system

Abstract

The system according to the embodiment aims to realize smooth communication with important people who are far away. [Solution] The system according to the embodiment comprises a learning unit, a downloading unit, a conversation unit, and a feedback unit. The learning unit learns information or audio information that forms Person A's personality. The downloading unit downloads personal data based on the information learned by the learning unit. The conversation unit conducts a conversation using a voice synthesized based on the personal data downloaded by the downloading unit. The feedback unit summarizes the content of the conversation conducted by the conversation unit and provides feedback to Person A.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has made it difficult to smoothly communicate with loved ones who are far away.

[0005] The system according to the embodiment aims to realize smooth communication with important people who are far away. [Means for solving the problem]

[0006] The system according to the embodiment comprises a learning unit, a downloading unit, a conversation unit, and a feedback unit. The learning unit learns information or voice information that forms Person A's personality. The downloading unit downloads personal data based on the information learned by the learning unit. The conversation unit conducts a conversation using a voice synthesized based on the personal data downloaded by the downloading unit. The feedback unit summarizes the content of the conversation conducted by the conversation unit and provides feedback to Person A. [Effects of the Invention]

[0007] The system according to the embodiment can realize smooth communication with important people who are far away. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. 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) A communication system according to an embodiment of the present invention uses a generation AI to learn information and voice information that define Person A's personality, and then uses that data to facilitate natural communication with a loved one who is far away. The communication system learns the information and voice information that define Person A's personality, downloads personal data based on that information, conducts a conversation in natural language using a synthesized voice, and summarizes the conversation and provides feedback to Person A. For example, the communication system learns Person A's past conversation history, vocal characteristics, personality, and so on. Next, the communication system downloads Person A's personal data via the Internet. Next, the communication system conducts a conversation in natural language using a synthesized voice based on Person A's personal data. For example, when Person A's loved one asks, "How was your day?", the communication system replies in Person A's voice, "It was a great day today." Next, the communication system summarizes the conversation and provides feedback to Person A. This allows Person A to understand the content of their communication with their loved one and further communicate accordingly. For example, Person A can consider, "Let's talk about this next time." This allows the communication system to facilitate natural communication with loved ones who are far away, creating a connection that eliminates the sense of distance. This allows the communication system to learn information that forms Person A's personality and voice information, enabling natural communication with loved ones who are far away. For example, by learning Person A's past conversation history, vocal characteristics, personality, etc., more natural conversation becomes possible. Also, by downloading Person A's personal data over the Internet, communication with loved ones who are far away becomes possible. Furthermore, more natural communication becomes possible by conversing in natural language using a voice synthesized based on Person A's personal data. Finally, by summarizing the content of the conversation and providing feedback to Person A, it becomes easier for A to understand the content of the communication.

[0029] The communication system according to the embodiment includes a learning unit, a downloading unit, a conversation unit, and a feedback unit. The learning unit learns information or voice information that forms Person A's personality. Examples of information that forms Person A's personality include past behavioral history and personality assessment results. The learning unit can also learn Person A's past conversation history, vocal characteristics, personality, and the like. For example, the learning unit collects and learns Person A's past conversation history from text logs or voice recordings. Furthermore, the learning unit can analyze and learn characteristics of Person A's voice, such as tone, pitch, and intonation. The downloading unit downloads personal data based on the information learned by the learning unit. The downloading unit downloads Person A's personal data, for example, via the Internet. The downloading unit can acquire data using protocols such as HTTP and FTP. The conversation unit converses using a voice synthesized based on the personal data downloaded by the downloading unit. The conversation unit reproduces Person A's voice using, for example, voice synthesis technology, and converses in natural language. The conversation unit can achieve conversational fluency and appropriate responses using natural language processing (NLP) technology. The feedback unit summarizes the content of the conversation conducted by the conversation unit and provides feedback to Person A. For example, the feedback unit summarizes the content of the conversation using a summarization algorithm and provides feedback by emphasizing information that is important to Person A. In this way, the communication system according to the embodiment can learn information and voice information that form Person A's personality, and can achieve natural communication with important people who are far away.

[0030] The learning unit can learn Person A's past conversation history, voice characteristics, and personality. For example, the learning unit collects and learns Person A's past conversation history from text logs and voice recordings. The learning unit can also analyze and learn Person A's voice characteristics, such as tone, pitch, and intonation. Furthermore, the learning unit can learn Person A's personality based on the results of a personality diagnostic test and analysis of Person A's behavioral patterns. This enables more natural conversations by learning Person A's past conversation history, voice characteristics, personality, etc. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input Person A's past conversation history into the generation AI, and have the generation AI analyze and learn the conversation history.

[0031] The download unit can download person A's personal data via the Internet. The download unit downloads person A's personal data via the Internet using protocols such as HTTP or FTP. The download unit can also set the data acquisition method and download protocol. Furthermore, the download unit can monitor the network status and download data at the optimal timing. This allows person A to communicate with loved ones who are far away by downloading their personal data via the Internet. Some or all of the above-mentioned processing in the download unit may be performed using, or without, a generation AI. For example, the download unit can input the network status into the generation AI, which can then determine the optimal download timing.

[0032] The conversation unit can conduct a conversation using a voice synthesized based on person A's personal data. The conversation unit can, for example, use voice synthesis technology to reproduce person A's voice and conduct a conversation in natural language. The conversation unit can use natural language processing (NLP) technology to achieve fluency in conversation and appropriate responses. The conversation unit can also reproduce characteristics of person A's voice, such as tone, pitch, and intonation, to perform more realistic voice synthesis. Furthermore, the conversation unit can take person A's personality and behavioral patterns into consideration to make the conversation flow more natural. This enables more natural communication by conducting a conversation in natural language using a voice synthesized based on person A's personal data. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can input person A's personal data into the generation AI, which can then perform voice synthesis and conversation generation.

[0033] The feedback unit can summarize the conversation content and provide feedback to Person A. For example, the feedback unit can summarize the conversation content using a summarization algorithm and provide feedback by emphasizing information that is important to Person A. The feedback unit can also improve the accuracy of the feedback by referring to Person A's past feedback history. Furthermore, the feedback unit can also customize the feedback method taking into account Person A's personality and behavioral patterns. In this way, by summarizing the conversation content and providing feedback to Person A, Person A can more easily understand the content of the communication. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input the conversation content into a generation AI, which can then generate a summary and feedback.

[0034] The learning unit can analyze Person A's past conversation history and learn reactions to specific topics. For example, the learning unit collects Person A's past conversation history from text logs and voice recordings and learns reactions to specific topics. The learning unit can also select specific topics using topic modeling or keyword extraction technology. For example, the learning unit can prioritize learning topics that Person A has frequently talked about in the past. Furthermore, the learning unit can also focus learning on topics to which Person A has shown strong reactions in the past. In this way, by analyzing Person A's past conversation history, reactions to specific topics can be learned, enabling more natural conversations. Some or all of the above-mentioned processing in the learning unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the learning unit can input Person A's past conversation history into a generation AI, and the generation AI can learn reactions to specific topics.

[0035] The learning unit can analyze the characteristics of person A's voice and learn the tone and intonation of the voice. For example, the learning unit can analyze the tone and intonation of person A's voice using speech waveform analysis or acoustic feature extraction technology. The learning unit can also analyze the pitch, lowness, speed, and slowness of person A's voice in detail and reflect this in the learning data. Furthermore, the learning unit can analyze emotional expressions (happiness, sadness, etc.) in person A's voice and incorporate this into the learning data. This enables more natural voice synthesis by analyzing the characteristics of person A's voice in detail. Some or all of the above-mentioned processing in the learning unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the learning unit can input feature data of person A's voice into the generation AI, and the generation AI can learn the tone and intonation of the voice.

[0036] The learning unit can learn data for generating more natural conversations based on person A's personality or behavioral patterns. The learning unit learns person A's personality and behavioral patterns, for example, based on the results of a personality diagnostic test or an analysis of person A's behavioral history. Furthermore, if person A has a sociable personality, the learning unit can also learn proactive conversation data. Furthermore, if person A has an introverted personality, the learning unit can also learn calm conversation data. This makes it possible to have more natural conversations by taking person A's personality and behavioral patterns into consideration. Some or all of the above-described processing in the learning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the learning unit can input person A's personality and behavioral pattern data into the generation AI, and have the generation AI learn the conversation data.

[0037] The learning unit can select the optimal study timing based on person A's lifestyle rhythm. For example, the learning unit evaluates person A's lifestyle rhythm based on daily activity patterns, sleep duration, etc. Furthermore, if person A has a morning-type lifestyle rhythm, the learning unit can have person A study in the morning hours. Furthermore, if person A has a nocturnal lifestyle rhythm, the learning unit can have person A study in the evening hours. This allows for efficient study by adjusting the study timing to match person A's lifestyle rhythm. Some or all of the above-mentioned processing in the learning unit may be performed using, or without, a generation AI, for example. For example, the learning unit can input person A's lifestyle rhythm data into the generation AI, and the generation AI can select the optimal study timing.

[0038] The learning unit can analyze Person A's social media activities and incorporate related data into learning. For example, the learning unit analyzes Person A's social media activities based on the content of posts, the number of likes, comments, etc. The learning unit can also incorporate content that Person A frequently posts on social media into learning data. Furthermore, the learning unit can analyze Person A's friendships on social media and learn related conversation data. In this way, by analyzing Person A's social media activities, related data can be incorporated into learning. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI, for example. For example, the learning unit can input Person A's social media data into the generation AI, and have the generation AI learn related data.

[0039] The learning unit can diversify conversation topics based on person A's hobbies or interests. For example, the learning unit collects person A's hobbies and interests from a questionnaire survey or an analysis of his / her behavioral history. The learning unit can also learn conversation data related to sports, which is person A's hobby. Furthermore, the learning unit can also learn conversation data related to movies and music, which are of interest to person A. In this way, conversation topics can be diversified by taking person A's hobbies and interests into consideration. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI, for example. For example, the learning unit can input person A's hobbies and interests data into the generation AI, and the generation AI can diversify conversation topics.

[0040] The download unit monitors the network status and can download data at the appropriate timing. The download unit evaluates the network status using indicators such as bandwidth, latency, and packet loss. If the network is congested, the download unit can also delay the download and wait for the optimal timing. Furthermore, if the network is stable, the download unit can also download data quickly. This allows data to be downloaded at the optimal timing by monitoring the network status. Some or all of the above-described processing in the download unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the download unit can input network status data into the generation AI, which can then determine the optimal download timing.

[0041] The download unit can efficiently acquire necessary data based on Person A's past download history. For example, the download unit collects Person A's past download history based on the download date and time, file type, etc. The download unit can also analyze the past download history and prioritize downloading related data. Furthermore, the download unit can also prioritize downloading frequently used data. This allows necessary data to be acquired efficiently by referring to Person A's past download history. Some or all of the above-described processing in the download unit may be performed using, or without, the generation AI. For example, the download unit can input Person A's past download history data into the generation AI, and the generation AI can acquire the necessary data.

[0042] The download unit can compress or optimize data based on the storage capacity of Person A's device. For example, the download unit evaluates the storage capacity of Person A's device based on the available capacity and the data compression rate. Furthermore, if the storage capacity is low, the download unit can compress and download the data. Furthermore, if the storage capacity is sufficient, the download unit can optimize and download the data. This allows data to be compressed and optimized by taking into account the storage capacity of Person A's device. Some or all of the above-described processing in the download unit may be performed using, or without, a generation AI. For example, the download unit can input storage capacity data of Person A's device into the generation AI, and the generation AI can compress and optimize the data.

[0043] The download unit can prioritize acquiring highly relevant data based on person A's geographical location information. The download unit, for example, acquires person A's geographical location information from GPS data or a location information service. Furthermore, if person A is in a specific area, the download unit can prioritize downloading data related to that area. Furthermore, if person A is traveling, the download unit can prioritize downloading data related to the travel destination. In this way, by taking person A's geographical location information into consideration, highly relevant data can be acquired preferentially. Some or all of the above-described processing in the download unit may be performed using, or without, a generation AI. For example, the download unit can input person A's geographical location information data into the generation AI, and the generation AI can acquire highly relevant data.

[0044] The download unit can analyze Person A's social media activity and download related data. The download unit can analyze Person A's social media activity, for example, from the content of posts, the number of likes, comments, etc. The download unit can also download data related to the content that Person A frequently posts on social media. Furthermore, the download unit can analyze Person A's friendships on social media and download related data. In this way, by analyzing Person A's social media activity, related data can be downloaded. Some or all of the above-described processing in the download unit can be performed using, or without, the generation AI, for example. For example, the download unit can input Person A's social media data into the generation AI, and the generation AI can download the related data.

[0045] The download unit can customize the download method based on Person A's past feedback. For example, the download unit collects Person A's past feedback from the date, time, and details of the feedback. The download unit can also analyze the past feedback and customize the download method. Furthermore, the download unit can prioritize downloading Person A's preferred data. In this way, the download method can be customized by reflecting Person A's past feedback. Some or all of the above-described processing in the download unit may be performed using, or without, a generation AI. For example, the download unit can input Person A's past feedback data into the generation AI and have the generation AI customize the download method.

[0046] The conversation unit can generate more natural responses based on Person A's past conversation history. For example, the conversation unit collects Person A's past conversation history from text logs or voice recordings. The conversation unit can also analyze the past conversation history and learn specific phrases. Furthermore, the conversation unit can generate natural responses based on topics that Person A has previously discussed. This makes it possible to generate more natural responses by referring to Person A's past conversation history. Some or all of the above-described processing in the conversation unit may be performed using, or without, a generation AI. For example, the conversation unit can input Person A's past conversation history data into the generation AI, which can then generate natural responses.

[0047] The conversation unit can reproduce the characteristics of person A's voice and perform realistic voice synthesis. The conversation unit, for example, reproduces the tone and intonation of person A's voice using speech waveform analysis and acoustic feature extraction technology. The conversation unit can also reproduce the high and low pitch, speed and slowness of person A's voice to achieve natural conversation. Furthermore, the conversation unit can reproduce emotional expressions (happiness, sadness, etc.) in person A's voice and perform realistic voice synthesis. In this way, by reproducing the characteristics of person A's voice, more realistic voice synthesis is possible. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can input feature data of person A's voice into the generation AI, which can then perform realistic voice synthesis.

[0048] The conversation unit can make the conversation flow naturally based on person A's personality or behavioral patterns. The conversation unit learns person A's personality and behavioral patterns based on, for example, the results of a personality diagnostic test or an analysis of person A's behavioral history. Furthermore, if person A has a sociable personality, the conversation unit can create a proactive conversation flow. Furthermore, if person A has an introverted personality, the conversation unit can create a calm conversation flow. In this way, the conversation can flow naturally by taking person A's personality and behavioral patterns into consideration. Some or all of the above-mentioned processing in the conversation unit may be performed using, or without, a generation AI, for example. For example, the conversation unit can input person A's personality and behavioral pattern data into the generation AI, and the generation AI can adjust the conversation flow.

[0049] The conversation unit can select the optimal conversation timing based on Person A's lifestyle rhythm. The conversation unit, for example, evaluates Person A's lifestyle rhythm based on daily activity patterns, sleep duration, etc. Furthermore, if Person A has a morning-type lifestyle rhythm, the conversation unit can also conduct the conversation in the morning hours. Furthermore, if Person A has a nocturnal lifestyle rhythm, the conversation unit can also conduct the conversation in the evening hours. This enables efficient conversation by adjusting the conversation timing to match Person A's lifestyle rhythm. Some or all of the above-mentioned processing in the conversation unit may be performed using, or without, a generation AI, for example. For example, the conversation unit can input Person A's lifestyle rhythm data into the generation AI, and the generation AI can select the optimal conversation timing.

[0050] The conversation unit can analyze Person A's social media activity and incorporate related topics into the conversation. The conversation unit, for example, analyzes Person A's social media activity based on the content of posts, the number of likes, comments, etc. The conversation unit can also incorporate content that Person A frequently posts on social media into the conversation. Furthermore, the conversation unit can analyze Person A's friendships on social media and incorporate related topics into the conversation. In this way, by analyzing Person A's social media activity, related topics can be incorporated into the conversation. Some or all of the above-mentioned processing in the conversation unit may be performed using, or without, a generation AI, for example. For example, the conversation unit can input Person A's social media data into the generation AI, and the generation AI can incorporate related topics into the conversation.

[0051] The conversation unit can diversify conversation topics based on person A's hobbies or interests. For example, the conversation unit collects person A's hobbies and interests from a questionnaire survey or an analysis of his / her behavioral history. The conversation unit can also incorporate topics related to sports, which is person A's hobby, into the conversation. Furthermore, the conversation unit can incorporate topics related to movies and music, which person A is interested in, into the conversation. In this way, conversation topics can be diversified by taking person A's hobbies and interests into consideration. Some or all of the above-described processing in the conversation unit may be performed using, or without, a generation AI, for example. For example, the conversation unit can input person A's hobbies and interests data into the generation AI, and the generation AI can diversify conversation topics.

[0052] The feedback unit can summarize the conversation content and emphasize information that is important to Person A. For example, the feedback unit can summarize the conversation content using a summarization algorithm and provide feedback that emphasizes information that is important to Person A. The feedback unit can also suggest a topic that Person A should talk about next. Furthermore, the feedback unit can also briefly summarize the main points of the conversation and provide this to Person A. By summarizing the conversation content and emphasizing important information, Person A can easily understand the topic that he or she should talk about next. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input the conversation content into a generation AI, which can then summarize and emphasize important information.

[0053] The feedback unit can improve the accuracy of feedback based on Person A's past feedback history. For example, the feedback unit collects Person A's past feedback history from details of the date and time and content of the feedback. The feedback unit can also analyze the past feedback history and adjust the content of the feedback. Furthermore, the feedback unit can extract and provide important information from Person A's past feedback history. In this way, the accuracy of feedback can be improved by referring to Person A's past feedback history. Some or all of the above-mentioned processing in the feedback unit may be performed using, or without, a generation AI, for example. For example, the feedback unit can input Person A's past feedback history data into the generation AI, and the generation AI can improve the accuracy of the feedback.

[0054] The feedback unit can customize the feedback method based on person A's personality or behavioral patterns. The feedback unit learns person A's personality and behavioral patterns based on, for example, the results of a personality diagnostic test or an analysis of person A's behavioral history. Furthermore, the feedback unit can provide positive feedback if person A has a sociable personality. Furthermore, the feedback unit can provide gentle feedback if person A has an introverted personality. In this way, the feedback method can be customized by taking person A's personality and behavioral patterns into consideration. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input person A's personality and behavioral pattern data into the generation AI, and use the generation AI to customize the feedback method.

[0055] The feedback unit can select the optimal feedback timing based on person A's lifestyle rhythm. The feedback unit, for example, evaluates person A's lifestyle rhythm based on daily activity patterns, sleep duration, etc. Furthermore, if person A has a morning-type lifestyle rhythm, the feedback unit can provide feedback in the morning hours. Furthermore, if person A has a nocturnal lifestyle rhythm, the feedback unit can provide feedback in the evening hours. This enables efficient feedback by adjusting the feedback timing to match person A's lifestyle rhythm. Some or all of the above-mentioned processing in the feedback unit may be performed using, or without, a generation AI, for example. For example, the feedback unit can input person A's lifestyle rhythm data into the generation AI, and the generation AI can select the optimal feedback timing.

[0056] The feedback unit can analyze Person A's social media activity and incorporate relevant information into the feedback. The feedback unit can, for example, analyze Person A's social media activity based on the content of posts, the number of likes, comments, etc. The feedback unit can also incorporate content that Person A frequently posts on social media into the feedback. Furthermore, the feedback unit can analyze Person A's friendships on social media and incorporate relevant information into the feedback. In this way, by analyzing Person A's social media activity, relevant information can be incorporated into the feedback. Some or all of the above-described processing in the feedback unit can be performed using, or without, a generation AI, for example. For example, the feedback unit can input Person A's social media data into the generation AI, and have the generation AI provide feedback of relevant information.

[0057] The feedback unit can diversify the content of the feedback based on person A's hobbies or interests. For example, the feedback unit collects person A's hobbies and interests from a questionnaire survey or an analysis of his / her behavioral history. The feedback unit can also incorporate information about sports that person A enjoys into the feedback. Furthermore, the feedback unit can also incorporate information about movies and music that person A is interested in into the feedback. In this way, the content of the feedback can be diversified by taking person A's hobbies and interests into consideration. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI, for example. For example, the feedback unit can input data about person A's hobbies and interests into the generation AI, and the generation AI can diversify the content of the feedback.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The communication system also includes a health management unit that monitors the user's health condition and can adjust the content of the conversation based on the user's health data. For example, if the user is tired, the system can suggest short conversations and provide relaxing topics. If the user is healthy and active, the system can suggest longer conversations and provide interesting topics. Furthermore, if the user is sick or injured, the system can offer comforting words and health advice. This enables appropriate communication according to the user's health condition.

[0060] The communication system also includes a schedule management unit that manages the user's schedule, allowing it to adjust the timing and content of conversations based on the user's schedule. For example, if the user has a busy schedule, the system can suggest short conversations to ensure efficient communication. If the user has a relaxed schedule, the system can suggest longer conversations and provide relaxing topics. Furthermore, if the user has an important event coming up, the system can provide information related to that event and support preparations. This enables appropriate communication based on the user's schedule.

[0061] The communication system also includes an hobby learning module that learns the user's hobbies and interests, allowing it to diversify conversation topics based on the user's interests. For example, if the user is interested in sports, the system can provide topics about the latest sports news and game results. If the user is interested in movies or music, the system can provide topics about new movies and popular music. Furthermore, if the user is interested in travel, the system can provide topics about travel destinations and recommended tourist spots. This enables diverse communication based on the user's hobbies and interests.

[0062] The communication system further includes a history analysis unit that analyzes the user's past conversation history, and can suggest the next conversation topic based on the content of the past conversation. For example, it can prioritize suggestions of topics that the user has frequently discussed in the past. It can also prioritize suggestions of topics to which the user has responded strongly in the past. It can also re-suggest topics in which the user has shown interest in the past but has not discussed in depth. This enables natural communication based on the user's past conversation history.

[0063] The communication system may further include a geographic information unit that prioritizes the acquisition of highly relevant data based on the user's geographic location information. For example, if the user is in a specific area, data related to that area may be downloaded preferentially. If the user is traveling, data related to the travel destination may be downloaded preferentially. If the user is participating in a specific event, data related to that event may be downloaded preferentially. This makes it possible to acquire appropriate data based on the user's geographic location information.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The learning unit learns information or voice information that forms Person A's personality. Specifically, it collects and learns past behavioral history, personality diagnosis results, past conversation history, and voice characteristics (tone, pitch, intonation), etc. Step 2: The downloading unit downloads personal data based on the information learned by the learning unit. For example, the downloading unit obtains personal data of Person A via the Internet using a protocol such as HTTP or FTP. Step 3: The conversation unit uses a voice synthesized based on the personal data downloaded by the download unit. Using voice synthesis technology and natural language processing (NLP) technology, it reproduces Person A's voice and enables natural conversation. Step 4: The feedback unit summarizes the conversation conducted by the conversation unit and provides feedback to Person A. The conversation is summarized using a summary algorithm, and important information is emphasized and provided as feedback.

[0066] (Example 2) A communication system according to an embodiment of the present invention uses a generation AI to learn information and voice information that define Person A's personality, and then uses that data to facilitate natural communication with a loved one who is far away. The communication system learns the information and voice information that define Person A's personality, downloads personal data based on that information, conducts a conversation in natural language using a synthesized voice, and summarizes the conversation and provides feedback to Person A. For example, the communication system learns Person A's past conversation history, vocal characteristics, personality, and so on. Next, the communication system downloads Person A's personal data via the Internet. Next, the communication system conducts a conversation in natural language using a synthesized voice based on Person A's personal data. For example, when Person A's loved one asks, "How was your day?", the communication system replies in Person A's voice, "It was a great day today." Next, the communication system summarizes the conversation and provides feedback to Person A. This allows Person A to understand the content of their communication with their loved one and further communicate accordingly. For example, Person A can consider, "Let's talk about this next time." This allows the communication system to facilitate natural communication with loved ones who are far away, creating a connection that eliminates the sense of distance. This allows the communication system to learn information that forms Person A's personality and voice information, enabling natural communication with loved ones who are far away. For example, by learning Person A's past conversation history, vocal characteristics, personality, etc., more natural conversation becomes possible. Also, by downloading Person A's personal data over the Internet, communication with loved ones who are far away becomes possible. Furthermore, more natural communication becomes possible by conversing in natural language using a voice synthesized based on Person A's personal data. Finally, by summarizing the content of the conversation and providing feedback to Person A, it becomes easier for A to understand the content of the communication.

[0067] The communication system according to the embodiment includes a learning unit, a downloading unit, a conversation unit, and a feedback unit. The learning unit learns information or voice information that forms Person A's personality. Examples of information that forms Person A's personality include past behavioral history and personality assessment results. The learning unit can also learn Person A's past conversation history, vocal characteristics, personality, and the like. For example, the learning unit collects and learns Person A's past conversation history from text logs or voice recordings. Furthermore, the learning unit can analyze and learn characteristics of Person A's voice, such as tone, pitch, and intonation. The downloading unit downloads personal data based on the information learned by the learning unit. The downloading unit downloads Person A's personal data, for example, via the Internet. The downloading unit can acquire data using protocols such as HTTP and FTP. The conversation unit converses using a voice synthesized based on the personal data downloaded by the downloading unit. The conversation unit reproduces Person A's voice using, for example, voice synthesis technology, and converses in natural language. The conversation unit can achieve conversational fluency and appropriate responses using natural language processing (NLP) technology. The feedback unit summarizes the content of the conversation conducted by the conversation unit and provides feedback to Person A. For example, the feedback unit summarizes the content of the conversation using a summarization algorithm and provides feedback by emphasizing information that is important to Person A. In this way, the communication system according to the embodiment can learn information and voice information that form Person A's personality, and can achieve natural communication with important people who are far away.

[0068] The learning unit can learn Person A's past conversation history, voice characteristics, and personality. For example, the learning unit collects and learns Person A's past conversation history from text logs and voice recordings. The learning unit can also analyze and learn Person A's voice characteristics, such as tone, pitch, and intonation. Furthermore, the learning unit can learn Person A's personality based on the results of a personality diagnostic test and analysis of Person A's behavioral patterns. This enables more natural conversations by learning Person A's past conversation history, voice characteristics, personality, etc. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input Person A's past conversation history into the generation AI, and have the generation AI analyze and learn the conversation history.

[0069] The download unit can download person A's personal data via the Internet. The download unit downloads person A's personal data via the Internet using protocols such as HTTP or FTP. The download unit can also set the data acquisition method and download protocol. Furthermore, the download unit can monitor the network status and download data at the optimal timing. This allows person A to communicate with loved ones who are far away by downloading their personal data via the Internet. Some or all of the above-mentioned processing in the download unit may be performed using, or without, a generation AI. For example, the download unit can input the network status into the generation AI, which can then determine the optimal download timing.

[0070] The conversation unit can conduct a conversation using a voice synthesized based on person A's personal data. The conversation unit can, for example, use voice synthesis technology to reproduce person A's voice and conduct a conversation in natural language. The conversation unit can use natural language processing (NLP) technology to achieve fluency in conversation and appropriate responses. The conversation unit can also reproduce characteristics of person A's voice, such as tone, pitch, and intonation, to perform more realistic voice synthesis. Furthermore, the conversation unit can take person A's personality and behavioral patterns into consideration to make the conversation flow more natural. This enables more natural communication by conducting a conversation in natural language using a voice synthesized based on person A's personal data. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can input person A's personal data into the generation AI, which can then perform voice synthesis and conversation generation.

[0071] The feedback unit can summarize the conversation content and provide feedback to Person A. For example, the feedback unit can summarize the conversation content using a summarization algorithm and provide feedback by emphasizing information that is important to Person A. The feedback unit can also improve the accuracy of the feedback by referring to Person A's past feedback history. Furthermore, the feedback unit can also customize the feedback method taking into account Person A's personality and behavioral patterns. In this way, by summarizing the conversation content and providing feedback to Person A, Person A can more easily understand the content of the communication. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input the conversation content into a generation AI, which can then generate a summary and feedback.

[0072] The learning unit can estimate Person A's emotions and select training data based on the estimated emotions. The learning unit, for example, estimates Person A's emotions using voice analysis or facial expression recognition technology. For example, the learning unit analyzes changes in Person A's tone of voice and facial expressions to calculate an emotion score. The learning unit can also select training data based on Person A's estimated emotions. For example, if Person A is feeling stressed, the learning unit can prioritize learning conversation data that is relaxing. Furthermore, if Person A is happy, the learning unit can prioritize learning positive conversation data. In this way, by selecting training data based on Person A's emotions, more appropriate data can be learned. Some or all of the above-described processing in the learning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the learning unit can input Person A's emotion data into the generation AI, and the generation AI can select training data.

[0073] The learning unit can analyze Person A's past conversation history and learn reactions to specific topics. For example, the learning unit collects Person A's past conversation history from text logs and voice recordings and learns reactions to specific topics. The learning unit can also select specific topics using topic modeling or keyword extraction technology. For example, the learning unit can prioritize learning topics that Person A has frequently talked about in the past. Furthermore, the learning unit can also focus learning on topics to which Person A has shown strong reactions in the past. In this way, by analyzing Person A's past conversation history, reactions to specific topics can be learned, enabling more natural conversations. Some or all of the above-mentioned processing in the learning unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the learning unit can input Person A's past conversation history into a generation AI, and the generation AI can learn reactions to specific topics.

[0074] The learning unit can analyze the characteristics of person A's voice and learn the tone and intonation of the voice. For example, the learning unit can analyze the tone and intonation of person A's voice using speech waveform analysis or acoustic feature extraction technology. The learning unit can also analyze the pitch, lowness, speed, and slowness of person A's voice in detail and reflect this in the learning data. Furthermore, the learning unit can analyze emotional expressions (happiness, sadness, etc.) in person A's voice and incorporate this into the learning data. This enables more natural voice synthesis by analyzing the characteristics of person A's voice in detail. Some or all of the above-mentioned processing in the learning unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the learning unit can input feature data of person A's voice into the generation AI, and the generation AI can learn the tone and intonation of the voice.

[0075] The learning unit can learn data for generating more natural conversations based on person A's personality or behavioral patterns. The learning unit learns person A's personality and behavioral patterns, for example, based on the results of a personality diagnostic test or an analysis of person A's behavioral history. Furthermore, if person A has a sociable personality, the learning unit can also learn proactive conversation data. Furthermore, if person A has an introverted personality, the learning unit can also learn calm conversation data. This makes it possible to have more natural conversations by taking person A's personality and behavioral patterns into consideration. Some or all of the above-described processing in the learning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the learning unit can input person A's personality and behavioral pattern data into the generation AI, and have the generation AI learn the conversation data.

[0076] The learning unit can estimate Person A's emotions and adjust the learning frequency based on the estimated emotions. The learning unit, for example, estimates Person A's emotions using voice analysis or facial expression recognition technology. For example, the learning unit analyzes changes in Person A's tone of voice and facial expressions to calculate an emotion score. The learning unit can also adjust the learning frequency based on Person A's estimated emotions. For example, if Person A is feeling stressed, the learning frequency can be reduced to reduce the burden. Furthermore, if Person A is relaxed, the learning unit can increase the learning frequency to efficiently collect data. This enables more appropriate learning by adjusting the learning frequency based on Person A's emotions. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input Person A's emotion data into the generation AI, and the generation AI can adjust the learning frequency.

[0077] The learning unit can select the optimal study timing based on person A's lifestyle rhythm. For example, the learning unit evaluates person A's lifestyle rhythm based on daily activity patterns, sleep duration, etc. Furthermore, if person A has a morning-type lifestyle rhythm, the learning unit can have person A study in the morning hours. Furthermore, if person A has a nocturnal lifestyle rhythm, the learning unit can have person A study in the evening hours. This allows for efficient study by adjusting the study timing to match person A's lifestyle rhythm. Some or all of the above-mentioned processing in the learning unit may be performed using, or without, a generation AI, for example. For example, the learning unit can input person A's lifestyle rhythm data into the generation AI, and the generation AI can select the optimal study timing.

[0078] The learning unit can analyze Person A's social media activities and incorporate related data into learning. For example, the learning unit analyzes Person A's social media activities based on the content of posts, the number of likes, comments, etc. The learning unit can also incorporate content that Person A frequently posts on social media into learning data. Furthermore, the learning unit can analyze Person A's friendships on social media and learn related conversation data. In this way, by analyzing Person A's social media activities, related data can be incorporated into learning. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI, for example. For example, the learning unit can input Person A's social media data into the generation AI, and have the generation AI learn related data.

[0079] The learning unit can diversify conversation topics based on person A's hobbies or interests. For example, the learning unit collects person A's hobbies and interests from a questionnaire survey or an analysis of his / her behavioral history. The learning unit can also learn conversation data related to sports, which is person A's hobby. Furthermore, the learning unit can also learn conversation data related to movies and music, which are of interest to person A. In this way, conversation topics can be diversified by taking person A's hobbies and interests into consideration. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI, for example. For example, the learning unit can input person A's hobbies and interests data into the generation AI, and the generation AI can diversify conversation topics.

[0080] The download unit can estimate Person A's emotions and set a priority order for the data to be downloaded based on Person A's estimated emotions. The download unit, for example, estimates Person A's emotions using voice analysis or facial expression recognition technology. For example, the download unit can analyze Person A's tone of voice and changes in facial expressions to calculate an emotion score. The download unit can also set a priority order for the data to be downloaded based on Person A's estimated emotions. For example, if Person A is feeling stressed, the download unit can prioritize downloading data that helps them relax. Furthermore, if Person A is happy, the download unit can prioritize downloading positive data. In this way, by determining the priority order for the data to be downloaded based on Person A's emotions, more appropriate data can be downloaded. Some or all of the above-described processing in the download unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the download unit can input Person A's emotion data into the generation AI and have the generation AI set a priority order for the data to be downloaded.

[0081] The download unit monitors the network status and can download data at the appropriate timing. The download unit evaluates the network status using indicators such as bandwidth, latency, and packet loss. If the network is congested, the download unit can also delay the download and wait for the optimal timing. Furthermore, if the network is stable, the download unit can also download data quickly. This allows data to be downloaded at the optimal timing by monitoring the network status. Some or all of the above-described processing in the download unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the download unit can input network status data into the generation AI, which can then determine the optimal download timing.

[0082] The download unit can efficiently acquire necessary data based on Person A's past download history. For example, the download unit collects Person A's past download history based on the download date and time, file type, etc. The download unit can also analyze the past download history and prioritize downloading related data. Furthermore, the download unit can also prioritize downloading frequently used data. This allows necessary data to be acquired efficiently by referring to Person A's past download history. Some or all of the above-described processing in the download unit may be performed using, or without, the generation AI. For example, the download unit can input Person A's past download history data into the generation AI, and the generation AI can acquire the necessary data.

[0083] The download unit can compress or optimize data based on the storage capacity of Person A's device. For example, the download unit evaluates the storage capacity of Person A's device based on the available capacity and the data compression rate. Furthermore, if the storage capacity is low, the download unit can compress and download the data. Furthermore, if the storage capacity is sufficient, the download unit can optimize and download the data. This allows data to be compressed and optimized by taking into account the storage capacity of Person A's device. Some or all of the above-described processing in the download unit may be performed using, or without, a generation AI. For example, the download unit can input storage capacity data of Person A's device into the generation AI, and the generation AI can compress and optimize the data.

[0084] The download unit can estimate Person A's emotions and set the type of data to download based on Person A's estimated emotions. The download unit, for example, estimates Person A's emotions using voice analysis or facial expression recognition technology. For example, the download unit can analyze Person A's tone of voice and changes in facial expressions to calculate an emotion score. The download unit can also set the type of data to download based on Person A's estimated emotions. For example, if Person A is feeling stressed, the download unit can prioritize relaxing data. Furthermore, if Person A is happy, the download unit can prioritize positive data. In this way, by selecting the type of data to download based on Person A's emotions, more appropriate data can be downloaded. Some or all of the above-described processing in the download unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the download unit can input Person A's emotional data into the generation AI and have the generation AI set the type of data to download.

[0085] The download unit can prioritize acquiring highly relevant data based on person A's geographical location information. The download unit, for example, acquires person A's geographical location information from GPS data or a location information service. Furthermore, if person A is in a specific area, the download unit can prioritize downloading data related to that area. Furthermore, if person A is traveling, the download unit can prioritize downloading data related to the travel destination. In this way, by taking person A's geographical location information into consideration, highly relevant data can be acquired preferentially. Some or all of the above-described processing in the download unit may be performed using, or without, a generation AI. For example, the download unit can input person A's geographical location information data into the generation AI, and the generation AI can acquire highly relevant data.

[0086] The download unit can analyze Person A's social media activity and download related data. The download unit can analyze Person A's social media activity, for example, from the content of posts, the number of likes, comments, etc. The download unit can also download data related to the content that Person A frequently posts on social media. Furthermore, the download unit can analyze Person A's friendships on social media and download related data. In this way, by analyzing Person A's social media activity, related data can be downloaded. Some or all of the above-described processing in the download unit can be performed using, or without, the generation AI, for example. For example, the download unit can input Person A's social media data into the generation AI, and the generation AI can download the related data.

[0087] The download unit can customize the download method based on Person A's past feedback. For example, the download unit collects Person A's past feedback from the date, time, and details of the feedback. The download unit can also analyze the past feedback and customize the download method. Furthermore, the download unit can prioritize downloading Person A's preferred data. In this way, the download method can be customized by reflecting Person A's past feedback. Some or all of the above-described processing in the download unit may be performed using, or without, a generation AI. For example, the download unit can input Person A's past feedback data into the generation AI and have the generation AI customize the download method.

[0088] The conversation unit can estimate Person A's emotions and adjust the tone or content of the conversation based on the estimated emotions of Person A. The conversation unit, for example, estimates Person A's emotions using voice analysis or facial expression recognition technology. For example, the conversation unit analyzes changes in Person A's tone of voice and facial expression to calculate an emotion score. The conversation unit can also adjust the tone and content of the conversation based on the estimated emotions of Person A. For example, if Person A is feeling stressed, the conversation unit can use a calm tone. Furthermore, if Person A is happy, the conversation unit can use a bright tone. This allows for more appropriate conversation by adjusting the tone and content of the conversation based on Person A's emotions. Some or all of the above-described processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can input Person A's emotion data into the generation AI, and the generation AI can adjust the tone and content of the conversation.

[0089] The conversation unit can generate more natural responses based on Person A's past conversation history. For example, the conversation unit collects Person A's past conversation history from text logs or voice recordings. The conversation unit can also analyze the past conversation history and learn specific phrases. Furthermore, the conversation unit can generate natural responses based on topics that Person A has previously discussed. This makes it possible to generate more natural responses by referring to Person A's past conversation history. Some or all of the above-described processing in the conversation unit may be performed using, or without, a generation AI. For example, the conversation unit can input Person A's past conversation history data into the generation AI, which can then generate natural responses.

[0090] The conversation unit can reproduce the characteristics of person A's voice and perform realistic voice synthesis. The conversation unit, for example, reproduces the tone and intonation of person A's voice using speech waveform analysis and acoustic feature extraction technology. The conversation unit can also reproduce the high and low pitch, speed and slowness of person A's voice to achieve natural conversation. Furthermore, the conversation unit can reproduce emotional expressions (happiness, sadness, etc.) in person A's voice and perform realistic voice synthesis. In this way, by reproducing the characteristics of person A's voice, more realistic voice synthesis is possible. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can input feature data of person A's voice into the generation AI, which can then perform realistic voice synthesis.

[0091] The conversation unit can make the conversation flow naturally based on person A's personality or behavioral patterns. The conversation unit learns person A's personality and behavioral patterns based on, for example, the results of a personality diagnostic test or an analysis of person A's behavioral history. Furthermore, if person A has a sociable personality, the conversation unit can create a proactive conversation flow. Furthermore, if person A has an introverted personality, the conversation unit can create a calm conversation flow. In this way, the conversation can flow naturally by taking person A's personality and behavioral patterns into consideration. Some or all of the above-mentioned processing in the conversation unit may be performed using, or without, a generation AI, for example. For example, the conversation unit can input person A's personality and behavioral pattern data into the generation AI, and the generation AI can adjust the conversation flow.

[0092] The conversation unit can estimate Person A's emotions and adjust the length of the conversation based on the estimated emotions of Person A. The conversation unit, for example, estimates Person A's emotions using voice analysis or facial expression recognition technology. For example, the conversation unit analyzes changes in Person A's tone of voice and facial expressions to calculate an emotion score. The conversation unit can also adjust the length of the conversation based on the estimated emotions of Person A. For example, if Person A is feeling stressed, the conversation can be short. Furthermore, if Person A is relaxed, the conversation unit can also have a longer conversation. This allows for more appropriate conversation by adjusting the length of the conversation based on Person A's emotions. Some or all of the above-mentioned processing in the conversation unit may be performed using, or without, a generation AI. For example, the conversation unit can input Person A's emotion data into the generation AI, and the generation AI can adjust the length of the conversation.

[0093] The conversation unit can select the optimal conversation timing based on Person A's lifestyle rhythm. The conversation unit, for example, evaluates Person A's lifestyle rhythm based on daily activity patterns, sleep duration, etc. Furthermore, if Person A has a morning-type lifestyle rhythm, the conversation unit can also conduct the conversation in the morning hours. Furthermore, if Person A has a nocturnal lifestyle rhythm, the conversation unit can also conduct the conversation in the evening hours. This enables efficient conversation by adjusting the conversation timing to match Person A's lifestyle rhythm. Some or all of the above-mentioned processing in the conversation unit may be performed using, or without, a generation AI, for example. For example, the conversation unit can input Person A's lifestyle rhythm data into the generation AI, and the generation AI can select the optimal conversation timing.

[0094] The conversation unit can analyze Person A's social media activity and incorporate related topics into the conversation. The conversation unit, for example, analyzes Person A's social media activity based on the content of posts, the number of likes, comments, etc. The conversation unit can also incorporate content that Person A frequently posts on social media into the conversation. Furthermore, the conversation unit can analyze Person A's friendships on social media and incorporate related topics into the conversation. In this way, by analyzing Person A's social media activity, related topics can be incorporated into the conversation. Some or all of the above-mentioned processing in the conversation unit may be performed using, or without, a generation AI, for example. For example, the conversation unit can input Person A's social media data into the generation AI, and the generation AI can incorporate related topics into the conversation.

[0095] The conversation unit can diversify conversation topics based on person A's hobbies or interests. For example, the conversation unit collects person A's hobbies and interests from a questionnaire survey or an analysis of his / her behavioral history. The conversation unit can also incorporate topics related to sports, which is person A's hobby, into the conversation. Furthermore, the conversation unit can incorporate topics related to movies and music, which person A is interested in, into the conversation. In this way, conversation topics can be diversified by taking person A's hobbies and interests into consideration. Some or all of the above-described processing in the conversation unit may be performed using, or without, a generation AI, for example. For example, the conversation unit can input person A's hobbies and interests data into the generation AI, and the generation AI can diversify conversation topics.

[0096] The feedback unit can estimate Person A's emotions and adjust the content of the feedback based on the estimated emotions of Person A. The feedback unit, for example, estimates Person A's emotions using voice analysis or facial expression recognition technology. For example, the feedback unit analyzes changes in Person A's tone of voice and facial expressions to calculate an emotion score. The feedback unit can also adjust the content of the feedback based on the estimated emotions of Person A. For example, if Person A is feeling stressed, the feedback unit can provide concise and positive feedback. Furthermore, if Person A is relaxed, the feedback unit can provide detailed feedback. This enables more appropriate feedback by adjusting the content of the feedback based on Person A's emotions. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input Person A's emotion data into the generation AI, and the generation AI can adjust the content of the feedback.

[0097] The feedback unit can summarize the conversation content and emphasize information that is important to Person A. For example, the feedback unit can summarize the conversation content using a summarization algorithm and provide feedback that emphasizes information that is important to Person A. The feedback unit can also suggest a topic that Person A should talk about next. Furthermore, the feedback unit can also briefly summarize the main points of the conversation and provide this to Person A. By summarizing the conversation content and emphasizing important information, Person A can easily understand the topic that he or she should talk about next. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input the conversation content into a generation AI, which can then summarize and emphasize important information.

[0098] The feedback unit can improve the accuracy of feedback based on Person A's past feedback history. For example, the feedback unit collects Person A's past feedback history from details of the date and time and content of the feedback. The feedback unit can also analyze the past feedback history and adjust the content of the feedback. Furthermore, the feedback unit can extract and provide important information from Person A's past feedback history. In this way, the accuracy of feedback can be improved by referring to Person A's past feedback history. Some or all of the above-mentioned processing in the feedback unit may be performed using, or without, a generation AI, for example. For example, the feedback unit can input Person A's past feedback history data into the generation AI, and the generation AI can improve the accuracy of the feedback.

[0099] The feedback unit can customize the feedback method based on person A's personality or behavioral patterns. The feedback unit learns person A's personality and behavioral patterns based on, for example, the results of a personality diagnostic test or an analysis of person A's behavioral history. Furthermore, the feedback unit can provide positive feedback if person A has a sociable personality. Furthermore, the feedback unit can provide gentle feedback if person A has an introverted personality. In this way, the feedback method can be customized by taking person A's personality and behavioral patterns into consideration. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input person A's personality and behavioral pattern data into the generation AI, and use the generation AI to customize the feedback method.

[0100] The feedback unit can estimate Person A's emotions and adjust the frequency of feedback based on the estimated emotions of Person A. The feedback unit, for example, estimates Person A's emotions using voice analysis or facial expression recognition technology. For example, the feedback unit analyzes changes in Person A's tone of voice and facial expressions to calculate an emotion score. The feedback unit can also adjust the frequency of feedback based on the estimated emotions of Person A. For example, if Person A is feeling stressed, the feedback frequency can be reduced to alleviate the burden. Furthermore, if Person A is relaxed, the feedback unit can increase the feedback frequency to provide information efficiently. This enables more appropriate feedback by adjusting the feedback frequency based on Person A's emotions. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input Person A's emotion data into the generation AI, and the generation AI can adjust the feedback frequency.

[0101] The feedback unit can select the optimal feedback timing based on person A's lifestyle rhythm. The feedback unit, for example, evaluates person A's lifestyle rhythm based on daily activity patterns, sleep duration, etc. Furthermore, if person A has a morning-type lifestyle rhythm, the feedback unit can provide feedback in the morning hours. Furthermore, if person A has a nocturnal lifestyle rhythm, the feedback unit can provide feedback in the evening hours. This enables efficient feedback by adjusting the feedback timing to match person A's lifestyle rhythm. Some or all of the above-mentioned processing in the feedback unit may be performed using, or without, a generation AI, for example. For example, the feedback unit can input person A's lifestyle rhythm data into the generation AI, and the generation AI can select the optimal feedback timing.

[0102] The feedback unit can analyze Person A's social media activity and incorporate relevant information into the feedback. The feedback unit can, for example, analyze Person A's social media activity based on the content of posts, the number of likes, comments, etc. The feedback unit can also incorporate content that Person A frequently posts on social media into the feedback. Furthermore, the feedback unit can analyze Person A's friendships on social media and incorporate relevant information into the feedback. In this way, by analyzing Person A's social media activity, relevant information can be incorporated into the feedback. Some or all of the above-described processing in the feedback unit can be performed using, or without, a generation AI, for example. For example, the feedback unit can input Person A's social media data into the generation AI, and have the generation AI provide feedback of relevant information.

[0103] The feedback unit can diversify the content of the feedback based on person A's hobbies or interests. For example, the feedback unit collects person A's hobbies and interests from a questionnaire survey or an analysis of his / her behavioral history. The feedback unit can also incorporate information about sports that person A enjoys into the feedback. Furthermore, the feedback unit can also incorporate information about movies and music that person A is interested in into the feedback. In this way, the content of the feedback can be diversified by taking person A's hobbies and interests into consideration. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI, for example. For example, the feedback unit can input data about person A's hobbies and interests into the generation AI, and the generation AI can diversify the content of the feedback. === Hard Collateral 1-1 === Each of the multiple elements including the learning unit, download unit, conversation unit, and feedback unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart device 14 and learns Person A's past conversation history and voice characteristics. The download unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and downloads Person A's personal data via the Internet. The conversation unit is realized, for example, by the control unit 46A of the smart device 14 and reproduces Person A's voice using voice synthesis technology to conduct a conversation in natural language. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the content of the conversation and provides feedback to Person A. === Hard Collateral 1-2 === Each of the multiple elements including the learning unit, download unit, conversation unit, and feedback unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart glasses 214 and learns Person A's past conversation history and voice characteristics. The download unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and downloads Person A's personal data via the Internet. The conversation unit is realized, for example, by the control unit 46A of the smart glasses 214 and reproduces Person A's voice using voice synthesis technology to converse in natural language. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the content of the conversation and provides feedback to Person A. === Hard Collateral 1-3 === Each of the multiple elements including the learning unit, download unit, conversation unit, and feedback unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the headset type terminal 314 and learns the past conversation history and voice characteristics of Person A. The download unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and downloads Person A's personal data via the Internet. The conversation unit is realized, for example, by the control unit 46A of the headset type terminal 314 and reproduces Person A's voice using speech synthesis technology to converse in natural language. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the content of the conversation and provides feedback to Person A. === Hard Collateral 1-4 === Each of the multiple elements including the learning unit, download unit, conversation unit, and feedback unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the robot 414 and learns Person A's past conversation history and vocal characteristics. The download unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and downloads Person A's personal data via the Internet. The conversation unit is realized, for example, by the control unit 46A of the robot 414 and reproduces Person A's voice using voice synthesis technology and conducts a conversation in natural language. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the content of the conversation and provides feedback to Person A.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The communication system further includes an emotion estimation unit that can estimate the user's emotions in real time and adjust the tone and content of the conversation based on those emotions. For example, if the user is feeling stressed, the system can speak to them in a calm tone and offer relaxing topics. If the user is happy, the system can continue the conversation in a cheerful tone and offer positive topics. If the user is sad, the system can speak to them in a comforting tone and offer words of encouragement. This enables appropriate communication according to the user's emotions.

[0106] The communication system also includes a health management unit that monitors the user's health condition and can adjust the content of the conversation based on the user's health data. For example, if the user is tired, the system can suggest short conversations and provide relaxing topics. If the user is healthy and active, the system can suggest longer conversations and provide interesting topics. Furthermore, if the user is sick or injured, the system can offer comforting words and health advice. This enables appropriate communication according to the user's health condition.

[0107] The communication system also includes a schedule management unit that manages the user's schedule, allowing it to adjust the timing and content of conversations based on the user's schedule. For example, if the user has a busy schedule, the system can suggest short conversations to ensure efficient communication. If the user has a relaxed schedule, the system can suggest longer conversations and provide relaxing topics. Furthermore, if the user has an important event coming up, the system can provide information related to that event and support preparations. This enables appropriate communication based on the user's schedule.

[0108] The communication system also includes an hobby learning module that learns the user's hobbies and interests, allowing it to diversify conversation topics based on the user's interests. For example, if the user is interested in sports, the system can provide topics about the latest sports news and game results. If the user is interested in movies or music, the system can provide topics about new movies and popular music. Furthermore, if the user is interested in travel, the system can provide topics about travel destinations and recommended tourist spots. This enables diverse communication based on the user's hobbies and interests.

[0109] The communication system further includes a history analysis unit that analyzes the user's past conversation history, and can suggest the next conversation topic based on the content of the past conversation. For example, it can prioritize suggestions of topics that the user has frequently discussed in the past. It can also prioritize suggestions of topics to which the user has responded strongly in the past. It can also re-suggest topics in which the user has shown interest in the past but has not discussed in depth. This enables natural communication based on the user's past conversation history.

[0110] The communication system may further include a feedback adjustment unit that estimates the user's emotions and adjusts the content of the feedback based on the estimated emotions. For example, if the user is feeling stressed, the system may provide concise, positive feedback. If the user is feeling relaxed, the system may provide detailed feedback. If the user is feeling sad, the system may provide comforting feedback. This allows for appropriate feedback according to the user's emotions.

[0111] The communication system can further include a conversation adjustment unit that estimates the user's emotions and adjusts the length of the conversation based on the estimated emotions. For example, if the user is feeling stressed, the system can suggest a short conversation. If the user is feeling relaxed, the system can suggest a longer conversation. If the user is excited, the system can suggest a longer conversation that shares that excitement. This allows the length of the conversation to be appropriate according to the user's emotions.

[0112] The communication system may further include a tone adjustment unit that estimates the user's emotions and adjusts the tone of the conversation based on the estimated emotions. For example, if the user is feeling stressed, the system may speak to the user in a calm tone. If the user is happy, the system may continue the conversation in a cheerful tone. If the user is sad, the system may speak to the user in a comforting tone. This makes it possible to communicate in an appropriate tone according to the user's emotions.

[0113] The communication system can further include a content adjustment unit that estimates the user's emotions and adjusts the content of the conversation based on the estimated emotions. For example, if the user is feeling stressed, the system can provide relaxing topics. If the user is happy, the system can provide positive topics. If the user is sad, the system can provide comforting topics. This makes it possible to communicate with appropriate content according to the user's emotions.

[0114] The communication system may further include a geographic information unit that prioritizes the acquisition of highly relevant data based on the user's geographic location information. For example, if the user is in a specific area, data related to that area may be downloaded preferentially. If the user is traveling, data related to the travel destination may be downloaded preferentially. If the user is participating in a specific event, data related to that event may be downloaded preferentially. This makes it possible to acquire appropriate data based on the user's geographic location information.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The learning unit learns information or voice information that forms Person A's personality. Specifically, it collects and learns past behavioral history, personality diagnosis results, past conversation history, and voice characteristics (tone, pitch, intonation), etc. Step 2: The downloading unit downloads personal data based on the information learned by the learning unit. For example, the downloading unit obtains personal data of Person A via the Internet using a protocol such as HTTP or FTP. Step 3: The conversation unit uses a voice synthesized based on the personal data downloaded by the download unit. Using voice synthesis technology and natural language processing (NLP) technology, it reproduces Person A's voice and enables natural conversation. Step 4: The feedback unit summarizes the conversation conducted by the conversation unit and provides feedback to Person A. The conversation is summarized using a summary algorithm, and important information is emphasized and provided as feedback.

[0117] 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.

[0118] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A learning section that learns information or audio information that forms Mr. A's personality; a download unit that downloads personal data based on the information learned by the learning unit; a conversation unit that converses using a voice synthesized based on the personal data downloaded by the download unit; a feedback unit that summarizes the content of the conversation carried out by the conversation unit and provides the summary to person A as feedback; A system characterized by:

2. The learning unit Learn about A's past conversation history, voice characteristics, and personality 2. The system of claim 1.

3. The download unit Downloading A's personal data via the Internet 2. The system of claim 1.

4. The conversation unit is The conversation is conducted using a voice synthesized based on A's personal data.

2. The system of claim 1.

5. The feedback unit Summarize the conversation and provide feedback to A 2. The system of claim 1.

6. The learning unit Estimate person A's emotions and select learning data based on the estimated emotions of person A.

2. The system of claim 1.

7. The learning unit Analyze A's past conversation history and learn how he responds to specific topics 2. The system of claim 1.

8. The learning unit Analyze the characteristics of A's voice and learn his tone and intonation 2. The system of claim 1.

Images