System

Abstract

An object of the system according to the embodiment is to allow a user having a scene mutism to have a conversation as the user desires.SOLUTION: A system includes a recording unit, an interpretation unit, a listening unit, a generation unit, and an output unit. The recording unit records a conversation log. The interpretation unit interprets user's hobbies and preferences on the basis of the conversation log recorded by the recording unit. The listening unit listens to the speech of the other person using a voice recognition technique. The generation unit generates response candidates based on the hobbies and preferences interpreted by the interpretation unit. The output unit outputs a content selected by the user from the response candidates generated by the generation unit by the voice of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that it is difficult for users with selective mutism to converse as they wish.

[0005] The system according to the embodiment aims to enable a user with selective mutism to converse as he or she wishes. [Means for solving the problem]

[0006] The system according to the embodiment includes a recording unit, an interpretation unit, a listening unit, a generation unit, and an output unit. The recording unit records a conversation log. The interpretation unit interprets a user's interests and preferences based on the conversation log recorded by the recording unit. The listening unit listens to what others say using speech recognition technology. The generation unit generates candidate responses based on the interests and preferences interpreted by the interpretation unit. The output unit outputs, in the user's voice, a response selected by the user from the candidate responses generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment allows a user with selective mutism to converse as they wish. [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 conversation support system according to an embodiment of the present invention enables a user with selective mutism to express their opinions and feelings. The conversation support system records a conversation log of a scene in which the user can speak freely, interprets the user's hobbies and preferences, listens to what others say, generates response candidates, and outputs them in the user's voice. For example, the conversation support system records a conversation log of a scene in which the user is speaking. This conversation log is used to interpret the user's hobbies and preferences. Next, the conversation support system listens to what others say in a public place where it is difficult for the user to speak using voice recognition technology. The system automatically generates multiple response candidates based on the user's characteristics. The user selects what they want to say from the generated response candidates. The selected response is output in the user's voice. This allows the conversation support system to enable a user with selective mutism to express their opinions and feelings. This allows the conversation support system to improve the user's communication ability and prevent social isolation. For example, the user can express their opinions and feelings through the system even in a situation where it is difficult for them to express their own opinions and feelings.

[0029] A conversation support system according to an embodiment includes a recording unit, an interpretation unit, a listening unit, a generation unit, and an output unit. The recording unit records a conversation log of a user's conversation. For example, the recording unit can record scenes in which the user talks about hobbies or conversations with friends. The recording unit can also record the conversation log in audio or text format. The interpretation unit interprets the user's hobbies and preferences based on the conversation log recorded by the recording unit. For example, the interpretation unit can analyze information such as what topics the user is interested in and what expressions the user prefers. The interpretation unit can also analyze the conversation log using natural language processing technology. The listening unit listens to what others say using speech recognition technology. For example, the listening unit can listen to what others say in real time when the user has difficulty speaking at school or work. The listening unit can also use speech recognition technology using deep learning. The generation unit generates response candidates based on the hobbies and preferences interpreted by the interpretation unit. For example, when another person asks, "What did you do over the weekend?", the generation unit can generate candidate responses such as "I went to the movies" or "I hung out with friends" based on the user's hobbies and preferences. The generation unit can also generate candidate responses using natural language generation technology. The output unit outputs a response selected by the user from the candidate responses generated by the generation unit in the user's voice. For example, the output unit can output the selected response by imitating the user's voice. The output unit can also generate the user's voice using speech synthesis technology. This allows the conversation support system according to the embodiment to express the user's opinions and feelings. For example, even in situations where it is difficult for the user to express their own opinions and feelings, the user can express their opinions and feelings through the system.

[0030] During recording, the recording unit can analyze the frequency and tone of a user's speech and prioritize recording important conversations. For example, if the user speaks frequently, the recording unit can focus on recording those parts. Furthermore, if the user's tone becomes elevated, the recording unit can determine that the speech is important and prioritize recording it. Furthermore, if the user's speech contains emotional content, the recording unit can also record that part in detail. This allows important conversations to be prioritized by analyzing the frequency and tone of a user's speech. The frequency of speech is measured, for example, by the number of speeches within a certain period of time or the interval between speeches. The tone is measured, for example, by the pitch, strength, and emotional expression of the voice. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input the user's voice data into a generation AI and have the generation AI analyze the frequency and tone of speech.

[0031] The recording unit can classify and save the user's utterances by category when recording. For example, the recording unit classifies and saves the user's utterances into categories such as hobbies, work, and daily life. The recording unit can also classify the user's utterances by emotion and save them in positive, negative, and neutral categories. The recording unit can also classify the user's utterances by time of day and save them in categories such as morning, afternoon, and evening. By classifying and saving the user's utterances by category, subsequent analysis becomes easier. Categorization can be performed, for example, by topic, emotion, or time of day. Some or all of the above-mentioned processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input the user's utterance data into a generation AI and cause the generation AI to perform a process of classifying the data by category.

[0032] The recording unit simultaneously records background sounds and environmental sounds associated with the user's speech, allowing for later analysis. For example, the recording unit may record background sounds in the area where the user is speaking to complement the context of the speech. The recording unit may also record environmental sounds heard while the user is speaking, allowing for a detailed understanding of the context of the speech. The recording unit may also simultaneously record surrounding sounds associated with the user's speech, allowing for later analysis of the intent of the speech. By recording background sounds and environmental sounds associated with the user's speech, the intent of the speech can be analyzed more accurately. The background sounds and environmental sounds may include, for example, ambient noise or specific environmental sounds (such as the sound of rain or cars). Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit may input the user's speech data and background sound data into a generation AI, causing the generation AI to analyze the intent of the speech.

[0033] During interpretation, the interpretation unit can extract keywords that appear particularly frequently in the conversation log and identify the hobbies and preferences. For example, the interpretation unit extracts frequently occurring keywords from the conversation log and identifies the hobbies and preferences. The interpretation unit can also analyze words that appear particularly frequently in the conversation log and identify the hobbies and preferences. The interpretation unit can also extract phrases that appear repeatedly in the conversation log and identify the hobbies and preferences. This makes it easier to identify the hobbies and preferences by extracting keywords that appear frequently in the conversation log. Methods for extracting frequently occurring keywords include, for example, an occurrence frequency threshold or co-occurrence network analysis. Some or all of the above-mentioned processing in the interpretation unit may be performed using, for example, AI, or may be performed without using AI. For example, the interpretation unit can input the conversation log data to a generation AI and cause the generation AI to extract frequently occurring keywords.

[0034] During interpretation, the interpretation unit can analyze the context of the user's utterances to interpret the hobbies and preferences in more detail. The interpretation unit, for example, analyzes the context of the user's utterances and interprets the hobbies and preferences in more detail. The interpretation unit can also analyze the context of the user's utterances and interpret the hobbies and preferences in more detail. The interpretation unit can also interpret the hobbies and preferences in more detail by taking into account background information of the user's utterances. In this way, by analyzing the context of the user's utterances, the hobbies and preferences can be interpreted in more detail. The context is analyzed, for example, based on the content of previous and subsequent utterances or related topics. Some or all of the above-mentioned processing in the interpretation unit may be performed using, for example, AI, or may be performed without using AI. For example, the interpretation unit can input the user's utterance data into a generation AI and have the generation AI perform context analysis.

[0035] During interpretation, the interpretation unit can improve the accuracy of the interpretation by referring to the user's past interpretation results. The interpretation unit can improve the accuracy of the current interpretation, for example, based on the user's past interpretation results. The interpretation unit can also adjust the interpretation method by referring to the user's past interpretation results. The interpretation unit can also analyze the user's past interpretation results and improve the accuracy of the interpretation. In this way, the accuracy of the interpretation is improved by referring to the user's past interpretation results. The past interpretation results are stored, for example, in a database and used in a machine learning model. Some or all of the above-mentioned processing in the interpretation unit may be performed, for example, using AI, or may be performed without using AI. For example, the interpretation unit can input past interpretation result data into the generation AI and cause the generation AI to improve the accuracy of the interpretation.

[0036] When listening, the listening unit can analyze the volume and tone of other people's speech and prioritize listening to important speech. For example, if the volume of another person's speech is loud, the listening unit determines that speech is important and prioritizes listening to it. Furthermore, if the tone of another person's speech becomes higher, the listening unit can determine that speech is important and prioritize listening to it. Furthermore, if the speech of another person contains emotional content, the listening unit can listen to the speech in detail. Thus, by analyzing the volume and tone of other people's speech, important speech can be prioritized. The volume and tone can be measured using, for example, decibel values ​​or pitch fluctuations. Some or all of the above-mentioned processing in the listening unit may be performed using, for example, AI, or may be performed without using AI. For example, the listening unit can input other people's voice data into the generation AI and have the generation AI perform volume and tone analysis.

[0037] The listening unit can translate the content of other people's utterances in real time while listening and provide the content to the user. For example, the listening unit can translate the content of other people's utterances in real time and provide the content to the user. The listening unit can also translate the content of other people's utterances and provide it in a language that is easy for the user to understand. The listening unit can also translate the content of other people's utterances in real time and provide it in a language selected by the user. In this way, the content of other people's utterances can be translated in real time and provided in a language that is easy for the user to understand. A method of real-time translation is performed, for example, using machine translation technology or a translation delay time. Some or all of the above-mentioned processing in the listening unit may be performed, for example, using AI, or may be performed without using AI. For example, the listening unit can input the data of other people's utterances into a generation AI and have the generation AI perform real-time translation.

[0038] When listening, the listening unit simultaneously analyzes background sounds and environmental sounds of the other person's speech, thereby enabling a more accurate understanding of the intention of the speech. For example, the listening unit analyzes background sounds heard while the other person is speaking to complement the intention of the speech. The listening unit can also analyze environmental sounds of the other person's speech to grasp the context of the speech in detail. The listening unit can also analyze surrounding sounds simultaneously with the other person's speech to more accurately understand the intention of the speech. In this way, by analyzing background sounds and environmental sounds of the other person's speech, the intention of the speech can be more accurately understood. Analysis of background sounds and environmental sounds is performed, for example, using ambient noise or specific environmental sounds (such as the sound of rain or the sound of cars). Some or all of the above-mentioned processing in the listening unit may be performed using, for example, AI, or may be performed without AI. For example, the listening unit can input the other person's speech data and background sound data into the generation AI and cause the generation AI to analyze the intention of the speech.

[0039] The generation unit can generate optimal reply candidates based on the content of other people's statements during generation. The generation unit, for example, analyzes the content of other people's statements and generates optimal reply candidates. The generation unit can also generate appropriate reply candidates by taking into account the context of other people's statements. The generation unit can also understand the intention of other people's statements and generate reply candidates accordingly. This enables more appropriate responses by generating optimal reply candidates based on the content of other people's statements. The optimal reply candidates are generated, for example, based on the suitability of the response based on the content of other people's statements. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input other people's statement data into a generation AI and cause the generation AI to generate optimal reply candidates.

[0040] The generation unit can improve the accuracy of response candidates by referring to the user's past response history during generation. The generation unit can improve the accuracy of current response candidates, for example, based on the user's past response history. The generation unit can also adjust response candidates by referring to the user's past response history. The generation unit can also analyze the user's past response history to improve the accuracy of response candidates. In this way, the accuracy of response candidates is improved by referring to the user's past response history. The past response history is stored, for example, in a database and used in a machine learning model. Some or all of the above-described processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input past response history data into a generation AI and cause the generation AI to improve the accuracy of response candidates.

[0041] During generation, the generation unit can analyze the context of the user's utterance to generate more detailed reply candidates. The generation unit, for example, analyzes the context of the user's utterance to generate detailed reply candidates. The generation unit can also analyze the context of the user's utterance to generate detailed reply candidates. The generation unit can also generate detailed reply candidates by taking into account background information of the user's utterance. In this way, by analyzing the context of the user's utterance, more detailed reply candidates can be generated. The context is analyzed based on, for example, the content of previous and subsequent utterances or related topics. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's utterance data into a generation AI and have the generation AI perform context analysis.

[0042] The output unit can adjust the tone and pitch of the user's voice during output to achieve more natural speech. For example, the output unit can adjust the tone of the user's voice to achieve more natural speech. The output unit can also adjust the pitch of the user's voice to achieve more natural speech. The output unit can also simultaneously adjust the tone and pitch of the user's voice to achieve more natural speech. This enables more natural speech by adjusting the tone and pitch of the user's voice. Tone and pitch adjustment methods include, for example, using voice synthesis technology or using pre-recorded speech. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without AI. For example, the output unit can input the user's voice data to a generation AI and have the generation AI adjust the tone and pitch.

[0043] The output unit can translate the user's utterance content in real time at the time of output and provide it to others. For example, the output unit can translate the user's utterance content in real time and provide it to others. The output unit can also translate the user's utterance content and provide it in a language that is easy for others to understand. The output unit can also translate the user's utterance in real time and provide it in a language selected by others. In this way, the user's utterance content can be translated in real time and provided in a language that is easy for others to understand. A method for real-time translation is performed, for example, using machine translation technology or a translation delay time. Some or all of the above-mentioned processing in the output unit may be performed, for example, using AI, or may be performed without using AI. For example, the output unit can input the user's utterance data to a generation AI and have the generation AI perform real-time translation.

[0044] The output unit can simultaneously reproduce background sounds and environmental sounds of the user's speech during output, thereby realizing more realistic speech. For example, the output unit can reproduce background sounds heard while the user is speaking, thereby realizing more realistic speech. The output unit can also reproduce environmental sounds of the user's speech, thereby conveying the context of the speech in detail. The output unit can also reproduce surrounding sounds simultaneously with the user's speech, thereby realizing more realistic speech. This allows for more realistic speech by reproducing background sounds and environmental sounds of the user's speech. Methods for reproducing background sounds and environmental sounds include, for example, ambient noise or specific environmental sounds (such as the sound of rain or the sound of cars). Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without AI. For example, the output unit can input the user's speech data and background sound data to a generation AI and cause the generation AI to reproduce the background sounds and environmental sounds.

[0045] The output unit can prioritize output of highly relevant content by taking into account the user's geographical location information. For example, when the user is in a specific location, the output unit prioritizes output of content related to that location. Furthermore, when the user is traveling, the output unit can prioritize output of content related to travel. Furthermore, when the user is at home, the output unit can prioritize output of content related to daily life. In this way, highly relevant content can be prioritized by taking the user's geographical location information into account. The geographical location information can be acquired, for example, using GPS data or a location information service. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's geographical location data to a generation AI and cause the generation AI to prioritize highly relevant content.

[0046] At the time of output, the output unit can analyze the user's social media activity and output related content. For example, the output unit prioritizes output of content that the user is talking about on social media. The output unit can also analyze the content posted by the user on social media and output related content. The output unit can also output related content by referring to the user's interactions with friends on social media. In this way, related content can be output by analyzing the user's social media activity. Methods for analyzing social media activity include, for example, analyzing the content posted and analyzing followers. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's social media data to a generation AI and cause the generation AI to output related content.

[0047] The output unit can customize the output method by reflecting the user's past feedback at the time of output. For example, the output unit adjusts the current output method based on the user's preferred output method in the past. The output unit can also customize the output method by referring to the user's past feedback. The output unit can also customize the output method by referring to content that the user has felt they wanted to output in the past. In this way, the output method can be customized by reflecting the user's past feedback. The past feedback can be stored, for example, in a database and used in a machine learning model. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's past feedback data into a generation AI and have the generation AI customize the output method.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The conversation support system may further include a schedule management unit that manages the user's schedule. The schedule management unit keeps track of the user's schedule and provides conversation support at appropriate times. For example, if the user has an important meeting or presentation coming up, the schedule management unit can enhance the functions of the conversation support system to match that timing and support the user so that they can speak with confidence. The schedule management unit can also adjust the timing of recording conversation logs based on the user's schedule. For example, the conversation log can be recorded in a time period when the user is relaxed, allowing detailed information to be collected. Furthermore, the schedule management unit can optimize the generation of response candidates based on the user's schedule, allowing the user to communicate efficiently.

[0050] The conversation support system may further include a learning management unit that manages the user's learning history. The learning management unit records what the user has learned in the past and topics of interest, and uses this information for conversation support. For example, if the user is interested in a particular field, the learning management unit can prioritize generating response candidates related to that field. The learning management unit can also analyze conversation logs based on the user's past learning to understand the user's level of understanding. Furthermore, the learning management unit can adjust the operation of the conversation support system based on the user's learning history to support the user in learning effectively. For example, when a user tries a new topic, the learning management unit can provide basic knowledge related to that topic, allowing the user to smoothly progress through the conversation.

[0051] The conversation support system may further include a hobby and preference analysis unit that digs deeper into the user's hobbies and interests. The hobby and preference analysis unit analyzes the user's conversation log and social media activity to gain a detailed understanding of the user's hobbies and interests. For example, if the user is interested in a particular movie or music, the hobby and preference analysis unit can provide related topics based on that information. The hobby and preference analysis unit can also generate response candidates based on the user's interests to help the user have enjoyable conversations. Furthermore, the hobby and preference analysis unit can track changes in the user's interests in real time and adjust the operation of the conversation support system accordingly. For example, if the user discovers a new hobby, the hobby and preference analysis unit can provide information related to that hobby, allowing the user to enjoy conversations on new topics.

[0052] The conversation support system may further include a network analysis unit that analyzes the user's social network. The network analysis unit analyzes the user's relationships with friends, family, colleagues, and the like, and supports the user in determining what type of communication to engage in. For example, the network analysis unit may analyze the topics the user frequently talks about with a particular friend and provide response candidates to facilitate conversations with that friend. The network analysis unit may also support the user in finding common topics when meeting a new person. Furthermore, the network analysis unit may track changes in the user's social network in real time and adjust the operation of the conversation support system accordingly. For example, if the user moves to a new workplace, the network analysis unit may support communication with new colleagues, allowing the user to quickly adapt to the new environment.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The recording unit records a conversation log of a scene in which the user is speaking. For example, the recording unit can record a scene in which the user talks about hobbies or a conversation with a friend. The recording unit can also record the conversation log in audio or text format. Step 2: The interpretation unit interprets the user's interests and preferences based on the conversation log recorded by the recording unit. For example, the interpretation unit can analyze information such as what topics the user is interested in and what expressions the user prefers. The interpretation unit can also analyze the conversation log using natural language processing technology. Step 3: The listening unit uses speech recognition technology to listen to what others are saying. For example, the listening unit can listen to what others are saying in real time when the user has difficulty speaking at school or work. The listening unit can also use speech recognition technology that uses deep learning. Step 4: The generation unit generates answer candidates based on the hobbies and preferences interpreted by the interpretation unit. For example, when someone asks, "What did you do over the weekend?", the generation unit can generate answer candidates such as "I watched a movie" or "I hung out with friends" based on the user's hobbies and preferences. The generation unit can also generate answer candidates using natural language generation technology. Step 5: The output unit outputs the response selected by the user from the candidate responses generated by the generation unit in the user's voice. For example, the output unit can output the selected response by imitating the user's voice. Alternatively, the output unit can generate the user's voice using speech synthesis technology.

[0055] (Example 2) A conversation support system according to an embodiment of the present invention enables a user with selective mutism to express their opinions and feelings. The conversation support system records a conversation log of a scene in which the user can speak freely, interprets the user's hobbies and preferences, listens to what others say, generates response candidates, and outputs them in the user's voice. For example, the conversation support system records a conversation log of a scene in which the user is speaking. This conversation log is used to interpret the user's hobbies and preferences. Next, the conversation support system listens to what others say in a public place where it is difficult for the user to speak using voice recognition technology. The system automatically generates multiple response candidates based on the user's characteristics. The user selects what they want to say from the generated response candidates. The selected response is output in the user's voice. This allows the conversation support system to enable a user with selective mutism to express their opinions and feelings. This allows the conversation support system to improve the user's communication ability and prevent social isolation. For example, the user can express their opinions and feelings through the system even in a situation where it is difficult for them to express their own opinions and feelings.

[0056] A conversation support system according to an embodiment includes a recording unit, an interpretation unit, a listening unit, a generation unit, and an output unit. The recording unit records a conversation log of a user's conversation. For example, the recording unit can record scenes in which the user talks about hobbies or conversations with friends. The recording unit can also record the conversation log in audio or text format. The interpretation unit interprets the user's hobbies and preferences based on the conversation log recorded by the recording unit. For example, the interpretation unit can analyze information such as what topics the user is interested in and what expressions the user prefers. The interpretation unit can also analyze the conversation log using natural language processing technology. The listening unit listens to what others say using speech recognition technology. For example, the listening unit can listen to what others say in real time when the user has difficulty speaking at school or work. The listening unit can also use speech recognition technology using deep learning. The generation unit generates response candidates based on the hobbies and preferences interpreted by the interpretation unit. For example, when another person asks, "What did you do over the weekend?", the generation unit can generate candidate responses such as "I went to the movies" or "I hung out with friends" based on the user's hobbies and preferences. The generation unit can also generate candidate responses using natural language generation technology. The output unit outputs a response selected by the user from the candidate responses generated by the generation unit in the user's voice. For example, the output unit can output the selected response by imitating the user's voice. The output unit can also generate the user's voice using speech synthesis technology. This allows the conversation support system according to the embodiment to express the user's opinions and feelings. For example, even in situations where it is difficult for the user to express their own opinions and feelings, the user can express their opinions and feelings through the system.

[0057] The recording unit can estimate the user's emotions and adjust the timing of recording the conversation log based on the estimated user emotions. For example, when the user is relaxed, the recording unit can continuously record the conversation log and collect detailed information. Furthermore, when the user is nervous, the recording unit can temporarily stop recording the conversation log and wait until the user calms down. Furthermore, when the user is excited, the recording unit can increase the frequency of recording the conversation log to avoid missing important comments. This allows the conversation log to be recorded at a more appropriate time by adjusting the timing of recording the conversation log according to the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone and pitch, and facial expression recognition. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or without AI. For example, the recording unit can input the user's voice data into a generation AI and have the generation AI perform emotion estimation.

[0058] During recording, the recording unit can analyze the frequency and tone of a user's speech and prioritize recording important conversations. For example, if the user speaks frequently, the recording unit can focus on recording those parts. Furthermore, if the user's tone becomes elevated, the recording unit can determine that the speech is important and prioritize recording it. Furthermore, if the user's speech contains emotional content, the recording unit can also record that part in detail. This allows important conversations to be prioritized by analyzing the frequency and tone of a user's speech. The frequency of speech is measured, for example, by the number of speeches within a certain period of time or the interval between speeches. The tone is measured, for example, by the pitch, strength, and emotional expression of the voice. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input the user's voice data into a generation AI and have the generation AI analyze the frequency and tone of speech.

[0059] The recording unit can classify and save the user's utterances by category when recording. For example, the recording unit classifies and saves the user's utterances into categories such as hobbies, work, and daily life. The recording unit can also classify the user's utterances by emotion and save them in positive, negative, and neutral categories. The recording unit can also classify the user's utterances by time of day and save them in categories such as morning, afternoon, and evening. By classifying and saving the user's utterances by category, subsequent analysis becomes easier. Categorization can be performed, for example, by topic, emotion, or time of day. Some or all of the above-mentioned processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input the user's utterance data into a generation AI and cause the generation AI to perform a process of classifying the data by category.

[0060] The recording unit simultaneously records background sounds and environmental sounds associated with the user's speech, allowing for later analysis. For example, the recording unit may record background sounds in the area where the user is speaking to complement the context of the speech. The recording unit may also record environmental sounds heard while the user is speaking, allowing for a detailed understanding of the context of the speech. The recording unit may also simultaneously record surrounding sounds associated with the user's speech, allowing for later analysis of the intent of the speech. By recording background sounds and environmental sounds associated with the user's speech, the intent of the speech can be analyzed more accurately. The background sounds and environmental sounds may include, for example, ambient noise or specific environmental sounds (such as the sound of rain or cars). Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit may input the user's speech data and background sound data into a generation AI, causing the generation AI to analyze the intent of the speech.

[0061] The interpretation unit can estimate the user's emotions and adjust the interpretation method of the hobbies and preferences based on the estimated user emotions. For example, if the user is relaxed, the interpretation unit can interpret detailed hobbies and preferences. If the user is nervous, the interpretation unit can interpret concise hobbies and preferences. If the user is excited, the interpretation unit can also interpret emotional hobbies and preferences. This enables more appropriate interpretation by adjusting the interpretation method of the hobbies and preferences according to the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone and pitch, and facial expression recognition. Some or all of the above-mentioned processing in the interpretation unit may be performed using, for example, AI, or without AI. For example, the interpretation unit can input the user's voice data into a generation AI and have the generation AI perform emotion estimation.

[0062] During interpretation, the interpretation unit can extract keywords that appear particularly frequently in the conversation log and identify the hobbies and preferences. For example, the interpretation unit extracts frequently occurring keywords from the conversation log and identifies the hobbies and preferences. The interpretation unit can also analyze words that appear particularly frequently in the conversation log and identify the hobbies and preferences. The interpretation unit can also extract phrases that appear repeatedly in the conversation log and identify the hobbies and preferences. This makes it easier to identify the hobbies and preferences by extracting keywords that appear frequently in the conversation log. Methods for extracting frequently occurring keywords include, for example, an occurrence frequency threshold or co-occurrence network analysis. Some or all of the above-mentioned processing in the interpretation unit may be performed using, for example, AI, or may be performed without using AI. For example, the interpretation unit can input the conversation log data to a generation AI and cause the generation AI to extract frequently occurring keywords.

[0063] During interpretation, the interpretation unit can analyze the context of the user's utterances to interpret the hobbies and preferences in more detail. The interpretation unit, for example, analyzes the context of the user's utterances and interprets the hobbies and preferences in more detail. The interpretation unit can also analyze the context of the user's utterances and interpret the hobbies and preferences in more detail. The interpretation unit can also interpret the hobbies and preferences in more detail by taking into account background information of the user's utterances. In this way, by analyzing the context of the user's utterances, the hobbies and preferences can be interpreted in more detail. The context is analyzed, for example, based on the content of previous and subsequent utterances or related topics. Some or all of the above-mentioned processing in the interpretation unit may be performed using, for example, AI, or may be performed without using AI. For example, the interpretation unit can input the user's utterance data into a generation AI and have the generation AI perform context analysis.

[0064] During interpretation, the interpretation unit can improve the accuracy of the interpretation by referring to the user's past interpretation results. The interpretation unit can improve the accuracy of the current interpretation, for example, based on the user's past interpretation results. The interpretation unit can also adjust the interpretation method by referring to the user's past interpretation results. The interpretation unit can also analyze the user's past interpretation results and improve the accuracy of the interpretation. In this way, the accuracy of the interpretation is improved by referring to the user's past interpretation results. The past interpretation results are stored, for example, in a database and used in a machine learning model. Some or all of the above-mentioned processing in the interpretation unit may be performed, for example, using AI, or may be performed without using AI. For example, the interpretation unit can input past interpretation result data into the generation AI and cause the generation AI to improve the accuracy of the interpretation.

[0065] The listening unit can estimate the user's emotions and adjust how it listens to what others say based on the estimated user emotions. For example, when the user is relaxed, the listening unit listens to all utterances equally. Furthermore, when the user is nervous, the listening unit can prioritize listening to important utterances. Furthermore, when the user is excited, the listening unit can prioritize listening to emotional utterances. This allows for more appropriate listening by adjusting how it listens to what others say based on the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone, pitch, and facial expression recognition. Some or all of the above-described processing in the listening unit may be performed using, for example, AI, or may be performed without AI. For example, the listening unit can input the user's voice data into a generation AI and have the generation AI perform emotion estimation.

[0066] When listening, the listening unit can analyze the volume and tone of other people's speech and prioritize listening to important speech. For example, if the volume of another person's speech is loud, the listening unit determines that speech is important and prioritizes listening to it. Furthermore, if the tone of another person's speech becomes higher, the listening unit can determine that speech is important and prioritize listening to it. Furthermore, if the speech of another person contains emotional content, the listening unit can listen to the speech in detail. Thus, by analyzing the volume and tone of other people's speech, important speech can be prioritized. The volume and tone can be measured using, for example, decibel values ​​or pitch fluctuations. Some or all of the above-mentioned processing in the listening unit may be performed using, for example, AI, or may be performed without using AI. For example, the listening unit can input other people's voice data into the generation AI and have the generation AI perform volume and tone analysis.

[0067] The listening unit can translate the content of other people's utterances in real time while listening and provide the content to the user. For example, the listening unit can translate the content of other people's utterances in real time and provide the content to the user. The listening unit can also translate the content of other people's utterances and provide it in a language that is easy for the user to understand. The listening unit can also translate the content of other people's utterances in real time and provide it in a language selected by the user. In this way, the content of other people's utterances can be translated in real time and provided in a language that is easy for the user to understand. A method of real-time translation is performed, for example, using machine translation technology or a translation delay time. Some or all of the above-mentioned processing in the listening unit may be performed, for example, using AI, or may be performed without using AI. For example, the listening unit can input the data of other people's utterances into a generation AI and have the generation AI perform real-time translation.

[0068] When listening, the listening unit simultaneously analyzes background sounds and environmental sounds of the other person's speech, thereby enabling a more accurate understanding of the intention of the speech. For example, the listening unit analyzes background sounds heard while the other person is speaking to complement the intention of the speech. The listening unit can also analyze environmental sounds of the other person's speech to grasp the context of the speech in detail. The listening unit can also analyze surrounding sounds simultaneously with the other person's speech to more accurately understand the intention of the speech. In this way, by analyzing background sounds and environmental sounds of the other person's speech, the intention of the speech can be more accurately understood. Analysis of background sounds and environmental sounds is performed, for example, using ambient noise or specific environmental sounds (such as the sound of rain or the sound of cars). Some or all of the above-mentioned processing in the listening unit may be performed using, for example, AI, or may be performed without AI. For example, the listening unit can input the other person's speech data and background sound data into the generation AI and cause the generation AI to analyze the intention of the speech.

[0069] The generation unit can estimate the user's emotions and adjust the response candidate generation method based on the estimated user's emotions. For example, if the user is relaxed, the generation unit can generate detailed response candidates. Furthermore, if the user is nervous, the generation unit can generate concise response candidates. Furthermore, if the user is excited, the generation unit can generate emotional response candidates. This allows for the generation of more appropriate response candidates by adjusting the response candidate generation method according to the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone and pitch, and facial expression recognition. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input the user's voice data into the generation AI and have the generation AI perform emotion estimation.

[0070] The generation unit can generate optimal reply candidates based on the content of other people's statements during generation. The generation unit, for example, analyzes the content of other people's statements and generates optimal reply candidates. The generation unit can also generate appropriate reply candidates by taking into account the context of other people's statements. The generation unit can also understand the intention of other people's statements and generate reply candidates accordingly. This enables more appropriate responses by generating optimal reply candidates based on the content of other people's statements. The optimal reply candidates are generated, for example, based on the suitability of the response based on the content of other people's statements. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input other people's statement data into a generation AI and cause the generation AI to generate optimal reply candidates.

[0071] The generation unit can improve the accuracy of response candidates by referring to the user's past response history during generation. The generation unit can improve the accuracy of current response candidates, for example, based on the user's past response history. The generation unit can also adjust response candidates by referring to the user's past response history. The generation unit can also analyze the user's past response history to improve the accuracy of response candidates. In this way, the accuracy of response candidates is improved by referring to the user's past response history. The past response history is stored, for example, in a database and used in a machine learning model. Some or all of the above-described processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input past response history data into a generation AI and cause the generation AI to improve the accuracy of response candidates.

[0072] During generation, the generation unit can analyze the context of the user's utterance to generate more detailed reply candidates. The generation unit, for example, analyzes the context of the user's utterance to generate detailed reply candidates. The generation unit can also analyze the context of the user's utterance to generate detailed reply candidates. The generation unit can also generate detailed reply candidates by taking into account background information of the user's utterance. In this way, by analyzing the context of the user's utterance, more detailed reply candidates can be generated. The context is analyzed based on, for example, the content of previous and subsequent utterances or related topics. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's utterance data into a generation AI and have the generation AI perform context analysis.

[0073] The output unit can estimate the user's emotions and adjust the output method based on the estimated user emotions. For example, if the user is relaxed, the output unit can output in a natural tone. Furthermore, if the user is nervous, the output unit can output in a calm tone. Furthermore, if the user is excited, the output unit can output in an emotional tone. This allows for more appropriate output by adjusting the output method according to the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone and pitch, and facial expression recognition. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without AI. For example, the output unit can input the user's voice data to a generation AI and have the generation AI perform emotion estimation.

[0074] The output unit can adjust the tone and pitch of the user's voice during output to achieve more natural speech. For example, the output unit can adjust the tone of the user's voice to achieve more natural speech. The output unit can also adjust the pitch of the user's voice to achieve more natural speech. The output unit can also simultaneously adjust the tone and pitch of the user's voice to achieve more natural speech. This enables more natural speech by adjusting the tone and pitch of the user's voice. Tone and pitch adjustment methods include, for example, using voice synthesis technology or using pre-recorded speech. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without AI. For example, the output unit can input the user's voice data to a generation AI and have the generation AI adjust the tone and pitch.

[0075] The output unit can translate the user's utterance content in real time at the time of output and provide it to others. For example, the output unit can translate the user's utterance content in real time and provide it to others. The output unit can also translate the user's utterance content and provide it in a language that is easy for others to understand. The output unit can also translate the user's utterance in real time and provide it in a language selected by others. In this way, the user's utterance content can be translated in real time and provided in a language that is easy for others to understand. A method for real-time translation is performed, for example, using machine translation technology or a translation delay time. Some or all of the above-mentioned processing in the output unit may be performed, for example, using AI, or may be performed without using AI. For example, the output unit can input the user's utterance data to a generation AI and have the generation AI perform real-time translation.

[0076] The output unit can simultaneously reproduce background sounds and environmental sounds of the user's speech during output, thereby realizing more realistic speech. For example, the output unit can reproduce background sounds heard while the user is speaking, thereby realizing more realistic speech. The output unit can also reproduce environmental sounds of the user's speech, thereby conveying the context of the speech in detail. The output unit can also reproduce surrounding sounds simultaneously with the user's speech, thereby realizing more realistic speech. This allows for more realistic speech by reproducing background sounds and environmental sounds of the user's speech. Methods for reproducing background sounds and environmental sounds include, for example, ambient noise or specific environmental sounds (such as the sound of rain or the sound of cars). Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without AI. For example, the output unit can input the user's speech data and background sound data to a generation AI and cause the generation AI to reproduce the background sounds and environmental sounds.

[0077] The output unit can estimate the user's emotions and determine the priority of content to be output based on the estimated user's emotions. For example, when the user is relaxed, the output unit outputs all content equally. Furthermore, when the user is nervous, the output unit can prioritize output of important content. Furthermore, when the user is excited, the output unit can prioritize output of emotional content. This allows more appropriate content to be output by determining the priority of content to be output according to the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone, pitch, and facial expression recognition. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without AI. For example, the output unit can input the user's voice data to a generation AI and have the generation AI perform emotion estimation.

[0078] The output unit can prioritize output of highly relevant content by taking into account the user's geographical location information. For example, when the user is in a specific location, the output unit prioritizes output of content related to that location. Furthermore, when the user is traveling, the output unit can prioritize output of content related to travel. Furthermore, when the user is at home, the output unit can prioritize output of content related to daily life. In this way, highly relevant content can be prioritized by taking the user's geographical location information into account. The geographical location information can be acquired, for example, using GPS data or a location information service. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's geographical location data to a generation AI and cause the generation AI to prioritize highly relevant content.

[0079] At the time of output, the output unit can analyze the user's social media activity and output related content. For example, the output unit prioritizes output of content that the user is talking about on social media. The output unit can also analyze the content posted by the user on social media and output related content. The output unit can also output related content by referring to the user's interactions with friends on social media. In this way, related content can be output by analyzing the user's social media activity. Methods for analyzing social media activity include, for example, analyzing the content posted and analyzing followers. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's social media data to a generation AI and cause the generation AI to output related content.

[0080] The output unit can customize the output method by reflecting the user's past feedback at the time of output. For example, the output unit adjusts the current output method based on the user's preferred output method in the past. The output unit can also customize the output method by referring to the user's past feedback. The output unit can also customize the output method by referring to content that the user has felt they wanted to output in the past. In this way, the output method can be customized by reflecting the user's past feedback. The past feedback can be stored, for example, in a database and used in a machine learning model. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's past feedback data into a generation AI and have the generation AI customize the output method. === Hard Collateral 1-1 === Each of the multiple elements, including the recording unit, interpretation unit, listening unit, generation unit, and output unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the recording unit is realized by the computer 36 of the smart device 14 or the processor 28 of the data processing device 12. For example, the interpretation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the listening unit is realized via the microphone 38B of the smart device 14 or the communication I / F 26 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the output unit is realized by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned recording unit, interpretation unit, listening unit, generation unit, and output unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the recording unit is realized by the computer 36 of the smart glasses 214 or the processor 28 of the data processing device 12. For example, the interpretation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the listening unit is realized via the microphone 238 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the output unit is realized by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned recording unit, interpretation unit, listening unit, generation unit, and output unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the recording unit is realized by the computer 36 of the headset type terminal 314 or the processor 28 of the data processing device 12. For example, the interpretation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the listening unit is realized via the microphone 238 of the headset type terminal 314 or the communication I / F 26 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the output unit is realized by the speaker 240 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned recording unit, interpretation unit, listening unit, generation unit, and output unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the recording unit is realized by the computer 36 of the robot 414 or the processor 28 of the data processing device 12. For example, the interpretation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the listening unit is realized via the microphone 238 of the robot 414 or the communication I / F 26 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the output unit is realized by the speaker 240 of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The conversation support system may further include a health monitor unit that monitors the user's health condition. The health monitor unit measures the user's vital signs, such as heart rate, blood pressure, and body temperature, in real time to understand the user's health condition. For example, when a user is nervous, their heart rate often increases, so the health monitor unit can detect fluctuations in heart rate and estimate the user's state of tension. Also, when a user is relaxed, their heart rate and blood pressure stabilize, so the health monitor unit can estimate the user's state of relaxation based on this data. Furthermore, the health monitor unit can adjust the operation of the conversation support system based on the user's health condition. For example, when a user is feeling unwell, the conversation support system can reduce the number of response candidates generated to allow the user to have a conversation without straining themselves.

[0083] The conversation support system may further include a schedule management unit that manages the user's schedule. The schedule management unit keeps track of the user's schedule and provides conversation support at appropriate times. For example, if the user has an important meeting or presentation coming up, the schedule management unit can enhance the functions of the conversation support system to match that timing and support the user so that they can speak with confidence. The schedule management unit can also adjust the timing of recording conversation logs based on the user's schedule. For example, the conversation log can be recorded in a time period when the user is relaxed, allowing detailed information to be collected. Furthermore, the schedule management unit can optimize the generation of response candidates based on the user's schedule, allowing the user to communicate efficiently.

[0084] The conversation support system may further include a learning management unit that manages the user's learning history. The learning management unit records what the user has learned in the past and topics of interest, and uses this information for conversation support. For example, if the user is interested in a particular field, the learning management unit can prioritize generating response candidates related to that field. The learning management unit can also analyze conversation logs based on the user's past learning to understand the user's level of understanding. Furthermore, the learning management unit can adjust the operation of the conversation support system based on the user's learning history to support the user in learning effectively. For example, when a user tries a new topic, the learning management unit can provide basic knowledge related to that topic, allowing the user to smoothly progress through the conversation.

[0085] The conversation support system may further include a hobby and preference analysis unit that digs deeper into the user's hobbies and interests. The hobby and preference analysis unit analyzes the user's conversation log and social media activity to gain a detailed understanding of the user's hobbies and interests. For example, if the user is interested in a particular movie or music, the hobby and preference analysis unit can provide related topics based on that information. The hobby and preference analysis unit can also generate response candidates based on the user's interests to help the user have enjoyable conversations. Furthermore, the hobby and preference analysis unit can track changes in the user's interests in real time and adjust the operation of the conversation support system accordingly. For example, if the user discovers a new hobby, the hobby and preference analysis unit can provide information related to that hobby, allowing the user to enjoy conversations on new topics.

[0086] The conversation support system may further include a relaxation unit for stabilizing the user's emotions. The relaxation unit provides a relaxing environment when the user is tense or stressed. For example, the relaxation unit may play music that helps the user relax and create a comfortable atmosphere. The relaxation unit may also provide guidance for the user to take deep breaths or meditate, thereby calming the user's mind. Furthermore, the relaxation unit may adjust the relaxation method according to the user's emotional state to provide an optimal relaxation effect. For example, if the user is very tense, the relaxation unit may provide a more powerful relaxation method to help the user relax quickly.

[0087] The conversation support system may further include a network analysis unit that analyzes the user's social network. The network analysis unit analyzes the user's relationships with friends, family, colleagues, and the like, and supports the user in determining what type of communication to engage in. For example, the network analysis unit may analyze the topics the user frequently talks about with a particular friend and provide response candidates to facilitate conversations with that friend. The network analysis unit may also support the user in finding common topics when meeting a new person. Furthermore, the network analysis unit may track changes in the user's social network in real time and adjust the operation of the conversation support system accordingly. For example, if the user moves to a new workplace, the network analysis unit may support communication with new colleagues, allowing the user to quickly adapt to the new environment.

[0088] The conversation support system may further include a feedback unit that estimates the user's emotions and provides appropriate feedback to the user based on the estimated emotions. When the user is relaxed, the feedback unit may provide positive feedback to boost the user's confidence. When the user is nervous, the feedback unit may provide encouraging words or advice to relax. When the user is excited, the feedback unit may provide advice to stay calm and stabilize the user's emotions. Thus, the feedback unit can improve the user's communication ability by providing appropriate feedback according to the user's emotions. The emotion estimation may be performed using, for example, techniques such as voice tone and pitch, or facial expression recognition. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or without AI.

[0089] The conversation support system may further include a speech adjustment unit that estimates the user's emotions and adjusts the user's speech content based on the estimated emotions. When the user is relaxed, the speech adjustment unit can provide detailed speech content, allowing the user to speak with confidence. When the user is nervous, the speech adjustment unit can provide concise and easy-to-understand speech content, allowing the user to continue the conversation without strain. Furthermore, when the user is excited, the speech adjustment unit can provide speech content to calm the user down, stabilizing the user's emotions. In this way, the speech adjustment unit can improve the user's communication ability by adjusting the speech content according to the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone and pitch, and facial expression recognition. Some or all of the above-mentioned processing in the speech adjustment unit may be performed using, for example, AI, or without AI.

[0090] The conversation support system may further include a timing adjustment unit that estimates the user's emotions and adjusts the timing of the user's speech based on the estimated emotions. When the user is relaxed, the timing adjustment unit can encourage the user to speak at a natural timing, allowing the user to smoothly progress in the conversation. When the user is nervous, the timing adjustment unit can encourage the user to speak by providing appropriate pauses, allowing the user to continue the conversation without strain. When the user is excited, the timing adjustment unit can encourage the user to speak by providing pauses to calm the user down, thereby stabilizing the user's emotions. In this way, the timing adjustment unit can improve the user's communication ability by adjusting the timing of speech according to the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone and pitch, and facial expression recognition. Some or all of the above-mentioned processing in the timing adjustment unit may be performed using, for example, AI, or without AI.

[0091] The conversation support system may further include a content adjustment unit that estimates the user's emotions and adjusts the content of the user's utterances based on the estimated emotions. When the user is relaxed, the content adjustment unit can provide detailed utterances to enable the user to speak with confidence. When the user is nervous, the content adjustment unit can provide concise and easy-to-understand utterances to enable the user to continue the conversation without strain. When the user is excited, the content adjustment unit can provide utterances to calm the user down and stabilize the user's emotions. Thus, the content adjustment unit can improve the user's communication ability by adjusting the utterances according to the user's emotions. Emotion estimation is performed using, for example, techniques such as voice tone and pitch, and facial expression recognition. Some or all of the above-described processing in the content adjustment unit may be performed using, for example, AI, or without AI.

[0092] The processing flow of the second embodiment will be briefly explained below.

[0093] Step 1: The recording unit records a conversation log of a scene in which the user is speaking. For example, the recording unit can record a scene in which the user talks about hobbies or a conversation with a friend. The recording unit can also record the conversation log in audio or text format. Step 2: The interpretation unit interprets the user's interests and preferences based on the conversation log recorded by the recording unit. For example, the interpretation unit can analyze information such as what topics the user is interested in and what expressions the user prefers. The interpretation unit can also analyze the conversation log using natural language processing technology. Step 3: The listening unit uses speech recognition technology to listen to what others are saying. For example, the listening unit can listen to what others are saying in real time when the user has difficulty speaking at school or work. The listening unit can also use speech recognition technology that uses deep learning. Step 4: The generation unit generates answer candidates based on the hobbies and preferences interpreted by the interpretation unit. For example, when someone asks, "What did you do over the weekend?", the generation unit can generate answer candidates such as "I watched a movie" or "I hung out with friends" based on the user's hobbies and preferences. The generation unit can also generate answer candidates using natural language generation technology. Step 5: The output unit outputs the response selected by the user from the candidate responses generated by the generation unit in the user's voice. For example, the output unit can output the selected response by imitating the user's voice. Alternatively, the output unit can generate the user's voice using speech synthesis technology.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0114] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0130] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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."

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] [Explanation of symbols]

[0166] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a recording unit that records a conversation log; an interpretation unit that interprets the user's interests and preferences based on the conversation log recorded by the recording unit; a listening section that listens to what others say using speech recognition technology; a generation unit that generates answer candidates based on the interests and preferences interpreted by the interpretation unit; an output unit that outputs, in the user's voice, a response selected by the user from the response candidates generated by the generation unit; A system characterized by:

2. The recording unit The system estimates the user's emotions and adjusts the timing of recording the conversation log based on the estimated user emotions.

2. The system of claim 1.

3. The recording unit During recording, the frequency and tone of your speech are analyzed to prioritize important conversations.

2. The system of claim 1.

4. The recording unit When recording, users' comments are categorized and saved.

2. The system of claim 1.

5. The recording unit During recording, background and environmental sounds of the user's speech are also recorded and used for later analysis.

2. The system of claim 1.

6. The interpretation unit Estimate the user's emotions and adjust the interpretation method of the user's preferences based on the estimated emotions.

2. The system of claim 1.

7. The interpretation unit During interpretation, frequently occurring keywords are extracted from the conversation log to identify interests and preferences.

2. The system of claim 1.

8. The interpretation unit During interpretation, the context of the user's comments is analyzed to interpret their preferences in more detail.

2. The system of claim 1.

Images