the user has learned in the past and their learning outcomes. It can also create an optimal learning plan that suits the user's learning style and pace. It can also provide appropriate resources and support for any problems or questions the user faces while studying. In this way, by providing a customized learning plan based on the user's learning history, it can maximize the effectiveness of learning and support the user's growth.

[0045] The generative AI service can visualize the user's learning progress and provide feedback to increase motivation to learn. For example, it can visualize the user's achieved learning goals and progress using graphs and charts, allowing the user to feel a sense of accomplishment. It can also maintain the user's motivation to learn by clearly indicating the next goal to be achieved and learning steps the user should take. Furthermore, it can improve the effectiveness of learning by providing appropriate resources and support for problems and questions the user faces during learning. In this way, it can support the user's growth by visualizing the user's learning progress and providing feedback to increase motivation to learn.

[0046] The generative AI service can also share the owner's learning history with other users and build an online community for collaborative learning. For example, if the owner is studying a particular topic, they can form a study group with other users who are interested in that topic and study together. The owner can also share with other users any problems or questions they encounter while studying and hold discussions to find solutions. Furthermore, by sharing what they have learned with other users and receiving feedback, the effectiveness of their learning can be improved. This makes it possible to provide an online community that supports the owner's learning and allows them to study together.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The knowledge growth section grows based on the owner's knowledge and experience. For example, if the owner learns a new language, the knowledge growth section learns that language and becomes able to converse at the same level as the owner. The knowledge growth section also learns based on prompts that include the owner's knowledge and experience. Step 2: The dialogue initiator actively engages with the user based on the knowledge developed by the knowledge growth component. For example, the dialogue initiator spontaneously provides advice and information in response to problems or questions the user faces in daily life. The dialogue initiator also generates appropriate dialogue based on prompts that reflect the user's situation and emotions. Step 3: The knowledge update unit periodically updates the knowledge developed by the knowledge growth unit. For example, when the user acquires knowledge in a new field, the knowledge update unit learns the knowledge in that field and provides appropriate advice to the user. The knowledge update unit also periodically updates its own knowledge base as the user grows.

[0049] (Example 2) The generative AI service according to the embodiment of the present invention is a service that grows in accordance with the knowledge and experience of its owner and actively engages with the owner. This allows the generative AI service to update its knowledge base in accordance with the owner's growth, and is the first step towards creating a human-like artificial general intelligence (AGI).

[0050] A generative AI service according to an embodiment includes a knowledge growth unit, a dialogue initiation unit, and a knowledge update unit. The knowledge growth unit grows based on the knowledge and experience of the user. For example, if the user learns a new language, the knowledge growth unit learns that language and becomes able to converse at the same level as the user. The knowledge growth unit also learns based on prompts including the content and experience of the user. The dialogue initiation unit actively speaks to the user based on the knowledge grown by the knowledge growth unit. For example, the dialogue initiation unit spontaneously provides advice and information in response to problems and questions the user faces in daily life. The dialogue initiation unit also generates appropriate dialogue based on prompts that reflect the user's situation and emotions. The knowledge update unit regularly updates the knowledge grown by the knowledge growth unit. For example, if the user acquires knowledge in a new field, the knowledge update unit learns the knowledge in that field and provides appropriate advice to the user. The knowledge update unit also regularly updates its own knowledge base as the user grows. As a result, the generative AI service of the embodiment grows based on the owner's knowledge and experience, and by actively talking to it, it can update its knowledge base in line with the owner's growth.

[0051] The knowledge growth unit can analyze learning history in real time and predict and suggest the next piece of knowledge to learn. For example, if the user is taking an online course, the knowledge growth unit analyzes the progress data in real time and uses a generation AI to suggest the next topic to learn. For example, if the user is learning the basics of programming, the unit suggests the algorithm or data structure to learn next. The knowledge growth unit also uses an algorithm to predict the next piece of knowledge to learn based on the user's learning history. For example, it predicts the next piece of knowledge to learn based on the topics the user has learned in the past and their learning outcomes. The knowledge growth unit also takes into account the format and timing of the suggestion when suggesting predicted knowledge. For example, it makes suggestions during times when the user is concentrating on studying. In this way, learning efficiency can be improved by analyzing the user's learning history and suggesting the next piece of knowledge to learn.

[0052] The knowledge growth unit can analyze a user's learning style and automatically generate learning content optimized for that style. For example, if the user has a visual learning style, the generation AI in the knowledge growth unit automatically generates visual learning materials (videos, infographics, etc.). For example, if the user is studying history, the generation AI can generate videos that visually explain historical events. The knowledge growth unit also analyzes the user's learning style based on styles such as visual, auditory, and tactile. For example, if the user has an auditory learning style, the generation AI can generate audio learning materials. The knowledge growth unit also takes into account optimization criteria and algorithms when generating learning content optimized for a user's learning style. For example, the generation AI can generate content tailored to the user's learning pace and level of understanding. This maximizes learning effectiveness by providing learning content optimized for the user's learning style.

[0053] The knowledge growth unit uses the emotion estimation function to detect stress or excitement felt by the user while studying and adjust the progress of the study. For example, the knowledge growth unit detects the stress felt by the user while studying, and the generation AI suggests taking a break to relax. For example, if the user is tired after studying for a long time, it suggests a short break or relaxation exercises. The knowledge growth unit also detects the excitement felt by the user while studying and adjusts the progress of the study. For example, if the user is excited, it suggests speeding up the pace of study. The knowledge growth unit also uses the emotion estimation function to analyze the user's emotional state in real time. For example, it estimates emotions based on changes in heart rate and facial expression analysis. This allows the learning effect to be maximized by adjusting the progress of the study according to the user's emotional state.

[0054] The dialogue initiation unit analyzes the dialogue history, predicts the next topic to discuss, and can start the dialogue at an appropriate time. For example, the dialogue initiation unit analyzes the owner's past dialogue history, and the generation AI predicts the next topic to discuss. For example, it suggests related topics based on topics that the owner has recently been interested in. The dialogue initiation unit also uses an algorithm to predict the next topic to discuss based on the owner's dialogue history. For example, it predicts the next topic to discuss based on what the owner has previously said and the results of the dialogue. The dialogue initiation unit also takes into account the owner's schedule and frequency of dialogue to determine the appropriate time to start the dialogue. For example, it can start the dialogue when the owner is relaxed. In this way, by analyzing the owner's dialogue history and starting the dialogue at an appropriate time, it is possible to provide a dialogue that will interest the owner.

[0055] The dialogue initiation unit can analyze the owner's lifestyle and automatically adjust the schedule so that the generation AI speaks at the optimal timing. The dialogue initiation unit, for example, analyzes the owner's lifestyle and automatically adjusts the schedule so that the generation AI speaks at the optimal timing. For example, if the owner is most relaxed in the morning, the generation AI will speak at that time. The dialogue initiation unit also analyzes the owner's lifestyle based on their sleep patterns and activity levels to analyze the owner's lifestyle. For example, if the owner has a nocturnal lifestyle, the generation AI will speak to them in the evening. The dialogue initiation unit also takes into account the algorithms and adjustment criteria used when automatically adjusting the schedule. For example, the dialogue timing is adjusted to match the owner's schedule. This makes it possible to provide more effective dialogue by adjusting the dialogue timing to match the owner's lifestyle.

[0056] The dialogue initiation unit uses the emotion estimation function to analyze the owner's emotional state in real time and can speak with an appropriate tone and content. For example, the dialogue initiation unit uses the emotion estimation function to analyze the owner's emotional state in real time, and the generation AI speaks with an appropriate tone. For example, if the owner is tired, it speaks with a gentle tone. The dialogue initiation unit also speaks with appropriate content based on the owner's emotional state. For example, if the owner is feeling stressed, it suggests ways to relax. The dialogue initiation unit also uses the emotion estimation function to perform facial expression analysis and voice analysis to analyze the owner's emotional state. For example, it infers emotions based on changes in the owner's facial expression and tone of voice. This makes it possible to provide a more effective dialogue by speaking with an appropriate tone and content according to the owner's emotional state.

[0057] The knowledge update unit can periodically evaluate the learning progress and automatically update the knowledge base based on that evaluation. For example, the knowledge update unit periodically evaluates the learning progress of the owner, and builds a system in which the generation AI automatically updates the knowledge base based on that evaluation. For example, when the owner acquires a new skill, information related to that skill is added to the knowledge base. In addition, to evaluate the learning progress, the knowledge update unit performs an evaluation based on the learning achievement level and learning speed. For example, when the owner achieves a certain learning goal, the progress is evaluated. In addition, when automatically updating the knowledge base, the knowledge update unit takes into account the algorithm to be used and the timing of the update. For example, the knowledge base is updated to match the owner's learning pace. In this way, by evaluating the owner's learning progress and automatically updating the knowledge base, it is possible to always provide the latest knowledge.

[0058] The knowledge updating unit can analyze the learning content and automatically collect the latest research papers and articles related to that content and add them to the knowledge base. For example, the knowledge updating unit analyzes the learning content of the owner, and the generation AI automatically collects the latest research papers related to that content and adds them to the knowledge base. For example, if the owner is studying machine learning, the knowledge updating unit collects the latest papers on machine learning. In addition, to analyze the learning content, the knowledge updating unit performs an analysis based on the learning topic and depth of learning. For example, if the owner is deepening their knowledge in a particular field, the knowledge updating unit collects the latest information related to that field. In addition, when collecting research papers and articles, the knowledge updating unit takes into account the database used and the frequency of collection. For example, the knowledge updating unit periodically searches a database to collect the latest information. In this way, the latest information related to the owner's learning content is automatically collected and added to the knowledge base, thereby always providing the latest knowledge.

[0059] The knowledge updating unit can use the emotion estimation function to analyze the owner's emotional reactions when acquiring new knowledge and provide feedback to maximize the effectiveness of learning. For example, the knowledge updating unit can use the emotion estimation function to analyze the owner's emotional reactions when acquiring new knowledge, and the generation AI can provide feedback to maximize the effectiveness of learning. For example, the knowledge updating unit can suggest that the owner should continue learning when they are excited. The knowledge updating unit can also provide feedback to maximize the effectiveness of learning based on the owner's emotional reactions. For example, the knowledge updating unit can suggest that the owner should continue learning when they are relaxed. The knowledge updating unit can also use the emotion estimation function to perform facial expression analysis and voice analysis to analyze the owner's emotional reactions. For example, the knowledge updating unit can estimate emotions based on changes in the owner's facial expressions and tone of voice. This can maximize the effectiveness of learning by providing feedback based on the owner's emotional reactions.

[0060] The knowledge update unit can build a platform for sharing the knowledge base with other generation AI users and collaboratively updating knowledge. For example, the knowledge update unit builds an online platform for sharing the owner's knowledge base with other generation AI users and collaboratively updating knowledge. For example, the owner can share what they have learned with other users and collaboratively deepen their knowledge. In addition, the knowledge update unit takes into account the attributes of the generation AI users and the type of AI used to share the knowledge base. For example, it matches users with knowledge in the same field. In addition, the knowledge update unit takes into account the technology to be used and the functions to be provided when building the platform. For example, it provides online forums and chat functions. This allows the owner's knowledge base to be shared with other users and collaboratively updating knowledge, thereby promoting the deepening and expansion of knowledge.

[0061] The knowledge updating unit can visualize the knowledge base, identify knowledge gaps, and suggest learning content to fill those gaps. The knowledge updating unit, for example, builds a system that visualizes the user's knowledge base and identifies knowledge gaps. For example, it displays topics learned by the user in mind map format and identifies unstudied topics. The knowledge updating unit also performs analysis based on learning achievement and unstudied topics to identify knowledge gaps. For example, if the user is deepening their knowledge in a particular field, it identifies unstudied topics related to that field. The knowledge updating unit also takes into account the tools to be used and the format of the suggestion when suggesting learning content to fill knowledge gaps. For example, it suggests visual teaching materials or interactive learning content. This makes it possible to improve learning efficiency by visualizing the user's knowledge base, identifying knowledge gaps, and suggesting learning content to fill them.

[0062] The knowledge updating unit can use the emotion estimation function to suggest the optimal learning method based on the owner's emotional reactions when acquiring new knowledge. For example, the knowledge updating unit uses the emotion estimation function to analyze the owner's emotional reactions when acquiring new knowledge, and the generation AI suggests the optimal learning method. For example, it suggests visual learning materials when the owner is relaxed. The knowledge updating unit also suggests the optimal learning method based on the owner's emotional reactions. For example, it suggests interactive learning content when the owner is excited. The knowledge updating unit also uses the emotion estimation function to perform facial expression analysis and voice analysis to analyze the owner's emotional reactions. For example, it estimates emotions based on changes in the owner's facial expressions and tone of voice. This makes it possible to maximize the effectiveness of learning by suggesting the optimal learning method based on the owner's emotional reactions.

[0063] The dialogue initiation unit can provide a function for sharing the content of the dialogue with other generated AI users and connecting users with common interests. For example, the dialogue initiation unit shares the content of the owner's dialogue with other generated AI users to build an online community that connects users with common interests. For example, it matches users with the same hobbies. The dialogue initiation unit also considers how to analyze the content of the dialogue and match users in order to connect users with common interests. For example, it identifies common interests based on the content of the owner's dialogue. The dialogue initiation unit also considers the technology to be used and the functions to be provided when building a platform for connection. For example, it provides an online forum or chat function. This allows the content of the owner's dialogue to be shared and connects users with common interests, thereby promoting the formation of a community.

[0064] The dialogue initiation unit can automatically suggest events and news related to the owner's hobbies and interests based on the dialogue history. For example, the dialogue initiation unit analyzes the owner's dialogue history, and the generation AI automatically suggests events related to the owner's hobbies and interests. For example, if the owner is interested in music, it suggests nearby concerts. The dialogue initiation unit also considers how to analyze the dialogue content and how to classify hobbies and interests in order to identify the owner's hobbies and interests based on the owner's dialogue history. For example, it identifies hobbies and interests based on content that the owner has previously spoken about. The dialogue initiation unit also considers the timing and format of the suggestion when suggesting events and news. For example, it makes suggestions during times when the owner is relaxing. This makes it possible to continue to attract the owner's interest by suggesting related events and news based on the owner's dialogue history.

[0065] The dialogue initiation unit uses the emotion estimation function to identify the time when the owner is most relaxed and can speak to them at that time. For example, the dialogue initiation unit uses the emotion estimation function to identify the time when the owner is relaxed, and the generation AI provides topics related to relaxation at that time. For example, when the owner is relaxed, the generation AI can introduce relaxation techniques. In addition, to identify the owner's relaxed state, the dialogue initiation unit performs analysis based on changes in heart rate and facial expression analysis. For example, it determines that the owner is relaxed when their heart rate is stable. In addition, the dialogue initiation unit takes into account the algorithms and criteria to be used when identifying the time when the owner is relaxed. For example, it identifies the time when the owner is relaxed based on the owner's daily rhythm. This makes it possible to provide a more effective dialogue by speaking to the owner when they are relaxed.

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

[0067] The generative AI service can also monitor the owner's health and provide health advice. For example, it can collect the owner's dietary and exercise data and suggest a balanced diet and appropriate exercise plan. It can also analyze the owner's sleep patterns and provide advice on how to get better quality sleep. Furthermore, if the owner is feeling stressed, it can suggest relaxation techniques and stress management methods. This allows it to provide comprehensive support for the owner's health and provide advice on how to live a healthier life.

[0068] The generative AI service can also suggest new hobbies and activities based on the owner's hobbies and interests. For example, if the owner is interested in music, it can suggest new ways to play instruments or create music. If the owner is interested in outdoor activities, it can provide ideas for new hiking trails and camping trips. Furthermore, if the owner is interested in art, it can suggest new art projects and techniques. This allows the service to provide suggestions for expanding the owner's hobbies and interests and enjoying new activities.

[0069] The generative AI service can also provide a platform for sharing the owner's learning progress with other users and for collaborative learning. For example, if the owner is learning about a particular topic, they can form a study group with other users who are interested in that topic and work together to advance their learning. The owner can also share with other users any problems or questions they encounter while studying and hold discussions to find solutions. Furthermore, by sharing what they have learned with other users and receiving feedback, the effectiveness of their learning can be improved. This can support the owner's learning and provide a platform for collaborative learning.

[0070] The generative AI service can analyze the owner's emotional state and provide music and videos that correspond to that emotion. For example, if the owner feels like relaxing, it can provide music and videos that have a relaxing effect. If the owner feels like concentrating, it can provide music and videos that will help them concentrate. Furthermore, if the owner feels like cheering up, it can provide energetic music and videos. In this way, by providing music and videos that correspond to the owner's emotional state, it can support the owner's mood and help them live a better life.

[0071] The generative AI service can analyze the owner's emotional state and suggest relaxation techniques according to the emotion. For example, if the owner is feeling stressed, it can suggest relaxation techniques such as deep breathing or meditation. If the owner is feeling anxious, it can suggest yoga or stretching methods to help them relax. Furthermore, if the owner is tired, it can suggest a short break or light exercise to refresh themselves. In this way, by providing relaxation techniques according to the owner's emotional state, it can help reduce the owner's stress and anxiety and maintain a more relaxed state.

[0072] The generative AI service can analyze the user's learning history and provide a customized learning plan to maximize the effectiveness of their learning. For example, it can suggest the next topic to study and the learning method based on the content the user has learned in the past and their learning outcomes. It can also create an optimal learning plan that suits the user's learning style and pace. It can also provide appropriate resources and support for any problems or questions the user faces while studying. In this way, by providing a customized learning plan based on the user's learning history, it can maximize the effectiveness of learning and support the user's growth.

[0073] The generative AI service can analyze the owner's emotional state and provide feedback according to that emotion. For example, if the owner experiences a success, it can provide positive feedback to reinforce that emotion. If the owner experiences a failure, it can provide words of encouragement to ease those emotions and advice on how to move forward. Furthermore, if the owner is feeling anxious, it can suggest relaxation techniques and stress management methods to alleviate those emotions. In this way, by providing feedback according to the owner's emotional state, it can support the owner's emotions and help them live a better life.

[0074] The generative AI service can visualize the user's learning progress and provide feedback to increase motivation to learn. For example, it can visualize the user's achieved learning goals and progress using graphs and charts, allowing the user to feel a sense of accomplishment. It can also maintain the user's motivation to learn by clearly indicating the next goal to be achieved and learning steps the user should take. Furthermore, it can improve the effectiveness of learning by providing appropriate resources and support for problems and questions the user faces during learning. In this way, it can support the user's growth by visualizing the user's learning progress and providing feedback to increase motivation to learn.

[0075] The generative AI service can analyze the owner's emotional state and provide a learning environment that suits their emotions. For example, if the owner is relaxed, it can suggest studying in a quiet environment. If the owner feels like concentrating, it can provide environmental settings and tools to improve concentration. Furthermore, if the owner is tired, it can suggest a short break or light exercise to refresh themselves. By providing a learning environment that suits the owner's emotional state, it can maximize the effectiveness of learning and support the owner's growth.

[0076] The generative AI service can also share the owner's learning history with other users and build an online community for collaborative learning. For example, if the owner is studying a particular topic, they can form a study group with other users who are interested in that topic and study together. The owner can also share with other users any problems or questions they encounter while studying and hold discussions to find solutions. Furthermore, by sharing what they have learned with other users and receiving feedback, the effectiveness of their learning can be improved. This makes it possible to provide an online community that supports the owner's learning and allows them to study together.

[0077] The processing flow of the second embodiment will be briefly explained below.

[0078] Step 1: The knowledge growth section grows based on the owner's knowledge and experience. For example, if the owner learns a new language, the knowledge growth section learns that language and becomes able to converse at the same level as the owner. The knowledge growth section also learns based on prompts that include the owner's knowledge and experience. Step 2: The dialogue initiator actively engages with the user based on the knowledge developed by the knowledge growth component. For example, the dialogue initiator spontaneously provides advice and information in response to problems or questions the user faces in daily life. The dialogue initiator also generates appropriate dialogue based on prompts that reflect the user's situation and emotions. Step 3: The knowledge update unit periodically updates the knowledge developed by the knowledge growth unit. For example, when the user acquires knowledge in a new field, the knowledge update unit learns the knowledge in that field and provides appropriate advice to the user. The knowledge update unit also periodically updates its own knowledge base as the user grows.

[0079] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0080] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0081] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0082] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0083] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0084] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0085] 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.

[0086] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0087] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0088] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0089] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0090] 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.

[0091] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0092] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0093] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0094] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0095] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0096] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0097] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0098] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0099] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0100] 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.

[0101] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0102] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0103] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0104] 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.

[0105] 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.

[0106] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0107] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0108] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0109] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0111] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0112] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0113] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0114] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0115] 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.

[0116] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0117] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0118] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0119] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0120] 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.

[0121] 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.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0123] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0125] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0128] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0129] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0130] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0131] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0132] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0133] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0134] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0135] 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.

[0136] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0137] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0138] 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.

[0139] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0140] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0141] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0142] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0143] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0144] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0145] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0146] 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. The knowledge growth part grows based on the owner's knowledge and experience, a dialogue initiation unit that actively talks to the owner based on the knowledge grown by the knowledge growth unit; a knowledge update unit that periodically updates the knowledge grown by the knowledge growth unit. A system characterized by:

2. The knowledge growth unit: Analyzes learning history in real time, predicts and suggests what knowledge should be learned next The system of claim 1 .

3. The dialogue initiation unit Analyzes conversation history, predicts the next topic to discuss, and starts the conversation at the right time The system of claim 1 .

4. The knowledge update unit Regularly assess learning progress and automatically update your knowledge base based on that assessment The system of claim 1 .

5. The knowledge growth unit: Using emotion estimation function, the system detects stress or excitement felt by the user during learning and adjusts the learning progress accordingly. The system of claim 1 .

Images