system

Abstract

The system according to the embodiment aims to efficiently analyze the contents of phone calls and emails from users and generate appropriate responses. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a generation unit, a conversion unit, and an output unit. The reception unit receives the contents of a phone call or email from a user. The analysis unit analyzes the contents received by the reception unit. The generation unit generates a response based on the contents analyzed by the analysis unit. The conversion unit converts the response generated by the generation unit into voice or text. The output unit outputs the response converted by the conversion 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 have had the problem of making it difficult to efficiently analyze the contents of phone calls and emails from users and generate appropriate responses.

[0005] The system according to the embodiment aims to efficiently analyze the contents of phone calls and emails from users and generate appropriate responses. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, a conversion unit, and an output unit. The reception unit receives the contents of a phone call or email from a user. The analysis unit analyzes the contents received by the reception unit. The generation unit generates a response based on the contents analyzed by the analysis unit. The conversion unit converts the response generated by the generation unit into voice or text. The output unit outputs the response converted by the conversion unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently analyze the contents of phone calls and emails from users and generate appropriate responses. [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 telephone and email proxy response system according to an embodiment of the present invention uses a generation AI to handle telephone and email calls. In this system, a user inputs the contents of a telephone call or email into the generation AI, which analyzes the contents and generates an appropriate response. The generated response is output as voice in the case of a telephone call and as text in the case of an email. This mechanism eliminates the need for users to handle telephone and email calls themselves, thereby improving work efficiency. For example, a user inputs the contents of a telephone call or email into the generation AI. In the case of a telephone call, the user inputs the contents of the received call as text. In the case of an email, the contents of the received email are input directly into the generation AI. This information is then input into the generation AI. The generation AI then analyzes the input information. The generation AI understands the contents of the input telephone call or email and generates an appropriate response. For example, in the case of a telephone call, the generation AI generates a response that answers the caller's question or provides the necessary information. In the case of an email, the generation AI generates a reply to the caller's email. In the case of a telephone call, the generation AI outputs the generated response as voice. The generation AI converts the generated response into voice and transmits it to the caller via telephone. For example, if the other party asks, "What are your meeting schedules?", the generation AI will respond by voice, saying, "The next meeting is tomorrow at 10:00." In the case of emails, the generated response is output as text. The generation AI converts the generated response to text and sends it to the other party as an email. For example, if the other party requests, "Please send me some materials," the generation AI will generate a reply such as, "I will send them to you with the materials attached," and send it as an email. This system eliminates the need for users to handle phone calls and emails themselves, thereby improving work efficiency. For example, busy businesspeople can save time by not having to handle numerous phone calls and emails. In addition, because the generation AI generates appropriate responses, the quality of communication also improves. As a result, telephone and email proxy response systems eliminate the need for users to handle phone calls and emails themselves, thereby improving work efficiency.

[0029] A telephone and email proxy response system according to an embodiment includes a reception unit, an analysis unit, a generation unit, a conversion unit, and an output unit. The reception unit receives the contents of a telephone call or email from a user. The contents of a telephone call or email from a user include, but are not limited to, inquiries, complaints, orders, etc. The reception unit inputs, for example, the contents of a telephone call received by the user as text. The reception unit can also input the contents of an email received directly to the generation AI. For example, the contents of an email received by the user are input directly as text. The analysis unit uses the generation AI to analyze the contents received by the reception unit. The analysis can be performed using, for example, natural language processing technology, keyword extraction, sentiment analysis, etc., but is not limited to, these examples. For example, the analysis unit uses natural language processing technology to understand the contents of the input telephone call or email. The analysis unit can also extract important information using keyword extraction technology. The analysis unit can also estimate the other party's emotions using sentiment analysis technology. The generation unit uses the generation AI to generate a response based on the contents analyzed by the analysis unit. Response generation is performed by, for example, template-based response generation, generation using a machine learning model, or the like, but is not limited to these examples. For example, the generation unit generates an answer to the other party's question using template-based response generation. The generation unit can also generate a response that provides necessary information using a machine learning model. The conversion unit converts the response generated by the generation unit into voice or text using a generation AI. Conversion is performed by, for example, speech synthesis technology, text generation technology, or the like, but is not limited to these examples. For example, the conversion unit converts the generated response into voice using speech synthesis technology. The conversion unit can also convert the generated response into text using text generation technology. The output unit outputs the response converted by the conversion unit using a generation AI. Output is performed by, for example, voice output over the telephone, text output via email, or the like, but is not limited to these examples. For example, the output unit communicates the generated response to the other party over the telephone using voice output over the telephone.The output unit can also output text to an email and send the generated response to the other party. This eliminates the need for the user to handle phone calls and emails by themselves, thereby improving work efficiency.

[0030] The reception unit can input the contents of a phone call received by the user as text. Methods for inputting the contents as text include, but are not limited to, voice recognition technology and manual input. For example, the reception unit inputs the contents of a phone call received by the user as text using voice recognition technology. The reception unit can also manually input the contents of a phone call received by the user as text. For example, the reception unit can automatically input the contents of a phone call received by the user as text using voice recognition technology. The reception unit can also manually input the contents of a phone call received by the user as text. In this way, inputting the contents of the phone call as text makes it easier for the generation AI to generate an appropriate response. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit can input the contents of a phone call received by the user to the generation AI, which can analyze the contents and output them as text.

[0031] The reception unit can input the content of the received email directly to the generation AI. Methods of inputting the content of the received email directly include, but are not limited to, for example, inputting the content of the email directly as text. For example, the reception unit inputs the content of the received email directly as text. The reception unit can also input the content of the received email directly to the generation AI. For example, the reception unit inputs the content of the received email directly as text. The reception unit can also input the content of the received email directly to the generation AI. This makes it easier for the generation AI to generate an appropriate response by inputting the content of the email directly. Some or all of the above-described processing in the reception unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the content of the received email to the generation AI, and the generation AI can analyze the content and generate an appropriate response.

[0032] The analysis unit can understand the content of the input phone call or email and generate a response. Methods for understanding the content include, but are not limited to, natural language processing technology and context analysis. The analysis unit can understand the content of the input phone call or email using, for example, natural language processing technology. The analysis unit can also understand the content of the input phone call or email using context analysis technology. For example, the analysis unit can understand the content of the input phone call or email using natural language processing technology. The analysis unit can also understand the content of the input phone call or email using context analysis technology. This allows the generation AI to understand the content of the phone call or email and generate an appropriate response, improving the quality of communication. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the content of the input phone call or email into the generation AI, which can then analyze and understand the content.

[0033] The generation unit can generate an answer to the other party's question or a response that provides necessary information. Methods for generating an answer to a question include, but are not limited to, FAQ-based answer generation and generation using a machine learning model. The generation unit can generate an answer to the other party's question using, for example, FAQ-based answer generation. The generation unit can also generate a response that provides necessary information using a machine learning model. For example, the generation unit can generate an answer to the other party's question using FAQ-based answer generation. The generation unit can also generate a response that provides necessary information using a machine learning model. This allows the generation AI to generate an appropriate answer to the other party's question, thereby reducing the burden on the user. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input an answer to the other party's question into the generation AI, and the generation AI can analyze the content of the answer and generate an appropriate answer.

[0034] The conversion unit can convert the generated response into speech and transmit it to the other party over the phone. Methods for converting into speech include, but are not limited to, speech synthesis technology and text-to-speech technology. The conversion unit can convert the generated response into speech using, for example, speech synthesis technology. The conversion unit can also convert the generated response into speech using text-to-speech technology. For example, the conversion unit can convert the generated response into speech using speech synthesis technology. The conversion unit can also convert the generated response into speech using text-to-speech technology. In this way, by converting the response generated by the generation AI into speech, telephone responses are automated. Some or all of the above-described processing in the conversion unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the conversion unit can input the generated response into the generation AI, which can analyze the content of the response and convert it into speech.

[0035] The conversion unit can convert the generated response into text and send it to the other party as an email. Methods for converting into text include, but are not limited to, natural language generation technology and template-based generation. The conversion unit can convert the generated response into text using, for example, natural language generation technology. The conversion unit can also convert the generated response into text using template-based generation. For example, the conversion unit can convert the generated response into text using natural language generation technology. The conversion unit can also convert the generated response into text using template-based generation. In this way, by converting the response generated by the generation AI into text, the email response is automated. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the conversion unit can input the generated response into the generation AI, which can analyze the content and convert it into text.

[0036] The reception unit can analyze the user's past phone call and email history and select the optimal reception method. For example, the reception unit uses the generation AI to suggest the optimal reception method based on the content of phone calls and emails the user frequently received in the past. The reception unit can also predict the content of phone calls and emails that should be received during a specific time period based on the user's past history, and the generation AI can receive calls during that time period. The reception unit can also analyze the user's past history and prioritize calls and emails from specific contacts. By analyzing the past history, the optimal reception method can be provided to the user. The history analysis is performed based on, for example, the content of past inquiries and response history. The generation AI can analyze the content of the user's past phone calls and emails and select the optimal reception method. The generation AI can also predict the content of phone calls and emails that should be received during a specific time period based on the user's past history. The generation AI can also prioritize calls and emails from specific contacts based on the user's past history. This allows the reception unit to analyze the user's past history in detail and provide the optimal reception method.

[0037] The reception unit can perform filtering based on the user's current work situation and areas of interest. For example, when the user is in a meeting, the generation AI can suspend accepting calls and emails and resume them after the meeting ends. Also, when the user is concentrating on a specific project, the reception unit can have the generation AI only accept calls and emails related to that project. Furthermore, the reception unit can prioritize accepting calls and emails that are highly relevant based on the user's areas of interest. This allows filtering based on the user's work situation and areas of interest, enabling important calls and emails to be prioritized. The work situation and areas of interest can be identified based on, for example, data on the user's work schedule and areas of interest. For example, the generation AI can analyze the user's work schedule and suspend accepting calls and emails during a meeting. Also, the generation AI can analyze data on the user's areas of interest and prioritize accepting calls and emails that are highly relevant. This allows the reception unit to gain a detailed understanding of the user's work situation and areas of interest and perform filtering.

[0038] The reception unit can prioritize receiving highly relevant content by taking into account the user's geographical location information. For example, when the user is in a specific area, the reception unit can prioritize receiving calls and emails related to that area. Furthermore, when the user is on a business trip, the reception unit can prioritize receiving calls and emails related to the business trip destination. Furthermore, when the user is at home, the reception unit can prioritize receiving calls and emails related to the user's home. This enables efficient response by prioritizing receiving highly relevant content based on the user's geographical location information. Geographical location information can be acquired, for example, using GPS data or a location information service. The generation AI can, for example, analyze the user's GPS data and prioritize receiving calls and emails related to a specific area. Furthermore, the generation AI can acquire the user's geographical location information using a location information service and prioritize receiving highly relevant content. This allows the reception unit to grasp the user's geographical location information in detail and prioritize receiving highly relevant content.

[0039] The reception unit can analyze the user's social media activity and receive related content. For example, if the user posts about a specific topic on social media, the reception unit can prioritize receiving calls and emails related to that topic. Furthermore, if the user is participating in a specific event on social media, the reception unit can prioritize receiving calls and emails related to that event. Furthermore, if the user belongs to a specific group on social media, the reception unit can prioritize receiving calls and emails related to that group. In this way, by analyzing social media activity, content related to the user can be prioritized. Analysis of social media activity is performed based on, for example, the content of posts and the reactions of followers. For example, the generation AI can analyze the content of the user's social media posts and receive related content. Furthermore, the generation AI can analyze the reactions of the user's followers and receive related content. In this way, the reception unit can analyze the user's social media activity in detail and receive related content.

[0040] The analysis unit can adjust the level of detail of the analysis based on the importance of the phone call or email. For example, in the case of a phone call or email that is highly important, the generation AI can perform a detailed analysis. In addition, in the case of a phone call or email that is low in importance, the analysis unit can also have the generation AI perform a concise analysis. Furthermore, the analysis unit can also have the generation AI determine the priority of the analysis based on the importance. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance. The importance is evaluated based on, for example, the importance score or the depth of the analysis. For example, the generation AI can analyze the importance of phone calls or emails and perform a detailed analysis. In addition, the generation AI can perform a concise analysis for phone calls or emails that are low in importance. This allows the analysis unit to evaluate the importance of phone calls and emails in detail and adjust the level of detail of the analysis.

[0041] The analysis unit can apply different analysis algorithms depending on the category of the call or email. For example, in the case of a business-related call or email, the generation AI can apply a business analysis algorithm. Furthermore, in the case of a private call or email, the analysis unit can also apply a private analysis algorithm. Furthermore, in the case of an urgent call or email, the analysis unit can also apply an emergency analysis algorithm. This allows for applying an analysis algorithm according to the category to provide more appropriate analysis results. The application of the analysis algorithm is based on, for example, a text analysis algorithm or a voice analysis algorithm. For example, the generation AI can apply a business analysis algorithm to business-related calls or emails. Furthermore, the generation AI can also apply a private analysis algorithm to private calls or emails. This allows the analysis unit to grasp the category of the call or email in detail and apply an appropriate analysis algorithm.

[0042] The analysis unit can determine the priority of analysis based on the time when a call or email was received. For example, the analysis unit prioritizes analysis of recently received call or email. The analysis unit can also postpone analysis of older call or email. Furthermore, the analysis unit can also have the generation AI determine the priority of analysis based on the time when it was received. This enables efficient analysis by determining the priority of analysis based on the time when it was received. The evaluation of the time when it was received is based on, for example, a reception time score or an importance evaluation. For example, the generation AI can prioritize analysis of recently received call or email. The generation AI can also postpone analysis of older call or email. This allows the analysis unit to evaluate the time when call or email was received in detail and determine the priority of analysis.

[0043] The analysis unit can adjust the order of analysis based on the relevance of phone calls and emails. For example, the analysis unit prioritizes analysis of highly relevant phone calls and emails. The analysis unit can also postpone analysis of less relevant phone calls and emails. Furthermore, the analysis unit can also allow the generation AI to determine the order of analysis based on relevance. As a result, by adjusting the order of analysis based on relevance, important content can be analyzed preferentially. The evaluation of relevance is performed based on, for example, a relevance score or an importance evaluation. For example, the generation AI can prioritize analysis of highly relevant phone calls and emails. The generation AI can also postpone analysis of less relevant phone calls and emails. As a result, the analysis unit can evaluate the relevance of phone calls and emails in detail and adjust the order of analysis.

[0044] The generation unit can adjust the level of detail of the response based on the importance of the other party's question. For example, the generation unit causes the generation AI to generate a detailed response to a question of high importance. The generation unit can also cause the generation AI to generate a concise response to a question of low importance. Furthermore, the generation unit can also cause the generation AI to determine the priority of the response according to the importance. This enables efficient responses by adjusting the level of detail of the response according to the importance. The importance is evaluated based on, for example, the importance score or the depth of the response. For example, the generation AI can generate a detailed response to a question of high importance. The generation AI can also generate a concise response to a question of low importance. This allows the generation unit to evaluate the importance of the other party's question in detail and adjust the level of detail of the response.

[0045] The generation unit can apply different generation algorithms depending on the category of the other party's question. For example, in the generation unit, the generation AI applies a business generation algorithm to a business-related question. Furthermore, in the generation unit, the generation AI can also apply a private generation algorithm to a private question. Furthermore, in the generation unit, the generation AI can also apply an emergency generation algorithm to an urgent question. In this way, by applying a generation algorithm according to the category, a more appropriate response can be provided. The application of a generation algorithm is based on, for example, a text generation algorithm or a voice generation algorithm. For example, the generation AI can apply a business generation algorithm to a business-related question. Furthermore, the generation AI can also apply a private generation algorithm to a private question. In this way, the generation unit can grasp the category of the other party's question in detail and apply an appropriate generation algorithm.

[0046] The generation unit can determine the priority of responses based on the time when the question was submitted by the other party. For example, the generation unit allows the generation AI to generate a response preferentially to a question that was recently submitted. The generation unit can also allow the generation AI to generate a response later to a question that was submitted earlier. Furthermore, the generation unit can allow the generation AI to determine the priority of responses according to the time of submission. This enables efficient responses by determining the priority of responses based on the time of submission. The evaluation of the submission time is based on, for example, a submission time score or an importance evaluation. For example, the generation AI can generate a response preferentially to a question that was recently submitted. The generation AI can also generate a response later to a question that was submitted earlier. This allows the generation unit to evaluate the time of submission of the other party's question in detail and determine the priority of responses.

[0047] The generation unit can adjust the order of responses based on the relevance of the other party's question. For example, the generation unit causes the generation AI to prioritize generating responses to highly relevant questions. The generation unit can also cause the generation AI to generate responses later to less relevant questions. Furthermore, the generation unit can also cause the generation AI to determine the order of responses according to relevance. As a result, by adjusting the order of responses based on relevance, important content can be prioritized in responses. The evaluation of relevance is performed based on, for example, a relevance score or an importance evaluation. For example, the generation AI can prioritize generating responses to highly relevant questions. The generation AI can also postpone generating responses to less relevant questions. As a result, the generation unit can evaluate the relevance of the other party's question in detail and adjust the order of responses.

[0048] The conversion unit can adjust the level of detail of the conversion based on the importance of the response. For example, the conversion unit allows the generation AI to generate detailed voice or text for a response with high importance. The conversion unit can also allow the generation AI to generate concise voice or text for a response with low importance. Furthermore, the conversion unit can also allow the generation AI to determine the priority of the conversion based on the importance. This enables efficient conversion by adjusting the level of detail of the conversion based on the importance. The evaluation of importance is based on, for example, the importance score or the depth of the conversion. For example, the generation AI can generate detailed voice or text for a response with high importance. The generation AI can also generate concise voice or text for a response with low importance. This allows the conversion unit to evaluate the importance of the response in detail and adjust the level of detail of the conversion.

[0049] The conversion unit can apply different conversion algorithms depending on the category of the response. For example, in the conversion unit, the generation AI can apply a business conversion algorithm to a business-related response. Furthermore, in the conversion unit, the generation AI can also apply a private conversion algorithm to a private response. Furthermore, in the conversion unit, the generation AI can also apply an emergency conversion algorithm to an urgent response. In this way, by applying a conversion algorithm according to the category, more appropriate conversion results can be provided. The application of the conversion algorithm is based on, for example, a text conversion algorithm or a speech conversion algorithm. For example, the generation AI can apply a business conversion algorithm to a business-related response. Furthermore, the generation AI can also apply a private conversion algorithm to a private response. In this way, the conversion unit can grasp the category of the response in detail and apply an appropriate conversion algorithm.

[0050] The conversion unit can determine the priority of conversion based on the submission time of the response. For example, the conversion unit allows the generation AI to prioritize conversion of recently submitted responses. The conversion unit can also allow the generation AI to postpone conversion of responses that were submitted earlier. Furthermore, the conversion unit allows the generation AI to determine the priority of conversion based on the submission time. This enables efficient conversion by determining the priority of conversion based on the submission time. The submission time is evaluated based on, for example, the submission time score or the importance evaluation. For example, the generation AI can prioritize conversion of recently submitted responses. The generation AI can also postpone conversion of responses that were submitted earlier. This allows the conversion unit to determine the priority of conversion by evaluating the submission time of responses in detail.

[0051] The conversion unit can adjust the order of conversion based on the relevance of the response. For example, the conversion unit allows the generation AI to prioritize conversion of highly relevant responses. Also, the conversion unit can allow the generation AI to postpone conversion of less relevant responses. Furthermore, the conversion unit can allow the generation AI to determine the order of conversion according to relevance. As a result, important content can be preferentially converted by adjusting the order of conversion based on relevance. The evaluation of relevance is performed based on, for example, a relevance score or an importance evaluation. For example, the generation AI can prioritize conversion of highly relevant responses. Also, the generation AI can postpone conversion of less relevant responses. As a result, the conversion unit can evaluate the relevance of responses in detail and adjust the order of conversion.

[0052] The output unit can adjust the level of detail of the output based on the importance of the response. For example, in the output unit, the generation AI outputs detailed voice or text for a response with high importance. In addition, the output unit can also cause the generation AI to output concise voice or text for a response with low importance. Furthermore, the output unit can also cause the generation AI to determine an output priority according to importance. This enables efficient output by adjusting the level of detail of the output according to importance. The evaluation of importance is performed based on, for example, an importance score or the depth of the output. For example, the generation AI can output detailed voice or text for a response with high importance. In addition, the generation AI can output concise voice or text for a response with low importance. This allows the output unit to evaluate the importance of a response in detail and adjust the level of detail of the output.

[0053] The output unit can apply different output algorithms depending on the category of the response. For example, in the output unit, the generation AI can apply a business output algorithm to a business-related response. Furthermore, in the output unit, the generation AI can also apply a private output algorithm to a private response. Furthermore, in the output unit, the generation AI can also apply an emergency output algorithm to an urgent response. In this way, by applying an output algorithm according to the category, a more appropriate output result can be provided. The application of an output algorithm is based on, for example, a text output algorithm or a voice output algorithm. For example, the generation AI can apply a business output algorithm to a business-related response. Furthermore, the generation AI can also apply a private output algorithm to a private response. In this way, the output unit can grasp the category of the response in detail and apply an appropriate output algorithm.

[0054] The output unit can determine the output priority based on the submission time of the response. For example, the output unit allows the generation AI to output recently submitted responses with priority. The output unit can also allow the generation AI to output older submitted responses later. Furthermore, the output unit can allow the generation AI to determine the output priority based on the submission time. This enables efficient output by determining the output priority based on the submission time. The submission time is evaluated based on, for example, a submission time score or an importance evaluation. For example, the generation AI can output recently submitted responses with priority. The generation AI can also output older submitted responses later. This allows the output unit to evaluate the submission time of responses in detail and determine the output priority.

[0055] The output unit can adjust the order of output based on the relevance of the responses. For example, the output unit allows the generation AI to prioritize output of highly relevant responses. Also, the output unit can allow the generation AI to postpone output of less relevant responses. Furthermore, the output unit can also allow the generation AI to determine the order of output based on relevance. As a result, important content can be prioritized by adjusting the order of output based on relevance. The evaluation of relevance is performed based on, for example, a relevance score or an importance evaluation. For example, the generation AI can prioritize output of highly relevant responses. Also, the generation AI can postpone output of less relevant responses. As a result, the output unit can evaluate the relevance of responses in detail and adjust the order of output.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] The reception unit can analyze the user's past response history and select the optimal response template. For example, it can analyze how the user responded to specific inquiries in the past and use that response as a reference when a similar inquiry is received. The reception unit can also extract specific patterns from the user's past response history, and the generation AI can generate responses based on those patterns. Furthermore, the reception unit can adjust the tone and style of responses to specific people based on the user's past response history. This makes it possible to utilize past history to provide more consistent responses.

[0058] The reception unit monitors the user's current activity status in real time and can accept phone calls and emails at the appropriate time. For example, if the user is in a meeting, the generation AI will accept phone calls and emails after the meeting ends. Also, if the user is on the move, the generation AI can delay accepting calls and emails until the user has finished moving. Furthermore, if the user is concentrating on a task, the generation AI can suspend accepting calls until the task is completed. This allows for flexible response according to the user's activity status.

[0059] The analysis unit can predict future inquiries based on the content of past user inquiries and prepare responses in advance. For example, it can analyze the content of inquiries frequently made by users in the past, and if there is a high possibility that similar inquiries will be made, generate a response in advance. The analysis unit can also predict that specific inquiries will increase depending on the season or event, and prepare responses to those inquiries. Furthermore, the analysis unit can predict that inquiries will increase at specific times based on the user's work schedule, and prepare responses to those inquiries. This enables quick responses based on predictions.

[0060] The generator can select the optimal response style based on the user's past response history. For example, it can analyze phrases and expressions used by the user in the past and generate responses in a similar style. The generator can also adjust the tone and style of responses to specific people based on the user's past response history. Furthermore, the generator can select a response template appropriate for a specific situation based on the user's past response history. This makes it possible to provide more consistent responses by utilizing past history.

[0061] The conversion unit can analyze the user's past voice and text conversion history and select the optimal conversion method. For example, it analyzes the voice tone and text style used by the user in the past and performs conversion in a similar manner. The conversion unit can also select a conversion template appropriate for a specific situation from the user's past conversion history. Furthermore, the conversion unit can adjust the tone and style of conversion for a specific person based on the user's past conversion history. This makes it possible to utilize past history to provide more consistent conversion.

[0062] The output unit can analyze the user's past output history and select the optimal output method. For example, it can analyze the voice tone and text style used by the user in the past and output in a similar manner. The output unit can also select an output template appropriate for a specific situation from the user's past output history. Furthermore, the output unit can adjust the tone and style of output for a specific person based on the user's past output history. This makes it possible to provide more consistent output by utilizing the past history.

[0063] The processing flow of the first embodiment will be briefly explained below.

[0064] Step 1: The reception unit receives the contents of phone calls or emails from users. The contents of phone calls or emails from users include inquiries, complaints, order details, etc. The reception unit inputs the contents of phone calls received by the user as text and inputs the contents of received emails directly into the generation AI. Step 2: The analysis unit uses the generation AI to analyze the content received by the reception unit. The analysis is performed using methods such as natural language processing technology, keyword extraction, and sentiment analysis. For example, the analysis unit uses natural language processing technology to understand the content of the input phone call or email, keyword extraction technology to extract important information, and sentiment analysis technology to estimate the other party's emotions. Step 3: The generation unit uses a generation AI to generate a response based on the content analyzed by the analysis unit. Response generation is performed using methods such as template-based response generation or generation using a machine learning model. For example, the generation unit uses template-based response generation to generate an answer to the other person's question, and generates a response that provides the necessary information using a machine learning model. Step 4: The conversion unit uses the generation AI to convert the response generated by the generation unit into voice or text. The conversion is performed using methods such as voice synthesis technology or text generation technology. For example, the conversion unit converts the generated response into voice using voice synthesis technology, and converts the generated response into text using text generation technology. Step 5: The output unit uses the generation AI to output the response converted by the conversion unit. The output is performed by a method such as voice output over the telephone or text output via email. For example, the output unit communicates the response generated using voice output over the telephone to the other party via telephone, and sends the response generated using text output via email to the other party as an email.

[0065] (Example 2) A telephone and email proxy response system according to an embodiment of the present invention uses a generation AI to handle telephone and email calls. In this system, a user inputs the contents of a telephone call or email into the generation AI, which analyzes the contents and generates an appropriate response. The generated response is output as voice in the case of a telephone call and as text in the case of an email. This mechanism eliminates the need for users to handle telephone and email calls themselves, thereby improving work efficiency. For example, a user inputs the contents of a telephone call or email into the generation AI. In the case of a telephone call, the user inputs the contents of the received call as text. In the case of an email, the contents of the received email are input directly into the generation AI. This information is then input into the generation AI. The generation AI then analyzes the input information. The generation AI understands the contents of the input telephone call or email and generates an appropriate response. For example, in the case of a telephone call, the generation AI generates a response that answers the caller's question or provides the necessary information. In the case of an email, the generation AI generates a reply to the caller's email. In the case of a telephone call, the generation AI outputs the generated response as voice. The generation AI converts the generated response into voice and transmits it to the caller via telephone. For example, if the other party asks, "What are your meeting schedules?", the generation AI will respond by voice, saying, "The next meeting is tomorrow at 10:00." In the case of emails, the generated response is output as text. The generation AI converts the generated response to text and sends it to the other party as an email. For example, if the other party requests, "Please send me some materials," the generation AI will generate a reply such as, "I will send them to you with the materials attached," and send it as an email. This system eliminates the need for users to handle phone calls and emails themselves, thereby improving work efficiency. For example, busy businesspeople can save time by not having to handle numerous phone calls and emails. In addition, because the generation AI generates appropriate responses, the quality of communication also improves. As a result, telephone and email proxy response systems eliminate the need for users to handle phone calls and emails themselves, thereby improving work efficiency.

[0066] A telephone and email proxy response system according to an embodiment includes a reception unit, an analysis unit, a generation unit, a conversion unit, and an output unit. The reception unit receives the contents of a telephone call or email from a user. The contents of a telephone call or email from a user include, but are not limited to, inquiries, complaints, orders, etc. The reception unit inputs, for example, the contents of a telephone call received by the user as text. The reception unit can also input the contents of an email received directly to the generation AI. For example, the contents of an email received by the user are input directly as text. The analysis unit uses the generation AI to analyze the contents received by the reception unit. The analysis can be performed using, for example, natural language processing technology, keyword extraction, sentiment analysis, etc., but is not limited to, these examples. For example, the analysis unit uses natural language processing technology to understand the contents of the input telephone call or email. The analysis unit can also extract important information using keyword extraction technology. The analysis unit can also estimate the other party's emotions using sentiment analysis technology. The generation unit uses the generation AI to generate a response based on the contents analyzed by the analysis unit. Response generation is performed by, for example, template-based response generation, generation using a machine learning model, or the like, but is not limited to these examples. For example, the generation unit generates an answer to the other party's question using template-based response generation. The generation unit can also generate a response that provides necessary information using a machine learning model. The conversion unit converts the response generated by the generation unit into voice or text using a generation AI. Conversion is performed by, for example, speech synthesis technology, text generation technology, or the like, but is not limited to these examples. For example, the conversion unit converts the generated response into voice using speech synthesis technology. The conversion unit can also convert the generated response into text using text generation technology. The output unit outputs the response converted by the conversion unit using a generation AI. Output is performed by, for example, voice output over the telephone, text output via email, or the like, but is not limited to these examples. For example, the output unit communicates the generated response to the other party over the telephone using voice output over the telephone.The output unit can also output text to an email and send the generated response to the other party. This eliminates the need for the user to handle phone calls and emails by themselves, thereby improving work efficiency.

[0067] The reception unit can input the contents of a phone call received by the user as text. Methods for inputting the contents as text include, but are not limited to, voice recognition technology and manual input. For example, the reception unit inputs the contents of a phone call received by the user as text using voice recognition technology. The reception unit can also manually input the contents of a phone call received by the user as text. For example, the reception unit can automatically input the contents of a phone call received by the user as text using voice recognition technology. The reception unit can also manually input the contents of a phone call received by the user as text. In this way, inputting the contents of the phone call as text makes it easier for the generation AI to generate an appropriate response. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit can input the contents of a phone call received by the user to the generation AI, which can analyze the contents and output them as text.

[0068] The reception unit can input the content of the received email directly to the generation AI. Methods of inputting the content of the received email directly include, but are not limited to, for example, inputting the content of the email directly as text. For example, the reception unit inputs the content of the received email directly as text. The reception unit can also input the content of the received email directly to the generation AI. For example, the reception unit inputs the content of the received email directly as text. The reception unit can also input the content of the received email directly to the generation AI. This makes it easier for the generation AI to generate an appropriate response by inputting the content of the email directly. Some or all of the above-described processing in the reception unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the content of the received email to the generation AI, and the generation AI can analyze the content and generate an appropriate response.

[0069] The analysis unit can understand the content of the input phone call or email and generate a response. Methods for understanding the content include, but are not limited to, natural language processing technology and context analysis. The analysis unit can understand the content of the input phone call or email using, for example, natural language processing technology. The analysis unit can also understand the content of the input phone call or email using context analysis technology. For example, the analysis unit can understand the content of the input phone call or email using natural language processing technology. The analysis unit can also understand the content of the input phone call or email using context analysis technology. This allows the generation AI to understand the content of the phone call or email and generate an appropriate response, improving the quality of communication. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the content of the input phone call or email into the generation AI, which can then analyze and understand the content.

[0070] The generation unit can generate an answer to the other party's question or a response that provides necessary information. Methods for generating an answer to a question include, but are not limited to, FAQ-based answer generation and generation using a machine learning model. The generation unit can generate an answer to the other party's question using, for example, FAQ-based answer generation. The generation unit can also generate a response that provides necessary information using a machine learning model. For example, the generation unit can generate an answer to the other party's question using FAQ-based answer generation. The generation unit can also generate a response that provides necessary information using a machine learning model. This allows the generation AI to generate an appropriate answer to the other party's question, thereby reducing the burden on the user. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input an answer to the other party's question into the generation AI, and the generation AI can analyze the content of the answer and generate an appropriate answer.

[0071] The conversion unit can convert the generated response into speech and transmit it to the other party over the phone. Methods for converting into speech include, but are not limited to, speech synthesis technology and text-to-speech technology. The conversion unit can convert the generated response into speech using, for example, speech synthesis technology. The conversion unit can also convert the generated response into speech using text-to-speech technology. For example, the conversion unit can convert the generated response into speech using speech synthesis technology. The conversion unit can also convert the generated response into speech using text-to-speech technology. In this way, by converting the response generated by the generation AI into speech, telephone responses are automated. Some or all of the above-described processing in the conversion unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the conversion unit can input the generated response into the generation AI, which can analyze the content of the response and convert it into speech.

[0072] The conversion unit can convert the generated response into text and send it to the other party as an email. Methods for converting into text include, but are not limited to, natural language generation technology and template-based generation. The conversion unit can convert the generated response into text using, for example, natural language generation technology. The conversion unit can also convert the generated response into text using template-based generation. For example, the conversion unit can convert the generated response into text using natural language generation technology. The conversion unit can also convert the generated response into text using template-based generation. In this way, by converting the response generated by the generation AI into text, the email response is automated. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the conversion unit can input the generated response into the generation AI, which can analyze the content and convert it into text.

[0073] The reception unit can estimate the user's emotions and adjust the timing of accepting phone calls and emails based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can have the generation AI delay accepting phone calls and emails until the user is relaxed. Furthermore, if the user is relaxed, the reception unit can have the generation AI immediately accept phone calls and emails. Furthermore, if the user is in a hurry, the reception unit can have the generation AI quickly accept phone calls and emails. This reduces the user's stress by adjusting the timing of accepting phone calls and emails according to the user's emotions. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. Furthermore, the generation AI can analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the reception unit to grasp the user's emotions in detail and adjust the timing of accepting phone calls and emails.

[0074] The reception unit can analyze the user's past phone call and email history and select the optimal reception method. For example, the reception unit uses the generation AI to suggest the optimal reception method based on the content of phone calls and emails the user frequently received in the past. The reception unit can also predict the content of phone calls and emails that should be received during a specific time period based on the user's past history, and the generation AI can receive calls during that time period. The reception unit can also analyze the user's past history and prioritize calls and emails from specific contacts. By analyzing the past history, the optimal reception method can be provided to the user. The history analysis is performed based on, for example, the content of past inquiries and response history. The generation AI can analyze the content of the user's past phone calls and emails and select the optimal reception method. The generation AI can also predict the content of phone calls and emails that should be received during a specific time period based on the user's past history. The generation AI can also prioritize calls and emails from specific contacts based on the user's past history. This allows the reception unit to analyze the user's past history in detail and provide the optimal reception method.

[0075] The reception unit can perform filtering based on the user's current work situation and areas of interest. For example, when the user is in a meeting, the generation AI can suspend accepting calls and emails and resume them after the meeting ends. Also, when the user is concentrating on a specific project, the reception unit can have the generation AI only accept calls and emails related to that project. Furthermore, the reception unit can prioritize accepting calls and emails that are highly relevant based on the user's areas of interest. This allows filtering based on the user's work situation and areas of interest, enabling important calls and emails to be prioritized. The work situation and areas of interest can be identified based on, for example, data on the user's work schedule and areas of interest. For example, the generation AI can analyze the user's work schedule and suspend accepting calls and emails during a meeting. Also, the generation AI can analyze data on the user's areas of interest and prioritize accepting calls and emails that are highly relevant. This allows the reception unit to gain a detailed understanding of the user's work situation and areas of interest and perform filtering.

[0076] The reception unit can estimate the user's emotions and determine the priority of the content to be received based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can have the generation AI postpone less important phone calls and emails. Furthermore, if the user is relaxed, the reception unit can have the generation AI prioritize more important phone calls and emails. Furthermore, if the user is in a hurry, the reception unit can have the generation AI prioritize urgent phone calls and emails. This allows important content to be processed first by determining the priority of the content to be received based on the user's emotions. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. Furthermore, the generation AI can analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the reception unit to grasp the user's emotions in detail and determine the priority of the content to be received.

[0077] The reception unit can prioritize receiving highly relevant content by taking into account the user's geographical location information. For example, when the user is in a specific area, the reception unit can prioritize receiving calls and emails related to that area. Furthermore, when the user is on a business trip, the reception unit can prioritize receiving calls and emails related to the business trip destination. Furthermore, when the user is at home, the reception unit can prioritize receiving calls and emails related to the user's home. This enables efficient response by prioritizing receiving highly relevant content based on the user's geographical location information. Geographical location information can be acquired, for example, using GPS data or a location information service. The generation AI can, for example, analyze the user's GPS data and prioritize receiving calls and emails related to a specific area. Furthermore, the generation AI can acquire the user's geographical location information using a location information service and prioritize receiving highly relevant content. This allows the reception unit to grasp the user's geographical location information in detail and prioritize receiving highly relevant content.

[0078] The reception unit can analyze the user's social media activity and receive related content. For example, if the user posts about a specific topic on social media, the reception unit can prioritize receiving calls and emails related to that topic. Furthermore, if the user is participating in a specific event on social media, the reception unit can prioritize receiving calls and emails related to that event. Furthermore, if the user belongs to a specific group on social media, the reception unit can prioritize receiving calls and emails related to that group. In this way, by analyzing social media activity, content related to the user can be prioritized. Analysis of social media activity is performed based on, for example, the content of posts and the reactions of followers. For example, the generation AI can analyze the content of the user's social media posts and receive related content. Furthermore, the generation AI can analyze the reactions of the user's followers and receive related content. In this way, the reception unit can analyze the user's social media activity in detail and receive related content.

[0079] 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 nervous, the generation AI can use a simple and easy-to-understand presentation. Furthermore, if the user is relaxed, the analysis unit can provide detailed analysis results. Furthermore, if the user is in a hurry, the generation AI can provide concise analysis results that focus on the main points. 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. Emotions can be estimated using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. Furthermore, the generation AI can analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the analysis unit to grasp the user's emotions in detail and adjust the way the analysis is presented.

[0080] The analysis unit can adjust the level of detail of the analysis based on the importance of the phone call or email. For example, in the case of a phone call or email that is highly important, the generation AI can perform a detailed analysis. In addition, in the case of a phone call or email that is low in importance, the analysis unit can also have the generation AI perform a concise analysis. Furthermore, the analysis unit can also have the generation AI determine the priority of the analysis based on the importance. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance. The importance is evaluated based on, for example, the importance score or the depth of the analysis. For example, the generation AI can analyze the importance of phone calls or emails and perform a detailed analysis. In addition, the generation AI can perform a concise analysis for phone calls or emails that are low in importance. This allows the analysis unit to evaluate the importance of phone calls and emails in detail and adjust the level of detail of the analysis.

[0081] The analysis unit can apply different analysis algorithms depending on the category of the call or email. For example, in the case of a business-related call or email, the generation AI can apply a business analysis algorithm. Furthermore, in the case of a private call or email, the analysis unit can also apply a private analysis algorithm. Furthermore, in the case of an urgent call or email, the analysis unit can also apply an emergency analysis algorithm. This allows for applying an analysis algorithm according to the category to provide more appropriate analysis results. The application of the analysis algorithm is based on, for example, a text analysis algorithm or a voice analysis algorithm. For example, the generation AI can apply a business analysis algorithm to business-related calls or emails. Furthermore, the generation AI can also apply a private analysis algorithm to private calls or emails. This allows the analysis unit to grasp the category of the call or email in detail and apply an appropriate analysis algorithm.

[0082] 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 cause the generation AI to perform a short, concise analysis. Furthermore, if the user is relaxed, the analysis unit can cause the generation AI to perform a detailed analysis. Furthermore, if the user is excited, the analysis unit can cause the generation AI to perform a visually stimulating analysis. This allows the analysis length to be adjusted according to the user's emotions, providing optimal analysis results for the user. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. Furthermore, the generation AI can analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the analysis unit to grasp the user's emotions in detail and adjust the length of the analysis.

[0083] The analysis unit can determine the priority of analysis based on the time when a call or email was received. For example, the analysis unit prioritizes analysis of recently received call or email. The analysis unit can also postpone analysis of older call or email. Furthermore, the analysis unit can also have the generation AI determine the priority of analysis based on the time when it was received. This enables efficient analysis by determining the priority of analysis based on the time when it was received. The evaluation of the time when it was received is based on, for example, a reception time score or an importance evaluation. For example, the generation AI can prioritize analysis of recently received call or email. The generation AI can also postpone analysis of older call or email. This allows the analysis unit to evaluate the time when call or email was received in detail and determine the priority of analysis.

[0084] The analysis unit can adjust the order of analysis based on the relevance of phone calls and emails. For example, the analysis unit prioritizes analysis of highly relevant phone calls and emails. The analysis unit can also postpone analysis of less relevant phone calls and emails. Furthermore, the analysis unit can also allow the generation AI to determine the order of analysis based on relevance. As a result, by adjusting the order of analysis based on relevance, important content can be analyzed preferentially. The evaluation of relevance is performed based on, for example, a relevance score or an importance evaluation. For example, the generation AI can prioritize analysis of highly relevant phone calls and emails. The generation AI can also postpone analysis of less relevant phone calls and emails. As a result, the analysis unit can evaluate the relevance of phone calls and emails in detail and adjust the order of analysis.

[0085] The generation unit can estimate the user's emotions and adjust the expression style of the generated response based on the estimated user emotions. For example, if the user is nervous, the generation AI can generate a simple and easy-to-understand response. Furthermore, if the user is relaxed, the generation unit can generate a detailed response. Furthermore, if the user is in a hurry, the generation unit can generate a concise response that focuses on the main points. This allows the response expression style to be adjusted according to the user's emotions, making it easier for the user to understand. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. Furthermore, the generation AI can analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the generation unit to grasp the user's emotions in detail and adjust the expression style of the generated response.

[0086] The generation unit can adjust the level of detail of the response based on the importance of the other party's question. For example, the generation unit causes the generation AI to generate a detailed response to a question of high importance. The generation unit can also cause the generation AI to generate a concise response to a question of low importance. Furthermore, the generation unit can also cause the generation AI to determine the priority of the response according to the importance. This enables efficient responses by adjusting the level of detail of the response according to the importance. The importance is evaluated based on, for example, the importance score or the depth of the response. For example, the generation AI can generate a detailed response to a question of high importance. The generation AI can also generate a concise response to a question of low importance. This allows the generation unit to evaluate the importance of the other party's question in detail and adjust the level of detail of the response.

[0087] The generation unit can apply different generation algorithms depending on the category of the other party's question. For example, in the generation unit, the generation AI applies a business generation algorithm to a business-related question. Furthermore, in the generation unit, the generation AI can also apply a private generation algorithm to a private question. Furthermore, in the generation unit, the generation AI can also apply an emergency generation algorithm to an urgent question. In this way, by applying a generation algorithm according to the category, a more appropriate response can be provided. The application of a generation algorithm is based on, for example, a text generation algorithm or a voice generation algorithm. For example, the generation AI can apply a business generation algorithm to a business-related question. Furthermore, the generation AI can also apply a private generation algorithm to a private question. In this way, the generation unit can grasp the category of the other party's question in detail and apply an appropriate generation algorithm.

[0088] The generation unit can estimate the user's emotions and adjust the length of the response to be generated based on the estimated user emotions. For example, if the user is in a hurry, the generation AI can generate a short, to-the-point response. Furthermore, if the user is relaxed, the generation unit can generate a detailed response. Furthermore, if the user is excited, the generation unit can generate a visually stimulating response. This allows the optimal response to be provided by adjusting the length of the response according to the user's emotions. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. Furthermore, the generation AI can analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the generation unit to grasp the user's emotions in detail and adjust the length of the response to be generated.

[0089] The generation unit can determine the priority of responses based on the time when the question was submitted by the other party. For example, the generation unit allows the generation AI to generate a response preferentially to a question that was recently submitted. The generation unit can also allow the generation AI to generate a response later to a question that was submitted earlier. Furthermore, the generation unit can allow the generation AI to determine the priority of responses according to the time of submission. This enables efficient responses by determining the priority of responses based on the time of submission. The evaluation of the submission time is based on, for example, a submission time score or an importance evaluation. For example, the generation AI can generate a response preferentially to a question that was recently submitted. The generation AI can also generate a response later to a question that was submitted earlier. This allows the generation unit to evaluate the time of submission of the other party's question in detail and determine the priority of responses.

[0090] The generation unit can adjust the order of responses based on the relevance of the other party's question. For example, the generation unit causes the generation AI to prioritize generating responses to highly relevant questions. The generation unit can also cause the generation AI to generate responses later to less relevant questions. Furthermore, the generation unit can also cause the generation AI to determine the order of responses according to relevance. As a result, by adjusting the order of responses based on relevance, important content can be prioritized in responses. The evaluation of relevance is performed based on, for example, a relevance score or an importance evaluation. For example, the generation AI can prioritize generating responses to highly relevant questions. The generation AI can also postpone generating responses to less relevant questions. As a result, the generation unit can evaluate the relevance of the other party's question in detail and adjust the order of responses.

[0091] The conversion unit can estimate the user's emotions and adjust the expression method of the converted voice or text based on the estimated user emotions. For example, if the user is nervous, the conversion unit generates a calm voice or simple text. Furthermore, if the user is relaxed, the conversion unit can generate a detailed voice or text. Furthermore, if the user is in a hurry, the conversion unit can generate a concise voice or text. This allows the voice or text expression method to be adjusted according to the user's emotions, providing a response that is easy for the user to understand. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. Furthermore, the generation AI can analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the conversion unit to grasp the user's emotions in detail and adjust the expression method of the converted voice or text.

[0092] The conversion unit can adjust the level of detail of the conversion based on the importance of the response. For example, the conversion unit allows the generation AI to generate detailed voice or text for a response with high importance. The conversion unit can also allow the generation AI to generate concise voice or text for a response with low importance. Furthermore, the conversion unit can also allow the generation AI to determine the priority of the conversion based on the importance. This enables efficient conversion by adjusting the level of detail of the conversion based on the importance. The evaluation of importance is based on, for example, the importance score or the depth of the conversion. For example, the generation AI can generate detailed voice or text for a response with high importance. The generation AI can also generate concise voice or text for a response with low importance. This allows the conversion unit to evaluate the importance of the response in detail and adjust the level of detail of the conversion.

[0093] The conversion unit can apply different conversion algorithms depending on the category of the response. For example, in the conversion unit, the generation AI can apply a business conversion algorithm to a business-related response. Furthermore, in the conversion unit, the generation AI can also apply a private conversion algorithm to a private response. Furthermore, in the conversion unit, the generation AI can also apply an emergency conversion algorithm to an urgent response. In this way, by applying a conversion algorithm according to the category, more appropriate conversion results can be provided. The application of the conversion algorithm is based on, for example, a text conversion algorithm or a speech conversion algorithm. For example, the generation AI can apply a business conversion algorithm to a business-related response. Furthermore, the generation AI can also apply a private conversion algorithm to a private response. In this way, the conversion unit can grasp the category of the response in detail and apply an appropriate conversion algorithm.

[0094] The conversion unit can estimate the user's emotions and adjust the length of the converted voice or text based on the estimated user emotions. For example, if the user is in a hurry, the conversion unit can generate short, concise voice or text. If the user is relaxed, the conversion unit can generate detailed voice or text. Furthermore, if the user is excited, the conversion unit can generate visually stimulating voice or text. This allows the optimal response for the user to be provided by adjusting the length of the voice or text according to the user's emotions. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. The generation AI can also analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the conversion unit to grasp the user's emotions in detail and adjust the length of the converted voice or text.

[0095] The conversion unit can determine the priority of conversion based on the submission time of the response. For example, the conversion unit allows the generation AI to prioritize conversion of recently submitted responses. The conversion unit can also allow the generation AI to postpone conversion of responses that were submitted earlier. Furthermore, the conversion unit allows the generation AI to determine the priority of conversion based on the submission time. This enables efficient conversion by determining the priority of conversion based on the submission time. The submission time is evaluated based on, for example, the submission time score or the importance evaluation. For example, the generation AI can prioritize conversion of recently submitted responses. The generation AI can also postpone conversion of responses that were submitted earlier. This allows the conversion unit to determine the priority of conversion by evaluating the submission time of responses in detail.

[0096] The conversion unit can adjust the order of conversion based on the relevance of the response. For example, the conversion unit allows the generation AI to prioritize conversion of highly relevant responses. Also, the conversion unit can allow the generation AI to postpone conversion of less relevant responses. Furthermore, the conversion unit can allow the generation AI to determine the order of conversion according to relevance. As a result, important content can be preferentially converted by adjusting the order of conversion based on relevance. The evaluation of relevance is performed based on, for example, a relevance score or an importance evaluation. For example, the generation AI can prioritize conversion of highly relevant responses. Also, the generation AI can postpone conversion of less relevant responses. As a result, the conversion unit can evaluate the relevance of responses in detail and adjust the order of conversion.

[0097] The output unit can estimate the user's emotions and adjust the expression method of the output voice and text based on the estimated user emotions. For example, if the user is nervous, the generation AI can output a calm voice and simple text. Furthermore, if the user is relaxed, the output unit can also output a detailed voice and text. Furthermore, if the user is in a hurry, the output unit can also output a concise voice and text. This allows the output unit to adjust the expression method of the voice and text according to the user's emotions, providing a response that is easy for the user to understand. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. Furthermore, the generation AI can analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the output unit to grasp the user's emotions in detail and adjust the expression method of the output voice and text.

[0098] The output unit can adjust the level of detail of the output based on the importance of the response. For example, in the output unit, the generation AI outputs detailed voice or text for a response with high importance. In addition, the output unit can also cause the generation AI to output concise voice or text for a response with low importance. Furthermore, the output unit can also cause the generation AI to determine an output priority according to importance. This enables efficient output by adjusting the level of detail of the output according to importance. The evaluation of importance is performed based on, for example, an importance score or the depth of the output. For example, the generation AI can output detailed voice or text for a response with high importance. In addition, the generation AI can output concise voice or text for a response with low importance. This allows the output unit to evaluate the importance of a response in detail and adjust the level of detail of the output.

[0099] The output unit can apply different output algorithms depending on the category of the response. For example, in the output unit, the generation AI can apply a business output algorithm to a business-related response. Furthermore, in the output unit, the generation AI can also apply a private output algorithm to a private response. Furthermore, in the output unit, the generation AI can also apply an emergency output algorithm to an urgent response. In this way, by applying an output algorithm according to the category, a more appropriate output result can be provided. The application of an output algorithm is based on, for example, a text output algorithm or a voice output algorithm. For example, the generation AI can apply a business output algorithm to a business-related response. Furthermore, the generation AI can also apply a private output algorithm to a private response. In this way, the output unit can grasp the category of the response in detail and apply an appropriate output algorithm.

[0100] The output unit can estimate the user's emotions and adjust the length of the audio or text to be output based on the estimated user's emotions. For example, if the user is in a hurry, the generation AI can output short, concise audio or text. If the user is relaxed, the output unit can also output detailed audio or text. Furthermore, if the user is excited, the output unit can also output visually stimulating audio or text. This allows the optimal response for the user to be provided by adjusting the length of the audio or text according to the user's emotions. Emotion estimation is performed using, for example, emotion analysis technology or facial expression recognition technology. For example, the generation AI can analyze the user's facial expression data to estimate emotions. The generation AI can also analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's biometric data to estimate emotions. This allows the output unit to grasp the user's emotions in detail and adjust the length of the audio or text to be output.

[0101] The output unit can determine the output priority based on the submission time of the response. For example, the output unit allows the generation AI to output recently submitted responses with priority. The output unit can also allow the generation AI to output older submitted responses later. Furthermore, the output unit can allow the generation AI to determine the output priority based on the submission time. This enables efficient output by determining the output priority based on the submission time. The submission time is evaluated based on, for example, a submission time score or an importance evaluation. For example, the generation AI can output recently submitted responses with priority. The generation AI can also output older submitted responses later. This allows the output unit to evaluate the submission time of responses in detail and determine the output priority.

[0102] The output unit can adjust the order of output based on the relevance of the responses. For example, the output unit allows the generation AI to prioritize output of highly relevant responses. Also, the output unit can allow the generation AI to postpone output of less relevant responses. Furthermore, the output unit can also allow the generation AI to determine the order of output based on relevance. As a result, important content can be prioritized by adjusting the order of output based on relevance. The evaluation of relevance is performed based on, for example, a relevance score or an importance evaluation. For example, the generation AI can prioritize output of highly relevant responses. Also, the generation AI can postpone output of less relevant responses. As a result, the output unit can evaluate the relevance of responses in detail and adjust the order of output. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, conversion unit, and output unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives the contents of a phone call or email from a user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the received contents using a generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a response based on the analyzed contents. The conversion unit is realized by the control unit 46A of the smart device 14 and converts the generated response into voice or text. The output unit is realized by the control unit 46A of the smart device 14 and outputs the converted response. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, conversion unit, and output unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives the contents of a phone call or email from a user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the received contents using a generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a response based on the analyzed contents. The conversion unit is realized by the control unit 46A of the smart glasses 214 and converts the generated response into voice or text. The output unit is realized by the control unit 46A of the smart glasses 214 and outputs the converted response. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, conversion unit, and output unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives the contents of a phone call or email from a user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the received contents using a generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a response based on the analyzed contents. The conversion unit is realized by the control unit 46A of the headset type terminal 314 and converts the generated response into voice or text. The output unit is realized by the control unit 46A of the headset type terminal 314 and outputs the converted response. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, conversion unit, and output unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives the contents of telephone calls and emails from users. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the received contents using a generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a response based on the analyzed contents. The conversion unit is realized by the control unit 46A of the robot 414 and converts the generated response into voice or text. The output unit is realized by the control unit 46A of the robot 414 and outputs the converted response.

[0103] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0104] The reception unit can analyze the user's past response history and select the optimal response template. For example, it can analyze how the user responded to specific inquiries in the past and use that response as a reference when a similar inquiry is received. The reception unit can also extract specific patterns from the user's past response history, and the generation AI can generate responses based on those patterns. Furthermore, the reception unit can adjust the tone and style of responses to specific people based on the user's past response history. This makes it possible to utilize past history to provide more consistent responses.

[0105] The reception unit monitors the user's current activity status in real time and can accept phone calls and emails at the appropriate time. For example, if the user is in a meeting, the generation AI will accept phone calls and emails after the meeting ends. Also, if the user is on the move, the generation AI can delay accepting calls and emails until the user has finished moving. Furthermore, if the user is concentrating on a task, the generation AI can suspend accepting calls until the task is completed. This allows for flexible response according to the user's activity status.

[0106] The reception unit can estimate the user's emotions and adjust the tone of the response based on the estimated emotions. For example, if the user is feeling stressed, the generation AI can generate a response in a calm tone. Alternatively, if the user is relaxed, the generation AI can generate a response in a friendly tone. Furthermore, if the user is in a hurry, the generation AI can generate a concise and quick response. This makes it possible to respond in an appropriate tone according to the user's emotions.

[0107] The analysis unit can predict future inquiries based on the content of past user inquiries and prepare responses in advance. For example, it can analyze the content of inquiries frequently made by users in the past, and if there is a high possibility that similar inquiries will be made, generate a response in advance. The analysis unit can also predict that specific inquiries will increase depending on the season or event, and prepare responses to those inquiries. Furthermore, the analysis unit can predict that inquiries will increase at specific times based on the user's work schedule, and prepare responses to those inquiries. This enables quick responses based on predictions.

[0108] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is feeling stressed, the generation AI will prioritize analyzing content of high importance. On the other hand, if the user is relaxed, the generation AI can also perform a detailed analysis, including content of low importance. Furthermore, if the user is in a hurry, the generation AI can perform an analysis quickly and provide results that focus on the main points. This enables efficient analysis according to the user's emotions.

[0109] The generator can select the optimal response style based on the user's past response history. For example, it can analyze phrases and expressions used by the user in the past and generate responses in a similar style. The generator can also adjust the tone and style of responses to specific people based on the user's past response history. Furthermore, the generator can select a response template appropriate for a specific situation based on the user's past response history. This makes it possible to provide more consistent responses by utilizing past history.

[0110] The generation unit can estimate the user's emotions and adjust the level of detail in the response based on the estimated emotions. For example, if the user is nervous, the generation AI can generate a simple and easy-to-understand response. Alternatively, if the user is relaxed, the generation AI can generate a detailed response. Furthermore, if the user is in a hurry, the generation AI can generate a concise response that hits the main points. This makes it possible to provide a response with an appropriate level of detail according to the user's emotions.

[0111] The conversion unit can analyze the user's past voice and text conversion history and select the optimal conversion method. For example, it analyzes the voice tone and text style used by the user in the past and performs conversion in a similar manner. The conversion unit can also select a conversion template appropriate for a specific situation from the user's past conversion history. Furthermore, the conversion unit can adjust the tone and style of conversion for a specific person based on the user's past conversion history. This makes it possible to utilize past history to provide more consistent conversion.

[0112] The conversion unit can estimate the user's emotions and adjust the level of detail of the conversion based on the estimated emotions. For example, if the user is nervous, the generation AI can generate simple, easy-to-understand voice and text. Alternatively, if the user is relaxed, the generation AI can generate detailed voice and text. Furthermore, if the user is in a hurry, the generation AI can generate concise voice and text that focuses on the main points. This makes it possible to convert with an appropriate level of detail according to the user's emotions.

[0113] The output unit can analyze the user's past output history and select the optimal output method. For example, it can analyze the voice tone and text style used by the user in the past and output in a similar manner. The output unit can also select an output template appropriate for a specific situation from the user's past output history. Furthermore, the output unit can adjust the tone and style of output for a specific person based on the user's past output history. This makes it possible to provide more consistent output by utilizing the past history.

[0114] The processing flow of the second embodiment will be briefly explained below.

[0115] Step 1: The reception unit receives the contents of phone calls or emails from users. The contents of phone calls or emails from users include inquiries, complaints, order details, etc. The reception unit inputs the contents of phone calls received by the user as text and inputs the contents of received emails directly into the generation AI. Step 2: The analysis unit uses the generation AI to analyze the content received by the reception unit. The analysis is performed using methods such as natural language processing technology, keyword extraction, and sentiment analysis. For example, the analysis unit uses natural language processing technology to understand the content of the input phone call or email, keyword extraction technology to extract important information, and sentiment analysis technology to estimate the other party's emotions. Step 3: The generation unit uses a generation AI to generate a response based on the content analyzed by the analysis unit. Response generation is performed using methods such as template-based response generation or generation using a machine learning model. For example, the generation unit uses template-based response generation to generate an answer to the other person's question, and generates a response that provides the necessary information using a machine learning model. Step 4: The conversion unit uses the generation AI to convert the response generated by the generation unit into voice or text. The conversion is performed using methods such as voice synthesis technology or text generation technology. For example, the conversion unit converts the generated response into voice using voice synthesis technology, and converts the generated response into text using text generation technology. Step 5: The output unit uses the generation AI to output the response converted by the conversion unit. The output is performed by a method such as voice output over the telephone or text output via email. For example, the output unit communicates the response generated using voice output over the telephone to the other party via telephone, and sends the response generated using text output via email to the other party as an email.

[0116] 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.

[0117] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0118] 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.

[0119] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0120] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0134] 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.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0137] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0150] 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.

[0151] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0152] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0153] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0167] 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.

[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] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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."

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] [Explanation of symbols]

[0188] 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 reception unit that receives the contents of a call or email from a user; an analysis unit that analyzes the content received by the reception unit; a generation unit that generates a response based on the content analyzed by the analysis unit; a conversion unit that converts the response generated by the generation unit into voice or text; an output unit that outputs the response converted by the conversion unit; A system characterized by:

2. The reception unit Enter the contents of the phone call received by the user as text 2. The system of claim 1.

3. The reception unit Input the contents of the received email directly into the generation AI 2. The system of claim 1.

4. The analysis unit Understand incoming phone calls or emails and generate responses 2. The system of claim 1.

5. The generation unit Generate responses that answer questions or provide necessary information 2. The system of claim 1.

6. The conversion unit Convert the generated response into speech and transmit it to the other party over the phone 2. The system of claim 1.

7. The conversion unit Convert the generated response into text and send it to the recipient as an email 2. The system of claim 1.

8. The reception unit Estimate the user's emotions and adjust the timing of accepting phone calls and emails based on the estimated user emotions.

2. The system of claim 1.

Images