System

Abstract

An object of the system according to the embodiment is to analyze the content of an utterance or the tone of a voice of a partner during a conversation and generate an appropriate question or topic in real time.SOLUTION: A system according to an embodiment includes a statement analysis unit, a tone analysis unit, and a question generation unit. The statement analysis unit analyzes a statement content of the other party. The tone analysis unit analyzes the tone of the voice of the other party. The question generation unit generates an appropriate question or topic based on the information obtained by the statement analysis unit and the tone analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to properly analyze the content and tone of the other person's speech during a conversation and generate appropriate questions and topics in real time.

[0005] The system according to the embodiment aims to analyze the content of what the other person is saying and the tone of their voice during a conversation, and to generate appropriate questions and topics in real time. [Means for solving the problem]

[0006] The system according to the embodiment includes a utterance analysis unit, a tone analysis unit, and a question generation unit. The utterance analysis unit analyzes the content of the other person's utterance. The tone analysis unit analyzes the tone of the other person's voice. The question generation unit generates appropriate questions and topics based on the information obtained by the utterance analysis unit and the tone analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the content of what the other person is saying and the tone of their voice during a conversation, and generate appropriate questions and topics in real time. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The dialogue AI system according to the embodiment of the present invention analyzes the content and tone of the other person's speech and suggests questions and exciting topics in real time, thereby smoothly progressing the dialogue and deepening the relationship with the other person.

[0029] The dialogue AI system according to the embodiment includes a utterance analysis unit, a tone analysis unit, and a question generation unit. The utterance analysis unit analyzes the content of the other party's utterance. For example, if the other party says, "I went on a trip recently," the utterance analysis unit analyzes the utterance and suggests questions and topics related to the trip. The utterance analysis unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to analyze the content of the utterance and generate appropriate questions and topics. The tone analysis unit analyzes the tone of the other party's voice. For example, if the other party speaks in an excited voice, the tone analysis unit suggests exciting topics that match the other party's emotion. The tone analysis unit uses the generation AI to analyze the tone of the voice and grasp the other party's emotional state. The question generation unit generates appropriate questions and topics based on the information obtained by the utterance analysis unit and the tone analysis unit. For example, if the other party says, "I saw a movie recently," the question generation unit suggests questions such as, "What kind of movie did you see?" and "What did you like best about that movie?" The question generator uses a generation AI to generate appropriate questions and topics based on the content of statements and the tone of voice. This allows the dialogue AI system according to the embodiment to smoothly advance a dialogue and deepen relationships with the other party. For example, in conversations with friends or business meetings, it is expected that the dialogue will proceed smoothly and deepen relationships with the other party.

[0030] When analyzing the content of a conversation, the utterance analysis unit can refer to the conversation history and generate questions that reflect the other person's interests and concerns. The utterance analysis unit, for example, stores the conversation history of the other person in a database and refers to that history when analyzing the conversation. For example, it generates related questions based on the hobbies and interests that the other person has previously mentioned. The utterance analysis unit uses a generation AI to analyze the conversation history and generate questions that reflect the other person's interests and concerns. This allows for deeper conversations by generating questions based on the other person's interests and concerns.

[0031] When analyzing the tone of the other person's voice, the tone analysis unit can generate more appropriate questions based on the other person's cultural background and regional expressions. For example, the tone analysis unit registers the other person's cultural background and regional expressions in a database and refers to that information when analyzing what is being said. For example, it understands slang and expressions used in a specific region and generates appropriate questions. The tone analysis unit uses generation AI to analyze cultural background and regional expressions and generate appropriate questions. This allows more appropriate questions to be generated by taking into account the other person's cultural background and regional expressions.

[0032] When analyzing the content of a conversation, the utterance analysis unit can refer to the conversation history and generate questions that reflect the other person's interests and concerns. The utterance analysis unit, for example, stores the conversation history of the other person in a database and refers to that history when analyzing the conversation. For example, it generates related questions based on the hobbies and interests that the other person has previously mentioned. The utterance analysis unit uses a generation AI to analyze the conversation history and generate questions that reflect the other person's interests and concerns. This allows for deeper conversations by generating questions based on the other person's interests and concerns.

[0033] When analyzing the content of a conversation, the utterance analysis unit can generate more appropriate questions based on the other person's cultural background and regional expressions. For example, the utterance analysis unit registers the other person's cultural background and regional expressions in a database and refers to that information when analyzing the content of the conversation. For example, it understands the slang and expressions used in a specific region and generates appropriate questions. The utterance analysis unit uses generative AI to analyze the cultural background and regional expressions and generate appropriate questions. This allows for the generation of more appropriate questions by taking into account the other person's cultural background and regional expressions.

[0034] When analyzing the tone of the other person's voice, the tone analysis unit performs a detailed analysis of the frequency and rhythm of the other person's voice, allowing for a more accurate understanding of their emotional state. For example, the tone analysis unit develops a voice analysis algorithm for detailed analysis of the frequency and rhythm of the voice. For example, it analyzes the pitch and speed of the voice to estimate the emotional state. The tone analysis unit uses generative AI to analyze the frequency and rhythm of the voice and understand the emotional state. This allows for a more accurate understanding of the other person's emotional state, improving the quality of the conversation.

[0035] The tone analysis unit can analyze the analysis results of the other person's voice tone in association with the other person's physical state and suggest appropriate topics. For example, the tone analysis unit develops an algorithm to associate the analysis results of the voice tone with the other person's physical state. For example, if the voice tone is low, it can infer fatigue. The tone analysis unit uses generative AI to analyze the voice tone and physical state and suggest appropriate topics. This improves the quality of the conversation by suggesting topics based on the other person's physical state.

[0036] The tone analysis unit can integrate the results of voice tone analysis with other sensor data to grasp the overall emotional state. The tone analysis unit, for example, builds a system for integrating the results of voice tone analysis with other sensor data. For example, it integrates heart rate and facial expression data to grasp the overall emotional state. The tone analysis unit uses generative AI to analyze voice tone and other sensor data to grasp the overall emotional state. This understanding of the overall emotional state improves the quality of dialogue.

[0037] The tone analysis unit analyzes the results of the voice tone analysis in association with the progress of the dialogue, thereby optimizing the flow of the dialogue. For example, the tone analysis unit develops an algorithm for associating the results of the voice tone analysis with the progress of the dialogue. For example, if the voice tone changes during the dialogue, the change is detected and the dialogue flow is adjusted. The tone analysis unit uses generative AI to analyze the voice tone and the progress of the dialogue, and optimize the dialogue flow. This optimizes the dialogue flow, thereby improving the quality of the dialogue.

[0038] The question generation unit can refer to the other party's past answers when proposing questions and generate consistent questions. The question generation unit, for example, stores the other party's past answers in a database and refers to those answers when proposing questions. For example, it generates questions related to what the other party has previously said. The question generation unit uses a generation AI to analyze past answers and generate consistent questions. This improves the quality of the dialogue by generating consistent questions based on the other party's past answers.

[0039] The question generation unit can generate questions that promote deeper dialogue by taking into account the expertise and interests of the other party when proposing questions. For example, the question generation unit registers the other party's expertise and interests in a database and refers to that information when proposing questions. For example, the question generation unit generates questions related to the other party's field of expertise. The question generation unit uses generation AI to analyze the expertise and interests and generate questions that promote deeper dialogue. This allows for deeper dialogue by generating questions based on the other party's expertise and interests.

[0040] The question generation unit can share the question suggestion results with other dialogue AI systems, maintaining consistency in dialogue between different systems. The question generation unit, for example, develops an API for sharing the question suggestion results with other dialogue AI systems. For example, it integrates dialogue data between different systems to achieve consistent dialogue. The question generation unit uses the generation AI to analyze the suggestion results and share them with other systems. This maintains consistency in dialogue between different systems, improving the quality of dialogue.

[0041] The question generation unit can visualize the proposed question content results, allowing the user to intuitively understand the progress of the dialogue. The question generation unit, for example, develops an interface for visualizing the proposed question content results. For example, the progress of the dialogue is displayed in a graph or chart. The question generation unit uses a generation AI to analyze and visualize the proposed results. This allows the progress of the dialogue to be intuitively understood, improving the quality of the dialogue.

[0042] The question generation unit can refer to the other party's past comments to generate consistent topics when suggesting exciting topics. For example, the question generation unit stores the other party's past comments in a database and refers to those comments when suggesting topics. For example, it generates topics related to what the other party has previously said. The question generation unit uses a generation AI to analyze the other party's past comments and generate consistent topics. This improves the quality of the conversation by generating consistent topics based on the other party's past comments.

[0043] The question generation unit can generate topics that encourage deeper conversations by taking into account the interests and concerns of the other party when suggesting exciting topics. For example, the question generation unit registers the interests and concerns of the other party in a database and refers to that information when suggesting topics. For example, it generates topics related to themes that interest the other party. The question generation unit uses generative AI to analyze interests and concerns and generate topics that encourage deeper conversations. This allows for deeper conversations by generating topics based on the interests and concerns of the other party.

[0044] The question generation unit can share the results of suggesting popular topics with other dialogue AI systems, maintaining consistency in dialogue between different systems. The question generation unit, for example, develops an API for sharing the results of suggesting popular topics with other dialogue AI systems. For example, it can integrate dialogue data between different systems to achieve consistent dialogue. The question generation unit uses the generation AI to analyze the proposal results and share them with other systems. This maintains consistency in dialogue between different systems, improving the quality of dialogue.

[0045] The question generation unit can visualize the proposed results of popular topics, allowing the user to intuitively understand the progress of the dialogue. The question generation unit, for example, develops an interface for visualizing the proposed results of popular topics. For example, the progress of the dialogue can be displayed in graphs or charts. The question generation unit uses a generation AI to analyze and visualize the proposed results. This allows the progress of the dialogue to be intuitively understood, improving the quality of the dialogue.

[0046] The dialogue AI system includes a dialogue progress management unit. The dialogue progress management unit analyzes the content of the other party's remarks and tone of voice in real time to manage the progress of the dialogue and optimize the flow of the dialogue. For example, the dialogue progress management unit builds a system that analyzes the content of the other party's remarks and tone of voice in real time. For example, it analyzes the content of the remarks and tone of voice simultaneously to optimize the flow of the dialogue. The dialogue progress management unit uses a generative AI to analyze the content of the remarks and tone of voice and optimize the flow of the dialogue. This optimizes the flow of the dialogue and improves the quality of the dialogue.

[0047] The dialogue progress management unit can refer to the other party's past dialogue history in managing the dialogue progress and progress the dialogue in a consistent manner. The dialogue progress management unit, for example, stores the other party's past dialogue history in a database and refers to that history when managing the dialogue progress. For example, it suggests topics related to what the other party has previously said. The dialogue progress management unit uses a generative AI to analyze the past dialogue history and progress the dialogue in a consistent manner. This improves the quality of the dialogue by progressing the dialogue in a consistent manner based on the other party's past dialogue history.

[0048] The dialogue progress management unit can share the dialogue progress management results with other dialogue AI systems and maintain the consistency of dialogue between different systems. The dialogue progress management unit, for example, develops an API for sharing the dialogue progress management results with other dialogue AI systems. For example, it can integrate dialogue data between different systems to achieve consistent dialogue. The dialogue progress management unit uses a generative AI to analyze the progress management results and share them with other systems. This maintains the consistency of dialogue between different systems, improving the quality of dialogue.

[0049] The dialogue progress management unit can visualize the dialogue progress management results, allowing the user to intuitively understand the dialogue progress. The dialogue progress management unit, for example, develops an interface for visualizing the dialogue progress management results. For example, the dialogue progress is displayed in graphs or charts. The dialogue progress management unit uses generative AI to analyze and visualize the progress management results. This allows the user to intuitively understand the dialogue progress, improving the quality of the dialogue.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The conversational AI system can further include a gesture analysis unit that analyzes the user's gestures. The gesture analysis unit, for example, captures the user's hand movements and facial expressions with a camera and analyzes those movements. For example, if the user waves their hand, the gesture analysis unit analyzes that movement and understands whether the user is intending to say hello or say goodbye. Also, if the user frowns, the gesture analysis unit can analyze that movement and infer whether the user is feeling confused or dissatisfied. This allows the conversational AI system to proceed more naturally based on the user's gestures.

[0052] The conversational AI system can further include an environmental sound analysis unit that analyzes the user's environmental sounds. The environmental sound analysis unit, for example, captures surrounding sounds with a microphone and analyzes the sounds. For example, if the surroundings are noisy, the environmental sound analysis unit analyzes the sounds and automatically adjusts the volume of the dialogue. Also, if the surroundings are quiet, the environmental sound analysis unit can analyze the quietness and adjust the tone of the dialogue to a calmer tone. This allows the conversational AI system to provide dialogue that is appropriate for the user's environment.

[0053] The conversational AI system may further include an eye-tracking unit that tracks the user's gaze. The eye-tracking unit, for example, captures the user's eye movements with a camera and analyzes those movements. For example, when the user looks in a particular direction, the eye-tracking unit analyzes that direction and identifies the object in which the user is interested. In addition, when the user looks away, the eye-tracking unit can analyze that behavior and estimate the possibility that the user is losing interest in the conversation. This allows the conversational AI system to adjust the conversation based on the user's gaze.

[0054] The conversational AI system can further include a health monitoring unit that monitors the user's health condition. The health monitoring unit measures, for example, the user's heart rate and body temperature using a sensor and analyzes the data. For example, if the user's heart rate is elevated, the health monitoring unit analyzes the data and estimates the possibility that the user is nervous. Also, if the user's body temperature is high, the health monitoring unit can analyze the data and estimate the possibility that the user is not feeling well. This allows the conversational AI system to adjust the dialogue based on the user's health condition.

[0055] The conversational AI system can further include a behavioral analysis unit that analyzes the user's behavioral history. The behavioral analysis unit, for example, stores the user's past behavioral data in a database and analyzes that data. For example, it can analyze data on places the user has visited or events they have attended in the past and suggest related topics. It can also analyze data on the user's past activities and generate questions that reflect the user's interests. This allows the conversational AI system to deepen the dialogue based on the user's behavioral history.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The utterance analysis unit analyzes the content of the other person's utterance. For example, if the other person says, "I went on a trip recently," the utterance analysis unit analyzes the utterance and suggests questions and topics related to the trip. The utterance analysis unit uses a generative AI (for example, a text generation AI or a multimodal generation AI) to analyze the utterance content and generate appropriate questions and topics. Step 2: The tone analysis unit analyzes the tone of the other person's voice. For example, if the other person is speaking in an excited voice, the system will suggest exciting topics that match that emotion. The tone analysis unit uses generative AI to analyze the tone of the voice and understand the person's emotional state. Step 3: The question generation unit generates appropriate questions and topics based on the information obtained by the utterance analysis unit and tone analysis unit. For example, if the other person says, "I saw a movie recently," it will suggest questions such as, "What kind of movie did you see?" or "What did you like best about that movie?" The question generation unit uses generative AI to generate appropriate questions and topics based on the content of the utterance and the tone of voice.

[0058] (Example 2) The dialogue AI system according to the embodiment of the present invention analyzes the content and tone of the other person's speech and suggests questions and exciting topics in real time, thereby smoothly progressing the dialogue and deepening the relationship with the other person.

[0059] The dialogue AI system according to the embodiment includes a utterance analysis unit, a tone analysis unit, and a question generation unit. The utterance analysis unit analyzes the content of the other party's utterance. For example, if the other party says, "I went on a trip recently," the utterance analysis unit analyzes the utterance and suggests questions and topics related to the trip. The utterance analysis unit uses a generation AI (e.g., a text generation AI or a multimodal generation AI) to analyze the content of the utterance and generate appropriate questions and topics. The tone analysis unit analyzes the tone of the other party's voice. For example, if the other party speaks in an excited voice, the tone analysis unit suggests exciting topics that match the other party's emotion. The tone analysis unit uses the generation AI to analyze the tone of the voice and grasp the other party's emotional state. The question generation unit generates appropriate questions and topics based on the information obtained by the utterance analysis unit and the tone analysis unit. For example, if the other party says, "I saw a movie recently," the question generation unit suggests questions such as, "What kind of movie did you see?" and "What did you like best about that movie?" The question generator uses a generation AI to generate appropriate questions and topics based on the content of statements and the tone of voice. This allows the dialogue AI system according to the embodiment to smoothly advance a dialogue and deepen relationships with the other party. For example, in conversations with friends or business meetings, it is expected that the dialogue will proceed smoothly and deepen relationships with the other party.

[0060] When analyzing the content of a conversation, the utterance analysis unit can refer to the conversation history and generate questions that reflect the other person's interests and concerns. The utterance analysis unit, for example, stores the conversation history of the other person in a database and refers to that history when analyzing the conversation. For example, it generates related questions based on the hobbies and interests that the other person has previously mentioned. The utterance analysis unit uses a generation AI to analyze the conversation history and generate questions that reflect the other person's interests and concerns. This allows for deeper conversations by generating questions based on the other person's interests and concerns.

[0061] When analyzing the tone of the other person's voice, the tone analysis unit can generate more appropriate questions based on the other person's cultural background and regional expressions. For example, the tone analysis unit registers the other person's cultural background and regional expressions in a database and refers to that information when analyzing what is being said. For example, it understands slang and expressions used in a specific region and generates appropriate questions. The tone analysis unit uses generation AI to analyze cultural background and regional expressions and generate appropriate questions. This allows more appropriate questions to be generated by taking into account the other person's cultural background and regional expressions.

[0062] The question generation unit can infer emotions from the content of the other person's remarks and tone of voice, and generate questions based on those emotions. For example, the question generation unit uses an emotion estimation function to build a system that infers emotions in real time from the content of the other person's remarks. For example, if the other person is happy, it generates questions that match that emotion. The question generation unit uses a generation AI to infer emotions from the content of the remarks and tone of voice, and generates questions based on those emotions. This makes it possible to adjust the atmosphere of the conversation by generating questions based on the other person's emotions.

[0063] When analyzing the content of a conversation, the utterance analysis unit can refer to the conversation history and generate questions that reflect the other person's interests and concerns. The utterance analysis unit, for example, stores the conversation history of the other person in a database and refers to that history when analyzing the conversation. For example, it generates related questions based on the hobbies and interests that the other person has previously mentioned. The utterance analysis unit uses a generation AI to analyze the conversation history and generate questions that reflect the other person's interests and concerns. This allows for deeper conversations by generating questions based on the other person's interests and concerns.

[0064] When analyzing the content of a conversation, the utterance analysis unit can generate more appropriate questions based on the other person's cultural background and regional expressions. For example, the utterance analysis unit registers the other person's cultural background and regional expressions in a database and refers to that information when analyzing the content of the conversation. For example, it understands the slang and expressions used in a specific region and generates appropriate questions. The utterance analysis unit uses generative AI to analyze the cultural background and regional expressions and generate appropriate questions. This allows for the generation of more appropriate questions by taking into account the other person's cultural background and regional expressions.

[0065] When analyzing the content of the other person's speech, the speech analysis unit can use an emotion estimation function to infer emotions from the content of the other person's speech and generate questions based on those emotions. For example, the speech analysis unit uses the emotion estimation function to build a system that estimates emotions in real time from the content of the other person's speech. For example, if the other person is happy, it generates questions that match that emotion. The speech analysis unit uses a generation AI to infer emotions from the content of the speech and tone of voice and generates questions based on those emotions. This makes it possible to adjust the atmosphere of the conversation by generating questions based on the other person's emotions.

[0066] When analyzing the tone of the other person's voice, the tone analysis unit performs a detailed analysis of the frequency and rhythm of the other person's voice, allowing for a more accurate understanding of their emotional state. For example, the tone analysis unit develops a voice analysis algorithm for detailed analysis of the frequency and rhythm of the voice. For example, it analyzes the pitch and speed of the voice to estimate the emotional state. The tone analysis unit uses generative AI to analyze the frequency and rhythm of the voice and understand the emotional state. This allows for a more accurate understanding of the other person's emotional state, improving the quality of the conversation.

[0067] The tone analysis unit can analyze the analysis results of the other person's voice tone in association with the other person's physical state and suggest appropriate topics. For example, the tone analysis unit develops an algorithm to associate the analysis results of the voice tone with the other person's physical state. For example, if the voice tone is low, it can infer fatigue. The tone analysis unit uses generative AI to analyze the voice tone and physical state and suggest appropriate topics. This improves the quality of the conversation by suggesting topics based on the other person's physical state.

[0068] The tone analysis unit can use the emotion estimation function to generate topics that match the mood of the other person based on the emotion estimated from the tone of voice. For example, the tone analysis unit uses the emotion estimation function to build a system that analyzes the emotion estimated from the tone of voice in real time. For example, if the tone of voice is high, it estimates the emotion of joy. The tone analysis unit uses a generation AI to estimate the emotion from the tone of voice and generate topics based on that emotion. This makes it possible to adjust the atmosphere of the conversation by generating topics that match the mood of the other person.

[0069] The tone analysis unit can integrate the results of voice tone analysis with other sensor data to grasp the overall emotional state. The tone analysis unit, for example, builds a system for integrating the results of voice tone analysis with other sensor data. For example, it integrates heart rate and facial expression data to grasp the overall emotional state. The tone analysis unit uses generative AI to analyze voice tone and other sensor data to grasp the overall emotional state. This understanding of the overall emotional state improves the quality of dialogue.

[0070] The tone analysis unit analyzes the results of the voice tone analysis in association with the progress of the dialogue, thereby optimizing the flow of the dialogue. For example, the tone analysis unit develops an algorithm for associating the results of the voice tone analysis with the progress of the dialogue. For example, if the voice tone changes during the dialogue, the change is detected and the dialogue flow is adjusted. The tone analysis unit uses generative AI to analyze the voice tone and the progress of the dialogue, and optimize the dialogue flow. This optimizes the dialogue flow, thereby improving the quality of the dialogue.

[0071] The tone analysis unit can use the emotion estimation function to adjust the tempo and content of a dialogue in real time based on changes in voice tone. The tone analysis unit, for example, uses the emotion estimation function to build a system that analyzes changes in voice tone in real time. For example, if there is a sudden change in voice tone, the change is detected and the tempo of the dialogue is adjusted. The tone analysis unit uses a generative AI to analyze changes in voice tone and adjust the tempo and content of the dialogue. This improves the quality of the dialogue by adjusting the tempo and content of the dialogue in real time.

[0072] The question generation unit can refer to the other party's past answers when proposing questions and generate consistent questions. The question generation unit, for example, stores the other party's past answers in a database and refers to those answers when proposing questions. For example, it generates questions related to what the other party has previously said. The question generation unit uses a generation AI to analyze past answers and generate consistent questions. This improves the quality of the dialogue by generating consistent questions based on the other party's past answers.

[0073] The question generation unit can generate questions that promote deeper dialogue by taking into account the expertise and interests of the other party when proposing questions. For example, the question generation unit registers the other party's expertise and interests in a database and refers to that information when proposing questions. For example, the question generation unit generates questions related to the other party's field of expertise. The question generation unit uses generation AI to analyze the expertise and interests and generate questions that promote deeper dialogue. This allows for deeper dialogue by generating questions based on the other party's expertise and interests.

[0074] The question generation unit uses the emotion estimation function to generate questions that match the emotional state of the other party, and can adjust the atmosphere of the conversation. The question generation unit, for example, uses the emotion estimation function to build a system that analyzes the emotional state of the other party in real time. For example, if the other party is happy, it generates questions that match that emotion. The question generation unit uses a generation AI to analyze the emotional state and generate questions based on that emotion. In this way, the atmosphere of the conversation can be adjusted by generating questions based on the emotional state of the other party.

[0075] The question generation unit can share the question suggestion results with other dialogue AI systems, maintaining consistency in dialogue between different systems. The question generation unit, for example, develops an API for sharing the question suggestion results with other dialogue AI systems. For example, it integrates dialogue data between different systems to achieve consistent dialogue. The question generation unit uses the generation AI to analyze the suggestion results and share them with other systems. This maintains consistency in dialogue between different systems, improving the quality of dialogue.

[0076] The question generation unit can visualize the proposed question content results, allowing the user to intuitively understand the progress of the dialogue. The question generation unit, for example, develops an interface for visualizing the proposed question content results. For example, the progress of the dialogue is displayed in a graph or chart. The question generation unit uses a generation AI to analyze and visualize the proposed results. This allows the progress of the dialogue to be intuitively understood, improving the quality of the dialogue.

[0077] The question generation unit can use the emotion estimation function to monitor the other party's emotional response in real time and adjust the content of the question. The question generation unit, for example, uses the emotion estimation function to build a system that monitors the other party's emotional response in real time. For example, it analyzes the other party's facial expression and voice and calculates an emotion score. The question generation unit uses a generation AI to analyze the emotional response and adjust the content of the question. This improves the quality of the dialogue by adjusting the content of the question based on the other party's emotional response.

[0078] The question generation unit can refer to the other party's past comments to generate consistent topics when suggesting exciting topics. For example, the question generation unit stores the other party's past comments in a database and refers to those comments when suggesting topics. For example, it generates topics related to what the other party has previously said. The question generation unit uses a generation AI to analyze the other party's past comments and generate consistent topics. This improves the quality of the conversation by generating consistent topics based on the other party's past comments.

[0079] The question generation unit can generate topics that encourage deeper conversations by taking into account the interests and concerns of the other party when suggesting exciting topics. For example, the question generation unit registers the interests and concerns of the other party in a database and refers to that information when suggesting topics. For example, it generates topics related to themes that interest the other party. The question generation unit uses generative AI to analyze interests and concerns and generate topics that encourage deeper conversations. This allows for deeper conversations by generating topics based on the interests and concerns of the other party.

[0080] The question generation unit uses the emotion estimation function to generate topics that match the emotional state of the other person, and can adjust the atmosphere of the conversation. For example, the question generation unit uses the emotion estimation function to build a system that analyzes the emotional state of the other person in real time. For example, if the other person is happy, it generates topics that match that emotion. The question generation unit uses a generation AI to analyze the emotional state and generate topics based on that emotion. In this way, the atmosphere of the conversation can be adjusted by generating topics based on the emotional state of the other person.

[0081] The question generation unit can share the results of suggesting popular topics with other dialogue AI systems, maintaining consistency in dialogue between different systems. The question generation unit, for example, develops an API for sharing the results of suggesting popular topics with other dialogue AI systems. For example, it can integrate dialogue data between different systems to achieve consistent dialogue. The question generation unit uses the generation AI to analyze the proposal results and share them with other systems. This maintains consistency in dialogue between different systems, improving the quality of dialogue.

[0082] The question generation unit can visualize the proposed results of popular topics, allowing the user to intuitively understand the progress of the dialogue. The question generation unit, for example, develops an interface for visualizing the proposed results of popular topics. For example, the progress of the dialogue can be displayed in graphs or charts. The question generation unit uses a generation AI to analyze and visualize the proposed results. This allows the progress of the dialogue to be intuitively understood, improving the quality of the dialogue.

[0083] The question generation unit can use the emotion estimation function to monitor the other party's emotional response in real time and adjust the topic of conversation. The question generation unit, for example, uses the emotion estimation function to build a system that monitors the other party's emotional response in real time. For example, it analyzes the other party's facial expression and voice and calculates an emotion score. The question generation unit uses a generation AI to analyze the emotional response and adjust the topic of conversation. This improves the quality of the conversation by adjusting the topic of conversation based on the other party's emotional response.

[0084] The dialogue AI system includes a dialogue progress management unit. The dialogue progress management unit analyzes the content of the other party's remarks and tone of voice in real time to manage the progress of the dialogue and optimize the flow of the dialogue. For example, the dialogue progress management unit builds a system that analyzes the content of the other party's remarks and tone of voice in real time. For example, it analyzes the content of the remarks and tone of voice simultaneously to optimize the flow of the dialogue. The dialogue progress management unit uses a generative AI to analyze the content of the remarks and tone of voice and optimize the flow of the dialogue. This optimizes the flow of the dialogue and improves the quality of the dialogue.

[0085] The dialogue progress management unit can refer to the other party's past dialogue history in managing the dialogue progress and progress the dialogue in a consistent manner. The dialogue progress management unit, for example, stores the other party's past dialogue history in a database and refers to that history when managing the dialogue progress. For example, it suggests topics related to what the other party has previously said. The dialogue progress management unit uses a generative AI to analyze the past dialogue history and progress the dialogue in a consistent manner. This improves the quality of the dialogue by progressing the dialogue in a consistent manner based on the other party's past dialogue history.

[0086] The dialogue progress management unit uses the emotion estimation function to progress the dialogue in accordance with the emotional state of the other party, and can adjust the atmosphere of the dialogue. For example, the dialogue progress management unit uses the emotion estimation function to build a system that analyzes the emotional state of the other party in real time. For example, if the other party is happy, the dialogue progresses in accordance with that emotion. The dialogue progress management unit uses a generative AI to analyze the emotional state and progress the dialogue based on that emotion. In this way, the atmosphere of the dialogue can be adjusted by progressing the dialogue based on the emotional state of the other party.

[0087] The dialogue progress management unit can share the dialogue progress management results with other dialogue AI systems and maintain the consistency of dialogue between different systems. The dialogue progress management unit, for example, develops an API for sharing the dialogue progress management results with other dialogue AI systems. For example, it can integrate dialogue data between different systems to achieve consistent dialogue. The dialogue progress management unit uses a generative AI to analyze the progress management results and share them with other systems. This maintains the consistency of dialogue between different systems, improving the quality of dialogue.

[0088] The dialogue progress management unit can visualize the dialogue progress management results, allowing the user to intuitively understand the dialogue progress. The dialogue progress management unit, for example, develops an interface for visualizing the dialogue progress management results. For example, the dialogue progress is displayed in graphs or charts. The dialogue progress management unit uses generative AI to analyze and visualize the progress management results. This allows the user to intuitively understand the dialogue progress, improving the quality of the dialogue.

[0089] The dialogue progress management unit can use the emotion estimation function to monitor the other party's emotional reactions in real time and adjust the progress of the dialogue. The dialogue progress management unit, for example, uses the emotion estimation function to build a system that monitors the other party's emotional reactions in real time. For example, it analyzes the other party's facial expressions and voice and calculates an emotion score. The dialogue progress management unit uses generative AI to analyze the emotional reactions and adjust the progress of the dialogue. This improves the quality of the dialogue by adjusting the progress of the dialogue based on the other party's emotional reactions.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The conversational AI system can further include a gesture analysis unit that analyzes the user's gestures. The gesture analysis unit, for example, captures the user's hand movements and facial expressions with a camera and analyzes those movements. For example, if the user waves their hand, the gesture analysis unit analyzes that movement and understands the intention of greeting or farewell. Also, if the user frowns, the gesture analysis unit can analyze that movement and infer feelings of confusion or dissatisfaction. This allows the conversational AI system to proceed more naturally based on the user's gestures.

[0092] The conversational AI system can further include an environmental sound analysis unit that analyzes the user's environmental sounds. The environmental sound analysis unit, for example, captures surrounding sounds with a microphone and analyzes the sounds. For example, if the surroundings are noisy, the environmental sound analysis unit analyzes the sounds and automatically adjusts the volume of the dialogue. Also, if the surroundings are quiet, the environmental sound analysis unit can analyze the quietness and adjust the tone of the dialogue to a calmer tone. This allows the conversational AI system to provide dialogue that is appropriate for the user's environment.

[0093] The conversational AI system may further include an eye-tracking unit that tracks the user's gaze. The eye-tracking unit, for example, captures the user's eye movements with a camera and analyzes those movements. For example, when the user looks in a particular direction, the eye-tracking unit analyzes that direction and identifies the object in which the user is interested. In addition, when the user looks away, the eye-tracking unit can analyze that behavior and estimate the possibility that the user is losing interest in the conversation. This allows the conversational AI system to adjust the conversation based on the user's gaze.

[0094] The conversational AI system can further include a health monitoring unit that monitors the user's health condition. The health monitoring unit measures, for example, the user's heart rate and body temperature using a sensor and analyzes the data. For example, if the user's heart rate is elevated, the health monitoring unit analyzes the data and estimates the possibility that the user is nervous. Also, if the user's body temperature is high, the health monitoring unit can analyze the data and estimate the possibility that the user is not feeling well. This allows the conversational AI system to adjust the dialogue based on the user's health condition.

[0095] The conversational AI system can further include a behavioral analysis unit that analyzes the user's behavioral history. The behavioral analysis unit, for example, stores the user's past behavioral data in a database and analyzes that data. For example, it can analyze data on places the user has visited or events they have attended in the past and suggest related topics. It can also analyze data on the user's past activities and generate questions that reflect the user's interests. This allows the conversational AI system to deepen the dialogue based on the user's behavioral history.

[0096] The conversational AI system can further estimate the user's emotions and adjust the tempo of the conversation based on those emotions. For example, if the user is excited, the tempo of the conversation can be increased. On the other hand, if the user is calm, the tempo of the conversation can be decreased. This allows the conversational AI system to provide a conversation tempo that matches the user's emotions.

[0097] The conversational AI system can also estimate the user's emotions and adjust the content of the dialogue based on those emotions. For example, if the user is sad, it can provide a dialogue that comforts the user. If the user is happy, it can provide a dialogue that shares that joy. This allows the conversational AI system to provide dialogue content that matches the user's emotions.

[0098] The conversational AI system can further estimate the user's emotions and adjust the tone of the dialogue based on those emotions. For example, if the user is angry, the tone of the dialogue can be made calmer. If the user is having fun, the tone of the dialogue can be made brighter. This allows the conversational AI system to provide a dialogue tone that matches the user's emotions.

[0099] The conversational AI system can further estimate the user's emotions and adjust the length of the conversation based on those emotions. For example, if the user is tired, the conversation length can be shortened. Also, if the user is interested, the conversation length can be lengthened. This allows the conversational AI system to provide a conversation length that matches the user's emotions.

[0100] The conversational AI system can further estimate the user's emotions and adjust the frequency of conversations based on those emotions. For example, if the user is feeling stressed, the frequency of conversations can be reduced. On the other hand, if the user is relaxed, the frequency of conversations can be increased. This allows the conversational AI system to provide a frequency of conversations that matches the user's emotions.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The utterance analysis unit analyzes the content of the other person's utterance. For example, if the other person says, "I went on a trip recently," the utterance analysis unit analyzes the utterance and suggests questions and topics related to the trip. The utterance analysis unit uses a generative AI (for example, a text generation AI or a multimodal generation AI) to analyze the utterance content and generate appropriate questions and topics. Step 2: The tone analysis unit analyzes the tone of the other person's voice. For example, if the other person is speaking in an excited voice, the system will suggest exciting topics that match that emotion. The tone analysis unit uses generative AI to analyze the tone of the voice and understand the person's emotional state. Step 3: The question generation unit generates appropriate questions and topics based on the information obtained by the utterance analysis unit and tone analysis unit. For example, if the other person says, "I saw a movie recently," it will suggest questions such as, "What kind of movie did you see?" or "What did you like best about that movie?" The question generation unit uses generative AI to generate appropriate questions and topics based on the content of the utterance and the tone of voice.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] 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.

[0118] 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.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] 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.

[0130] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[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 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.

[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 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).

[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] 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.

[0144] 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.

[0145] 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.

[0146] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 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 speech analysis unit that analyzes the content of the speech of the other party; a tone analysis unit that analyzes the tone of the other person's voice; a question generation unit that generates appropriate questions and topics based on the information obtained by the utterance analysis unit and the tone analysis unit. A system characterized by:

2. The tone analysis unit When analyzing the tone of the other person's voice, it generates more appropriate questions based on their cultural background and regional expressions.

2. The system of claim 1.

3. The utterance analysis unit When analyzing what the other person is saying, it generates more appropriate questions based on their cultural background and regional expressions.

2. The system of claim 1.

4. The question generation unit When suggesting questions, the system references the other person's past answers and generates consistent questions.

2. The system of claim 1.

5. The tone analysis unit Using emotion estimation functionality, topics are generated that match the other person's mood based on emotions inferred from the tone of voice.

2. The system of claim 1.

Images