System

Abstract

An object of a system according to an embodiment is to predict a comfortable communication style of a partner and propose specific lines and sentences based on the prediction.SOLUTION: A system includes an information collection unit, an analysis unit, and a proposal unit. The information collection unit collects information on the other party. The analysis unit analyzes the information of the other party collected by the information collection unit and predicts a comfortable communication style of the other party. The proposal unit proposes a specific speech or sentence based on the communication style predicted by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that it is difficult to build good human relationships quickly with limited information.

[0005] The system according to the embodiment aims to predict the communication style that the other person finds comfortable and to suggest specific lines and sentences based on that. [Means for solving the problem]

[0006] The system according to the embodiment includes an information collection unit, an analysis unit, and a suggestion unit. The information collection unit collects information about the other party. The analysis unit analyzes the information about the other party collected by the information collection unit and predicts a communication style that will be comfortable for the other party. The suggestion unit suggests specific lines or sentences based on the communication style predicted by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can predict the communication style that the other person finds comfortable and suggest specific lines and sentences based on that. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The advisor system according to the embodiment of the present invention is a system that predicts the communication style that the other person is comfortable with and suggests lines and sentences that match that. As a result, the advisor system can suggest the optimal communication style based on the other person's information, and quickly build good human relationships.

[0029] An advisor system according to an embodiment includes an information collection unit, an analysis unit, and a suggestion unit. The information collection unit collects information about the other party, such as the other party's name, age, occupation, hobbies, and past communication history. The information collection unit can also analyze the other party's social media posts and comments to extract detailed hobbies and interests. For example, the information collection unit can identify the other party's hobbies and interests by extracting the topics the other party frequently posts about and the hashtags they use. The information collection unit can also analyze the other party's past email and chat history to extract specific phrases and phrasing patterns. For example, it can extract frequently used phrases and phrasing. The analysis unit analyzes the other party's information collected by the information collection unit and predicts the other party's comfortable communication style. For example, the generation AI analyzes the input information about the other party and predicts the other party's comfortable communication style. The generation AI uses data mining and natural language processing techniques to predict the other party's preferred tone and language and the topics they are interested in. The suggestion unit suggests specific lines and sentences based on the communication style predicted by the analysis unit. For example, the generation AI suggests specific lines and sentences based on the predicted communication style. The generation AI generates optimal expressions by taking into account the other party's information and the predicted style. As a result, the advisor system according to the embodiment suggests the optimal communication style based on the other party's information, enabling quick construction of good human relationships. For example, the user can actually communicate using the lines and sentences suggested by the generation AI. The generation AI can learn the other party's reactions and feedback and make its suggestions more accurate in the future.

[0030] The information collection unit can analyze social media posts or comments to extract hobbies or interests. For example, the information collection unit crawls the other party's social media account and analyzes the content of posts and comments. For example, it extracts the themes the other party frequently posts on and the hashtags they use to identify their hobbies and interests. The information collection unit also analyzes images and videos included in social media posts to extract the other party's hobbies and interests from visual information. For example, it obtains information such as whether the other party likes traveling or cooking from travel photos or cooking videos. The information collection unit also analyzes interactions in social media comment sections to identify topics on which the other party actively comments. For example, it extracts comments about specific sports teams or music artists. This allows for more accurate communication by extracting detailed hobbies and interests from the other party's social media.

[0031] The information collection unit can analyze email or chat history and extract phrase or phrasing patterns. For example, the information collection unit analyzes the other party's past email or chat history and extracts frequently used phrases and expressions. For example, it identifies specific greetings or closing words. The information collection unit also analyzes the content of emails or chats and identifies the tone in which the other party typically communicates. For example, it determines whether the language used is formal or casual. The information collection unit also extracts from the past communication history what topics the other party is interested in. For example, it analyzes whether specific projects or hobbies are frequently discussed. In this way, by extracting specific phrases and phrasing patterns from the past email or chat history, it becomes possible to communicate in a way that is tailored to the other party.

[0032] The information collection unit can analyze voice data and extract characteristics of voice tone or speaking style. The information collection unit, for example, analyzes the voice data of the other party and extracts characteristics of voice tone and speaking style. For example, it identifies patterns of voice pitch, speed, and intonation. The information collection unit also analyzes the emotional state of the other party when speaking from the voice data. For example, it extracts voice characteristics when the person is nervous or relaxed. The information collection unit also identifies specific phrases and phrasing patterns based on the other party's voice data. For example, it extracts frequently used greetings and catchphrases. In this way, by extracting characteristics of voice tone and speaking style from the voice data, it becomes possible to communicate in a way that is tailored to the other party.

[0033] The information collecting unit can analyze video conference footage and collect non-verbal communication styles from facial expressions or gestures. The information collecting unit, for example, analyzes the video conference footage and identifies the facial expressions and gestures of the other party. For example, it extracts facial expressions such as smiles and furrowed brows. The information collecting unit also analyzes what gestures the other party frequently uses from the video data. For example, it identifies hand movements and changes in posture. The information collecting unit also identifies the other party's non-verbal communication style based on the facial expression and gesture data. For example, it analyzes in what situations the other party shows positive facial expressions. In this way, by collecting non-verbal communication styles from the video conference footage, it becomes possible to communicate tailored to the other party.

[0034] The analysis unit analyzes communication history over time and can predict changes in communication style. The generation AI, for example, analyzes the other person's past email and chat history over time to identify changes in communication style. For example, it analyzes changes from initial formal language to casual language. The generation AI also predicts how the other person's communication style has changed over time based on time-series data. For example, it identifies patterns in which style changes depending on specific events or situations. The generation AI also analyzes past communication history and predicts the tone and language the other person prefers over time. For example, it analyzes changes in tone at specific times. In this way, by analyzing past communication history over time, it is possible to predict changes in the other person's communication style.

[0035] The analysis unit can predict communication styles for each region based on cultural background or regional characteristics. The generation AI predicts communication styles based on the other person's cultural background and regional characteristics, for example. For example, it considers etiquette and language usage in specific cultural spheres. The generation AI also creates a database of communication styles for each region and predicts the optimal style based on the other person's place of residence or birthplace. For example, it identifies greetings and expressions unique to the region. The generation AI also develops a prediction algorithm for communication styles that takes cultural background and regional characteristics into account. For example, it analyzes the differences in business communication between different cultural spheres. This makes it possible to predict the optimal communication style for each region by taking cultural background and regional characteristics into account.

[0036] The analysis unit can compare communication styles from different industries or occupations and predict a style based on the characteristics of the occupation. The generation AI, for example, creates a database of communication styles from different industries and occupations and predicts the optimal style based on the other person's occupational characteristics. For example, it takes into account the differences between technical and sales occupations. The generation AI also analyzes communication styles by industry and proposes the optimal style based on the other person's occupation. For example, it identifies the style differences between the creative industry and the financial industry. The generation AI also compares communication styles by occupation and develops an algorithm to predict a style based on the other person's occupational characteristics. For example, it analyzes the style differences between managers and engineers. This makes it possible to predict the optimal style based on the other person's occupational characteristics by comparing communication styles from different industries and occupations.

[0037] The analysis unit can predict an appropriate communication style based on a person's life stage. The generation AI predicts the optimal communication style based on the other person's life stage, for example. For example, it might suggest a casual style for a student and a formal style for a working adult. The generation AI also creates a database of communication styles for each life stage and predicts the optimal style for the other person's stage. For example, it might suggest a relaxed style for a retiree. The generation AI also develops a prediction algorithm for communication styles based on life stage. For example, it might identify a style suitable for the transition period from student to working adult. This makes it possible to communicate tailored to the other person by predicting the appropriate communication style based on their life stage.

[0038] The suggestion unit can suggest lines and sentences appropriate for specific situations based on communication history. The generation AI, for example, analyzes the other party's past email and chat history to suggest lines and sentences appropriate for specific situations. For example, it generates sentences appropriate for meeting invitation emails or project progress reports. The generation AI also identifies the other party's preferred language in specific situations from past communication history and suggests lines and sentences based on that. For example, it generates thank-you emails or congratulatory messages. The generation AI also develops algorithms that suggest optimal lines and sentences based on past communication history for specific situations. For example, it generates sentences appropriate for handling complaints or apologizing emails. This makes it possible to communicate tailored to the other party by suggesting lines and sentences appropriate for specific situations based on past communication history.

[0039] The suggestion unit can generate lines or sentences that reflect the topic or interest. For example, the generation AI generates lines and sentences that reflect the other person's preferred topics based on their hobbies and interests. For example, if the other person likes sports, it will suggest sentences that incorporate sports-related topics. The generation AI also identifies topics of interest from the other person's past communication history and generates lines and sentences based on that. For example, if the other person likes travel, it will suggest sentences that incorporate travel-related topics. The generation AI also analyzes the other person's social media posts and comments to generate lines and sentences that reflect their interests. For example, if the other person likes music, it will suggest sentences that incorporate music-related topics. This makes it possible to generate lines and sentences that reflect the other person's preferred topics and interests, enabling communication that is tailored to the other person.

[0040] The suggestion unit can suggest lines or sentences that correspond to different languages ​​or cultures. The generation AI, for example, develops algorithms that generate lines and sentences that correspond to different languages. For example, it proposes sentences that correspond to multiple languages, such as English, French, and Chinese. The generation AI also builds systems that generate lines and sentences that correspond to different cultures. For example, it proposes sentences that incorporate greetings and expressions that are unique to each culture. The generation AI also develops algorithms that generate lines and sentences that take into account differences in language and culture. For example, it proposes sentences that are suitable for business communication in different cultural spheres. This makes international communication possible by proposing lines and sentences that correspond to different languages ​​and cultures.

[0041] The suggestion unit can suggest lines and sentences containing technical terms based on the other person's occupation or expertise. The generation AI generates lines and sentences containing technical terms based on the other person's occupation or expertise, for example. For example, it would suggest sentences containing technical terms for engineers. The generation AI also develops algorithms that generate lines and sentences based on expertise. For example, it would suggest sentences containing technical terms in the medical field. The generation AI also builds systems that generate lines and sentences that take into account the other person's occupational characteristics. For example, it would suggest sentences containing legal terminology. This makes it possible to have specialized communication by suggesting lines and sentences containing technical terms based on the other person's occupation or expertise.

[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 advisor system may further include a health management unit that monitors the user's health condition. The health management unit, for example, monitors the user's heart rate and sleep patterns to analyze the user's health condition. For example, it may analyze heart rate fluctuations and sleep quality to identify the user's stress level and fatigue level. The health management unit may also suggest appropriate rest and exercise based on the user's health data. For example, it may provide advice on how to relax during times of high stress. The health management unit may also suggest a communication style that corresponds to the user's health condition. For example, it may suggest simple and easy-to-understand communication when the user is feeling fatigued. This enables communication that takes the user's health condition into consideration.

[0044] The advisor system can further include a learning analysis unit that analyzes the user's learning history. The learning analysis unit, for example, analyzes the content the user has learned in the past and their learning progress. For example, it can identify the learning history of a specific subject or skill. The learning analysis unit can also analyze the user's learning style and level of understanding and suggest the optimal learning method. For example, it can suggest materials that make extensive use of diagrams and graphs to users who find visual learning effective. The learning analysis unit can also suggest the next content or skills to learn based on the user's learning history. For example, it can suggest applied content once the basics have been solidified. This enables effective learning support that takes the user's learning history into consideration.

[0045] The advisor system may further include a purchase analysis unit that analyzes the user's purchasing history. The purchase analysis unit, for example, analyzes products and services purchased by the user in the past. For example, it may determine whether the user frequently purchases products of a particular brand or category. The purchase analysis unit may also analyze the user's purchasing patterns and suggest optimal products and services. For example, if there is a product that is purchased regularly, it may predict and suggest the next purchase timing. The purchase analysis unit may also suggest related products and services based on the user's purchasing history. For example, it may suggest products related to a particular hobby. This enables personalized suggestions that take the user's purchasing history into consideration.

[0046] The advisor system may further include a location information analysis unit that analyzes the user's location information. The location information analysis unit may, for example, analyze the user's current location and past movement history. For example, it may determine whether the user frequently visits specific locations. The location information analysis unit may also make optimal suggestions based on the user's location information. For example, it may suggest restaurants or cafes close to the user's current location. The location information analysis unit may also analyze the user's movement patterns and suggest optimal means of transportation and routes. For example, it may suggest routes that shorten commuting time. This enables real-time suggestions that take the user's location information into consideration.

[0047] The advisor system can also analyze the user's purchasing history to suggest products and services suited to specific events or seasons. For example, based on products and services the user has purchased in the past, it can suggest products suitable for events such as Christmas or birthdays. It can also analyze seasonal purchasing patterns to suggest products and services suited to the season. For example, outdoor equipment and cooling products can be suggested in the summer. It can also predict what products the user will prefer for what events or seasons based on the purchasing history. For example, warm clothing and heating appliances can be suggested in the winter. This makes it possible to make suggestions suited to events and seasons, taking into account the user's purchasing history.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The information gathering unit collects information about the other party. For example, it collects the other party's name, age, occupation, hobbies, and past communication history. The information gathering unit can also analyze the other party's social media posts and comments to extract detailed hobbies and interests. For example, it can extract the themes that the other party frequently posts about and the hashtags they use to identify their hobbies and interests. Furthermore, the information gathering unit can analyze the other party's past email and chat history to extract specific phrases and phrasing patterns. For example, it can extract frequently used phrases and phrasing. Step 2: The analysis unit analyzes the information about the other person collected by the information collection unit and predicts a communication style that will be comfortable for that other person. For example, the generation AI analyzes the input information about the other person and predicts a communication style that will be comfortable for that other person. The generation AI uses data mining and natural language processing technology to predict what tone and language the other person prefers and what topics they are interested in. Step 3: The suggestion unit suggests specific lines and sentences based on the communication style predicted by the analysis unit. For example, the generation AI suggests specific lines and sentences based on the predicted communication style. The generation AI generates optimal expressions taking into account the other person's information and the predicted style. As a result, the advisor system according to the embodiment suggests an optimal communication style based on the other person's information, enabling the user to quickly build good relationships. For example, the user can actually communicate using the lines and sentences suggested by the generation AI. The generation AI learns the other person's reactions and feedback, and can make its suggestions more accurate from the next time onwards.

[0050] (Example 2) The advisor system according to the embodiment of the present invention is a system that predicts the communication style that the other person is comfortable with and suggests lines and sentences that match that. As a result, the advisor system can suggest the optimal communication style based on the other person's information, and quickly build good human relationships.

[0051] An advisor system according to an embodiment includes an information collection unit, an analysis unit, and a suggestion unit. The information collection unit collects information about the other party, such as the other party's name, age, occupation, hobbies, and past communication history. The information collection unit can also analyze the other party's social media posts and comments to extract detailed hobbies and interests. For example, the information collection unit can identify the other party's hobbies and interests by extracting the topics the other party frequently posts about and the hashtags they use. The information collection unit can also analyze the other party's past email and chat history to extract specific phrases and phrasing patterns. For example, it can extract frequently used phrases and phrasing. The analysis unit analyzes the other party's information collected by the information collection unit and predicts the other party's comfortable communication style. For example, the generation AI analyzes the input information about the other party and predicts the other party's comfortable communication style. The generation AI uses data mining and natural language processing techniques to predict the other party's preferred tone and language and the topics they are interested in. The suggestion unit suggests specific lines and sentences based on the communication style predicted by the analysis unit. For example, the generation AI suggests specific lines and sentences based on the predicted communication style. The generation AI generates optimal expressions by taking into account the other party's information and the predicted style. As a result, the advisor system according to the embodiment suggests the optimal communication style based on the other party's information, enabling quick construction of good human relationships. For example, the user can actually communicate using the lines and sentences suggested by the generation AI. The generation AI can learn the other party's reactions and feedback and make its suggestions more accurate in the future.

[0052] The information collection unit can analyze social media posts or comments to extract hobbies or interests. For example, the information collection unit crawls the other party's social media account and analyzes the content of posts and comments. For example, it extracts the themes the other party frequently posts on and the hashtags they use to identify their hobbies and interests. The information collection unit also analyzes images and videos included in social media posts to extract the other party's hobbies and interests from visual information. For example, it obtains information such as whether the other party likes traveling or cooking from travel photos or cooking videos. The information collection unit also analyzes interactions in social media comment sections to identify topics on which the other party actively comments. For example, it extracts comments about specific sports teams or music artists. This allows for more accurate communication by extracting detailed hobbies and interests from the other party's social media.

[0053] The information collection unit can analyze email or chat history and extract phrase or phrasing patterns. For example, the information collection unit analyzes the other party's past email or chat history and extracts frequently used phrases and expressions. For example, it identifies specific greetings or closing words. The information collection unit also analyzes the content of emails or chats and identifies the tone in which the other party typically communicates. For example, it determines whether the language used is formal or casual. The information collection unit also extracts from the past communication history what topics the other party is interested in. For example, it analyzes whether specific projects or hobbies are frequently discussed. In this way, by extracting specific phrases and phrasing patterns from the past email or chat history, it becomes possible to communicate in a way that is tailored to the other party.

[0054] The information collection unit can use the emotion estimation function to analyze emotional fluctuations from communication and collect emotion-based information. The information collection unit, for example, analyzes past email and chat history using the emotion estimation function to identify the other party's emotional fluctuations. For example, it extracts periods of strong positive emotions and periods of strong negative emotions. The information collection unit also uses the emotion estimation function to quantify the intensity of emotions from the content of the other party's communication and identify patterns in which particular emotions are strongly expressed. For example, it analyzes periods of high stress and periods of relaxation. The information collection unit also identifies, based on the emotion estimation data, topics and situations in which the other party shows positive emotions. For example, it analyzes whether the other party shows positive reactions to success stories or words of gratitude. In this way, by analyzing emotional fluctuations using the emotion estimation function, it is possible to collect information based on the other party's emotions.

[0055] The information collection unit can analyze voice data and extract characteristics of voice tone or speaking style. The information collection unit, for example, analyzes the voice data of the other party and extracts characteristics of voice tone and speaking style. For example, it identifies patterns of voice pitch, speed, and intonation. The information collection unit also analyzes the emotional state of the other party when speaking from the voice data. For example, it extracts voice characteristics when the person is nervous or relaxed. The information collection unit also identifies specific phrases and phrasing patterns based on the other party's voice data. For example, it extracts frequently used greetings and catchphrases. In this way, by extracting characteristics of voice tone and speaking style from the voice data, it becomes possible to communicate in a way that is tailored to the other party.

[0056] The information collecting unit can analyze video conference footage and collect non-verbal communication styles from facial expressions or gestures. The information collecting unit, for example, analyzes the video conference footage and identifies the facial expressions and gestures of the other party. For example, it extracts facial expressions such as smiles and furrowed brows. The information collecting unit also analyzes what gestures the other party frequently uses from the video data. For example, it identifies hand movements and changes in posture. The information collecting unit also identifies the other party's non-verbal communication style based on the facial expression and gesture data. For example, it analyzes in what situations the other party shows positive facial expressions. In this way, by collecting non-verbal communication styles from the video conference footage, it becomes possible to communicate tailored to the other party.

[0057] The information collection unit can use the emotion estimation function to estimate emotions in real time from facial expressions or tone of voice and collect that information. For example, the information collection unit analyzes the other party's facial expressions in real time during a video conference to estimate emotions. For example, it detects smiling or surprised expressions and calculates an emotion score. The information collection unit also analyzes voice data in real time to estimate emotions from tone of voice. For example, it identifies emotions based on changes in voice pitch and speed. The information collection unit also integrates facial expression and tone of voice data to build a system that estimates the other party's emotions in real time. For example, it adjusts the content of communication based on the emotion score. In this way, by estimating emotions in real time and collecting that information, communication based on the other party's emotions becomes possible.

[0058] The analysis unit analyzes communication history over time and can predict changes in communication style. The generation AI, for example, analyzes the other person's past email and chat history over time to identify changes in communication style. For example, it analyzes changes from initial formal language to casual language. The generation AI also predicts how the other person's communication style has changed over time based on time-series data. For example, it identifies patterns in which style changes depending on specific events or situations. The generation AI also analyzes past communication history and predicts the tone and language the other person prefers over time. For example, it analyzes changes in tone at specific times. In this way, by analyzing past communication history over time, it is possible to predict changes in the other person's communication style.

[0059] The analysis unit can predict communication styles for each region based on cultural background or regional characteristics. The generation AI predicts communication styles based on the other person's cultural background and regional characteristics, for example. For example, it considers etiquette and language usage in specific cultural spheres. The generation AI also creates a database of communication styles for each region and predicts the optimal style based on the other person's place of residence or birthplace. For example, it identifies greetings and expressions unique to the region. The generation AI also develops a prediction algorithm for communication styles that takes cultural background and regional characteristics into account. For example, it analyzes the differences in business communication between different cultural spheres. This makes it possible to predict the optimal communication style for each region by taking cultural background and regional characteristics into account.

[0060] The analysis unit can use the emotion estimation function to analyze emotional fluctuations and predict a communication style based on those emotions. The generation AI, for example, uses the emotion estimation function to analyze the other person's emotional fluctuations and predict a communication style based on those emotions. For example, it can suggest a casual style when positive emotions are strong. The generation AI also predicts what communication style the other person will prefer based on the emotional state they are in, based on the emotional data. For example, it can suggest a formal style when they are under high stress. The generation AI also analyzes the emotion estimation data and develops an algorithm to predict the optimal communication style based on the other person's emotions. For example, it can adjust the style based on the emotion score. This makes it possible to predict a communication style based on emotions by analyzing emotional fluctuations using the emotion estimation function.

[0061] The analysis unit can compare communication styles from different industries or occupations and predict a style based on the characteristics of the occupation. The generation AI, for example, creates a database of communication styles from different industries and occupations and predicts the optimal style based on the other person's occupational characteristics. For example, it takes into account the differences between technical and sales occupations. The generation AI also analyzes communication styles by industry and proposes the optimal style based on the other person's occupation. For example, it identifies the style differences between the creative industry and the financial industry. The generation AI also compares communication styles by occupation and develops an algorithm to predict a style based on the other person's occupational characteristics. For example, it analyzes the style differences between managers and engineers. This makes it possible to predict the optimal style based on the other person's occupational characteristics by comparing communication styles from different industries and occupations.

[0062] The analysis unit can predict an appropriate communication style based on a person's life stage. The generation AI predicts the optimal communication style based on the other person's life stage, for example. For example, it might suggest a casual style for a student and a formal style for a working adult. The generation AI also creates a database of communication styles for each life stage and predicts the optimal style for the other person's stage. For example, it might suggest a relaxed style for a retiree. The generation AI also develops a prediction algorithm for communication styles based on life stage. For example, it might identify a style suitable for the transition period from student to working adult. This makes it possible to communicate tailored to the other person by predicting the appropriate communication style based on their life stage.

[0063] The analysis unit can use the emotion estimation function to predict a real-time communication style according to the other person's emotional state. The generation AI, for example, uses the emotion estimation function to analyze the other person's emotional state in real time and predicts the optimal communication style based on the results. For example, a casual style is suggested when the emotion score is high. The generation AI also develops an algorithm to predict a communication style according to the other person's emotional state based on real-time emotion data. For example, a formal style is suggested when stress is high. The generation AI also collects emotion estimation data in real time and builds a system that predicts the optimal style according to the other person's emotional state. For example, the style is dynamically adjusted based on the emotion score. In this way, the emotion estimation function can be used to analyze the other person's emotional state in real time, making it possible to predict the optimal communication style according to the other person's emotional state.

[0064] The suggestion unit can suggest lines and sentences appropriate for specific situations based on communication history. The generation AI, for example, analyzes the other party's past email and chat history to suggest lines and sentences appropriate for specific situations. For example, it generates sentences appropriate for meeting invitation emails or project progress reports. The generation AI also identifies the other party's preferred language in specific situations from past communication history and suggests lines and sentences based on that. For example, it generates thank-you emails or congratulatory messages. The generation AI also develops algorithms that suggest optimal lines and sentences based on past communication history for specific situations. For example, it generates sentences appropriate for handling complaints or apologizing emails. This makes it possible to communicate tailored to the other party by suggesting lines and sentences appropriate for specific situations based on past communication history.

[0065] The suggestion unit can generate lines or sentences that reflect the topic or interest. For example, the generation AI generates lines and sentences that reflect the other person's preferred topics based on their hobbies and interests. For example, if the other person likes sports, it will suggest sentences that incorporate sports-related topics. The generation AI also identifies topics of interest from the other person's past communication history and generates lines and sentences based on that. For example, if the other person likes travel, it will suggest sentences that incorporate travel-related topics. The generation AI also analyzes the other person's social media posts and comments to generate lines and sentences that reflect their interests. For example, if the other person likes music, it will suggest sentences that incorporate music-related topics. This makes it possible to generate lines and sentences that reflect the other person's preferred topics and interests, enabling communication that is tailored to the other person.

[0066] The suggestion unit can use the emotion estimation function to suggest lines and sentences that correspond to the other person's emotional state. The generation AI, for example, uses the emotion estimation function to analyze the other person's emotional state in real time and suggests optimal lines and sentences based on the results. For example, it suggests words of encouragement when the other person is feeling stressed. The generation AI also develops an algorithm that generates lines and sentences that correspond to the other person's emotional state based on emotional data. For example, it suggests words of congratulations when the other person is showing positive emotions. The generation AI also collects emotion estimation data in real time and builds a system that suggests optimal lines and sentences that correspond to the other person's emotional state. For example, it suggests words of comfort when the other person is sad. This makes it possible to communicate tailored to the other person by using the emotion estimation function to suggest lines and sentences that correspond to the other person's emotional state.

[0067] The suggestion unit can suggest lines or sentences that correspond to different languages ​​or cultures. The generation AI, for example, develops algorithms that generate lines and sentences that correspond to different languages. For example, it proposes sentences that correspond to multiple languages, such as English, French, and Chinese. The generation AI also builds systems that generate lines and sentences that correspond to different cultures. For example, it proposes sentences that incorporate greetings and expressions that are unique to each culture. The generation AI also develops algorithms that generate lines and sentences that take into account differences in language and culture. For example, it proposes sentences that are suitable for business communication in different cultural spheres. This makes international communication possible by proposing lines and sentences that correspond to different languages ​​and cultures.

[0068] The suggestion unit can suggest lines and sentences containing technical terms based on the other person's occupation or expertise. The generation AI generates lines and sentences containing technical terms based on the other person's occupation or expertise, for example. For example, it would suggest sentences containing technical terms for engineers. The generation AI also develops algorithms that generate lines and sentences based on expertise. For example, it would suggest sentences containing technical terms in the medical field. The generation AI also builds systems that generate lines and sentences that take into account the other person's occupational characteristics. For example, it would suggest sentences containing legal terminology. This makes it possible to have specialized communication by suggesting lines and sentences containing technical terms based on the other person's occupation or expertise.

[0069] The suggestion unit can use the emotion estimation function to suggest lines and sentences that empathize with the other person's emotions. The generation AI, for example, uses the emotion estimation function to generate lines and sentences that empathize with the other person's emotions. For example, when the other person is sad, it suggests words of empathy. The generation AI also develops an algorithm that generates lines and sentences that empathize with the other person's emotions based on emotion data. For example, when the other person is happy, it suggests words of congratulations. The generation AI also collects emotion estimation data in real time and builds a system that suggests lines and sentences that empathize with the other person's emotions. For example, when the other person is angry, it suggests words of comfort. This makes it possible to communicate tailored to the other person by using the emotion estimation function to suggest lines and sentences that empathize with the other person's emotions.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The advisor system may further include a health management unit that monitors the user's health condition. The health management unit, for example, monitors the user's heart rate and sleep patterns to analyze the user's health condition. For example, it may analyze heart rate fluctuations and sleep quality to identify the user's stress level and fatigue level. The health management unit may also suggest appropriate rest and exercise based on the user's health data. For example, it may provide advice on how to relax during times of high stress. The health management unit may also suggest a communication style that corresponds to the user's health condition. For example, it may suggest simple and easy-to-understand communication when the user is feeling fatigued. This enables communication that takes the user's health condition into consideration.

[0072] The advisor system can further include a learning analysis unit that analyzes the user's learning history. The learning analysis unit, for example, analyzes the content the user has learned in the past and their learning progress. For example, it can identify the learning history of a specific subject or skill. The learning analysis unit can also analyze the user's learning style and level of understanding and suggest the optimal learning method. For example, it can suggest materials that make extensive use of diagrams and graphs to users who find visual learning effective. The learning analysis unit can also suggest the next content or skills to learn based on the user's learning history. For example, it can suggest applied content once the basics have been solidified. This enables effective learning support that takes the user's learning history into consideration.

[0073] The advisor system may further include a purchase analysis unit that analyzes the user's purchasing history. The purchase analysis unit, for example, analyzes products and services purchased by the user in the past. For example, it may determine whether the user frequently purchases products of a particular brand or category. The purchase analysis unit may also analyze the user's purchasing patterns and suggest optimal products and services. For example, if there is a product that is purchased regularly, it may predict and suggest the next purchase timing. The purchase analysis unit may also suggest related products and services based on the user's purchasing history. For example, it may suggest products related to a particular hobby. This enables personalized suggestions that take the user's purchasing history into consideration.

[0074] The advisor system may further include a location information analysis unit that analyzes the user's location information. The location information analysis unit may, for example, analyze the user's current location and past movement history. For example, it may determine whether the user frequently visits specific locations. The location information analysis unit may also make optimal suggestions based on the user's location information. For example, it may suggest restaurants or cafes close to the user's current location. The location information analysis unit may also analyze the user's movement patterns and suggest optimal means of transportation and routes. For example, it may suggest routes that shorten commuting time. This enables real-time suggestions that take the user's location information into consideration.

[0075] The advisor system can also estimate the user's emotions and suggest appropriate music and videos based on the estimated emotions. For example, relaxing music can be suggested when the user is feeling stressed. On the other hand, energetic music and videos can be suggested when the user is showing positive emotions. The system can also predict what kind of music and videos the user will prefer based on the emotion estimation data. For example, fun videos can be suggested when the emotion score is high. It is also possible to build a system that collects emotion estimation data in real time and suggests the most appropriate music and videos according to the user's emotional state. This makes it possible to suggest entertainment based on the user's emotions.

[0076] The advisor system can also estimate the user's emotions and suggest appropriate exercise and relaxation methods based on the estimated emotions. For example, yoga or meditation can be suggested when the user is feeling stressed. Also, energetic exercise can be suggested when the user is showing positive emotions. Based on the emotion estimation data, it can also predict what type of exercise or relaxation method the user will prefer depending on their emotional state. For example, active exercise can be suggested when the emotion score is high. It is also possible to build a system that collects emotion estimation data in real time and suggests optimal exercise and relaxation methods according to the user's emotional state. This makes it possible to suggest health management based on the user's emotions.

[0077] The advisor system can also estimate the user's emotions and suggest appropriate reading and learning content based on the estimated emotions. For example, it can suggest light reading material when the user wants to relax. It can also suggest content suitable for studying when the user wants to concentrate. It can also predict what type of reading and learning content a user will prefer based on their emotional state, based on the emotion estimation data. For example, it can suggest more difficult learning content when the emotion score is high. It can also build a system that collects emotion estimation data in real time and suggests optimal reading and learning content according to the user's emotional state. This makes it possible to provide knowledge based on the user's emotions.

[0078] The advisor system can further estimate the user's emotions and suggest appropriate meals and recipes based on the estimated emotions. For example, when a user is feeling stressed, it can suggest relaxing meals. When a user is showing positive emotions, it can suggest energetic meals and recipes. It can also predict what kind of meals and recipes a user will prefer depending on their emotional state based on the emotion estimation data. For example, it can suggest enjoyable meals when the emotion score is high. It is also possible to build a system that collects emotion estimation data in real time and suggests optimal meals and recipes according to the user's emotional state. This makes it possible to suggest meals based on the user's emotions.

[0079] The advisor system can further estimate the user's emotions and suggest suitable travel destinations and tourist attractions based on the estimated emotions. For example, quiet travel destinations can be suggested when the user wants to relax. On the other hand, active tourist attractions can be suggested when the user is showing energetic emotions. The advisor system can also predict what type of travel destinations and tourist attractions the user will prefer based on the emotion estimation data. For example, adventurous travel destinations can be suggested when the emotion score is high. It is also possible to build a system that collects emotion estimation data in real time and suggests optimal travel destinations and tourist attractions according to the user's emotional state. This makes it possible to suggest trips based on the user's emotions.

[0080] The advisor system can also analyze the user's purchasing history to suggest products and services suited to specific events or seasons. For example, based on products and services the user has purchased in the past, it can suggest products suitable for events such as Christmas or birthdays. It can also analyze seasonal purchasing patterns to suggest products and services suited to the season. For example, outdoor equipment and cooling products can be suggested in the summer. It can also predict what products the user will prefer for what events or seasons based on the purchasing history. For example, warm clothing and heating appliances can be suggested in the winter. This makes it possible to make suggestions suited to events and seasons, taking into account the user's purchasing history.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The information gathering unit collects information about the other party. For example, it collects the other party's name, age, occupation, hobbies, and past communication history. The information gathering unit can also analyze the other party's social media posts and comments to extract detailed hobbies and interests. For example, it can extract the themes that the other party frequently posts about and the hashtags they use to identify their hobbies and interests. Furthermore, the information gathering unit can analyze the other party's past email and chat history to extract specific phrases and phrasing patterns. For example, it can extract frequently used phrases and phrasing. Step 2: The analysis unit analyzes the information about the other person collected by the information collection unit and predicts a communication style that will be comfortable for that other person. For example, the generation AI analyzes the input information about the other person and predicts a communication style that will be comfortable for that other person. The generation AI uses data mining and natural language processing technology to predict what tone and language the other person prefers and what topics they are interested in. Step 3: The suggestion unit suggests specific lines and sentences based on the communication style predicted by the analysis unit. For example, the generation AI suggests specific lines and sentences based on the predicted communication style. The generation AI generates optimal expressions taking into account the other person's information and the predicted style. As a result, the advisor system according to the embodiment suggests an optimal communication style based on the other person's information, enabling the user to quickly build good relationships. For example, the user can actually communicate using the lines and sentences suggested by the generation AI. The generation AI learns the other person's reactions and feedback, and can make its suggestions more accurate from the next time onwards.

[0083] 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.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] 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.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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).

[0092] 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.

[0093] 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.

[0094] 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.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0097] 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.

[0098] 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.

[0099] 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 AI 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.

[0100] 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.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0109] 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.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] 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.

[0113] 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.

[0114] 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 AI 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.

[0115] 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.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] 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.

[0129] 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.

[0130] 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 AI 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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."

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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, in order to avoid confusion and to 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.

[0149] 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]

[0150] 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 information gathering unit that gathers information about the other party; an analysis unit that analyzes the information about the other party collected by the information collection unit and predicts a communication style that is comfortable for the other party; a suggestion unit that suggests specific lines and sentences based on the communication style predicted by the analysis unit. A system characterized by:

2. The information collecting unit Analyzing social media posts or comments to extract hobbies or interests 2. The system of claim 1.

3. The information collecting unit Analyze email or chat history to extract phrases or phrasing patterns 2. The system of claim 1.

4. The information collecting unit Analyzing emotional fluctuations from communication and collecting information based on said emotions 2. The system of claim 1.

5. The information collecting unit Analyzing the voice data and extracting characteristics of the tone of voice or the speaking style.

2. The system of claim 1.

Images