System

Abstract

An object of a system according to an embodiment is to analyze a facial expression or a gesture of a partner in a remote conference and propose an appropriate communication method.SOLUTION: A system includes an analysis unit, a proposal unit, and a provision unit. The analysis part analyzes the expression and gesture of the opposite party in real time. The proposal unit proposes an effective communication method on the basis of the analysis result obtained by the analysis unit. The providing unit provides the interviewer with the method proposed by the proposal unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to accurately grasp the facial expressions and gestures of other people in remote meetings and to communicate appropriately.

[0005] The system according to the embodiment aims to analyze facial expressions and gestures of other parties in a remote conference and propose appropriate communication methods. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a suggestion unit, and a provision unit. The analysis unit analyzes the facial expressions and gestures of the other person in real time. The suggestion unit suggests an effective communication method based on the analysis results obtained by the analysis unit. The provision unit provides the method suggested by the suggestion unit to the interviewee. [Effects of the Invention]

[0007] The system according to the embodiment can analyze facial expressions and gestures of other parties in a remote conference and suggest appropriate communication methods. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A remote conference system according to an embodiment of the present invention analyzes the facial expressions and attitudes of other parties, capturing inner thoughts that cannot be conveyed in words and supporting smooth communication. During remote conferences or interviews, the remote conference system uses a generation AI to analyze the other party's facial expressions, gestures, facial color, and eye contact in real time, and proposes several effective communication patterns based on the analysis results. For example, when a party smiles, the remote conference system analyzes the degree and duration of the smile to estimate the other party's emotional state. The remote conference system can also analyze the frequency and direction of the other party's averted eyes to estimate the other party's interest and level of nervousness. Next, the remote conference system uses the generation AI to propose several effective communication patterns based on the analysis results. For example, if the other party is nervous, the system suggests topics and questions to relax them. Furthermore, if the other party shows interest, the system suggests topics related to that interest. This allows the remote conference system to gain a deeper understanding of the other party's inner thoughts and facilitate smooth communication. The remote conference system can also fully utilize the persona function to narrow down targets. For example, it is possible to suggest specific communication methods to visually impaired people. This allows the remote conferencing system to provide communication support tailored to individual needs. This overcomes the drawback of remote conferencing, which is the difficulty of face-to-face communication, and enables smoother communication. For example, it can be used in a variety of situations, such as job interviews, business meetings, and counseling.

[0029] A remote conference system according to an embodiment includes an analysis unit, a suggestion unit, and a provision unit. The analysis unit analyzes the facial expressions and gestures of the other party in real time. The facial expressions and gestures of the other party include, but are not limited to, extraction of facial feature points, classification of emotions, hand movements, and body movements. For example, the analysis unit extracts facial feature points and classifies emotions. The analysis unit can also analyze hand movements and body movements to classify gestures. The analysis unit can also analyze facial color and eye contact. For example, the analysis unit can analyze changes in facial redness and blood flow to estimate emotions. The analysis unit can also analyze eye contact direction and movement to estimate levels of interest and tension. The suggestion unit suggests an effective communication method based on the analysis results obtained by the analysis unit. For example, the suggestion unit can suggest topics or questions to relax the other party. The suggestion unit can also suggest topics related to the other party's interests. The suggestion unit can also use a persona function to suggest a communication method for a specific target. For example, a specific communication method is suggested to a visually impaired person. The providing unit provides the method suggested by the suggesting unit to the interviewee. The providing unit may provide the suggestion by voice, text, or the like, but is not limited to these examples. The providing unit may provide the suggestion by voice, for example. The providing unit may also provide the suggestion by text. As a result, the remote conference system according to the embodiment can support smooth communication by analyzing the facial expressions and gestures of the other party and suggesting and providing an appropriate communication method.

[0030] The analysis unit can analyze the other person's facial expressions, gestures, facial color, and eye contact in real time. The analysis unit, for example, extracts facial feature points and classifies emotions. The analysis unit can also analyze hand movements and body movements to classify gestures. The analysis unit can also analyze changes in facial redness and blood flow to estimate emotions. The analysis unit can also analyze the direction and movement of gaze to estimate the level of interest and tension. This allows for more accurate analysis results by analyzing the other person's facial expressions, gestures, facial color, and eye contact in real time. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input data on the other person's facial expressions and gestures into the generation AI and have the generation AI perform the analysis.

[0031] The suggestion unit can suggest topics or questions to relax the other person based on the analysis results. The suggestion unit can suggest, for example, topics related to hobbies. The suggestion unit can also suggest light conversation. The suggestion unit can also suggest open-ended questions. For example, the suggestion unit can suggest a question such as, "What are your hobbies these days?" The suggestion unit can also suggest closed-ended questions. For example, the suggestion unit can suggest a question such as, "What is your favorite color?" In this way, by suggesting topics or questions to relax the other person, it is possible to ease tension in the other person. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the analysis results into the generation AI and have the generation AI suggest topics or questions to relax the other person.

[0032] The suggestion unit can suggest topics related to the interests of the other party based on the analysis results. The suggestion unit can suggest topics related to hobbies, for example. The suggestion unit can also suggest topics related to work. The suggestion unit can also suggest topics related to recent events. For example, the suggestion unit can suggest a topic such as, "What are your recent hobbies?" The suggestion unit can also suggest a topic such as, "Tell me about your recent work projects." The suggestion unit can also suggest a topic such as, "Is there anything in the news recently that caught your attention?" This enables more interesting communication by suggesting topics related to the interests of the other party. Some or all of the above-mentioned processing by the suggestion unit can be performed using, or without, a generation AI. For example, the suggestion unit can input the analysis results into a generation AI and have the generation AI suggest topics related to the interests of the other party.

[0033] The providing unit can provide the method suggested by the suggesting unit to the interviewee. The providing unit can provide the suggestion content by voice, for example. The providing unit can also provide the suggestion content by text. The providing unit can also provide the suggestion content by visual means. For example, the providing unit can provide a suggestion by voice, such as "To relax, try talking about your hobbies." The providing unit can also provide a suggestion by text, such as "What are your recent hobbies?" The providing unit can also provide a suggestion by visual means, such as "We will suggest topics related to your hobbies." By providing the suggested communication method to the interviewee, the interviewee can communicate appropriately. Some or all of the above-mentioned processing by the providing unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the providing unit can input the suggestion content into a generation AI and have the generation AI provide the suggestion content.

[0034] The suggestion unit can use the persona function to suggest a method for a specific target. The suggestion unit can, for example, suggest a specific communication method for a visually impaired person. The suggestion unit can also suggest a specific communication method for an elderly person. The suggestion unit can also suggest a specific communication method for a child. For example, the suggestion unit can suggest a verbal communication method for a visually impaired person. The suggestion unit can also suggest a slower speaking style for an elderly person. The suggestion unit can also suggest a communication method using simple language for a child. In this way, by using the persona function, the optimal communication method for a specific target can be suggested. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input persona information into the generation AI and have the generation AI suggest a communication method for the specific target.

[0035] The analysis unit can improve the analysis algorithm by referring to data on the other party's past facial expressions and gestures. For example, the analysis unit can refer to past meeting data to learn the other party's facial expression patterns and improve analysis accuracy. The analysis unit can also refer to past gesture data to analyze emotional reactions to specific gestures. The analysis unit can also optimize the analysis algorithm by referring to past data on facial color and eye contact. In this way, by referring to past data, the analysis algorithm can be optimized and analysis accuracy can be improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input data on past facial expressions and gestures into a generation AI, and have the generation AI optimize the analysis algorithm.

[0036] During analysis, the analysis unit can also include the tone of the other person's voice and speaking speed as analysis targets. For example, the analysis unit can analyze the tone of the other person's voice to estimate the strength of their emotion. The analysis unit can also analyze the speed of the other person's voice to estimate the level of tension or excitement. The analysis unit can also analyze changes in the tone and speed of the voice to estimate changes in emotion in real time. By including the tone and speed of the voice as analysis targets, more multifaceted analysis becomes possible. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input data on the tone and speed of the other person's voice into the generation AI and have the generation AI perform the analysis.

[0037] During analysis, the analysis unit can correct the analysis results based on the other party's background information (e.g., the content of past conversations). The analysis unit, for example, refers to the content of past conversations and analyzes changes in the other party's emotions. The analysis unit can also correct the analysis results by taking the other party's background information into account. The analysis unit can also correct the analysis results by comparing the content of past conversations with the current facial expressions and gestures. In this way, by taking background information into account, more accurate analysis results can be obtained. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the other party's background information into the generation AI and have the generation AI correct the analysis results.

[0038] During analysis, the analysis unit can also include changes in the other person's clothing and accessories in the analysis targets. The analysis unit, for example, analyzes the color and style of the other person's clothing to infer changes in emotions. The analysis unit can also analyze the presence and type of accessories the other person is wearing to infer changes in emotions. The analysis unit can also analyze changes in the other person's clothing and accessories and correct the analysis results. By including changes in clothing and accessories in the analysis targets, more multifaceted analysis is possible. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, the generation AI, for example. For example, the analysis unit can input data on the other person's clothing and accessories into the generation AI and have the generation AI perform the analysis.

[0039] During analysis, the analysis unit can analyze the frequency and patterns of the other party's gestures. For example, the analysis unit can analyze the frequency of the other party's gestures to estimate the strength of their emotion. The analysis unit can also analyze the pattern of the other party's gestures to estimate the type of emotion. The analysis unit can also analyze changes in the frequency and patterns of gestures to estimate changes in emotion in real time. This allows for more accurate estimation of changes in emotion by analyzing the frequency and patterns of gestures. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the other party's gesture data into the generation AI and have the generation AI perform the analysis.

[0040] During the analysis, the analysis unit can analyze the other person's sitting style and changes in posture. For example, the analysis unit analyzes the other person's sitting style to estimate the level of relaxation or tension. The analysis unit can also analyze changes in the other person's posture to estimate changes in emotions. The analysis unit can also analyze changes in sitting style and posture in real time to estimate changes in emotions. This allows for more accurate estimation of changes in emotions by analyzing changes in sitting style and posture. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI, for example. For example, the analysis unit can input data on the other person's sitting style and posture into the generation AI and have the generation AI perform the analysis.

[0041] When making a suggestion, the suggestion unit can improve the accuracy of the suggestion by referring to the other party's past reaction data. For example, the suggestion unit can suggest an optimal topic by referring to the past reaction data. The suggestion unit can also suggest effective questions by referring to the past reaction data. The suggestion unit can also make suggestions that match the other party's interests by referring to the past reaction data. In this way, by referring to the past reaction data, the accuracy of the suggestion can be improved. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI, for example. For example, the suggestion unit can input past reaction data into the generation AI, which can improve the accuracy of the suggestion.

[0042] When making a proposal, the suggestion unit can customize the proposal content according to the cultural background and language of the other party. For example, the suggestion unit can suggest an appropriate topic taking into account the cultural background of the other party. The suggestion unit can also suggest easy-to-understand expressions according to the other party's language. The suggestion unit can also suggest an appropriate communication method based on the other party's culture and language. This enables more appropriate proposals by customizing the proposal content according to the cultural background and language. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the other party's cultural background and language data into the generation AI, causing the generation AI to customize the proposal content.

[0043] When making a proposal, the suggestion unit can adjust the proposal content based on the other party's current situation (e.g., time of day or location). The suggestion unit, for example, takes into account the other party's current time of day to suggest an appropriate topic. The suggestion unit can also take into account the other party's current location to suggest a related topic. The suggestion unit can also take into account the other party's current situation to suggest an optimal communication method. This enables more appropriate proposals by taking the current situation into consideration. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI, for example. For example, the suggestion unit can input the other party's current situation data into the generation AI, causing the generation AI to adjust the proposal content.

[0044] When making a suggestion, the suggestion unit can customize the suggestion content based on the hobbies and interests of the other party. For example, the suggestion unit can take the other party's hobbies into consideration and suggest related topics. The suggestion unit can also take the other party's interests into consideration and suggest questions that will pique their interest. The suggestion unit can also suggest optimal communication methods based on the other party's hobbies and interests. This allows for customizing the suggestion content based on the hobbies and interests, making it possible to make more interesting suggestions. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the other party's hobby and interest data into the generation AI, allowing the generation AI to customize the suggestion content.

[0045] When making a proposal, the suggestion unit can adjust the proposal content according to the other party's occupation and position. For example, the suggestion unit can consider the other party's occupation and suggest related topics. The suggestion unit can also consider the other party's position and suggest appropriate questions. The suggestion unit can also suggest the optimal communication method based on the other party's occupation and position. This enables more appropriate proposals by adjusting the proposal content according to the occupation and position. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the other party's occupation and position data into the generation AI and have the generation AI adjust the proposal content.

[0046] When making a proposal, the suggestion unit can improve the proposal content by reflecting the other party's past feedback. For example, the suggestion unit refers to past feedback and improves the proposal content. The suggestion unit can also make effective suggestions based on past feedback. The suggestion unit can also reflect past feedback and suggest an optimal communication method. In this way, the proposal content can be continuously improved by reflecting past feedback. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input past feedback data into the generation AI, causing the generation AI to improve the proposal content.

[0047] The providing unit can improve the information providing method by referring to the other party's past reaction data when providing information. For example, the providing unit can refer to the past reaction data and select the optimal information providing method. The providing unit can also refer to the past reaction data and suggest an effective information providing method. The providing unit can also refer to the past reaction data and provide information that matches the other party's interests. By referring to the past reaction data, the providing method can be optimized and more effective information can be provided. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using a generation AI or without using a generation AI. For example, the providing unit can input past reaction data into the generation AI and have the generation AI improve the information providing method.

[0048] The providing unit can customize the providing format according to the other party's device information (e.g., the terminal being used) when providing information. The providing unit, for example, refers to the other party's device information and selects the optimal display format. The providing unit can also refer to the other party's device information and suggest an effective information providing method. The providing unit can also refer to the other party's device information and provide information optimized for the other party's device. This enables more appropriate information to be provided by customizing the providing format according to the device information. Some or all of the above-described processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the other party's device information into the generation AI and have the generation AI customize the providing format.

[0049] The providing unit can adjust the information providing method based on the other party's current situation (e.g., network environment) when providing information. The providing unit, for example, refers to the other party's network environment and selects the optimal information providing method. The providing unit can also refer to the other party's network environment and provide information in a format that can be displayed even with low bandwidth. The providing unit can also refer to the other party's network environment and adjust the information providing method in real time. This enables more appropriate information to be provided by taking the current situation into consideration. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the other party's network environment data into the generation AI and have the generation AI adjust the information providing method.

[0050] The providing unit can provide the provided content in multiple languages ​​depending on the language setting of the other party (e.g., the language used) when providing the content. For example, the providing unit references the language setting of the other party and provides information in an appropriate language. The providing unit can also reference the language setting of the other party and provide information in multiple languages. The providing unit can also reference the language setting of the other party and provide a language switching function. This makes it possible to support multiple languages ​​depending on the language setting, thereby catering to a wider range of users. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit inputs the language setting data of the other party into the generation AI, and the generation AI can make the provided content multilingual.

[0051] The providing unit can customize the format of information provided according to the visual and auditory characteristics of the other party when providing the information. For example, the providing unit can refer to the visual characteristics of the other party and provide the information in a format that is highly visible. The providing unit can also refer to the auditory characteristics of the other party and provide the information in a format that is easy to hear. The providing unit can also refer to the visual and auditory characteristics of the other party and select the optimal information provision method. This enables more appropriate information to be provided by customizing the format of information provided according to the visual and auditory characteristics. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the providing unit can input data on the visual and auditory characteristics of the other party into the generation AI and have the generation AI customize the format of information provided.

[0052] The providing unit can improve the information providing method by reflecting the other party's feedback (e.g., the content of past conversations) when providing information. The providing unit can, for example, refer to the other party's feedback and improve the information providing method. The providing unit can also suggest an effective information providing method based on the other party's feedback. The providing unit can also reflect the other party's feedback and select the optimal information providing method. In this way, by reflecting the feedback, the providing method can be continuously improved. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the other party's feedback data into the generation AI, causing the generation AI to improve the information providing method.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The analysis unit can improve the analysis algorithm by referring to the other party's past facial expression and gesture data. For example, by referring to past meeting data, the analysis unit can learn the other party's facial expression patterns and improve analysis accuracy. It can also analyze emotional responses to specific gestures by referring to past gesture data. Furthermore, it can optimize the analysis algorithm by referring to past data on facial color and eye contact. In this way, by referring to past data, the analysis algorithm can be optimized and analysis accuracy can be improved.

[0055] When making a suggestion, the suggestion unit can improve the accuracy of the suggestion by referring to the other party's past reaction data. For example, the suggestion unit can suggest an optimal topic by referring to the past reaction data. It can also suggest effective questions by referring to the past reaction data. It can also make suggestions that match the other party's interests by referring to the past reaction data. In this way, the suggestion unit can improve the accuracy of the suggestion by referring to the past reaction data.

[0056] When making a proposal, the suggestion unit can customize the content of the proposal according to the cultural background and language of the other party. For example, it can suggest appropriate topics taking into account the cultural background of the other party. It can also suggest easy-to-understand expressions according to the other party's language. It can also suggest appropriate communication methods based on the other party's culture and language. This allows for more appropriate proposals by customizing the content of the proposal according to the cultural background and language.

[0057] The providing unit can customize the format of information provided depending on the device information of the other party (for example, the terminal being used) when providing information. For example, it can refer to the device information of the other party and select the optimal display format. It can also refer to the device information of the other party and suggest an effective method of providing information. It can also refer to the device information of the other party and provide information optimized for the other party's device. This makes it possible to provide more appropriate information by customizing the format of information provided depending on the device information.

[0058] When making a proposal, the suggestion unit can adjust the content of the proposal based on the other party's current situation (for example, time of day or location). For example, it can suggest an appropriate topic taking into account the other party's current time of day. It can also suggest a related topic taking into account the other party's current location. It can also suggest the optimal communication method taking into account the other party's current situation. This makes it possible to make more appropriate proposals by taking into account the current situation.

[0059] The providing unit can customize the format of information provided depending on the visual and auditory characteristics of the other party when providing the information. For example, the providing unit can refer to the visual characteristics of the other party and provide information in a format that is highly visible. The providing unit can also refer to the auditory characteristics of the other party and provide information in a format that is easy to hear. Furthermore, the providing unit can refer to the visual and auditory characteristics of the other party and select the optimal information provision method. In this way, customizing the format of information provided depending on the visual and auditory characteristics enables more appropriate information to be provided.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The analysis unit analyzes the other person's facial expressions and gestures in real time. Specifically, it extracts facial features, classifies emotions, analyzes hand and body movements, and analyzes facial color and eye contact. For example, it analyzes changes in facial redness and blood flow to estimate emotions, and analyzes eye direction and movement to estimate interest and tension. Step 2: The proposal unit proposes effective communication methods based on the analysis results obtained by the analysis unit. Specifically, it suggests topics and questions that will put the other person at ease, topics related to the other person's interests, and communication methods for specific targets using the persona function. For example, it proposes a specific communication method for a visually impaired person. Step 3: The providing unit provides the method proposed by the proposing unit to the interviewer. Specifically, this includes providing the method by voice or text. For example, the proposed content can be provided by voice or text.

[0062] (Example 2) A remote conference system according to an embodiment of the present invention analyzes the facial expressions and attitudes of other parties, capturing inner thoughts that cannot be conveyed in words and supporting smooth communication. During remote conferences or interviews, the remote conference system uses a generation AI to analyze the other party's facial expressions, gestures, facial color, and eye contact in real time, and proposes several effective communication patterns based on the analysis results. For example, when a party smiles, the remote conference system analyzes the degree and duration of the smile to estimate the other party's emotional state. The remote conference system can also analyze the frequency and direction of the other party's averted eyes to estimate the other party's interest and level of nervousness. Next, the remote conference system uses the generation AI to propose several effective communication patterns based on the analysis results. For example, if the other party is nervous, the system suggests topics and questions to relax them. Furthermore, if the other party shows interest, the system suggests topics related to that interest. This allows the remote conference system to gain a deeper understanding of the other party's inner thoughts and facilitate smooth communication. The remote conference system can also fully utilize the persona function to narrow down targets. For example, it is possible to suggest specific communication methods to visually impaired people. This allows the remote conferencing system to provide communication support tailored to individual needs. This overcomes the drawback of remote conferencing, which is the difficulty of face-to-face communication, and enables smoother communication. For example, it can be used in a variety of situations, such as job interviews, business meetings, and counseling.

[0063] A remote conference system according to an embodiment includes an analysis unit, a suggestion unit, and a provision unit. The analysis unit analyzes the facial expressions and gestures of the other party in real time. The facial expressions and gestures of the other party include, but are not limited to, extraction of facial feature points, classification of emotions, hand movements, and body movements. For example, the analysis unit extracts facial feature points and classifies emotions. The analysis unit can also analyze hand movements and body movements to classify gestures. The analysis unit can also analyze facial color and eye contact. For example, the analysis unit can analyze changes in facial redness and blood flow to estimate emotions. The analysis unit can also analyze eye contact direction and movement to estimate levels of interest and tension. The suggestion unit suggests an effective communication method based on the analysis results obtained by the analysis unit. For example, the suggestion unit can suggest topics or questions to relax the other party. The suggestion unit can also suggest topics related to the other party's interests. The suggestion unit can also use a persona function to suggest a communication method for a specific target. For example, a specific communication method is suggested to a visually impaired person. The providing unit provides the method suggested by the suggesting unit to the interviewee. The providing unit may provide the suggestion by voice, text, or the like, but is not limited to these examples. The providing unit may provide the suggestion by voice, for example. The providing unit may also provide the suggestion by text. As a result, the remote conference system according to the embodiment can support smooth communication by analyzing the facial expressions and gestures of the other party and suggesting and providing an appropriate communication method.

[0064] The analysis unit can analyze the other person's facial expressions, gestures, facial color, and eye contact in real time. The analysis unit, for example, extracts facial feature points and classifies emotions. The analysis unit can also analyze hand movements and body movements to classify gestures. The analysis unit can also analyze changes in facial redness and blood flow to estimate emotions. The analysis unit can also analyze the direction and movement of gaze to estimate the level of interest and tension. This allows for more accurate analysis results by analyzing the other person's facial expressions, gestures, facial color, and eye contact in real time. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input data on the other person's facial expressions and gestures into the generation AI and have the generation AI perform the analysis.

[0065] The suggestion unit can suggest topics or questions to relax the other person based on the analysis results. The suggestion unit can suggest, for example, topics related to hobbies. The suggestion unit can also suggest light conversation. The suggestion unit can also suggest open-ended questions. For example, the suggestion unit can suggest a question such as, "What are your hobbies these days?" The suggestion unit can also suggest closed-ended questions. For example, the suggestion unit can suggest a question such as, "What is your favorite color?" In this way, by suggesting topics or questions to relax the other person, it is possible to ease tension in the other person. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the analysis results into the generation AI and have the generation AI suggest topics or questions to relax the other person.

[0066] The suggestion unit can suggest topics related to the interests of the other party based on the analysis results. The suggestion unit can suggest topics related to hobbies, for example. The suggestion unit can also suggest topics related to work. The suggestion unit can also suggest topics related to recent events. For example, the suggestion unit can suggest a topic such as, "What are your recent hobbies?" The suggestion unit can also suggest a topic such as, "Tell me about your recent work projects." The suggestion unit can also suggest a topic such as, "Is there anything in the news recently that caught your attention?" This enables more interesting communication by suggesting topics related to the interests of the other party. Some or all of the above-mentioned processing by the suggestion unit can be performed using, or without, a generation AI. For example, the suggestion unit can input the analysis results into a generation AI and have the generation AI suggest topics related to the interests of the other party.

[0067] The providing unit can provide the method suggested by the suggesting unit to the interviewee. The providing unit can provide the suggestion content by voice, for example. The providing unit can also provide the suggestion content by text. The providing unit can also provide the suggestion content by visual means. For example, the providing unit can provide a suggestion by voice, such as "To relax, try talking about your hobbies." The providing unit can also provide a suggestion by text, such as "What are your recent hobbies?" The providing unit can also provide a suggestion by visual means, such as "We will suggest topics related to your hobbies." By providing the suggested communication method to the interviewee, the interviewee can communicate appropriately. Some or all of the above-mentioned processing by the providing unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the providing unit can input the suggestion content into a generation AI and have the generation AI provide the suggestion content.

[0068] The suggestion unit can use the persona function to suggest a method for a specific target. The suggestion unit can, for example, suggest a specific communication method for a visually impaired person. The suggestion unit can also suggest a specific communication method for an elderly person. The suggestion unit can also suggest a specific communication method for a child. For example, the suggestion unit can suggest a verbal communication method for a visually impaired person. The suggestion unit can also suggest a slower speaking style for an elderly person. The suggestion unit can also suggest a communication method using simple language for a child. In this way, by using the persona function, the optimal communication method for a specific target can be suggested. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input persona information into the generation AI and have the generation AI suggest a communication method for the specific target.

[0069] The analysis unit can estimate the other party's emotions and change the accuracy of the analysis based on the estimated emotions. For example, the analysis unit can analyze the degree and duration of the other party's smile to estimate the positivity of the other party's emotions. The analysis unit can also analyze the frequency and direction of the other party's averted eyes to estimate the level of tension or interest. The analysis unit can also analyze the tone and speed of the other party's voice to estimate changes in emotions in real time. This allows for adjusting the accuracy of the analysis based on the other party's emotions to obtain more accurate analysis results. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the analysis unit can input the other party's emotion data into the generation AI and have the generation AI adjust the accuracy of the analysis.

[0070] The analysis unit can improve the analysis algorithm by referring to data on the other party's past facial expressions and gestures. For example, the analysis unit can refer to past meeting data to learn the other party's facial expression patterns and improve analysis accuracy. The analysis unit can also refer to past gesture data to analyze emotional reactions to specific gestures. The analysis unit can also optimize the analysis algorithm by referring to past data on facial color and eye contact. In this way, by referring to past data, the analysis algorithm can be optimized and analysis accuracy can be improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input data on past facial expressions and gestures into a generation AI, and have the generation AI optimize the analysis algorithm.

[0071] During analysis, the analysis unit can also include the tone of the other person's voice and speaking speed as analysis targets. For example, the analysis unit can analyze the tone of the other person's voice to estimate the strength of their emotion. The analysis unit can also analyze the speed of the other person's voice to estimate the level of tension or excitement. The analysis unit can also analyze changes in the tone and speed of the voice to estimate changes in emotion in real time. By including the tone and speed of the voice as analysis targets, more multifaceted analysis becomes possible. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input data on the tone and speed of the other person's voice into the generation AI and have the generation AI perform the analysis.

[0072] During analysis, the analysis unit can correct the analysis results based on the other party's background information (e.g., the content of past conversations). The analysis unit, for example, refers to the content of past conversations and analyzes changes in the other party's emotions. The analysis unit can also correct the analysis results by taking the other party's background information into account. The analysis unit can also correct the analysis results by comparing the content of past conversations with the current facial expressions and gestures. In this way, by taking background information into account, more accurate analysis results can be obtained. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the other party's background information into the generation AI and have the generation AI correct the analysis results.

[0073] The analysis unit can estimate the other party's emotions and change the display method of the analysis results based on the estimated emotions. For example, the analysis unit estimates the other party's emotions and displays them in bright colors if they are positive. The analysis unit can also display them in subdued colors if they are negative. The analysis unit can also provide a simple display method if the person is nervous. This allows for adjusting the display method based on the emotion to provide analysis results that are easier to understand. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the analysis unit can input the other party's emotion data into the generation AI and have the generation AI adjust the display method of the analysis results.

[0074] During analysis, the analysis unit can also include changes in the other person's clothing and accessories in the analysis targets. The analysis unit, for example, analyzes the color and style of the other person's clothing to infer changes in emotions. The analysis unit can also analyze the presence and type of accessories the other person is wearing to infer changes in emotions. The analysis unit can also analyze changes in the other person's clothing and accessories and correct the analysis results. By including changes in clothing and accessories in the analysis targets, more multifaceted analysis is possible. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, the generation AI, for example. For example, the analysis unit can input data on the other person's clothing and accessories into the generation AI and have the generation AI perform the analysis.

[0075] During analysis, the analysis unit can analyze the frequency and patterns of the other party's gestures. For example, the analysis unit can analyze the frequency of the other party's gestures to estimate the strength of their emotion. The analysis unit can also analyze the pattern of the other party's gestures to estimate the type of emotion. The analysis unit can also analyze changes in the frequency and patterns of gestures to estimate changes in emotion in real time. This allows for more accurate estimation of changes in emotion by analyzing the frequency and patterns of gestures. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the other party's gesture data into the generation AI and have the generation AI perform the analysis.

[0076] During the analysis, the analysis unit can analyze the other person's sitting style and changes in posture. For example, the analysis unit analyzes the other person's sitting style to estimate the level of relaxation or tension. The analysis unit can also analyze changes in the other person's posture to estimate changes in emotions. The analysis unit can also analyze changes in sitting style and posture in real time to estimate changes in emotions. This allows for more accurate estimation of changes in emotions by analyzing changes in sitting style and posture. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI, for example. For example, the analysis unit can input data on the other person's sitting style and posture into the generation AI and have the generation AI perform the analysis.

[0077] The suggestion unit can estimate the other party's emotions and change the content of the suggestion based on the estimated emotions. For example, the suggestion unit can estimate the other party's emotions and suggest topics to relax them. The suggestion unit can also estimate the other party's emotions and suggest questions to pique their interest. The suggestion unit can also estimate the other party's emotions and suggest humor to ease tension. This enables more effective suggestions by adjusting the content of the suggestion based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the suggestion unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the suggestion unit can input the other party's emotion data into the generation AI, causing the generation AI to adjust the content of the suggestion.

[0078] When making a suggestion, the suggestion unit can improve the accuracy of the suggestion by referring to the other party's past reaction data. For example, the suggestion unit can suggest an optimal topic by referring to the past reaction data. The suggestion unit can also suggest effective questions by referring to the past reaction data. The suggestion unit can also make suggestions that match the other party's interests by referring to the past reaction data. In this way, by referring to the past reaction data, the accuracy of the suggestion can be improved. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI, for example. For example, the suggestion unit can input past reaction data into the generation AI, which can improve the accuracy of the suggestion.

[0079] When making a proposal, the suggestion unit can customize the proposal content according to the cultural background and language of the other party. For example, the suggestion unit can suggest an appropriate topic taking into account the cultural background of the other party. The suggestion unit can also suggest easy-to-understand expressions according to the other party's language. The suggestion unit can also suggest an appropriate communication method based on the other party's culture and language. This enables more appropriate proposals by customizing the proposal content according to the cultural background and language. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the other party's cultural background and language data into the generation AI, causing the generation AI to customize the proposal content.

[0080] When making a proposal, the suggestion unit can adjust the proposal content based on the other party's current situation (e.g., time of day or location). The suggestion unit, for example, takes into account the other party's current time of day to suggest an appropriate topic. The suggestion unit can also take into account the other party's current location to suggest a related topic. The suggestion unit can also take into account the other party's current situation to suggest an optimal communication method. This enables more appropriate proposals by taking the current situation into consideration. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI, for example. For example, the suggestion unit can input the other party's current situation data into the generation AI, causing the generation AI to adjust the proposal content.

[0081] The suggestion unit can estimate the other party's emotions and prioritize suggestions based on the estimated emotions. For example, the suggestion unit can estimate the other party's emotions and prioritize the most effective suggestions. The suggestion unit can also estimate the other party's emotions and prioritize suggestions with a high level of urgency. The suggestion unit can also estimate the other party's emotions and prioritize suggestions for relaxing the other party. This enables more effective suggestions by prioritizing suggestions based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the suggestion unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the suggestion unit can input the other party's emotion data into the generation AI and have the generation AI determine the priority of suggestions.

[0082] When making a suggestion, the suggestion unit can customize the suggestion content based on the hobbies and interests of the other party. For example, the suggestion unit can take the other party's hobbies into consideration and suggest related topics. The suggestion unit can also take the other party's interests into consideration and suggest questions that will pique their interest. The suggestion unit can also suggest optimal communication methods based on the other party's hobbies and interests. This allows for customizing the suggestion content based on the hobbies and interests, making it possible to make more interesting suggestions. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the other party's hobby and interest data into the generation AI, allowing the generation AI to customize the suggestion content.

[0083] When making a proposal, the suggestion unit can adjust the proposal content according to the other party's occupation and position. For example, the suggestion unit can consider the other party's occupation and suggest related topics. The suggestion unit can also consider the other party's position and suggest appropriate questions. The suggestion unit can also suggest the optimal communication method based on the other party's occupation and position. This enables more appropriate proposals by adjusting the proposal content according to the occupation and position. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the other party's occupation and position data into the generation AI and have the generation AI adjust the proposal content.

[0084] When making a proposal, the suggestion unit can improve the proposal content by reflecting the other party's past feedback. For example, the suggestion unit refers to past feedback and improves the proposal content. The suggestion unit can also make effective suggestions based on past feedback. The suggestion unit can also reflect past feedback and suggest an optimal communication method. In this way, the proposal content can be continuously improved by reflecting past feedback. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input past feedback data into the generation AI, causing the generation AI to improve the proposal content.

[0085] The providing unit can estimate the other party's emotions and change the format of the information to be provided based on the estimated emotions. For example, the providing unit can estimate the other party's emotions and provide information in bright colors if the other party's emotions are positive. The providing unit can also provide information in subdued colors if the other party's emotions are negative. The providing unit can also provide information in a simple format if the other party is nervous. This makes it possible to provide information that is easier to understand by adjusting the format of information based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the providing unit can input the other party's emotion data into the generation AI and have the generation AI adjust the format of the information.

[0086] The providing unit can improve the information providing method by referring to the other party's past reaction data when providing information. For example, the providing unit can refer to the past reaction data and select the optimal information providing method. The providing unit can also refer to the past reaction data and suggest an effective information providing method. The providing unit can also refer to the past reaction data and provide information that matches the other party's interests. By referring to the past reaction data, the providing method can be optimized and more effective information can be provided. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using a generation AI or without using a generation AI. For example, the providing unit can input past reaction data into the generation AI and have the generation AI improve the information providing method.

[0087] The providing unit can customize the providing format according to the other party's device information (e.g., the terminal being used) when providing information. The providing unit, for example, refers to the other party's device information and selects the optimal display format. The providing unit can also refer to the other party's device information and suggest an effective information providing method. The providing unit can also refer to the other party's device information and provide information optimized for the other party's device. This enables more appropriate information to be provided by customizing the providing format according to the device information. Some or all of the above-described processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the other party's device information into the generation AI and have the generation AI customize the providing format.

[0088] The providing unit can adjust the information providing method based on the other party's current situation (e.g., network environment) when providing information. The providing unit, for example, refers to the other party's network environment and selects the optimal information providing method. The providing unit can also refer to the other party's network environment and provide information in a format that can be displayed even with low bandwidth. The providing unit can also refer to the other party's network environment and adjust the information providing method in real time. This enables more appropriate information to be provided by taking the current situation into consideration. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the other party's network environment data into the generation AI and have the generation AI adjust the information providing method.

[0089] The providing unit can estimate the other party's emotions and set a priority order for information to be provided based on the estimated emotions. The providing unit, for example, estimates the other party's emotions and prioritizes providing the most important information. The providing unit can also estimate the other party's emotions and prioritize providing information with a high level of urgency. The providing unit can also estimate the other party's emotions and prioritize providing information for relaxing the other party. In this way, by determining the priority order of information based on emotions, more important information can be provided preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the providing unit can input the other party's emotion data into the generation AI and have the generation AI determine the priority order of information.

[0090] The providing unit can provide the provided content in multiple languages ​​depending on the language setting of the other party (e.g., the language used) when providing the content. For example, the providing unit references the language setting of the other party and provides information in an appropriate language. The providing unit can also reference the language setting of the other party and provide information in multiple languages. The providing unit can also reference the language setting of the other party and provide a language switching function. This makes it possible to support multiple languages ​​depending on the language setting, thereby catering to a wider range of users. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit inputs the language setting data of the other party into the generation AI, and the generation AI can make the provided content multilingual.

[0091] The providing unit can customize the format of information provided according to the visual and auditory characteristics of the other party when providing the information. For example, the providing unit can refer to the visual characteristics of the other party and provide the information in a format that is highly visible. The providing unit can also refer to the auditory characteristics of the other party and provide the information in a format that is easy to hear. The providing unit can also refer to the visual and auditory characteristics of the other party and select the optimal information provision method. This enables more appropriate information to be provided by customizing the format of information provided according to the visual and auditory characteristics. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the providing unit can input data on the visual and auditory characteristics of the other party into the generation AI and have the generation AI customize the format of information provided.

[0092] The providing unit can improve the information providing method by reflecting the other party's feedback (e.g., the content of past conversations) when providing information. The providing unit can, for example, refer to the other party's feedback and improve the information providing method. The providing unit can also suggest an effective information providing method based on the other party's feedback. The providing unit can also reflect the other party's feedback and select the optimal information providing method. In this way, by reflecting the feedback, the providing method can be continuously improved. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the other party's feedback data into the generation AI, causing the generation AI to improve the information providing method. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned analysis unit, suggestion unit, and provision unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit can analyze the facial expressions and gestures of the other person in real time using the camera 42 and microphone 38B of the smart device 14. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests an effective communication method based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the smart device 14, and provides the proposed method to the interviewee by voice or text. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, suggestion unit, and provision unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit can analyze the facial expressions and gestures of the other person in real time using the camera 42 and microphone 238 of the smart glasses 214. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests an effective communication method based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214, and provides the proposed method to the interviewee by voice or text. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, suggestion unit, and provision unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the analysis unit can analyze the facial expressions and gestures of the other person in real time using the camera 42 and microphone 238 of the headset-type terminal 314. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests an effective communication method based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and provides the suggested method to the interviewee by voice or text. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, suggestion unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit can analyze the facial expressions and gestures of the other person in real time using the camera 42 and microphone 238 of the robot 414. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests an effective communication method based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the robot 414, and provides the proposed method to the interviewee by voice or text.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The analysis unit can analyze the tone and speed of the other person's voice and estimate changes in emotion in real time. For example, if the other person's voice gets higher, it can be estimated that they are excited, and if the voice gets lower, it can be estimated that they are calm. Also, if the voice speed gets faster, it can be estimated that they are nervous, and if the voice speed gets slower, it can be estimated that they are relaxed. Thus, by analyzing the tone and speed of voice, it becomes possible to estimate emotions from more diverse angles. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI.

[0095] The suggestion unit can estimate the emotions of the other party and change the content of the suggestion based on the estimated emotions. For example, if the other party is nervous, it can suggest topics or questions to relax them. If the other party is excited, it can also suggest topics or questions to maintain their excitement. Furthermore, if the other party is calm, it can suggest topics or questions to encourage deeper discussion. This allows for more effective communication by adjusting the content of the suggestion based on emotions.

[0096] The information providing unit can estimate the emotion of the other party and change the format of the information to be provided based on the estimated emotion. For example, if the other party is showing positive emotion, the information can be provided in bright colors. If the other party is showing negative emotion, the information can be provided in subdued colors. Furthermore, if the other party is nervous, the information can be provided in a simple format. In this way, by adjusting the format of information based on emotion, it is possible to provide information that is easier to understand.

[0097] The analysis unit can improve the analysis algorithm by referring to the other party's past facial expression and gesture data. For example, by referring to past meeting data, the analysis unit can learn the other party's facial expression patterns and improve analysis accuracy. It can also analyze emotional responses to specific gestures by referring to past gesture data. Furthermore, it can optimize the analysis algorithm by referring to past data on facial color and eye contact. In this way, by referring to past data, the analysis algorithm can be optimized and analysis accuracy can be improved.

[0098] When making a suggestion, the suggestion unit can improve the accuracy of the suggestion by referring to the other party's past reaction data. For example, the suggestion unit can suggest an optimal topic by referring to the past reaction data. It can also suggest effective questions by referring to the past reaction data. It can also make suggestions that match the other party's interests by referring to the past reaction data. In this way, the suggestion unit can improve the accuracy of the suggestion by referring to the past reaction data.

[0099] The providing unit can estimate the emotion of the other party and set a priority order for the information to be provided based on the estimated emotion. For example, the providing unit can estimate the emotion of the other party and provide the most important information with priority. The providing unit can also estimate the emotion of the other party and provide information with high urgency with priority. Furthermore, the providing unit can estimate the emotion of the other party and provide information for relaxing the other party with priority. In this way, by determining the priority order of information based on emotion, more important information can be provided with priority.

[0100] When making a proposal, the suggestion unit can customize the content of the proposal according to the cultural background and language of the other party. For example, it can suggest appropriate topics taking into account the cultural background of the other party. It can also suggest easy-to-understand expressions according to the other party's language. It can also suggest appropriate communication methods based on the other party's culture and language. This allows for more appropriate proposals by customizing the content of the proposal according to the cultural background and language.

[0101] The providing unit can customize the format of information provided depending on the device information of the other party (for example, the terminal being used) when providing information. For example, it can refer to the device information of the other party and select the optimal display format. It can also refer to the device information of the other party and suggest an effective method of providing information. It can also refer to the device information of the other party and provide information optimized for the other party's device. This makes it possible to provide more appropriate information by customizing the format of information provided depending on the device information.

[0102] When making a proposal, the suggestion unit can adjust the content of the proposal based on the other party's current situation (for example, time of day or location). For example, it can suggest an appropriate topic taking into account the other party's current time of day. It can also suggest a related topic taking into account the other party's current location. It can also suggest the optimal communication method taking into account the other party's current situation. This makes it possible to make more appropriate proposals by taking into account the current situation.

[0103] The providing unit can customize the format of information provided depending on the visual and auditory characteristics of the other party when providing the information. For example, the providing unit can refer to the visual characteristics of the other party and provide information in a format that is highly visible. The providing unit can also refer to the auditory characteristics of the other party and provide information in a format that is easy to hear. Furthermore, the providing unit can refer to the visual and auditory characteristics of the other party and select the optimal information provision method. In this way, customizing the format of information provided depending on the visual and auditory characteristics enables more appropriate information to be provided.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The analysis unit analyzes the other person's facial expressions and gestures in real time. Specifically, it extracts facial features, classifies emotions, analyzes hand and body movements, and analyzes facial color and eye contact. For example, it analyzes changes in facial redness and blood flow to estimate emotions, and analyzes eye direction and movement to estimate interest and tension. Step 2: The proposal unit proposes effective communication methods based on the analysis results obtained by the analysis unit. Specifically, it suggests topics and questions that will put the other person at ease, topics related to the other person's interests, and communication methods for specific targets using the persona function. For example, it proposes a specific communication method for a visually impaired person. Step 3: The providing unit provides the method proposed by the proposing unit to the interviewer. Specifically, this includes providing the method by voice or text. For example, the proposed content can be provided by voice or text.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] 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.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] 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.

[0135] 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.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0137] 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.

[0138] 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.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0154] 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.

[0155] 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.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] 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.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] 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.

[0177] [Explanation of symbols]

[0178] 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 analysis unit that analyzes the other person's facial expressions and gestures in real time, a suggestion unit that suggests an effective communication method based on the analysis result obtained by the analysis unit; a providing unit that provides the interviewee with the method proposed by the proposing unit. A system characterized by:

2. The analysis unit Analyze the other person's facial expressions, gestures, facial color, and eye contact in real time 2. The system of claim 1.

3. The proposal unit Based on the analysis, suggest topics or questions to help you relax 2. The system of claim 1.

4. The proposal unit Based on the analysis results, it suggests topics related to the other person's interests.

2. The system of claim 1.

5. The providing unit The method suggested by the suggestion unit is provided to the interviewee.

2. The system of claim 1.

6. The proposal unit Use the persona feature to suggest methods for specific targets 2. The system of claim 1.

7. The analysis unit Estimate the other person's emotions and adjust the accuracy of the analysis based on the estimated emotions.

2. The system of claim 1.

8. The analysis unit Improve the analysis algorithm by referencing the other person's past facial expressions and gestures 2. The system of claim 1.

Images