system

Abstract

The system according to the embodiment aims to analyze the user's voice data, learn the individual habits, and provide appropriate responses and replies. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a reception unit, a generation unit, and a provision unit. The collection unit collects user voice data. The analysis unit analyzes the voice data collected by the collection unit and learns the user's habits. The reception unit receives questions from the user. The generation unit generates answers or replies to the questions received by the reception unit. The provision unit provides the answers or replies generated by the generation unit.

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 do not adequately utilize a user's voice data to learn their individual habits and provide appropriate responses or replies, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze the user's voice data, learn the individual habits, and provide appropriate responses and replies. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a reception unit, a generation unit, and a provision unit. The collection unit collects voice data of a user. The analysis unit analyzes the voice data collected by the collection unit and learns the user's habits. The reception unit receives questions from the user. The generation unit generates answers or replies to the questions received by the reception unit. The provision unit provides the answers or replies generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the user's voice data, learn the individual habits, and provide appropriate responses and replies. [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 system according to an embodiment of the present invention learns a user's habits through voice conversations and provides appropriate responses or replies in voice or text as "another you" when the user is unsure of what to do next, such as when conversing with someone or sending an email. For example, the system records the user's everyday conversations and uses AI to analyze the audio data. The AI ​​learns the user's habits, such as the user's speaking style, word choice, and expression. Next, when the user is unsure of what to do next when conversing with someone or sending an email, the system asks the system a question. The system accepts the user's question and generates an appropriate response or reply to the question. The AI ​​generates a response or reply using words and expressions commonly used by the user based on the user's habits learned in advance. The generated response or reply is provided to the user in voice or text. This allows the user to communicate smoothly and without hesitation. This allows the system to improve the user's communication skills, reduce stress, and support efficient communication. For example, the system can be used in a variety of situations, such as replying to emails in business situations and private conversations.

[0029] A communication support system according to an embodiment includes a collection unit, an analysis unit, a reception unit, a generation unit, and a provision unit. The collection unit collects voice data of a user. The collection unit, for example, records the user's everyday conversations as audio. The collection unit may also include an anonymization unit that anonymizes the voice data. The analysis unit analyzes the voice data collected by the collection unit and learns the user's habits. The analysis unit, for example, converts the voice data into text data using voice recognition technology and extracts features such as the user's speaking style, word choice, and expression. The analysis unit may also learn the user's habits using a machine learning algorithm. The reception unit receives questions from a user. The reception unit may, for example, include an input unit that supports both voice input and text input. The generation unit generates a response or reply to the question received by the reception unit. The generation unit generates a response or reply that reflects, for example, frequently used phrases by the user or a reaction pattern in a specific situation. The generation unit may also generate a response or reply based on the user's habits using a generation AI. The providing unit provides the response or reply generated by the generating unit. The providing unit provides the response or reply to the user, for example, in the form of voice or text. The providing unit may also include a feedback unit that receives feedback from the user. As a result, the communication support system according to the embodiment can collect and analyze the user's voice data and generate and provide an appropriate response or reply to a question. For example, the system records the user's everyday conversations as audio, and the AI ​​analyzes the audio data. The AI ​​learns the user's habits, such as the user's speaking style, word choice, and expression. Next, when the user is unsure of what to do next when talking to someone or sending an email, the user asks the system a question. The system accepts the user's question and generates an appropriate response or reply to the question. The AI ​​generates a response or reply using words and expressions commonly used by the user based on the user's habits that it has previously learned. The generated response or reply is provided to the user in the form of voice or text. This allows the user to communicate smoothly and without hesitation.

[0030] The collection unit includes an anonymization unit that anonymizes the collected voice data. The anonymization unit anonymizes the collected voice data. For example, the anonymization unit deletes personal identification information from the voice data. The anonymization unit can also convert the voice data using voice conversion technology. For example, the anonymization unit deletes information that can identify an individual from the voice data to generate anonymized voice data. The anonymization unit can also convert the voice data into a format that does not identify an individual. In this way, privacy can be protected by anonymizing the collected voice data.

[0031] The providing unit includes a feedback unit that receives feedback from users. The feedback unit receives feedback from users. The feedback unit, for example, collects user opinions and evaluations. The feedback unit can also analyze the feedback. For example, the feedback unit collects user opinions and evaluations and uses them to improve the system. The feedback unit can also analyze the collected feedback and evaluate the performance of the system. In this way, receiving feedback from users can be used to improve the system.

[0032] The reception unit includes an input unit that supports both voice input and text input. The input unit supports both voice input and text input. The input unit allows, for example, a user to input a question by voice. The input unit also allows a user to input a question by text. For example, the input unit converts voice input into text data using voice recognition technology. The input unit can also directly accept text input. This allows for support of both voice input and text input, thereby improving user convenience.

[0033] The analysis unit can learn the user's speaking style, word choice, and expression habits. For example, the analysis unit converts voice data into text data using voice recognition technology and extracts features such as the user's speaking style, word choice, and expression habits. The analysis unit can also learn the user's habits using a machine learning algorithm. For example, the analysis unit learns the user's frequently used phrases and reaction patterns in specific situations. The analysis unit can also analyze the user's speaking patterns and word choice to identify the user's habits. In this way, by learning the user's speaking style, word choice, expression habits, and other habits, it can generate more appropriate responses and replies.

[0034] The generation unit can generate replies and responses that reflect the user's frequently used phrases and reaction patterns in specific situations. For example, the generation unit generates replies that incorporate the user's frequently used phrases. The generation unit can also generate replies that reflect reaction patterns in specific situations. For example, the generation unit generates replies based on the user's frequently used phrases and reactions in specific situations. The generation unit can also generate natural replies that reflect the user's habits. In this way, by generating replies and responses that reflect the user's frequently used phrases and reaction patterns in specific situations, it is possible to provide the user with natural replies and responses.

[0035] The collection unit can analyze the user's past conversation history and select a collection method. The collection unit can customize the collection method based on, for example, patterns of frequent conversations the user has had in the past. The collection unit can also prioritize collection of conversations the user has had during specific time periods. Furthermore, the collection unit can also focus on collecting conversations about specific topics from the user's past conversation history. This makes it possible to select the optimal collection method and efficiently collect voice data by analyzing the user's past conversation history.

[0036] When collecting voice data, the collection unit can perform filtering based on the user's current situation and environment. For example, when the user is in a quiet environment, the collection unit collects voice data with high accuracy. In addition, when the user is in a noisy environment, the collection unit can also collect voice data using noise canceling technology. Furthermore, when the user is moving, the collection unit can perform appropriate filtering to maintain the quality of the collected voice data. Thus, by performing filtering based on the user's current situation and environment, the quality of the collected voice data can be improved.

[0037] When collecting voice data, the collection unit can select a collection means according to the user's input method. For example, if the user is using voice input, the collection unit prioritizes collection of voice data. Also, if the user is using text input, the collection unit can collect text data and analyze it in combination with voice data. Furthermore, if the user is using images, the collection unit can analyze image data and collect related voice data. This allows for efficient collection of voice data by selecting the optimal collection means according to the user's input method.

[0038] When collecting voice data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific location, the collection unit prioritizes collecting voice data related to that location. Furthermore, when the user is traveling, the collection unit can also prioritize collecting conversations at the travel destination. Furthermore, when the user is at home, the collection unit can also prioritize collecting everyday conversations. In this way, by prioritized collection of highly relevant data by taking into account the user's geographical location information, the relevance of the collected voice data can be improved.

[0039] When collecting voice data, the collection unit can analyze the user's social media activities and collect related data. For example, the collection unit collects voice data related to content posted by the user on social media. The collection unit can also collect voice data by referring to conversations between the user and friends on social media. Furthermore, the collection unit can analyze the user's activity patterns on social media and collect related voice data. This makes it possible to efficiently collect related voice data by analyzing the user's social media activities.

[0040] When collecting voice data, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit adjusts the collection method based on feedback provided by the user in the past. Furthermore, if the user prefers a particular collection method, the collection unit can preferentially use that method. Furthermore, the collection unit can analyze the user's past feedback and suggest the optimal collection method. In this way, the collection method can be customized by reflecting the user's past feedback, and voice data can be collected efficiently.

[0041] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the audio data. For example, the analysis unit performs a detailed analysis in the case of important conversation content. The analysis unit can also perform a concise analysis in the case of everyday conversation content. Furthermore, in the case of a conversation about a specific topic, the analysis unit can also perform a detailed analysis related to that topic. In this way, by adjusting the level of detail of the analysis based on the importance of the audio data, analysis can be performed efficiently.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the voice data. For example, in the case of a business conversation, the analysis unit applies a business analysis algorithm. In addition, in the case of a private conversation, the analysis unit can also apply a private analysis algorithm. Furthermore, in the case of a conversation related to a specific field of expertise, the analysis unit can also apply an analysis algorithm specialized for that field. In this way, by applying different analysis algorithms depending on the category of the voice data, analysis can be performed efficiently.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also improve the accuracy of the analysis by referring to feedback provided by the user in the past. Furthermore, the analysis unit can analyze the user's past analysis results and propose an optimal analysis method. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results.

[0044] During analysis, the analysis unit can determine the priority of analysis based on the time when the voice data was collected. For example, the analysis unit prioritizes analysis of the most recent voice data. The analysis unit can also prioritize analysis of voice data collected during a specific time period. Furthermore, the analysis unit can also prioritize analysis of voice data within a period specified by the user. In this way, by determining the priority of analysis based on the time when the voice data was collected, analysis can be performed efficiently.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the audio data. For example, the analysis unit prioritizes analysis of highly relevant audio data. The analysis unit can also prioritize analysis of audio data related to a specific topic. Furthermore, the analysis unit can also prioritize analysis of audio data related to a topic specified by the user. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the audio data.

[0046] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that make extensive use of technical terms. In addition, if the user does not have technical expertise, the analysis unit can also provide concise and easy-to-understand analysis results. Furthermore, the analysis unit can adjust the way in which the analysis results are expressed according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easy for the user to understand.

[0047] The reception unit can select the optimal reception method by analyzing the user's past question history when receiving a question. The reception unit can suggest the optimal reception method based on, for example, questions that the user has frequently asked in the past. The reception unit can also prioritize receiving questions that the user asks during a specific time period. Furthermore, the reception unit can also prioritize receiving questions related to a specific topic based on the user's past question history. In this way, by analyzing the user's past question history, the optimal reception method can be selected and questions can be received efficiently.

[0048] The reception unit can perform filtering based on the user's current situation and environment when receiving questions. For example, when the user is in a quiet environment, the reception unit can receive detailed questions. Furthermore, when the user is in a noisy environment, the reception unit can also preferentially receive concise questions. Furthermore, when the user is on the move, the reception unit can adjust the content of the questions to be received. In this way, filtering based on the user's current situation and environment can be performed, allowing questions to be received efficiently.

[0049] The reception unit can select the optimal reception means depending on the user's input method when receiving a question. For example, if the user is using voice input, the reception unit can prioritize receiving voice questions. Also, if the user is using text input, the reception unit can also prioritize receiving text questions. Furthermore, if the user is using images, the reception unit can also prioritize receiving questions related to images. In this way, by selecting the optimal reception means depending on the user's input method, questions can be received efficiently.

[0050] The reception unit can prioritize receiving highly relevant questions by taking into consideration the user's geographical location information when receiving questions. For example, when the user is in a specific location, the reception unit prioritizes receiving questions related to that location. Furthermore, when the user is traveling, the reception unit can also prioritize receiving questions about the travel destination. Furthermore, when the user is at home, the reception unit can also prioritize receiving everyday questions. In this way, by prioritizing highly relevant questions by taking into consideration the user's geographical location information, questions can be received efficiently.

[0051] The reception unit can analyze the user's social media activity and receive related questions at the time of reception. The reception unit, for example, receives questions related to content posted by the user on social media. The reception unit can also receive questions by referring to conversations between the user and friends on social media. Furthermore, the reception unit can analyze the user's social media activity patterns and receive related questions. In this way, related questions can be efficiently received by analyzing the user's social media activity.

[0052] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a question. The reception unit adjusts the reception method based on, for example, feedback provided by the user in the past. Furthermore, if the user prefers a specific reception method, the reception unit can preferentially use that method. Furthermore, the reception unit can analyze the user's past feedback and suggest the optimal reception method. In this way, the reception method can be customized by reflecting the user's past feedback, making it possible to efficiently receive questions.

[0053] The generator can adjust the level of detail of the generated answer based on the importance of the question during generation. For example, the generator generates a detailed answer for an important question. The generator can also generate a concise answer for an everyday question. Furthermore, the generator can generate a detailed answer related to a specific topic for a question about that topic. In this way, by adjusting the level of detail of the generated answer based on the importance of the question, answers and replies can be generated efficiently.

[0054] The generation unit can apply different generation algorithms depending on the question category during generation. For example, the generation unit can apply a business generation algorithm to a business-related question. The generation unit can also apply a private generation algorithm to a private question. Furthermore, the generation unit can apply a generation algorithm specialized for a specific field to a question related to that field. In this way, by applying different generation algorithms depending on the question category, answers and replies can be generated efficiently.

[0055] During generation, the generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit adjusts the generation algorithm based on the user's past generation results. The generation unit can also improve the accuracy of generation by referring to feedback provided by the user in the past. Furthermore, the generation unit can analyze the user's past generation results and propose an optimal generation method. In this way, the accuracy of generation can be improved by referring to the user's past generation results.

[0056] The generation unit can determine the generation priority based on the time of submission of the question at the time of generation. For example, the generation unit can generate replies with priority to the most recent question. The generation unit can also generate replies with priority to questions submitted within a specific time period. Furthermore, the generation unit can also generate replies with priority to questions submitted within a period specified by the user. In this way, by determining the generation priority based on the time of submission of the question, replies and responses can be generated efficiently.

[0057] The generation unit can adjust the order of generation based on the relevance of the questions during generation. For example, the generation unit can generate replies with priority to questions that are highly relevant. The generation unit can also generate replies with priority to questions related to a specific topic. Furthermore, the generation unit can also generate replies with priority to questions related to a topic specified by the user. In this way, by adjusting the order of generation based on the relevance of the questions, replies and responses can be generated efficiently.

[0058] The generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise during generation. For example, if the user has technical expertise, the generation unit generates a response that uses a lot of technical terminology. Also, if the user does not have technical expertise, the generation unit can generate a concise and easy-to-understand response. Furthermore, the generation unit can adjust the way the response is expressed according to the user's level of expertise. In this way, by adjusting the use of technical terminology in the generation according to the user's level of expertise, it is possible to provide a response or reply that is easy for the user to understand.

[0059] The providing unit can adjust the level of detail provided based on the importance of the reply or response when providing the reply. For example, the providing unit provides detailed information for an important reply. The providing unit can also provide concise information for an everyday reply. Furthermore, the providing unit can also provide detailed information related to a reply on a specific topic. In this way, by adjusting the level of detail provided based on the importance of the reply or response, it is possible to provide a reply or response efficiently.

[0060] The providing unit can apply different providing algorithms depending on the category of the response or reply when providing the response. For example, the providing unit applies a business providing algorithm to a business-related response. The providing unit can also apply a private providing algorithm to a private response. Furthermore, the providing unit can apply a providing algorithm specialized for a specific field to a response related to that field. In this way, by applying different providing algorithms depending on the category of the response or reply, it is possible to provide responses or replies efficiently.

[0061] The providing unit can improve the accuracy of the provision by referring to the user's past provision results when providing the information. For example, the providing unit adjusts the provision algorithm based on the user's past provision results. The providing unit can also improve the accuracy of the provision by referring to feedback provided by the user in the past. Furthermore, the providing unit can analyze the user's past provision results and propose an optimal provision method. In this way, the accuracy of the provision can be improved by referring to the user's past provision results.

[0062] The providing unit can determine the priority of providing based on the time of submission of the reply or response. For example, the providing unit can provide the most recent reply with priority. The providing unit can also provide with priority to replies submitted within a specific time period. Furthermore, the providing unit can provide with priority to replies submitted within a period specified by the user. In this way, by determining the priority of providing based on the time of submission of the reply or response, it is possible to provide replies or responses efficiently.

[0063] The providing unit can adjust the order of providing replies and responses based on the relevance of the replies and responses when providing them. For example, the providing unit can provide highly relevant replies with priority. The providing unit can also provide replies related to a specific topic with priority. Furthermore, the providing unit can also provide replies related to a topic specified by the user with priority. In this way, by adjusting the order of providing replies and responses based on the relevance of the replies and responses, replies and responses can be provided efficiently.

[0064] The providing unit can adjust the use of technical terminology in the provided response depending on the user's level of expertise when providing the response. For example, if the user has technical expertise, the providing unit can provide a response that uses a lot of technical terminology. Also, if the user does not have technical expertise, the providing unit can provide a concise and easy-to-understand response. Furthermore, the providing unit can adjust the way the response is expressed depending on the user's level of expertise. In this way, by adjusting the use of technical terminology in the provided response depending on the user's level of expertise, it is possible to provide a response or reply that is easy for the user to understand.

[0065] The anonymization unit can adjust the level of detail of anonymization based on the importance of the voice data during anonymization. For example, the anonymization unit performs detailed anonymization in the case of important conversation content. The anonymization unit can also perform simple anonymization in the case of everyday conversation content. Furthermore, in the case of a conversation about a specific topic, the anonymization unit can also perform detailed anonymization related to the topic. In this way, by adjusting the level of detail of anonymization based on the importance of the voice data, anonymization can be performed efficiently.

[0066] The anonymization unit can apply different anonymization algorithms depending on the category of the voice data during anonymization. For example, in the case of a business conversation, the anonymization unit applies a business anonymization algorithm. In addition, in the case of a private conversation, the anonymization unit can also apply a private anonymization algorithm. Furthermore, in the case of a conversation related to a specific field of expertise, the anonymization unit can also apply an anonymization algorithm specialized for that field. In this way, by applying different anonymization algorithms depending on the category of the voice data, anonymization can be performed efficiently.

[0067] During anonymization, the anonymization unit can determine the priority of anonymization based on the time when the voice data was collected. For example, the anonymization unit can prioritize anonymizing the most recent voice data. The anonymization unit can also prioritize anonymizing voice data collected during a specific time period. Furthermore, the anonymization unit can also prioritize anonymizing voice data within a period specified by the user. In this way, by determining the priority of anonymization based on the time when the voice data was collected, anonymization can be performed efficiently.

[0068] The anonymization unit can adjust the order of anonymization based on the relevance of the audio data during anonymization. For example, the anonymization unit can prioritize anonymize highly relevant audio data. The anonymization unit can also prioritize anonymize audio data related to a specific topic. Furthermore, the anonymization unit can also prioritize anonymize audio data related to a topic specified by the user. This allows for efficient anonymization by adjusting the order of anonymization based on the relevance of the audio data.

[0069] The feedback unit can adjust the level of detail of the feedback based on the importance of the response or reply when providing feedback. For example, the feedback unit provides detailed feedback for an important response. The feedback unit can also provide brief feedback for an everyday response. Furthermore, the feedback unit can also provide detailed feedback related to a specific topic for a response on that topic. In this way, by adjusting the level of detail of the feedback based on the importance of the response or reply, feedback can be provided efficiently.

[0070] The feedback unit can apply different feedback algorithms depending on the category of the response or reply when providing feedback. For example, the feedback unit can apply a business feedback algorithm to a business-related response. The feedback unit can also apply a private feedback algorithm to a private response. Furthermore, the feedback unit can also apply a feedback algorithm specialized for a specific field to a response related to that field. In this way, by applying different feedback algorithms depending on the category of the response or reply, feedback can be provided efficiently.

[0071] The feedback unit can improve the accuracy of feedback by referring to the user's past feedback results when providing feedback. For example, the feedback unit adjusts a feedback algorithm based on the user's past feedback results. The feedback unit can also improve the accuracy of feedback by referring to feedback provided by the user in the past. Furthermore, the feedback unit can analyze the user's past feedback results and suggest an optimal feedback method. In this way, the accuracy of feedback can be improved by referring to the user's past feedback results.

[0072] When providing feedback, the feedback unit can determine the priority of the feedback based on the time of submission of the response or reply. For example, the feedback unit can provide feedback preferentially to the most recent response. The feedback unit can also provide feedback preferentially to responses submitted within a specific time period. Furthermore, the feedback unit can also provide feedback preferentially to responses submitted within a period specified by the user. In this way, by determining the priority of feedback based on the time of submission of the response or reply, feedback can be provided efficiently.

[0073] The feedback unit can adjust the order of feedback based on the relevance of replies and replies when providing feedback. For example, the feedback unit can provide feedback preferentially to highly relevant replies. The feedback unit can also provide feedback preferentially to replies related to a specific topic. Furthermore, the feedback unit can also provide feedback preferentially to replies related to a topic specified by the user. In this way, by adjusting the order of feedback based on the relevance of replies and replies, feedback can be provided efficiently.

[0074] When inputting data, the input unit can select the optimal input method by analyzing the user's past input history. For example, the input unit can suggest the optimal input method based on input methods that the user has frequently used in the past. The input unit can also prioritize receiving inputs made by the user during a specific time period. Furthermore, the input unit can also prioritize receiving inputs related to a specific topic from the user's past input history. This allows the optimal input method to be selected by analyzing the user's past input history, enabling efficient input.

[0075] The input unit can filter input based on the user's current situation and environment. For example, when the user is in a quiet environment, the input unit accepts detailed input. Also, when the user is in a noisy environment, the input unit can preferentially accept brief input. Furthermore, when the user is moving, the input unit can adjust the content of the input to be accepted. This allows for efficient input by filtering based on the user's current situation and environment.

[0076] The input unit can prioritize inputting highly relevant questions in consideration of the user's geographical location information when inputting questions. For example, when the user is in a specific location, the input unit prioritizes inputting questions related to that location. Furthermore, when the user is traveling, the input unit can also prioritize inputting questions for the travel destination. Furthermore, when the user is at home, the input unit can also prioritize inputting everyday questions. This allows questions to be input efficiently by prioritized inputting highly relevant questions in consideration of the user's geographical location information.

[0077] The input unit can analyze the user's social media activity and input a related question at the time of input. For example, the input unit inputs a question related to content posted by the user on social media. The input unit can also input a question by referring to conversations between the user and friends on social media. Furthermore, the input unit can analyze the user's activity pattern on social media and input a related question. In this way, related questions can be input efficiently by analyzing the user's social media activity.

[0078] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0079] The collection unit can adjust the method of collecting voice data taking into account the user's geographical location information. For example, if the user is in a specific location, conversations related to that location can be collected with priority. Also, if the user is traveling, conversations at the travel destination can be collected with priority. Furthermore, if the user is at home, everyday conversations can be collected with priority. In this way, by adjusting the method of collecting voice data taking into account the user's geographical location information, the relevance of the collected voice data can be improved.

[0080] The analysis unit can adjust the analysis algorithm based on the user's past feedback. For example, it can analyze feedback provided by the user in the past and improve the accuracy of the analysis algorithm. Also, if the user prefers a specific analysis method, it can preferentially use that method. Furthermore, it can also suggest the optimal analysis method by referring to the user's past feedback. In this way, it is possible to improve the accuracy of the analysis by reflecting the user's past feedback.

[0081] The providing unit can adjust the providing algorithm based on the user's past providing results. For example, it can analyze feedback provided by the user in the past and improve the accuracy of the providing algorithm. Also, if the user prefers a specific providing method, it can preferentially use that method. Furthermore, it can also suggest the optimal providing method by referring to the user's past providing results. In this way, it is possible to improve the accuracy of the providing by reflecting the user's past providing results.

[0082] The collection unit can analyze the user's social media activities and collect related voice data. For example, it can collect voice data related to content posted by the user on social media. It can also collect voice data by referring to the user's conversations with friends on social media. It can also analyze the user's activity patterns on social media and collect related voice data. In this way, it is possible to efficiently collect related voice data by analyzing the user's social media activities.

[0083] The analysis unit can determine the priority of analysis based on the time when the voice data was collected. For example, the most recent voice data can be analyzed with priority. It can also analyze voice data collected during a specific time period with priority. It can also analyze voice data within a period specified by the user with priority. In this way, by determining the priority of analysis based on the time when the voice data was collected, it is possible to perform analysis efficiently.

[0084] The processing flow of the first embodiment will be briefly explained below.

[0085] Step 1: The collection unit records the user's everyday conversations as audio and collects audio data. The collection unit may also include an anonymization unit that anonymizes the audio data. Step 2: The analysis unit analyzes the voice data collected by the collection unit and learns the user's habits. The analysis unit uses voice recognition technology to convert the voice data into text data and extracts characteristics such as the user's speaking style, word choice, and expression. It can also learn the user's habits using machine learning algorithms. Step 3: The reception unit receives a question from the user. The reception unit may include an input unit that supports both voice input and text input. Step 4: The generator generates a response or reply to the question received by the receiver. The generator generates responses or replies that reflect the user's frequently used phrases and reaction patterns in specific situations. Generative AI can also be used to generate responses or replies based on the user's habits. Step 5: The providing unit provides the response or reply generated by the generating unit. The providing unit provides the response or reply to the user in the form of voice or text. The providing unit may also include a feedback unit that accepts feedback from the user.

[0086] (Example 2) A system according to an embodiment of the present invention learns a user's habits through voice conversations and provides appropriate responses or replies in voice or text as "another you" when the user is unsure of what to do next, such as when conversing with someone or sending an email. For example, the system records the user's everyday conversations and uses AI to analyze the audio data. The AI ​​learns the user's habits, such as the user's speaking style, word choice, and expression. Next, when the user is unsure of what to do next when conversing with someone or sending an email, the system asks the system a question. The system accepts the user's question and generates an appropriate response or reply to the question. The AI ​​generates a response or reply using words and expressions commonly used by the user based on the user's habits learned in advance. The generated response or reply is provided to the user in voice or text. This allows the user to communicate smoothly and without hesitation. This allows the system to improve the user's communication skills, reduce stress, and support efficient communication. For example, the system can be used in a variety of situations, such as replying to emails in business situations and private conversations.

[0087] A communication support system according to an embodiment includes a collection unit, an analysis unit, a reception unit, a generation unit, and a provision unit. The collection unit collects voice data of a user. The collection unit, for example, records the user's everyday conversations as audio. The collection unit may also include an anonymization unit that anonymizes the voice data. The analysis unit analyzes the voice data collected by the collection unit and learns the user's habits. The analysis unit, for example, converts the voice data into text data using voice recognition technology and extracts features such as the user's speaking style, word choice, and expression. The analysis unit may also learn the user's habits using a machine learning algorithm. The reception unit receives questions from a user. The reception unit may, for example, include an input unit that supports both voice input and text input. The generation unit generates a response or reply to the question received by the reception unit. The generation unit generates a response or reply that reflects, for example, frequently used phrases by the user or a reaction pattern in a specific situation. The generation unit may also generate a response or reply based on the user's habits using a generation AI. The providing unit provides the response or reply generated by the generating unit. The providing unit provides the response or reply to the user, for example, in the form of voice or text. The providing unit may also include a feedback unit that receives feedback from the user. As a result, the communication support system according to the embodiment can collect and analyze the user's voice data and generate and provide an appropriate response or reply to a question. For example, the system records the user's everyday conversations as audio, and the AI ​​analyzes the audio data. The AI ​​learns the user's habits, such as the user's speaking style, word choice, and expression. Next, when the user is unsure of what to do next when talking to someone or sending an email, the user asks the system a question. The system accepts the user's question and generates an appropriate response or reply to the question. The AI ​​generates a response or reply using words and expressions commonly used by the user based on the user's habits that it has previously learned. The generated response or reply is provided to the user in the form of voice or text. This allows the user to communicate smoothly and without hesitation.

[0088] The collection unit includes an anonymization unit that anonymizes the collected voice data. The anonymization unit anonymizes the collected voice data. For example, the anonymization unit deletes personal identification information from the voice data. The anonymization unit can also convert the voice data using voice conversion technology. For example, the anonymization unit deletes information that can identify an individual from the voice data to generate anonymized voice data. The anonymization unit can also convert the voice data into a format that does not identify an individual. In this way, privacy can be protected by anonymizing the collected voice data.

[0089] The providing unit includes a feedback unit that receives feedback from users. The feedback unit receives feedback from users. The feedback unit, for example, collects user opinions and evaluations. The feedback unit can also analyze the feedback. For example, the feedback unit collects user opinions and evaluations and uses them to improve the system. The feedback unit can also analyze the collected feedback and evaluate the performance of the system. In this way, receiving feedback from users can be used to improve the system.

[0090] The reception unit includes an input unit that supports both voice input and text input. The input unit supports both voice input and text input. The input unit allows, for example, a user to input a question by voice. The input unit also allows a user to input a question by text. For example, the input unit converts voice input into text data using voice recognition technology. The input unit can also directly accept text input. This allows for support of both voice input and text input, thereby improving user convenience.

[0091] The analysis unit can learn the user's speaking style, word choice, and expression habits. For example, the analysis unit converts voice data into text data using voice recognition technology and extracts features such as the user's speaking style, word choice, and expression habits. The analysis unit can also learn the user's habits using a machine learning algorithm. For example, the analysis unit learns the user's frequently used phrases and reaction patterns in specific situations. The analysis unit can also analyze the user's speaking patterns and word choice to identify the user's habits. In this way, by learning the user's speaking style, word choice, expression habits, and other habits, it can generate more appropriate responses and replies.

[0092] The generation unit can generate replies and responses that reflect the user's frequently used phrases and reaction patterns in specific situations. For example, the generation unit generates replies that incorporate the user's frequently used phrases. The generation unit can also generate replies that reflect reaction patterns in specific situations. For example, the generation unit generates replies based on the user's frequently used phrases and reactions in specific situations. The generation unit can also generate natural replies that reflect the user's habits. In this way, by generating replies and responses that reflect the user's frequently used phrases and reaction patterns in specific situations, it is possible to provide the user with natural replies and responses.

[0093] The collection unit can estimate the user's emotions and adjust the timing of collecting voice data based on the estimated user emotions. For example, when the user is relaxed, the collection unit collects voice data during natural conversation. Furthermore, when the user is feeling stressed, the collection unit can avoid collecting voice data and collect it when the user is calm. Furthermore, when the user is excited, the collection unit can collect voice data at the peak of the user's emotions to capture changes in emotion. This allows for the collection of more natural voice data by adjusting the timing of collecting voice data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0094] The collection unit can analyze the user's past conversation history and select a collection method. The collection unit can customize the collection method based on, for example, patterns of frequent conversations the user has had in the past. The collection unit can also prioritize collection of conversations the user has had during specific time periods. Furthermore, the collection unit can also focus on collecting conversations about specific topics from the user's past conversation history. This makes it possible to select the optimal collection method and efficiently collect voice data by analyzing the user's past conversation history.

[0095] When collecting voice data, the collection unit can perform filtering based on the user's current situation and environment. For example, when the user is in a quiet environment, the collection unit collects voice data with high accuracy. In addition, when the user is in a noisy environment, the collection unit can also collect voice data using noise canceling technology. Furthermore, when the user is moving, the collection unit can perform appropriate filtering to maintain the quality of the collected voice data. Thus, by performing filtering based on the user's current situation and environment, the quality of the collected voice data can be improved.

[0096] When collecting voice data, the collection unit can select a collection means according to the user's input method. For example, if the user is using voice input, the collection unit prioritizes collection of voice data. Also, if the user is using text input, the collection unit can collect text data and analyze it in combination with voice data. Furthermore, if the user is using images, the collection unit can analyze image data and collect related voice data. This allows for efficient collection of voice data by selecting the optimal collection means according to the user's input method.

[0097] The collection unit can estimate the user's emotions and determine the priority of the voice data to be collected based on the estimated user emotions. For example, if the user is nervous, the collection unit can prioritize collecting voice data when the user is relaxed. Also, if the user is having fun, the collection unit can prioritize collecting voice data at that time. Furthermore, if the user is angry, the collection unit can prioritize collecting voice data to capture that emotion. In this way, by determining the priority of the voice data to be collected based on the user's emotions, important voice data can be collected preferentially. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0098] When collecting voice data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific location, the collection unit prioritizes collecting voice data related to that location. Furthermore, when the user is traveling, the collection unit can also prioritize collecting conversations at the travel destination. Furthermore, when the user is at home, the collection unit can also prioritize collecting everyday conversations. In this way, by prioritized collection of highly relevant data by taking into account the user's geographical location information, the relevance of the collected voice data can be improved.

[0099] When collecting voice data, the collection unit can analyze the user's social media activities and collect related data. For example, the collection unit collects voice data related to content posted by the user on social media. The collection unit can also collect voice data by referring to conversations between the user and friends on social media. Furthermore, the collection unit can analyze the user's activity patterns on social media and collect related voice data. This makes it possible to efficiently collect related voice data by analyzing the user's social media activities.

[0100] When collecting voice data, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit adjusts the collection method based on feedback provided by the user in the past. Furthermore, if the user prefers a particular collection method, the collection unit can preferentially use that method. Furthermore, the collection unit can analyze the user's past feedback and suggest the optimal collection method. In this way, the collection method can be customized by reflecting the user's past feedback, and voice data can be collected efficiently.

[0101] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. If the user is nervous, the analysis unit can also provide concise and to-the-point analysis results. If the user is excited, the analysis unit can also provide visually easy-to-understand analysis results. By adjusting the way the analysis is presented based on the user's emotions, it is possible to provide analysis results that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0102] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the audio data. For example, the analysis unit performs a detailed analysis in the case of important conversation content. The analysis unit can also perform a concise analysis in the case of everyday conversation content. Furthermore, in the case of a conversation about a specific topic, the analysis unit can also perform a detailed analysis related to that topic. In this way, by adjusting the level of detail of the analysis based on the importance of the audio data, analysis can be performed efficiently.

[0103] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the voice data. For example, in the case of a business conversation, the analysis unit applies a business analysis algorithm. In addition, in the case of a private conversation, the analysis unit can also apply a private analysis algorithm. Furthermore, in the case of a conversation related to a specific field of expertise, the analysis unit can also apply an analysis algorithm specialized for that field. In this way, by applying different analysis algorithms depending on the category of the voice data, analysis can be performed efficiently.

[0104] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also improve the accuracy of the analysis by referring to feedback provided by the user in the past. Furthermore, the analysis unit can analyze the user's past analysis results and propose an optimal analysis method. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results.

[0105] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can provide a short and to-the-point analysis result. The analysis unit can also provide a detailed analysis result if the user is relaxed. Furthermore, if the user is excited, the analysis unit can provide a visually easy-to-understand analysis result. By adjusting the length of the analysis based on the user's emotions, it is possible to provide an analysis result of an appropriate length for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0106] During analysis, the analysis unit can determine the priority of analysis based on the time when the voice data was collected. For example, the analysis unit prioritizes analysis of the most recent voice data. The analysis unit can also prioritize analysis of voice data collected during a specific time period. Furthermore, the analysis unit can also prioritize analysis of voice data within a period specified by the user. In this way, by determining the priority of analysis based on the time when the voice data was collected, analysis can be performed efficiently.

[0107] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the audio data. For example, the analysis unit prioritizes analysis of highly relevant audio data. The analysis unit can also prioritize analysis of audio data related to a specific topic. Furthermore, the analysis unit can also prioritize analysis of audio data related to a topic specified by the user. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the audio data.

[0108] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that make extensive use of technical terms. In addition, if the user does not have technical expertise, the analysis unit can also provide concise and easy-to-understand analysis results. Furthermore, the analysis unit can adjust the way in which the analysis results are expressed according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easy for the user to understand.

[0109] The reception unit can estimate the user's emotions and adjust the reception method based on the estimated user emotions. For example, if the user is relaxed, the reception unit can provide detailed input options. Also, if the user is nervous, the reception unit can provide a simple interface. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input and quickly accept the call. In this way, by adjusting the reception method based on the user's emotions, it is possible to provide a reception method that is appropriate for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0110] The reception unit can select the optimal reception method by analyzing the user's past question history when receiving a question. The reception unit can suggest the optimal reception method based on, for example, questions that the user has frequently asked in the past. The reception unit can also prioritize receiving questions that the user asks during a specific time period. Furthermore, the reception unit can also prioritize receiving questions related to a specific topic based on the user's past question history. In this way, by analyzing the user's past question history, the optimal reception method can be selected and questions can be received efficiently.

[0111] The reception unit can perform filtering based on the user's current situation and environment when receiving questions. For example, when the user is in a quiet environment, the reception unit can receive detailed questions. Furthermore, when the user is in a noisy environment, the reception unit can also preferentially receive concise questions. Furthermore, when the user is on the move, the reception unit can adjust the content of the questions to be received. In this way, filtering based on the user's current situation and environment can be performed, allowing questions to be received efficiently.

[0112] The reception unit can select the optimal reception means depending on the user's input method when receiving a question. For example, if the user is using voice input, the reception unit can prioritize receiving voice questions. Also, if the user is using text input, the reception unit can also prioritize receiving text questions. Furthermore, if the user is using images, the reception unit can also prioritize receiving questions related to images. In this way, by selecting the optimal reception means depending on the user's input method, questions can be received efficiently.

[0113] The reception unit can estimate the user's emotions and determine the priority of questions to be received based on the estimated user emotions. For example, if the user is nervous, the reception unit can prioritize simple questions. Also, if the user is relaxed, the reception unit can prioritize detailed questions. Furthermore, if the user is in a hurry, the reception unit can prioritize questions that require a quick answer. In this way, by determining the priority of questions to be received based on the user's emotions, important questions can be received with priority. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0114] The reception unit can prioritize receiving highly relevant questions by taking into consideration the user's geographical location information when receiving questions. For example, when the user is in a specific location, the reception unit prioritizes receiving questions related to that location. Furthermore, when the user is traveling, the reception unit can also prioritize receiving questions about the travel destination. Furthermore, when the user is at home, the reception unit can also prioritize receiving everyday questions. In this way, by prioritizing highly relevant questions by taking into consideration the user's geographical location information, questions can be received efficiently.

[0115] The reception unit can analyze the user's social media activity and receive related questions at the time of reception. The reception unit, for example, receives questions related to content posted by the user on social media. The reception unit can also receive questions by referring to conversations between the user and friends on social media. Furthermore, the reception unit can analyze the user's social media activity patterns and receive related questions. In this way, related questions can be efficiently received by analyzing the user's social media activity.

[0116] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a question. The reception unit adjusts the reception method based on, for example, feedback provided by the user in the past. Furthermore, if the user prefers a specific reception method, the reception unit can preferentially use that method. Furthermore, the reception unit can analyze the user's past feedback and suggest the optimal reception method. In this way, the reception method can be customized by reflecting the user's past feedback, making it possible to efficiently receive questions.

[0117] The generation unit can estimate the user's emotions and adjust the expression style of the generated response or reply based on the estimated user's emotions. For example, if the user is relaxed, the generation unit can generate a response using soft expressions. If the user is nervous, the generation unit can also generate a response using concise and clear expressions. Furthermore, if the user is excited, the generation unit can also generate a response using expressions that reflect the user's emotions. In this way, by adjusting the expression style of the generated response or reply based on the user's emotions, it is possible to provide a response or reply that is appropriate for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0118] The generator can adjust the level of detail of the generated answer based on the importance of the question during generation. For example, the generator generates a detailed answer for an important question. The generator can also generate a concise answer for an everyday question. Furthermore, the generator can generate a detailed answer related to a specific topic for a question about that topic. In this way, by adjusting the level of detail of the generated answer based on the importance of the question, answers and replies can be generated efficiently.

[0119] The generation unit can apply different generation algorithms depending on the question category during generation. For example, the generation unit can apply a business generation algorithm to a business-related question. The generation unit can also apply a private generation algorithm to a private question. Furthermore, the generation unit can apply a generation algorithm specialized for a specific field to a question related to that field. In this way, by applying different generation algorithms depending on the question category, answers and replies can be generated efficiently.

[0120] During generation, the generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit adjusts the generation algorithm based on the user's past generation results. The generation unit can also improve the accuracy of generation by referring to feedback provided by the user in the past. Furthermore, the generation unit can analyze the user's past generation results and propose an optimal generation method. In this way, the accuracy of generation can be improved by referring to the user's past generation results.

[0121] The generation unit can estimate the user's emotions and adjust the length of the generated response or reply based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate a short, to-the-point response. If the user is relaxed, the generation unit can also generate a longer response that includes detailed explanations. Furthermore, if the user is excited, the generation unit can also generate a longer response that reflects the user's emotions. In this way, by adjusting the length of the response or reply generated based on the user's emotions, it is possible to provide a response or reply of an appropriate length for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0122] The generation unit can determine the generation priority based on the time of submission of the question at the time of generation. For example, the generation unit can generate replies with priority to the most recent question. The generation unit can also generate replies with priority to questions submitted within a specific time period. Furthermore, the generation unit can also generate replies with priority to questions submitted within a period specified by the user. In this way, by determining the generation priority based on the time of submission of the question, replies and responses can be generated efficiently.

[0123] The generation unit can adjust the order of generation based on the relevance of the questions during generation. For example, the generation unit can generate replies with priority to questions that are highly relevant. The generation unit can also generate replies with priority to questions related to a specific topic. Furthermore, the generation unit can also generate replies with priority to questions related to a topic specified by the user. In this way, by adjusting the order of generation based on the relevance of the questions, replies and responses can be generated efficiently.

[0124] The generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise during generation. For example, if the user has technical expertise, the generation unit generates a response that uses a lot of technical terminology. Also, if the user does not have technical expertise, the generation unit can generate a concise and easy-to-understand response. Furthermore, the generation unit can adjust the way the response is expressed according to the user's level of expertise. In this way, by adjusting the use of technical terminology in the generation according to the user's level of expertise, it is possible to provide a response or reply that is easy for the user to understand.

[0125] The providing unit can estimate the user's emotions and adjust the expression of the reply or response to be provided based on the estimated user's emotions. For example, if the user is relaxed, the providing unit can provide a reply using soft expressions. Furthermore, if the user is nervous, the providing unit can also provide a reply using concise and clear expressions. Furthermore, if the user is excited, the providing unit can also provide a reply using expressions that reflect the user's emotions. In this way, by adjusting the expression of the reply or response to be provided based on the user's emotions, it is possible to provide a reply or response that is appropriate for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0126] The providing unit can adjust the level of detail provided based on the importance of the reply or response when providing the reply. For example, the providing unit provides detailed information for an important reply. The providing unit can also provide concise information for an everyday reply. Furthermore, the providing unit can also provide detailed information related to a reply on a specific topic. In this way, by adjusting the level of detail provided based on the importance of the reply or response, it is possible to provide a reply or response efficiently.

[0127] The providing unit can apply different providing algorithms depending on the category of the response or reply when providing the response. For example, the providing unit applies a business providing algorithm to a business-related response. The providing unit can also apply a private providing algorithm to a private response. Furthermore, the providing unit can apply a providing algorithm specialized for a specific field to a response related to that field. In this way, by applying different providing algorithms depending on the category of the response or reply, it is possible to provide responses or replies efficiently.

[0128] The providing unit can improve the accuracy of the provision by referring to the user's past provision results when providing the information. For example, the providing unit adjusts the provision algorithm based on the user's past provision results. The providing unit can also improve the accuracy of the provision by referring to feedback provided by the user in the past. Furthermore, the providing unit can analyze the user's past provision results and propose an optimal provision method. In this way, the accuracy of the provision can be improved by referring to the user's past provision results.

[0129] The providing unit can estimate the user's emotions and adjust the length of the reply or response to be provided based on the estimated user's emotions. For example, if the user is in a hurry, the providing unit can provide a short, to-the-point reply. If the user is relaxed, the providing unit can also provide a longer reply including detailed explanations. If the user is excited, the providing unit can also provide a longer reply that reflects the user's emotions. In this way, by adjusting the length of the reply or response to be provided based on the user's emotions, it is possible to provide a reply or response of an appropriate length for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0130] The providing unit can determine the priority of providing based on the time of submission of the reply or response. For example, the providing unit can provide the most recent reply with priority. The providing unit can also provide with priority to replies submitted within a specific time period. Furthermore, the providing unit can provide with priority to replies submitted within a period specified by the user. In this way, by determining the priority of providing based on the time of submission of the reply or response, it is possible to provide replies or responses efficiently.

[0131] The providing unit can adjust the order of providing replies and responses based on the relevance of the replies and responses when providing them. For example, the providing unit can provide highly relevant replies with priority. The providing unit can also provide replies related to a specific topic with priority. Furthermore, the providing unit can also provide replies related to a topic specified by the user with priority. In this way, by adjusting the order of providing replies and responses based on the relevance of the replies and responses, replies and responses can be provided efficiently.

[0132] The providing unit can adjust the use of technical terminology in the provided response depending on the user's level of expertise when providing the response. For example, if the user has technical expertise, the providing unit can provide a response that uses a lot of technical terminology. Also, if the user does not have technical expertise, the providing unit can provide a concise and easy-to-understand response. Furthermore, the providing unit can adjust the way the response is expressed depending on the user's level of expertise. In this way, by adjusting the use of technical terminology in the provided response depending on the user's level of expertise, it is possible to provide a response or reply that is easy for the user to understand.

[0133] The anonymization unit can estimate the user's emotions and adjust the anonymization method based on the estimated user emotions. For example, if the user is relaxed, the anonymization unit can perform detailed anonymization. Furthermore, if the user is nervous, the anonymization unit can also perform simple anonymization. Furthermore, if the user is excited, the anonymization unit can also perform anonymization that reflects the user's emotions. In this way, by adjusting the anonymization method based on the user's emotions, appropriate anonymization can be performed for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0134] The anonymization unit can adjust the level of detail of anonymization based on the importance of the voice data during anonymization. For example, the anonymization unit performs detailed anonymization in the case of important conversation content. The anonymization unit can also perform simple anonymization in the case of everyday conversation content. Furthermore, in the case of a conversation about a specific topic, the anonymization unit can also perform detailed anonymization related to the topic. In this way, by adjusting the level of detail of anonymization based on the importance of the voice data, anonymization can be performed efficiently.

[0135] The anonymization unit can apply different anonymization algorithms depending on the category of the voice data during anonymization. For example, in the case of a business conversation, the anonymization unit applies a business anonymization algorithm. In addition, in the case of a private conversation, the anonymization unit can also apply a private anonymization algorithm. Furthermore, in the case of a conversation related to a specific field of expertise, the anonymization unit can also apply an anonymization algorithm specialized for that field. In this way, by applying different anonymization algorithms depending on the category of the voice data, anonymization can be performed efficiently.

[0136] The anonymization unit can estimate the user's emotions and determine anonymization priorities based on the estimated user emotions. For example, if the user is nervous, the anonymization unit can prioritize simple anonymization. Furthermore, if the user is relaxed, the anonymization unit can prioritize detailed anonymization. Furthermore, if the user is excited, the anonymization unit can prioritize anonymization that reflects the user's emotions. In this way, by determining the anonymization priorities based on the user's emotions, important voice data can be preferentially anonymized. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0137] During anonymization, the anonymization unit can determine the priority of anonymization based on the time when the voice data was collected. For example, the anonymization unit can prioritize anonymizing the most recent voice data. The anonymization unit can also prioritize anonymizing voice data collected during a specific time period. Furthermore, the anonymization unit can also prioritize anonymizing voice data within a period specified by the user. In this way, by determining the priority of anonymization based on the time when the voice data was collected, anonymization can be performed efficiently.

[0138] The anonymization unit can adjust the order of anonymization based on the relevance of the audio data during anonymization. For example, the anonymization unit can prioritize anonymize highly relevant audio data. The anonymization unit can also prioritize anonymize audio data related to a specific topic. Furthermore, the anonymization unit can also prioritize anonymize audio data related to a topic specified by the user. This allows for efficient anonymization by adjusting the order of anonymization based on the relevance of the audio data.

[0139] The feedback unit can estimate the user's emotions and adjust the feedback method based on the estimated user emotions. For example, if the user is relaxed, the feedback unit can provide detailed feedback. Furthermore, if the user is nervous, the feedback unit can provide concise and to-the-point feedback. Furthermore, if the user is excited, the feedback unit can provide feedback that reflects the user's emotions. In this way, by adjusting the feedback method based on the user's emotions, it is possible to provide appropriate feedback for the user. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0140] The feedback unit can adjust the level of detail of the feedback based on the importance of the response or reply when providing feedback. For example, the feedback unit provides detailed feedback for an important response. The feedback unit can also provide brief feedback for an everyday response. Furthermore, the feedback unit can also provide detailed feedback related to a specific topic for a response on that topic. In this way, by adjusting the level of detail of the feedback based on the importance of the response or reply, feedback can be provided efficiently.

[0141] The feedback unit can apply different feedback algorithms depending on the category of the response or reply when providing feedback. For example, the feedback unit can apply a business feedback algorithm to a business-related response. The feedback unit can also apply a private feedback algorithm to a private response. Furthermore, the feedback unit can also apply a feedback algorithm specialized for a specific field to a response related to that field. In this way, by applying different feedback algorithms depending on the category of the response or reply, feedback can be provided efficiently.

[0142] The feedback unit can improve the accuracy of feedback by referring to the user's past feedback results when providing feedback. For example, the feedback unit adjusts a feedback algorithm based on the user's past feedback results. The feedback unit can also improve the accuracy of feedback by referring to feedback provided by the user in the past. Furthermore, the feedback unit can analyze the user's past feedback results and suggest an optimal feedback method. In this way, the accuracy of feedback can be improved by referring to the user's past feedback results.

[0143] The feedback unit can estimate the user's emotions and determine the priority of feedback based on the estimated user's emotions. For example, if the user is nervous, the feedback unit can prioritize providing simple feedback. Furthermore, if the user is relaxed, the feedback unit can prioritize providing detailed feedback. Furthermore, if the user is excited, the feedback unit can prioritize providing feedback that reflects the user's emotions. In this way, by determining the priority of feedback based on the user's emotions, important feedback can be provided preferentially. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0144] When providing feedback, the feedback unit can determine the priority of the feedback based on the time of submission of the response or reply. For example, the feedback unit can provide feedback preferentially to the most recent response. The feedback unit can also provide feedback preferentially to responses submitted within a specific time period. Furthermore, the feedback unit can also provide feedback preferentially to responses submitted within a period specified by the user. In this way, by determining the priority of feedback based on the time of submission of the response or reply, feedback can be provided efficiently.

[0145] The feedback unit can adjust the order of feedback based on the relevance of replies and replies when providing feedback. For example, the feedback unit can provide feedback preferentially to highly relevant replies. The feedback unit can also provide feedback preferentially to replies related to a specific topic. Furthermore, the feedback unit can also provide feedback preferentially to replies related to a topic specified by the user. In this way, by adjusting the order of feedback based on the relevance of replies and replies, feedback can be provided efficiently.

[0146] The input unit can estimate the user's emotions and adjust the input method based on the estimated user emotions. For example, the input unit can provide detailed input options when the user is relaxed. The input unit can also provide a simple interface when the user is nervous. Furthermore, the input unit can prioritize voice input and allow quick input when the user is in a hurry. This allows the input method to be adjusted based on the user's emotions, thereby providing an appropriate input method for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0147] When inputting data, the input unit can select the optimal input method by analyzing the user's past input history. For example, the input unit can suggest the optimal input method based on input methods that the user has frequently used in the past. The input unit can also prioritize receiving inputs made by the user during a specific time period. Furthermore, the input unit can also prioritize receiving inputs related to a specific topic from the user's past input history. This allows the optimal input method to be selected by analyzing the user's past input history, enabling efficient input.

[0148] The input unit can filter input based on the user's current situation and environment. For example, when the user is in a quiet environment, the input unit accepts detailed input. Also, when the user is in a noisy environment, the input unit can preferentially accept brief input. Furthermore, when the user is moving, the input unit can adjust the content of the input to be accepted. This allows for efficient input by filtering based on the user's current situation and environment.

[0149] The input unit can estimate the user's emotions and determine the priority of questions to be input based on the estimated user emotions. For example, when the user is nervous, the input unit can prioritize simple questions. Furthermore, when the user is relaxed, the input unit can also prioritize detailed questions. Furthermore, when the user is in a hurry, the input unit can prioritize questions that require a quick answer. In this way, by determining the priority of questions to be input based on the user's emotions, important questions can be input preferentially. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0150] The input unit can prioritize inputting highly relevant questions in consideration of the user's geographical location information when inputting questions. For example, when the user is in a specific location, the input unit prioritizes inputting questions related to that location. Furthermore, when the user is traveling, the input unit can also prioritize inputting questions for the travel destination. Furthermore, when the user is at home, the input unit can also prioritize inputting everyday questions. This allows questions to be input efficiently by prioritized inputting highly relevant questions in consideration of the user's geographical location information.

[0151] The input unit can analyze the user's social media activity and input a related question at the time of input. For example, the input unit inputs a question related to content posted by the user on social media. The input unit can also input a question by referring to conversations between the user and friends on social media. Furthermore, the input unit can analyze the user's activity pattern on social media and input a related question. In this way, related questions can be input efficiently by analyzing the user's social media activity. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, reception unit, generation unit, and provision 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 collection unit collects user voice data using the camera 42 and microphone 38B of the smart device 14 and transmits the voice data to the data processing device 12 via the control unit 46A. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected voice data to learn the user's habits. The reception unit is realized by the control unit 46A of the smart device 14 and receives questions from the user. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a response or reply based on the user's habits. The provision unit is realized by the control unit 46A of the smart device 14 and provides the generated response or reply to the user in voice or text. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, reception unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects user voice data using the camera 42 and microphone 238 of the smart glasses 214 and transmits the voice data to the data processing device 12 via the control unit 46A. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected voice data to learn the user's habits. The reception unit is realized by the control unit 46A of the smart glasses 214 and receives user questions. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a response or reply based on the user's habits. The provision unit is realized by the control unit 46A of the smart glasses 214 and provides the generated response or reply to the user in the form of voice or text. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, reception unit, generation unit, and provision unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects user voice data using the camera 42 and microphone 238 of the headset-type terminal 314 and transmits the voice data to the data processing device 12 via the control unit 46A. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected voice data to learn the user's habits. The reception unit is realized by the control unit 46A of the headset-type terminal 314 and receives questions from the user. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a response or reply based on the user's habits. The provision unit is realized by the control unit 46A of the headset-type terminal 314 and provides the generated response or reply to the user in the form of voice or text. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, reception unit, generation unit, and provision unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects user voice data using the camera 42 and microphone 238 of the robot 414 and transmits the voice data to the data processing device 12 via the control unit 46A. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected voice data to learn the user's habits. The reception unit is realized by the control unit 46A of the robot 414 and receives questions from the user. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a response or reply based on the user's habits. The provision unit is realized by the control unit 46A of the robot 414 and provides the generated response or reply to the user in the form of voice or text.

[0152] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0153] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user's emotions. For example, if the user is feeling stressed, conversations that cause stress can be analyzed with priority. Also, if the user is relaxed, everyday conversations can be analyzed with priority. Furthermore, if the user is excited, conversations at the peak of that emotion can be analyzed with priority. In this way, by determining the analysis priority based on the user's emotions, more effective analysis can be performed.

[0154] The collection unit can adjust the method of collecting voice data taking into account the user's geographical location information. For example, if the user is in a specific location, conversations related to that location can be collected with priority. Also, if the user is traveling, conversations at the travel destination can be collected with priority. Furthermore, if the user is at home, everyday conversations can be collected with priority. In this way, by adjusting the method of collecting voice data taking into account the user's geographical location information, the relevance of the collected voice data can be improved.

[0155] The providing unit can estimate the user's emotions and adjust the tone of the reply or response provided based on the estimated user's emotions. For example, if the user is relaxed, the reply can be provided in a soft tone. If the user is nervous, the reply can be provided in a calm tone. Furthermore, if the user is excited, the reply can be provided in a tone that reflects the user's emotions. In this way, by adjusting the tone of the reply or response provided based on the user's emotions, it is possible to provide a reply or response that is appropriate for the user.

[0156] The analysis unit can adjust the analysis algorithm based on the user's past feedback. For example, it can analyze feedback provided by the user in the past and improve the accuracy of the analysis algorithm. Also, if the user prefers a specific analysis method, it can preferentially use that method. Furthermore, it can also suggest the optimal analysis method by referring to the user's past feedback. In this way, it is possible to improve the accuracy of the analysis by reflecting the user's past feedback.

[0157] The collection unit can estimate the user's emotions and filter the voice data to be collected based on the estimated user's emotions. For example, if the user is relaxed, natural conversations can be collected preferentially. Also, if the user is feeling stressed, conversations that cause stress can be filtered. Furthermore, if the user is excited, conversations at the peak of that emotion can be filtered. In this way, by filtering the voice data to be collected based on the user's emotions, more effective voice data can be collected.

[0158] The providing unit can adjust the providing algorithm based on the user's past providing results. For example, it can analyze feedback provided by the user in the past and improve the accuracy of the providing algorithm. Also, if the user prefers a specific providing method, it can preferentially use that method. Furthermore, it can also suggest the optimal providing method by referring to the user's past providing results. In this way, it is possible to improve the accuracy of the providing by reflecting the user's past providing results.

[0159] The analysis unit can estimate the user's emotions and adjust the level of detail of the analysis based on the estimated user emotions. For example, if the user is relaxed, a detailed analysis result can be provided. If the user is nervous, a concise and to-the-point analysis result can be provided. Furthermore, if the user is excited, a visually easy-to-understand analysis result can be provided. In this way, by adjusting the level of detail of the analysis based on the user's emotions, it is possible to provide an analysis result that is easy for the user to understand.

[0160] The collection unit can analyze the user's social media activities and collect related voice data. For example, it can collect voice data related to content posted by the user on social media. It can also collect voice data by referring to the user's conversations with friends on social media. It can also analyze the user's activity patterns on social media and collect related voice data. In this way, it is possible to efficiently collect related voice data by analyzing the user's social media activities.

[0161] The providing unit can estimate the user's emotions and adjust the length of the reply or response provided based on the estimated user's emotions. For example, if the user is in a hurry, a short, to-the-point reply can be provided. If the user is relaxed, a longer reply including detailed explanations can be provided. Furthermore, if the user is excited, a longer reply that reflects the user's emotions can be provided. In this way, by adjusting the length of the reply or response provided based on the user's emotions, it is possible to provide a reply or response of an appropriate length for the user.

[0162] The analysis unit can determine the priority of analysis based on the time when the voice data was collected. For example, the most recent voice data can be analyzed with priority. It can also analyze voice data collected during a specific time period with priority. It can also analyze voice data within a period specified by the user with priority. In this way, by determining the priority of analysis based on the time when the voice data was collected, it is possible to perform analysis efficiently.

[0163] The processing flow of the second embodiment will be briefly explained below.

[0164] Step 1: The collection unit records the user's everyday conversations as audio and collects audio data. The collection unit may also include an anonymization unit that anonymizes the audio data. Step 2: The analysis unit analyzes the voice data collected by the collection unit and learns the user's habits. The analysis unit uses voice recognition technology to convert the voice data into text data and extracts characteristics such as the user's speaking style, word choice, and expression. It can also learn the user's habits using machine learning algorithms. Step 3: The reception unit receives a question from the user. The reception unit may include an input unit that supports both voice input and text input. Step 4: The generator generates a response or reply to the question received by the receiver. The generator generates responses or replies that reflect the user's frequently used phrases and reaction patterns in specific situations. Generative AI can also be used to generate responses or replies based on the user's habits. Step 5: The providing unit provides the response or reply generated by the generating unit. The providing unit provides the response or reply to the user in the form of voice or text. The providing unit may also include a feedback unit that accepts feedback from the user.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0185] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0201] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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."

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] [Explanation of symbols]

[0237] 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 collection unit that collects user voice data; an analysis unit that analyzes the voice data collected by the collection unit and learns the habits of the user; a reception unit that receives questions from users; a generation unit that generates a response or reply to the question received by the reception unit; a providing unit that provides the answer or reply generated by the generating unit. A system characterized by:

2. The collecting unit Equipped with an anonymization unit that anonymizes collected voice data 2. The system of claim 1.

3. The providing unit A feedback unit is provided to receive feedback from users.

2. The system of claim 1.

4. The reception unit Equipped with an input section that supports both voice and text input 2. The system of claim 1.

5. The analysis unit Learn the user's speaking style, word choice, and expression habits 2. The system of claim 1.

6. The generation unit Generate responses and replies that reflect the user's frequently used phrases and reaction patterns in situations 2. The system of claim 1.

7. The collecting unit The user's emotions are estimated, and the timing of collecting voice data is adjusted based on the estimated user's emotions.

2. The system of claim 1.

8. The collecting unit Analyze the user's past conversation history and select the collection method 2. The system of claim 1.

9. The collecting unit As voice data is collected, it is filtered based on the user's current situation and environment.

2. The system of claim 1.

Images