System

Abstract

An object of a system according to an embodiment is to quickly create an appropriate conversation material suitable for a conversation target person.SOLUTION: A system includes an event collection unit, an interest determination unit, and a material creation unit. An event collector collects recent events using the generated AI. The interest specifying unit specifies an interest and concern of a target person of a conversation. The material creation section creates a conversation material based on the recent event collected by the event collection section and the interest / concern identified by the interest identification section.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 techniques have had the problem of making it difficult to quickly create appropriate conversation topics tailored to the person being spoken to.

[0005] The system according to the embodiment aims to quickly create appropriate conversation topics tailored to the person to be talked to. [Means for solving the problem]

[0006] The system according to the embodiment includes an event collection unit, an interest identification unit, and a topic creation unit. The event collection unit collects recent events using a generation AI. The interest identification unit identifies the interests and concerns of the conversation target. The topic creation unit creates conversation topics based on the recent events collected by the event collection unit and the interests and concerns identified by the interest identification unit. [Effects of the Invention]

[0007] The system according to the embodiment can quickly create appropriate conversation topics tailored to the person being talked to. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The conversation topic creation system according to an embodiment of the present invention is a system in which a generation AI collects recent events, identifies the interests and concerns of the person being talked to, and creates conversation topics based on the collected events. This allows the conversation topic creation system to efficiently create conversation starters.

[0029] A conversation topic creation system according to an embodiment includes an event collection unit, an interest identification unit, and a topic creation unit. The event collection unit uses a generation AI to collect recent events. For example, the generation AI collects news articles and social media posts. The generation AI can also collect blog and forum posts. The generation AI can also collect podcast and webinar content. For example, the generation AI collects and analyzes the latest news articles from news sites. The generation AI collects the latest posts using social media APIs. The generation AI collects the latest posts using RSS feeds from blogs and forums. The generation AI converts podcast audio data into text and analyzes it. The generation AI analyzes webinar recording data and extracts content. The interest identification unit identifies the interests and concerns of the conversation target. For example, the interest identification unit analyzes the target's profile information. The interest identification unit can also analyze the target's past conversation history. The interest identification unit can also analyze the target's social media posts and following accounts. For example, the interest identification unit identifies hobbies and interests from the target person's profile information. The interest identification unit identifies topics in which the target person is interested from past conversation history. The interest identification unit identifies topics on which the target person frequently posts from social media posts. The interest identification unit identifies the target person's interests from the content of accounts the target person follows. The topic creation unit creates conversation topics based on recent events collected by the event collection unit and the interests and concerns identified by the interest identification unit. For example, the topic creation unit uses a generation AI to combine the collected events and the identified interests and concerns to create conversation topics. The topic creation unit can also use an emotion estimation function to prioritize creating topics that evoke strong emotional responses. The topic creation unit can also create visually appealing topics, including visual data. For example, the topic creation unit uses a generation AI to generate conversation topics based on collected events and identified interests and concerns. The topic creation unit uses an emotion estimation function to prioritize creating topics that evoke strong emotional responses. The topic creation unit can also create visually appealing topics, including visual data.This allows the conversation topic creation system to efficiently start conversations. For example, before a business meeting, the AI ​​can suggest the latest industry news, which helps the conversation flow smoothly and builds trust. Even in personal friendships, the AI ​​can deepen relationships by suggesting conversation topics based on shared interests.

[0030] The event collection unit diversifies information sources and can include not only news but also podcast and webinar content as analysis targets. For example, the event collection unit's generative AI collects and analyzes not only news articles but also podcast episodes and webinar content. For example, podcasts about the latest technology are included as analysis targets. The event collection unit also converts audio data from podcasts and webinars into text, and the generative AI analyzes that content. For example, it uses speech recognition technology to convert audio data into text and analyzes it. The event collection unit also uses the generative AI to comprehensively analyze the content of news articles, podcasts, and webinars to evaluate recent events from multiple angles. For example, it combines data from different information sources for analysis. This diversifies information sources and enables more multifaceted analysis.

[0031] The event collection unit performs trend analysis of collected events along a timeline, making it possible to capture long-term changes. For example, the event collection unit organizes events collected by the generation AI along a timeline and performs trend analysis. For example, it analyzes technological progress over the past year in chronological order. The event collection unit also develops algorithms based on data along a timeline to enable the generation AI to capture long-term trends. For example, it analyzes the increase or decrease in events related to a specific theme. The event collection unit also visualizes the events collected by the generation AI along a timeline, visually displaying long-term changes. For example, it shows trends using graphs and charts. This makes it possible to capture long-term changes.

[0032] The event collection unit also analyzes from the perspectives of different cultural spheres and regions, making it possible to provide conversation topics from a global perspective. For example, the generation AI collects and analyzes news articles and social media posts from different cultural spheres and regions. For example, it compares and analyzes news from Asia, Europe, and America. The event collection unit also analyzes events from different cultural spheres to generate conversation topics from a global perspective. For example, it analyzes reactions to the same event from different cultural spheres. The generation AI also collects events from different regions and analyzes them taking into account cultural background and regional characteristics. For example, it evaluates trends and topicality in each region. This makes it possible to provide conversation topics from a global perspective.

[0033] The event collection unit can also analyze visual data and create conversation topics that include visual elements. For example, the event collection unit uses a generation AI to collect and analyze images and videos contained in news articles and social media posts. For example, the visual data is analyzed using image recognition technology. The event collection unit also uses a generation AI to create conversation topics that include visual elements based on the collected visual data. For example, the content of the images and videos is summarized and provided as conversation topics. The event collection unit also uses a generation AI to analyze the visual data and generate visually appealing conversation topics. For example, features of images and videos are extracted and used as conversation starters. This makes it possible to create conversation topics that include visual elements.

[0034] The interest identification unit can also include the subject's social media posts and followed accounts in its analysis. For example, the generation AI analyzes the subject's social media posts and followed accounts to identify interests. For example, it analyzes the topics the subject frequently posts to. The interest identification unit also identifies the subject's interests based on social media data. For example, it analyzes the content of followed accounts to identify areas of interest. The interest identification unit also analyzes the subject's social media activity and lists the subjects' interests. For example, it identifies topics that the subject frequently "likes" or "shares." By including social media posts and followed accounts in its analysis, it is possible to identify interests with greater accuracy.

[0035] The interest identification unit also analyzes the purchase history and browsing history of the target person, allowing for more accurate identification of interests. For example, the generation AI analyzes the purchase history of the target person to identify interests. For example, it identifies areas of interest based on data on products and services purchased in the past. The interest identification unit also analyzes the browsing history of the target person, allowing the generation AI to identify interests. For example, it analyzes the content of frequently visited websites and articles. The interest identification unit also lists the target person's interests based on the purchase history and browsing history. For example, it identifies interest in products and services in a specific category. In this way, by analyzing the purchase history and browsing history as well, it is possible to identify interests with greater accuracy.

[0036] The interest identification unit can provide relevant conversation topics by taking into account the interests of the subject's family and friends. For example, the generation AI analyzes the interests of the subject's family and friends and provides conversation topics based on that. For example, it lists topics that family and friends are interested in. The interest identification unit also analyzes the social media posts and accounts followed by the subject's family and friends to generate related conversation topics. For example, it identifies topics of common interest. The interest identification unit also customizes conversation topics by taking into account the interests of the subject's family and friends. For example, it provides events and news that family and friends are interested in as conversation topics. This allows the generation AI to provide more relevant conversation topics by taking into account the interests of family and friends.

[0037] The interest identification unit can also analyze trends in the subject's occupation and industry and provide industry-specific conversation topics. For example, the generation AI of the interest identification unit analyzes trends in the subject's occupation and industry and provides related conversation topics. For example, the latest industry news and technology trends are provided as conversation topics. The interest identification unit also collects data related to the subject's occupation, and the generation AI identifies interests and concerns. For example, information on events and conferences related to the occupation is analyzed. The interest identification unit also analyzes trends specific to the subject's industry and customizes the conversation topics. For example, the latest technology and market trends in the industry are provided as conversation topics. In this way, industry-specific conversation topics can be provided by analyzing trends in occupations and industries.

[0038] The material creation unit can analyze past success stories and incorporate effective expressions to include humor and wit. For example, the generation AI in the material creation unit analyzes past success stories and incorporates effective expressions that include humor and wit. For example, it extracts expressions that received particularly good responses from past conversation topics. In addition, in order to create conversation topics that include humor and wit, the generation AI learns from past success stories and lists effective expressions. For example, it incorporates jokes and funny anecdotes. In addition, the material creation unit can create conversation topics that include humor and wit based on past success stories. For example, it incorporates humor that suits a specific situation or theme. In this way, it is possible to analyze past success stories and incorporate effective expressions to include humor and wit.

[0039] The material creation unit can quote the target person's past statements and actions to provide personalized material. For example, the material creation unit uses a generation AI to analyze the target person's past statements and actions and quote them to create personalized conversation topics. For example, material is created based on what the target person has said in the past. The material creation unit also uses the generation AI to provide personalized conversation topics based on the target person's past behavioral data. For example, it quotes events and activities that the target person participated in. The material creation unit also uses the generation AI to list the target person's past statements and actions and create personalized conversation topics based on that. For example, it quotes topics that the target person has shown interest in. This makes it possible to quote the target person's past statements and actions and provide personalized material.

[0040] The topic creation unit can incorporate perspectives from different cultural spheres and regions to provide conversation topics from a global perspective. In the topic creation unit, for example, the generation AI creates conversation topics that incorporate perspectives from different cultural spheres and regions. For example, it uses information about the cultures and customs of different countries as material. The topic creation unit also analyzes events in different cultural spheres, and the generation AI provides conversation topics from a global perspective. For example, it uses international events and news as material. The topic creation unit also creates conversation topics that incorporate perspectives from different regions. For example, it evaluates trends and topicality in each region and provides them as conversation topics. This makes it possible to incorporate perspectives from different cultural spheres and provide conversation topics from a global perspective.

[0041] The topic creation unit can provide visually appealing topics, including visual data. For example, the topic creation unit includes images and videos in the conversation topics created by the generation AI to provide visually appealing topics. For example, images and videos related to news articles are attached. The topic creation unit also has the generation AI create visually appealing conversation topics based on the visual data. For example, the content of the images and videos is summarized and provided as conversation topics. The topic creation unit also has the generation AI analyze the visual data to generate visually appealing conversation topics. For example, the features of the images and videos are extracted and used as conversation starters. This makes it possible to provide visually appealing topics, including visual data.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The conversation topic creation system can also monitor the user's health status and provide health-related conversation topics. For example, it can analyze data obtained from the user's fitness tracker or smartwatch to provide health-related topics. It can also analyze the user's food records and sleep patterns to provide health advice and information as conversation topics. It can also provide conversation topics related to relaxation methods and stress management based on the user's health status. This allows it to provide conversation topics tailored to the user's health status.

[0044] The conversation topic creation system can also provide conversation topics based on the user's hobbies and special skills. For example, if the user likes cooking, topics related to the latest recipes and cooking tips can be provided. If the user is interested in sports, the system can provide the latest game results and player information as conversation topics. Furthermore, if the user is interested in music, it can provide information on new albums and concerts. In this way, conversation topics can be provided that match the user's hobbies and special skills.

[0045] The conversation topic creation system can also analyze the user's past travel history and provide conversation topics related to travel. For example, it can provide information about places the user has visited in the past and recommended travel destinations to visit next. It can also provide information about tourist spots and events that may interest the user as conversation topics. It can also provide advice on planning and preparing for a trip based on the user's travel history. This makes it possible to provide conversation topics that are tailored to the user's travel history.

[0046] The conversation topic creation system can also analyze the user's learning history and provide conversation topics related to education. For example, it can provide the latest research and discoveries related to the content the user has previously learned or the fields in which the user is interested. It can also provide information about new skills and knowledge the user wants to learn as conversation topics. It can also provide advice on learning methods and resources based on the user's learning history. This makes it possible to provide conversation topics that are tailored to the user's learning history.

[0047] The conversation topic creation system can also analyze weather information in the user's area and provide conversation topics related to the weather. For example, it can provide weather forecasts and weather information for the area where the user lives. It can also provide information on weather-related events and activities as conversation topics. It can also provide information on seasonal characteristics and climate in the user's area. This makes it possible to provide conversation topics that correspond to the weather information in the user's area.

[0048] The conversation topic creation system can also analyze the user's musical preferences and provide conversation topics related to music. For example, it can provide the latest news and release information about the user's favorite artists and genres. It can also introduce new artists and songs that the user might be interested in. It can also provide information about concerts and festivals based on the user's musical preferences. This allows it to provide conversation topics that match the user's musical preferences.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: The event collection unit uses generative AI to collect recent events. For example, generative AI collects news articles, social media posts, blog and forum posts, podcast and webinar content. Specifically, it collects and analyzes the latest news articles from news sites; collects the latest posts using social media APIs and the latest posts using blog and forum RSS feeds; converts podcast audio data into text and analyzes it; and analyzes webinar recordings to extract content. Step 2: The interest identification unit identifies the interests of the person being talked to. For example, it analyzes the person's profile information to identify their hobbies and interests. It analyzes past conversation history to identify topics in which the person is interested. It analyzes social media posts and followed accounts to identify interests based on the topics the person frequently posts on and the content of the accounts they follow. Step 3: The topic creation unit creates conversation topics based on recent events collected by the event collection unit and the interests identified by the interest identification unit. For example, a generative AI can be used to combine collected events and identified interests to create conversation topics. An emotion estimation function can also be used to prioritize the creation of topics that evoke strong emotional responses. Visually appealing topics can also be created by including visual data.

[0051] (Example 2) The conversation topic creation system according to an embodiment of the present invention is a system in which a generation AI collects recent events, identifies the interests and concerns of the person being talked to, and creates conversation topics based on the collected events. This allows the conversation topic creation system to efficiently create conversation starters.

[0052] A conversation topic creation system according to an embodiment includes an event collection unit, an interest identification unit, and a topic creation unit. The event collection unit uses a generation AI to collect recent events. For example, the generation AI collects news articles and social media posts. The generation AI can also collect blog and forum posts. The generation AI can also collect podcast and webinar content. For example, the generation AI collects and analyzes the latest news articles from news sites. The generation AI collects the latest posts using social media APIs. The generation AI collects the latest posts using RSS feeds from blogs and forums. The generation AI converts podcast audio data into text and analyzes it. The generation AI analyzes webinar recording data and extracts content. The interest identification unit identifies the interests and concerns of the conversation target. For example, the interest identification unit analyzes the target's profile information. The interest identification unit can also analyze the target's past conversation history. The interest identification unit can also analyze the target's social media posts and following accounts. For example, the interest identification unit identifies hobbies and interests from the target person's profile information. The interest identification unit identifies topics in which the target person is interested from past conversation history. The interest identification unit identifies topics on which the target person frequently posts from social media posts. The interest identification unit identifies the target person's interests from the content of accounts the target person follows. The topic creation unit creates conversation topics based on recent events collected by the event collection unit and the interests and concerns identified by the interest identification unit. For example, the topic creation unit uses a generation AI to combine the collected events and the identified interests and concerns to create conversation topics. The topic creation unit can also use an emotion estimation function to prioritize creating topics that evoke strong emotional responses. The topic creation unit can also create visually appealing topics, including visual data. For example, the topic creation unit uses a generation AI to generate conversation topics based on collected events and identified interests and concerns. The topic creation unit uses an emotion estimation function to prioritize creating topics that evoke strong emotional responses. The topic creation unit can also create visually appealing topics, including visual data.This allows the conversation topic creation system to efficiently start conversations. For example, before a business meeting, the AI ​​can suggest the latest industry news, which helps the conversation flow smoothly and builds trust. Even in personal friendships, the AI ​​can deepen relationships by suggesting conversation topics based on shared interests.

[0053] The event collection unit uses the emotion estimation function to evaluate the emotional impact of collected events and prioritize analysis of events that evoke strong emotional reactions. For example, the event collection unit performs emotion analysis on news articles and social media posts collected by the generation AI and calculates an emotion score. For example, it prioritizes analysis of events that evoke strong emotions such as joy or surprise. The event collection unit also uses the emotion estimation function to evaluate the emotional impact of collected events and list events with high emotion scores. For example, it selects moving stories and events that are popular. The event collection unit also performs emotion analysis on events collected by the generation AI and filters out events that evoke strong emotional reactions. For example, it prioritizes analysis of events that contain a large number of positive emotions. This allows it to prioritize analysis of events that evoke strong emotional reactions.

[0054] The event collection unit diversifies information sources and can include not only news but also podcast and webinar content as analysis targets. For example, the event collection unit's generative AI collects and analyzes not only news articles but also podcast episodes and webinar content. For example, podcasts about the latest technology are included as analysis targets. The event collection unit also converts audio data from podcasts and webinars into text, and the generative AI analyzes that content. For example, it uses speech recognition technology to convert audio data into text and analyzes it. The event collection unit also uses the generative AI to comprehensively analyze the content of news articles, podcasts, and webinars to evaluate recent events from multiple angles. For example, it combines data from different information sources for analysis. This diversifies information sources and enables more multifaceted analysis.

[0055] The event collection unit performs trend analysis of collected events along a timeline, making it possible to capture long-term changes. For example, the event collection unit organizes events collected by the generation AI along a timeline and performs trend analysis. For example, it analyzes technological progress over the past year in chronological order. The event collection unit also develops algorithms based on data along a timeline to enable the generation AI to capture long-term trends. For example, it analyzes the increase or decrease in events related to a specific theme. The event collection unit also visualizes the events collected by the generation AI along a timeline, visually displaying long-term changes. For example, it shows trends using graphs and charts. This makes it possible to capture long-term changes.

[0056] The event collection unit also analyzes from the perspectives of different cultural spheres and regions, making it possible to provide conversation topics from a global perspective. For example, the generation AI collects and analyzes news articles and social media posts from different cultural spheres and regions. For example, it compares and analyzes news from Asia, Europe, and America. The event collection unit also analyzes events from different cultural spheres to generate conversation topics from a global perspective. For example, it analyzes reactions to the same event from different cultural spheres. The generation AI also collects events from different regions and analyzes them taking into account cultural background and regional characteristics. For example, it evaluates trends and topicality in each region. This makes it possible to provide conversation topics from a global perspective.

[0057] The event collection unit can also analyze visual data and create conversation topics that include visual elements. For example, the event collection unit uses a generation AI to collect and analyze images and videos contained in news articles and social media posts. For example, the visual data is analyzed using image recognition technology. The event collection unit also uses a generation AI to create conversation topics that include visual elements based on the collected visual data. For example, the content of the images and videos is summarized and provided as conversation topics. The event collection unit also uses a generation AI to analyze the visual data and generate visually appealing conversation topics. For example, features of images and videos are extracted and used as conversation starters. This makes it possible to create conversation topics that include visual elements.

[0058] The event collection unit can analyze the user's emotional reactions to events collected using the emotion estimation function in real time and select events that will elicit a positive reaction. For example, the event collection unit can analyze the user's emotional reactions to events collected by the generation AI in real time and select events that will elicit a positive reaction. For example, it can analyze the user's facial expressions and voice. The event collection unit also uses the emotion estimation function to calculate the user's emotional score for the collected events and prioritizes selecting events that have a high number of positive reactions. For example, it can select events with moving stories or popular topics. The event collection unit also lists events that will elicit a positive reaction from the generation AI based on the user's emotional reaction data. For example, it prioritizes analyzing events with a high emotional score. This makes it possible to select events that will elicit a positive reaction.

[0059] The interest identification unit can use the emotion estimation function to extract topics that have elicited strong emotional responses from past conversation history. For example, the generation AI in the interest identification unit analyzes the subject's past conversation history and uses the emotion estimation function to extract topics that have elicited strong emotional responses. For example, it identifies topics that elicit strong positive emotions. The interest identification unit also uses the emotion estimation function to list topics that the subject has elicited strong emotional responses to in past conversations. For example, it extracts topics that elicit strong emotions of joy or excitement. The interest identification unit also analyzes the subject's past conversation history and identifies the subject's interests and concerns based on the emotion score. For example, it prioritizes selecting topics with high emotion scores. This makes it possible to extract topics that have elicited strong emotional responses.

[0060] The interest identification unit can also include the subject's social media posts and followed accounts in its analysis. For example, the generation AI analyzes the subject's social media posts and followed accounts to identify interests. For example, it analyzes the topics the subject frequently posts to. The interest identification unit also identifies the subject's interests based on social media data. For example, it analyzes the content of followed accounts to identify areas of interest. The interest identification unit also analyzes the subject's social media activity and lists the subjects' interests. For example, it identifies topics that the subject frequently "likes" or "shares." By including social media posts and followed accounts in its analysis, it is possible to identify interests with greater accuracy.

[0061] The interest identification unit also analyzes the purchase history and browsing history of the target person, allowing for more accurate identification of interests. For example, the generation AI analyzes the purchase history of the target person to identify interests. For example, it identifies areas of interest based on data on products and services purchased in the past. The interest identification unit also analyzes the browsing history of the target person, allowing the generation AI to identify interests. For example, it analyzes the content of frequently visited websites and articles. The interest identification unit also lists the target person's interests based on the purchase history and browsing history. For example, it identifies interest in products and services in a specific category. In this way, by analyzing the purchase history and browsing history as well, it is possible to identify interests with greater accuracy.

[0062] The interest identification unit can provide relevant conversation topics by taking into account the interests of the subject's family and friends. For example, the generation AI analyzes the interests of the subject's family and friends and provides conversation topics based on that. For example, it lists topics that family and friends are interested in. The interest identification unit also analyzes the social media posts and accounts followed by the subject's family and friends to generate related conversation topics. For example, it identifies topics of common interest. The interest identification unit also customizes conversation topics by taking into account the interests of the subject's family and friends. For example, it provides events and news that family and friends are interested in as conversation topics. This allows the generation AI to provide more relevant conversation topics by taking into account the interests of family and friends.

[0063] The interest identification unit can also analyze trends in the subject's occupation and industry and provide industry-specific conversation topics. For example, the generation AI of the interest identification unit analyzes trends in the subject's occupation and industry and provides related conversation topics. For example, the latest industry news and technology trends are provided as conversation topics. The interest identification unit also collects data related to the subject's occupation, and the generation AI identifies interests and concerns. For example, information on events and conferences related to the occupation is analyzed. The interest identification unit also analyzes trends specific to the subject's industry and customizes the conversation topics. For example, the latest technology and market trends in the industry are provided as conversation topics. In this way, industry-specific conversation topics can be provided by analyzing trends in occupations and industries.

[0064] The interest identification unit can use the emotion estimation function to identify topics for which the subject shows the most positive emotions and provide conversation topics related to those topics. The interest identification unit, for example, uses the emotion estimation function to identify topics for which the subject shows the most positive emotions. For example, it analyzes past conversation history and social media posts. The interest identification unit also uses the generation AI to analyze the subject's emotional responses in real time and list topics that evoke strong positive emotions. For example, it identifies topics that evoke strong emotions such as joy and excitement. The interest identification unit also uses the generation AI to select topics that evoke positive emotions based on the emotion estimation data and provide related conversation topics. For example, it prioritizes selecting topics with high emotion scores. This makes it possible to identify topics that evoke positive emotions and provide conversation topics related to those topics.

[0065] The material creation unit uses the emotion estimation function to evaluate the emotional impact of the conversation topics created, and can prioritize the creation of topics that evoke strong emotional responses. The material creation unit, for example, performs an emotion analysis on the conversation topics created by the generation AI and calculates an emotion score. For example, it prioritizes the creation of topics that evoke strong emotions such as joy or surprise. The material creation unit also uses the emotion estimation function to evaluate the emotional impact of the conversation topics created by the generation AI and lists topics with high emotion scores. For example, it selects topics with moving stories or that are highly topical. The material creation unit also performs an emotion analysis on the conversation topics created by the generation AI and filters out topics that evoke strong emotional responses. For example, it prioritizes the creation of topics that contain a lot of positive emotions. This makes it possible to prioritize the creation of topics that evoke strong emotional responses.

[0066] The material creation unit can analyze past success stories and incorporate effective expressions to include humor and wit. For example, the generation AI in the material creation unit analyzes past success stories and incorporates effective expressions that include humor and wit. For example, it extracts expressions that received particularly good responses from past conversation topics. In addition, in order to create conversation topics that include humor and wit, the generation AI learns from past success stories and lists effective expressions. For example, it incorporates jokes and funny anecdotes. In addition, the material creation unit can create conversation topics that include humor and wit based on past success stories. For example, it incorporates humor that suits a specific situation or theme. In this way, it is possible to analyze past success stories and incorporate effective expressions to include humor and wit.

[0067] The material creation unit can quote the target person's past statements and actions to provide personalized material. For example, the material creation unit uses a generation AI to analyze the target person's past statements and actions and quote them to create personalized conversation topics. For example, material is created based on what the target person has said in the past. The material creation unit also uses the generation AI to provide personalized conversation topics based on the target person's past behavioral data. For example, it quotes events and activities that the target person participated in. The material creation unit also uses the generation AI to list the target person's past statements and actions and create personalized conversation topics based on that. For example, it quotes topics that the target person has shown interest in. This makes it possible to quote the target person's past statements and actions and provide personalized material.

[0068] The topic creation unit can incorporate perspectives from different cultural spheres and regions to provide conversation topics from a global perspective. In the topic creation unit, for example, the generation AI creates conversation topics that incorporate perspectives from different cultural spheres and regions. For example, it uses information about the cultures and customs of different countries as material. The topic creation unit also analyzes events in different cultural spheres, and the generation AI provides conversation topics from a global perspective. For example, it uses international events and news as material. The topic creation unit also creates conversation topics that incorporate perspectives from different regions. For example, it evaluates trends and topicality in each region and provides them as conversation topics. This makes it possible to incorporate perspectives from different cultural spheres and provide conversation topics from a global perspective.

[0069] The topic creation unit can provide visually appealing topics, including visual data. For example, the topic creation unit includes images and videos in the conversation topics created by the generation AI to provide visually appealing topics. For example, images and videos related to news articles are attached. The topic creation unit also has the generation AI create visually appealing conversation topics based on the visual data. For example, the content of the images and videos is summarized and provided as conversation topics. The topic creation unit also has the generation AI analyze the visual data to generate visually appealing conversation topics. For example, the features of the images and videos are extracted and used as conversation starters. This makes it possible to provide visually appealing topics, including visual data.

[0070] The topic creation unit can analyze the user's emotional response to the conversation topics created using the emotion estimation function in real time, and continuously provide topics that elicit positive responses. The topic creation unit, for example, uses the emotion estimation function to analyze the user's emotional response to the created conversation topics in real time, and provides topics that elicit positive responses. For example, it analyzes the user's facial expressions and voice. The topic creation unit also lists conversation topics that elicit positive responses based on the user's emotional response data, and provides topics that elicit positive responses based on the emotion estimation data, for example. For example, it provides topics with a high emotional score as a priority. The topic creation unit also continuously provides conversation topics that elicit positive responses based on the emotion estimation data, for example, it dynamically adjusts the topics according to changes in the user's emotions. This allows the generation AI to continuously provide topics that elicit positive responses.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The conversation topic creation system can also monitor the user's health status and provide health-related conversation topics. For example, it can analyze data obtained from the user's fitness tracker or smartwatch to provide health-related topics. It can also analyze the user's food records and sleep patterns to provide health advice and information as conversation topics. It can also provide conversation topics related to relaxation methods and stress management based on the user's health status. This allows it to provide conversation topics tailored to the user's health status.

[0073] The conversation topic creation system can also estimate the user's emotions and adjust conversation topics based on the estimated emotions. For example, if the user is feeling stressed, it can provide topics that will help them relax or change their mood. If the user is happy, it can also provide positive topics that will further enhance their emotions. Furthermore, if the user is sad, it can also provide topics that will comfort or encourage them. In this way, it is possible to provide conversation topics that correspond to the user's emotions.

[0074] The conversation topic creation system can also provide conversation topics based on the user's hobbies and special skills. For example, if the user likes cooking, topics related to the latest recipes and cooking tips can be provided. If the user is interested in sports, the system can provide the latest game results and player information as conversation topics. Furthermore, if the user is interested in music, it can provide information on new albums and concerts. In this way, conversation topics can be provided that match the user's hobbies and special skills.

[0075] The conversation topic creation system can also analyze the user's past travel history and provide conversation topics related to travel. For example, it can provide information about places the user has visited in the past and recommended travel destinations to visit next. It can also provide information about tourist spots and events that may interest the user as conversation topics. It can also provide advice on planning and preparing for a trip based on the user's travel history. This makes it possible to provide conversation topics that are tailored to the user's travel history.

[0076] The conversation topic creation system can further estimate the user's emotions and adjust the tone of the conversation topics based on the estimated emotions. For example, if the user is relaxed, a calm tone of topic can be provided. If the user is excited, an energetic tone of topic can be provided to further increase the user's excitement. Furthermore, if the user is depressed, a gentle tone of topic can be provided to comfort and encourage the user. In this way, conversation topics with a tone that matches the user's emotions can be provided.

[0077] The conversation topic creation system can also analyze the user's learning history and provide conversation topics related to education. For example, it can provide the latest research and discoveries related to the content the user has previously learned or the fields in which the user is interested. It can also provide information about new skills and knowledge the user wants to learn as conversation topics. It can also provide advice on learning methods and resources based on the user's learning history. This makes it possible to provide conversation topics that are tailored to the user's learning history.

[0078] The conversation topic creation system can further estimate the user's emotions and adjust the difficulty of the conversation topics based on the estimated emotions. For example, if the user is relaxed, simple and easy topics can be provided. On the other hand, if the user is concentrating, more difficult topics that allow for in-depth discussion can be provided. Furthermore, if the user is tired, it is possible to provide light topics or topics that will help the user relax. In this way, conversation topics of a difficulty level that corresponds to the user's emotions can be provided.

[0079] The conversation topic creation system can also analyze weather information in the user's area and provide conversation topics related to the weather. For example, it can provide weather forecasts and weather information for the area where the user lives. It can also provide information on weather-related events and activities as conversation topics. It can also provide information on seasonal characteristics and climate in the user's area. This makes it possible to provide conversation topics that correspond to the weather information in the user's area.

[0080] The conversation topic creation system can further estimate the user's emotions and adjust the length of the conversation topic based on the estimated emotions. For example, if the user is busy, it can provide short, concise topics. If the user is relaxed, it can provide detailed, in-depth topics. Furthermore, if the user is tired, it can provide short, relaxing topics. In this way, it is possible to provide conversation topics of a length that matches the user's emotions.

[0081] The conversation topic creation system can also analyze the user's musical preferences and provide conversation topics related to music. For example, it can provide the latest news and release information about the user's favorite artists and genres. It can also introduce new artists and songs that the user might be interested in. It can also provide information about concerts and festivals based on the user's musical preferences. This allows it to provide conversation topics that match the user's musical preferences.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: The event collection unit uses generative AI to collect recent events. For example, generative AI collects news articles, social media posts, blog and forum posts, podcast and webinar content. Specifically, it collects and analyzes the latest news articles from news sites; collects the latest posts using social media APIs and the latest posts using blog and forum RSS feeds; converts podcast audio data into text and analyzes it; and analyzes webinar recordings to extract content. Step 2: The interest identification unit identifies the interests of the person being talked to. For example, it analyzes the person's profile information to identify their hobbies and interests. It analyzes past conversation history to identify topics in which the person is interested. It analyzes social media posts and followed accounts to identify interests based on the topics the person frequently posts on and the content of the accounts they follow. Step 3: The topic creation unit creates conversation topics based on recent events collected by the event collection unit and the interests identified by the interest identification unit. For example, a generative AI can be used to combine collected events and identified interests to create conversation topics. An emotion estimation function can also be used to prioritize the creation of topics that evoke strong emotional responses. Visually appealing topics can also be created by including visual data.

[0084] 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.

[0085] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0086] 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.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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).

[0093] 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.

[0094] 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.

[0095] 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.

[0096] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0097] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0112] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0128] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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."

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0151] 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. an event collection unit that uses generative AI to collect recent events; an interest identification unit that identifies the interests and concerns of a conversation target; a topic creation unit that creates a conversation topic based on the recent events collected by the event collection unit and the interests and concerns identified by the interest identification unit. A system characterized by:

2. The event collection unit Evaluate the emotional impact of collected events and prioritize analysis of events that evoke strong emotional responses 2. The system of claim 1.

3. The event collection unit Analyzing from different cultural and regional perspectives to provide conversation topics from a global perspective 2. The system of claim 1.

4. The interest identification unit Extracting topics that elicit strong emotional responses from past conversation history 2. The system of claim 1.

5. The material creation unit Evaluate the emotional impact of your conversation topics and prioritize those that evoke strong emotional responses.

2. The system of claim 1.

6. The event collection unit Diversify your sources of information and include podcasts and webinars in your analysis, in addition to news.

2. The system of claim 1.

7. The interest identification unit The purchasing history and browsing history of the target person are also analyzed to identify their interests and concerns with greater precision.

2. The system of claim 1.

8. The material creation unit Incorporating perspectives from different cultures and regions to provide conversation topics from a global perspective 2. The system of claim 1.

Images