system

Abstract

The system according to this embodiment aims to understand the user's emotions and personalize the conversation based on those emotions. [Solution] The system according to this embodiment comprises an emotion recognition unit, a dialogue management unit, and a personalization unit. The emotion recognition unit understands the user's emotions. The dialogue management unit performs advanced dialogue management based on the emotions understood by the emotion recognition unit. The personalization unit personalizes the interaction with the user based on the dialogue conducted by the dialogue management unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, understanding the user's emotions and personalizing the dialogue based on them have not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to understand the user's emotions and personalize the dialogue based on them.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an emotion recognition unit, a dialogue management unit, and a personalization unit. The emotion recognition unit understands the user's emotions. The dialogue management unit performs advanced dialogue management based on the emotions understood by the emotion recognition unit. The personalization unit personalizes the interaction with the user based on the dialogue conducted by the dialogue management unit. [Effects of the Invention]

[0007] The system according to this embodiment can understand the user's emotions and personalize the conversation based on them. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of 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), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The communication agent system according to an embodiment of the present invention is a system that provides customized conversational services to corporate and individual users by utilizing AI and robotics. This system understands the user's emotions using emotion recognition technology, performs advanced dialogue management using natural language processing, and personalizes user interactions using machine learning. For example, the communication agent system can recognize the user's emotions in real time and generate appropriate responses. For example, if the user is feeling stressed, the system can provide relaxing content. Also, if the user is excited, the system can provide content that shares that excitement. Furthermore, the communication agent system can provide corporate clients with improved business process efficiency and enhanced customer service. For example, the system streamlines business processes by optimizing workflows and optimally allocating resources. It can also improve customer service by accelerating customer responses and personalizing services. For individual users, it can improve the quality of daily life and provide entertainment. For example, the system can provide support for health management, time management, and stress reduction. It can also provide entertainment content such as games, music, and movies. As a result, the communication agent system achieves improved user satisfaction, increased engagement, and faster problem-solving speed. Furthermore, we aim to create new user experiences through the fusion of AI and robotics, and to continuously improve services through sustainable technological advancements. This will enable the communication agent system to understand user emotions and personalize dialogue management and interactions based on those emotions.

[0029] The communication agent system according to this embodiment comprises an emotion recognition unit, a dialogue management unit, and a personalization unit. The emotion recognition unit understands the user's emotions. For example, the emotion recognition unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. The emotion recognition unit can also analyze the tone of the user's voice using voice analysis technology and estimate their emotions. Furthermore, the emotion recognition unit can analyze the user's text messages using text analysis technology and estimate their emotions. For example, the emotion recognition unit can capture the user's facial expressions with a camera, and the AI ​​can analyze subtle changes in facial expressions to estimate their emotions. The emotion recognition unit can also collect the tone of the user's voice with a microphone, and the AI ​​can analyze the pitch and tempo of the voice to estimate their emotions. Furthermore, the emotion recognition unit can analyze the user's text messages, and the AI ​​can estimate their emotions from the content of the text. The dialogue management unit performs advanced dialogue management based on the emotions understood by the emotion recognition unit. For example, the dialogue management unit can understand the user's intentions using natural language processing technology and generate appropriate responses. Furthermore, the dialogue management unit can manage the flow of the conversation and conduct conversations that are tailored to the user's intentions. It can also adjust the tone and content of the conversation according to the user's emotions. For example, if the user is sad, the dialogue management unit can make the tone of the conversation gentle and provide comforting content. If the user is excited, the dialogue management unit can make the tone brighter and provide content that shares their excitement. Furthermore, if the user is angry, the dialogue management unit can calm the tone of the conversation and provide content that responds calmly. The personalization unit personalizes the interaction with the user based on the conversation conducted by the dialogue management unit. For example, the personalization unit can use machine learning techniques to learn the user's past behavior history, preferences, and interests, and personalize the interaction. It can also customize the interaction based on the user's current situation and interests. Furthermore, the personalization unit can adjust the method of interaction based on the user's emotions. For example, if the user is sad, the personalization unit can provide comforting content.Furthermore, the personalization unit can provide content that shares the user's excitement if the user is excited. Additionally, if the user is angry, the personalization unit can provide content that responds calmly. This allows the communication agent system according to the embodiment to understand the user's emotions and personalize dialogue management and interaction based on those emotions.

[0030] The emotion recognition unit employs a variety of technologies to understand the user's emotions. Specifically, it can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. For example, by capturing the user's face through a camera and having the AI ​​analyze subtle changes in facial expression, it can estimate emotions such as joy, sadness, anger, and surprise with high accuracy. The emotion recognition unit can also analyze the tone of the user's voice using voice analysis technology and estimate their emotions. The AI ​​analyzes voice data collected through a microphone and estimates emotions from changes in voice pitch, tempo, and volume. For example, a high-pitched, fast voice is judged to indicate excitement, while a low-pitched, slow voice is judged to indicate calmness. Furthermore, the emotion recognition unit can analyze the user's text messages using text analysis technology and estimate their emotions. Using natural language processing technology, it analyzes the content and context of the text to identify positive and negative emotions. For example, if the text contains words like "happy" or "joyful," it estimates positive emotions, while conversely, if it contains words like "sad" or "angry," it estimates negative emotions. This allows the emotion recognition unit to comprehensively understand the user's emotions from facial expressions, voice, and text, enabling more accurate emotion estimation. By combining these technologies, the emotion recognition unit can capture the user's emotions from multiple perspectives and track emotional changes in real time. As a result, the emotion recognition unit can quickly and accurately understand the user's emotions and reflect them in subsequent conversations and interactions.

[0031] The dialogue management unit performs advanced dialogue management based on emotions understood by the emotion recognition unit. Specifically, it can understand the user's intent using natural language processing technology and generate appropriate responses. For example, if a user says, "I'm tired today," the dialogue management unit understands that intent and suggests ways to relax. The dialogue management unit can also manage the flow of the dialogue and conduct conversations in accordance with the user's intent. For example, if a user asks a question, it provides an appropriate answer to that question and further provides related information to facilitate the conversation. Furthermore, the dialogue management unit can adjust the tone and content of the dialogue according to the user's emotions. For example, if a user is sad, it can make the tone of the dialogue gentle and provide comforting content. If a user is excited, it can make the tone of the dialogue cheerful and provide content that shares their excitement. Furthermore, if a user is angry, it can make the tone of the dialogue calm and provide content that responds calmly. By combining these functions, the dialogue management unit can achieve flexible dialogues that respond to the user's emotions and improve user satisfaction. The dialogue management unit receives information from the emotion recognition unit in real time and immediately adjusts the content and tone of the dialogue to provide dialogues that are attentive to the user's emotions. Furthermore, the dialogue management unit can achieve more personalized conversations by referring to past conversation history and learning user preferences and patterns. This allows the dialogue management unit to provide appropriate conversations that respond to the user's emotions and build a relationship of trust with the user.

[0032] The Personalization Unit personalizes user interactions based on conversations conducted by the Dialogue Management Unit. Specifically, it can use machine learning technology to learn the user's past behavior history, preferences, and interests, and personalize interactions accordingly. For example, it can learn topics the user has shown interest in in the past and features they frequently use, and provide relevant information and services based on that. The Personalization Unit can also customize interactions based on the user's current situation and interests. For example, if the user is currently traveling, it can provide travel-related information and services. Furthermore, the Personalization Unit can adjust the way it interacts based on the user's emotions. For example, if the user is sad, it can provide comforting content. If the user is excited, it can provide content that shares their excitement. Furthermore, if the user is angry, it can provide content that calms them down. By combining these functions, the Personalization Unit can provide optimal interactions tailored to the user's emotions and situation, thereby improving user satisfaction. The Personalization Unit receives information from the Dialogue Management Unit in real time and instantly adjusts interactions according to the user's emotions and situation. The Personalization Unit can also collect user feedback and continuously improve the accuracy and effectiveness of interactions. For example, by analyzing how users react to the content provided and reviewing the interaction methods based on the results, the personalization unit can consistently provide users with the most optimal interaction, thereby increasing user satisfaction.

[0033] The communication agent system includes a business support department that provides corporate clients with business process efficiency improvements and enhanced customer service. The business support department can, for example, optimize business workflows. It analyzes business processes and reduces unnecessary steps to improve efficiency. It can also optimize resource allocation. The business support department monitors resource usage and reallocates resources as needed. Furthermore, the business support department can expedite customer responses. It processes customer inquiries quickly and provides appropriate responses. For example, it automatically categorizes customer inquiries and assigns them to the appropriate personnel. It can also refer to a customer's past inquiry history to provide prompt responses. Additionally, the business support department can personalize services. It learns a customer's past behavior and preferences to provide services tailored to individual needs. For example, it refers to a customer's past purchase history and suggests relevant products and services. It can also provide customized services based on customer preferences. This enables the system to provide corporate clients with business process efficiency improvements and enhanced customer service.

[0034] The communication agent system includes a personal support unit that provides individual users with improved quality of life and entertainment. The personal support unit can, for example, provide health management support. It monitors users' health data and manages their health status. It can also provide health advice to users. For example, it analyzes users' diet and exercise records and suggests healthy lifestyle habits. Furthermore, the personal support unit can support time management. It manages users' schedules and suggests efficient time use. For example, it supports efficient time management by organizing and prioritizing users' appointments. The personal support unit can also support stress reduction. It monitors users' stress levels and suggests ways to relax. For example, it provides users with relaxing music and meditation content. Finally, the personal support unit can provide entertainment. It provides entertainment content such as games, music, and movies based on users' preferences. For example, it refers to users' past viewing history and suggests relevant content. Furthermore, the Personal Support Department can also provide entertainment content customized based on user preferences. This makes it possible to improve the quality of life and provide entertainment for individual users.

[0035] The emotion recognition unit can understand the user's emotions using emotion recognition technology. For example, the emotion recognition unit can analyze the user's facial expressions using facial expression recognition technology and estimate their emotions. The emotion recognition unit extracts the features of the facial expressions, and the AI ​​estimates the emotions based on those features. The emotion recognition unit can also analyze the tone of the user's voice using speech recognition technology and estimate their emotions. The emotion recognition unit analyzes the pitch and tempo of the voice, and the AI ​​estimates the emotions based on that data. Furthermore, the emotion recognition unit can analyze the user's text messages using text analysis technology and estimate their emotions. The emotion recognition unit analyzes the content of the text, and the AI ​​estimates the emotions from that content. In this way, by using emotion recognition technology, the user's emotions can be accurately understood. Some or all of the above-described processes in the emotion recognition unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the emotion recognition unit can input the user's facial expression data into a generative AI, and the generative AI can analyze the features of the facial expressions and estimate the emotions.

[0036] The dialogue management unit can perform advanced dialogue management using natural language processing. For example, the dialogue management unit can analyze user utterances using morphological analysis techniques to understand the meaning of words. The dialogue management unit performs morphological analysis, divides the words in the utterance, and analyzes the meaning of each word. The dialogue management unit can also analyze the grammatical structure of utterances using grammatical analysis techniques to understand the meaning of sentences. The dialogue management unit performs grammatical analysis, analyzes the grammatical structure of utterances, and understands the meaning of sentences. Furthermore, the dialogue management unit can also understand the intent of utterances using semantic analysis techniques. The dialogue management unit performs semantic analysis, analyzes the intent of utterances, and generates appropriate responses. In this way, advanced dialogue management becomes possible by using natural language processing. Some or all of the above-described processes in the dialogue management unit may be performed using, for example, a generative AI, or they may not be performed using a generative AI. For example, the dialogue management unit can input user utterance data into a generative AI, which can analyze the meaning of the utterances and generate appropriate responses.

[0037] The personalization unit can personalize user interactions by utilizing machine learning. For example, the personalization unit can learn the user's past behavior history using supervised learning techniques and personalize the interaction. The personalization unit collects the user's past behavior data and learns from that data using a supervised learning algorithm. The personalization unit can also personalize interactions by clustering the user's preferences and interests using unsupervised learning techniques. The personalization unit clusters the user's behavior data and identifies the user's preferences and interests. Furthermore, the personalization unit can optimize user interactions using reinforcement learning techniques. The personalization unit optimizes interactions using a reinforcement learning algorithm based on feedback obtained through user interactions. In this way, user interactions can be personalized by utilizing machine learning. Some or all of the above processes in the personalization unit may be performed using, for example, generative AI, or not using generative AI. For example, the personalization unit can input user behavior data into a generative AI, and the generative AI can learn from that data and personalize the interaction.

[0038] The Business Support Department can select the optimal support method by referring to the past business data of corporate clients when providing business support. For example, the Business Support Department can store the past business data of corporate clients in a database, and the AI ​​can select the optimal support method. The Business Support Department can refer to past business data, and the AI ​​can select the optimal support method based on that data. The Business Support Department can also analyze the past business data of corporate clients in chronological order, and the AI ​​can learn patterns of support methods. The Business Support Department can analyze past business data in chronological order, and the AI ​​can learn patterns of support methods based on that data. Furthermore, the Business Support Department can store the past business data of corporate clients in the cloud, and the AI ​​can access that data in real time to select the optimal support method. The Business Support Department can store past business data in the cloud, and the AI ​​can refer to that data in real time to select the optimal support method. This allows the optimal support method to be selected by referring to past business data. Some or all of the above processes in the Business Support Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Business Support Department can input the past business data of corporate clients into a generative AI, and the generative AI can select the optimal support method based on that data.

[0039] The Business Support Department can select the optimal support method when providing business support, taking into account the geographical location information of corporate clients. For example, if a corporate client is in a specific location, the Business Support Department can provide support methods relevant to that location. The Business Support Department provides support methods relevant to that location based on geographical location information. The Business Support Department can also analyze the corporate client's travel history and customize support methods for specific locations. The Business Support Department analyzes travel history and customizes support methods for specific locations. Furthermore, the Business Support Department can combine the corporate client's current location with past business data and adjust support methods in real time. The Business Support Department analyzes the combination of current location and past business data and adjusts support methods in real time. This allows for the selection of the optimal support method by considering geographical location information. Some or all of the above processing in the Business Support Department may be performed using, for example, a generative AI, or without a generative AI. For example, the Business Support Department can input the corporate client's geographical location data into a generative AI, and the generative AI can select a support method based on that data.

[0040] The Personal Support Department can select the optimal support method by referring to the individual user's past life data when providing personal support. For example, the Personal Support Department can store the individual user's past life data in a database, and the AI ​​can select the optimal support method. The Personal Support Department can refer to past life data, and the AI ​​can select the optimal support method based on that data. The Personal Support Department can also analyze the individual user's past life data in chronological order, and the AI ​​can learn patterns of support methods. The Personal Support Department can analyze past life data in chronological order, and the AI ​​can learn patterns of support methods based on that data. Furthermore, the Personal Support Department can store the individual user's past life data in the cloud, and the AI ​​can access that data in real time to select the optimal support method. The Personal Support Department can store past life data in the cloud, and the AI ​​can refer to that data in real time to select the optimal support method. This allows the optimal support method to be selected by referring to past life data. Some or all of the above processes in the Personal Support Department may be performed using, for example, a generative AI, or without using a generative AI. For example, the Personal Support Department can input a user's past lifestyle data into a generating AI, which can then select the most suitable support method based on that data.

[0041] The Personal Support Unit can select the optimal support method when providing personal support, taking into account the geographical location information of the individual user. For example, if an individual user is in a specific location, the Personal Support Unit can provide support methods relevant to that location. The Personal Support Unit provides support methods relevant to that location based on geographical location information. The Personal Support Unit can also analyze the individual user's travel history and customize support methods for specific locations. The Personal Support Unit analyzes the travel history and customizes support methods for specific locations. Furthermore, the Personal Support Unit can combine the individual user's current location with past lifestyle data and adjust support methods in real time. The Personal Support Unit analyzes the combination of current location and past lifestyle data and adjusts support methods in real time. This allows for the selection of the optimal support method by considering geographical location information. Some or all of the above processing in the Personal Support Unit may be performed using, for example, a generative AI, or without a generative AI. For example, the Personal Support Unit can input the individual user's geographical location data into a generative AI, which can then select a support method based on that data.

[0042] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0043] Communication agent systems can achieve more natural dialogue by referencing the user's past dialogue history and learning dialogue patterns. For example, the dialogue management unit stores the user's past dialogue history in a database, and the AI ​​learns dialogue patterns based on that data. The dialogue management unit can also analyze the user's past dialogue history chronologically and predict the flow of the conversation. Furthermore, the dialogue management unit can store the user's past dialogue history in the cloud, and the AI ​​can access it in real time to learn dialogue patterns. This allows for more natural dialogue by referring to past dialogue history.

[0044] The communication agent system can customize the content of conversations based on the user's current situation and interests. For example, the conversation management unit can capture the user's current situation with sensors, and the AI ​​can customize the conversation content based on that data. The conversation management unit can also store the user's interests in a database, and the AI ​​can customize the conversation content based on that data. Furthermore, the conversation management unit can simultaneously analyze the user's current situation and interests, and the AI ​​can customize the conversation content in a comprehensive manner. This allows for more appropriate conversations by customizing the content based on the current situation and interests.

[0045] The communication agent system can adjust the content of conversations by taking into account the user's geographical location. For example, the conversation management unit can provide location-related information if the user is in a specific location. The conversation management unit can also analyze the user's movement history and customize the conversation content for specific locations. Furthermore, the conversation management unit can combine the user's current location with past conversation history to adjust the conversation content in real time. This allows for more appropriate adjustment of conversation content by considering geographical location information.

[0046] The communication agent system can analyze a user's social media activity and adjust the content of the conversation accordingly. For example, the conversation management unit can analyze a user's social media posts and adjust the conversation based on the content of those posts. The conversation management unit can also analyze a user's social media reactions (likes, comments, etc.) and adjust the conversation accordingly. Furthermore, the conversation management unit can analyze the time of day a user is active on social media and adjust the conversation for specific time periods. This allows for more appropriate adjustment of conversation content by analyzing social media activity.

[0047] A communication agent system can select the optimal personalization method by referring to a user's past interaction data. For example, the personalization unit can store the user's past interaction data in a database, and the AI ​​can select the optimal personalization method based on that data. The personalization unit can also analyze the user's past interaction data in chronological order and learn personalization patterns. Furthermore, the personalization unit can store the user's past interaction data in the cloud, and the AI ​​can access it in real time to select the personalization method. This allows the system to select the optimal personalization method by referring to past interaction data.

[0048] The following briefly describes the processing flow for example form 1.

[0049] Step 1: The emotion recognition unit understands the user's emotions. The emotion recognition unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. It can also analyze the tone of the user's voice using voice analysis technology and estimate their emotions. Furthermore, it can analyze the user's text messages using text analysis technology and estimate their emotions. For example, the emotion recognition unit can capture the user's facial expressions with a camera, and the AI ​​will analyze subtle changes in facial expressions to estimate their emotions. It can also collect the tone of the user's voice with a microphone, and the AI ​​will analyze the pitch and tempo of the voice to estimate their emotions. Furthermore, it can analyze the user's text messages, and the AI ​​will estimate their emotions from the content of the text. Step 2: The dialogue management unit performs advanced dialogue management based on the emotions understood by the emotion recognition unit. The dialogue management unit can understand the user's intent using natural language processing technology and generate appropriate responses. It can also manage the flow of the dialogue and conduct conversations in accordance with the user's intent. Furthermore, it can adjust the tone and content of the dialogue according to the user's emotions. For example, if the user is sad, the dialogue tone can be made gentle and comforting content can be provided. If the user is excited, the dialogue tone can be made cheerful and content that shares the excitement can be provided. Furthermore, if the user is angry, the dialogue tone can be made calm and content that responds calmly can be provided. Step 3: The personalization unit personalizes the interaction with the user based on the conversation conducted by the dialogue management unit. The personalization unit can learn the user's past behavior history, preferences, and interests using machine learning technology to personalize the interaction. It can also customize the interaction based on the user's current situation and interests. Furthermore, it can adjust the method of interaction based on the user's emotions. For example, if the user is sad, it can provide comforting content. If the user is excited, it can provide content that shares their excitement. Furthermore, if the user is angry, it can provide content that calms them down.

[0050] (Example of form 2) The communication agent system according to an embodiment of the present invention is a system that provides customized conversational services to corporate and individual users by utilizing AI and robotics. This system understands the user's emotions using emotion recognition technology, performs advanced dialogue management using natural language processing, and personalizes user interactions using machine learning. For example, the communication agent system can recognize the user's emotions in real time and generate appropriate responses. For example, if the user is feeling stressed, the system can provide relaxing content. Also, if the user is excited, the system can provide content that shares that excitement. Furthermore, the communication agent system can provide corporate clients with improved business process efficiency and enhanced customer service. For example, the system streamlines business processes by optimizing workflows and optimally allocating resources. It can also improve customer service by accelerating customer responses and personalizing services. For individual users, it can improve the quality of daily life and provide entertainment. For example, the system can provide support for health management, time management, and stress reduction. It can also provide entertainment content such as games, music, and movies. As a result, the communication agent system achieves improved user satisfaction, increased engagement, and faster problem-solving speed. Furthermore, we aim to create new user experiences through the fusion of AI and robotics, and to continuously improve services through sustainable technological advancements. This will enable the communication agent system to understand user emotions and personalize dialogue management and interactions based on those emotions.

[0051] The communication agent system according to this embodiment comprises an emotion recognition unit, a dialogue management unit, and a personalization unit. The emotion recognition unit understands the user's emotions. For example, the emotion recognition unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. The emotion recognition unit can also analyze the tone of the user's voice using voice analysis technology and estimate their emotions. Furthermore, the emotion recognition unit can analyze the user's text messages using text analysis technology and estimate their emotions. For example, the emotion recognition unit can capture the user's facial expressions with a camera, and the AI ​​can analyze subtle changes in facial expressions to estimate their emotions. The emotion recognition unit can also collect the tone of the user's voice with a microphone, and the AI ​​can analyze the pitch and tempo of the voice to estimate their emotions. Furthermore, the emotion recognition unit can analyze the user's text messages, and the AI ​​can estimate their emotions from the content of the text. The dialogue management unit performs advanced dialogue management based on the emotions understood by the emotion recognition unit. For example, the dialogue management unit can understand the user's intentions using natural language processing technology and generate appropriate responses. Furthermore, the dialogue management unit can manage the flow of the conversation and conduct conversations that are tailored to the user's intentions. It can also adjust the tone and content of the conversation according to the user's emotions. For example, if the user is sad, the dialogue management unit can make the tone of the conversation gentle and provide comforting content. If the user is excited, the dialogue management unit can make the tone brighter and provide content that shares their excitement. Furthermore, if the user is angry, the dialogue management unit can calm the tone of the conversation and provide content that responds calmly. The personalization unit personalizes the interaction with the user based on the conversation conducted by the dialogue management unit. For example, the personalization unit can use machine learning techniques to learn the user's past behavior history, preferences, and interests, and personalize the interaction. It can also customize the interaction based on the user's current situation and interests. Furthermore, the personalization unit can adjust the method of interaction based on the user's emotions. For example, if the user is sad, the personalization unit can provide comforting content.Furthermore, the personalization unit can provide content that shares the user's excitement if the user is excited. Additionally, if the user is angry, the personalization unit can provide content that responds calmly. This allows the communication agent system according to the embodiment to understand the user's emotions and personalize dialogue management and interaction based on those emotions.

[0052] The emotion recognition unit employs a variety of technologies to understand the user's emotions. Specifically, it can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. For example, by capturing the user's face through a camera and having the AI ​​analyze subtle changes in facial expression, it can estimate emotions such as joy, sadness, anger, and surprise with high accuracy. The emotion recognition unit can also analyze the tone of the user's voice using voice analysis technology and estimate their emotions. The AI ​​analyzes voice data collected through a microphone and estimates emotions from changes in voice pitch, tempo, and volume. For example, a high-pitched, fast voice is judged to indicate excitement, while a low-pitched, slow voice is judged to indicate calmness. Furthermore, the emotion recognition unit can analyze the user's text messages using text analysis technology and estimate their emotions. Using natural language processing technology, it analyzes the content and context of the text to identify positive and negative emotions. For example, if the text contains words like "happy" or "joyful," it estimates positive emotions, while conversely, if it contains words like "sad" or "angry," it estimates negative emotions. This allows the emotion recognition unit to comprehensively understand the user's emotions from facial expressions, voice, and text, enabling more accurate emotion estimation. By combining these technologies, the emotion recognition unit can capture the user's emotions from multiple perspectives and track emotional changes in real time. As a result, the emotion recognition unit can quickly and accurately understand the user's emotions and reflect them in subsequent conversations and interactions.

[0053] The dialogue management unit performs advanced dialogue management based on emotions understood by the emotion recognition unit. Specifically, it can understand the user's intent using natural language processing technology and generate appropriate responses. For example, if a user says, "I'm tired today," the dialogue management unit understands that intent and suggests ways to relax. The dialogue management unit can also manage the flow of the dialogue and conduct conversations in accordance with the user's intent. For example, if a user asks a question, it provides an appropriate answer to that question and further provides related information to facilitate the conversation. Furthermore, the dialogue management unit can adjust the tone and content of the dialogue according to the user's emotions. For example, if a user is sad, it can make the tone of the dialogue gentle and provide comforting content. If a user is excited, it can make the tone of the dialogue cheerful and provide content that shares their excitement. Furthermore, if a user is angry, it can make the tone of the dialogue calm and provide content that responds calmly. By combining these functions, the dialogue management unit can achieve flexible dialogues that respond to the user's emotions and improve user satisfaction. The dialogue management unit receives information from the emotion recognition unit in real time and immediately adjusts the content and tone of the dialogue to provide dialogues that are attentive to the user's emotions. Furthermore, the dialogue management unit can achieve more personalized conversations by referring to past conversation history and learning user preferences and patterns. This allows the dialogue management unit to provide appropriate conversations that respond to the user's emotions and build a relationship of trust with the user.

[0054] The Personalization Unit personalizes user interactions based on conversations conducted by the Dialogue Management Unit. Specifically, it can use machine learning technology to learn the user's past behavior history, preferences, and interests, and personalize interactions accordingly. For example, it can learn topics the user has shown interest in in the past and features they frequently use, and provide relevant information and services based on that. The Personalization Unit can also customize interactions based on the user's current situation and interests. For example, if the user is currently traveling, it can provide travel-related information and services. Furthermore, the Personalization Unit can adjust the way it interacts based on the user's emotions. For example, if the user is sad, it can provide comforting content. If the user is excited, it can provide content that shares their excitement. Furthermore, if the user is angry, it can provide content that calms them down. By combining these functions, the Personalization Unit can provide optimal interactions tailored to the user's emotions and situation, thereby improving user satisfaction. The Personalization Unit receives information from the Dialogue Management Unit in real time and instantly adjusts interactions according to the user's emotions and situation. The Personalization Unit can also collect user feedback and continuously improve the accuracy and effectiveness of interactions. For example, by analyzing how users react to the content provided and reviewing the interaction methods based on the results, the personalization unit can consistently provide users with the most optimal interaction, thereby increasing user satisfaction.

[0055] The communication agent system includes a business support department that provides corporate clients with business process efficiency improvements and enhanced customer service. The business support department can, for example, optimize business workflows. It analyzes business processes and reduces unnecessary steps to improve efficiency. It can also optimize resource allocation. The business support department monitors resource usage and reallocates resources as needed. Furthermore, the business support department can expedite customer responses. It processes customer inquiries quickly and provides appropriate responses. For example, it automatically categorizes customer inquiries and assigns them to the appropriate personnel. It can also refer to a customer's past inquiry history to provide prompt responses. Additionally, the business support department can personalize services. It learns a customer's past behavior and preferences to provide services tailored to individual needs. For example, it refers to a customer's past purchase history and suggests relevant products and services. It can also provide customized services based on customer preferences. This enables the system to provide corporate clients with business process efficiency improvements and enhanced customer service.

[0056] The communication agent system includes a personal support unit that provides individual users with improved quality of life and entertainment. The personal support unit can, for example, provide health management support. It monitors users' health data and manages their health status. It can also provide health advice to users. For example, it analyzes users' diet and exercise records and suggests healthy lifestyle habits. Furthermore, the personal support unit can support time management. It manages users' schedules and suggests efficient time use. For example, it supports efficient time management by organizing and prioritizing users' appointments. The personal support unit can also support stress reduction. It monitors users' stress levels and suggests ways to relax. For example, it provides users with relaxing music and meditation content. Finally, the personal support unit can provide entertainment. It provides entertainment content such as games, music, and movies based on users' preferences. For example, it refers to users' past viewing history and suggests relevant content. Furthermore, the Personal Support Department can also provide entertainment content customized based on user preferences. This makes it possible to improve the quality of life and provide entertainment for individual users.

[0057] The emotion recognition unit can understand the user's emotions using emotion recognition technology. For example, the emotion recognition unit can analyze the user's facial expressions using facial expression recognition technology and estimate their emotions. The emotion recognition unit extracts the features of the facial expressions, and the AI ​​estimates the emotions based on those features. The emotion recognition unit can also analyze the tone of the user's voice using speech recognition technology and estimate their emotions. The emotion recognition unit analyzes the pitch and tempo of the voice, and the AI ​​estimates the emotions based on that data. Furthermore, the emotion recognition unit can analyze the user's text messages using text analysis technology and estimate their emotions. The emotion recognition unit analyzes the content of the text, and the AI ​​estimates the emotions from that content. In this way, by using emotion recognition technology, the user's emotions can be accurately understood. Some or all of the above-described processes in the emotion recognition unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the emotion recognition unit can input the user's facial expression data into a generative AI, and the generative AI can analyze the features of the facial expressions and estimate the emotions.

[0058] The dialogue management unit can perform advanced dialogue management using natural language processing. For example, the dialogue management unit can analyze user utterances using morphological analysis techniques to understand the meaning of words. The dialogue management unit performs morphological analysis, divides the words in the utterance, and analyzes the meaning of each word. The dialogue management unit can also analyze the grammatical structure of utterances using grammatical analysis techniques to understand the meaning of sentences. The dialogue management unit performs grammatical analysis, analyzes the grammatical structure of utterances, and understands the meaning of sentences. Furthermore, the dialogue management unit can also understand the intent of utterances using semantic analysis techniques. The dialogue management unit performs semantic analysis, analyzes the intent of utterances, and generates appropriate responses. In this way, advanced dialogue management becomes possible by using natural language processing. Some or all of the above-described processes in the dialogue management unit may be performed using, for example, a generative AI, or they may not be performed using a generative AI. For example, the dialogue management unit can input user utterance data into a generative AI, which can analyze the meaning of the utterances and generate appropriate responses.

[0059] The personalization unit can personalize user interactions by utilizing machine learning. For example, the personalization unit can learn the user's past behavior history using supervised learning techniques and personalize the interaction. The personalization unit collects the user's past behavior data and learns from that data using a supervised learning algorithm. The personalization unit can also personalize interactions by clustering the user's preferences and interests using unsupervised learning techniques. The personalization unit clusters the user's behavior data and identifies the user's preferences and interests. Furthermore, the personalization unit can optimize user interactions using reinforcement learning techniques. The personalization unit optimizes interactions using a reinforcement learning algorithm based on feedback obtained through user interactions. In this way, user interactions can be personalized by utilizing machine learning. Some or all of the above processes in the personalization unit may be performed using, for example, generative AI, or not using generative AI. For example, the personalization unit can input user behavior data into a generative AI, and the generative AI can learn from that data and personalize the interaction.

[0060] The emotion recognition unit can analyze the user's facial expressions and voice tone, estimate emotions, and improve the accuracy of emotion recognition based on the estimated emotions. For example, the emotion recognition unit can capture the user's facial expressions with a camera, and the AI ​​analyzes subtle changes in facial expressions to estimate emotions. The emotion recognition unit extracts features of the facial expressions, and the AI ​​estimates emotions based on those features. The emotion recognition unit can also collect the user's voice tone with a microphone, and the AI ​​analyzes the pitch and tempo of the voice to estimate emotions. The emotion recognition unit extracts features of the voice, and the AI ​​estimates emotions based on those features. Furthermore, the emotion recognition unit can simultaneously analyze the user's facial expressions and voice tone, and the AI ​​estimates emotions in a combined manner. The emotion recognition unit analyzes the features of facial expressions and voice in combination, and the AI ​​estimates emotions based on that data. This improves the accuracy of emotion recognition by analyzing the user's facial expressions and voice tone. Some or all of the above processing in the emotion recognition unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the emotion recognition unit can input user facial expression data and voice data into a generating AI, which can then analyze the data to estimate emotions.

[0061] The emotion recognition unit can refer to the user's past emotional data to more accurately recognize the current emotion. For example, the emotion recognition unit can store the user's past emotional data in a database, and the AI ​​can compare it with the current emotion for recognition. The emotion recognition unit refers to past emotional data, and the AI ​​recognizes the current emotion based on that data. The emotion recognition unit can also analyze the user's past emotional data in chronological order, and the AI ​​can learn patterns of emotion change. The emotion recognition unit analyzes past emotional data in chronological order, and the AI ​​learns patterns of emotion change based on that data. Furthermore, the emotion recognition unit can store the user's past emotional data in the cloud, and the AI ​​can access and recognize it in real time. The emotion recognition unit stores past emotional data in the cloud, and the AI ​​refers to that data in real time to recognize the current emotion. This allows for a more accurate recognition of the current emotion by referring to past emotional data. Some or all of the above processes in the emotion recognition unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the emotion recognition unit can input the user's past emotional data into a generative AI, and the generative AI can recognize the current emotion based on that data.

[0062] The emotion recognition unit can understand emotions by analyzing the user's physical movements and posture during emotion recognition. For example, the emotion recognition unit can capture the user's physical movements with sensors, and the AI ​​analyzes the movement patterns to estimate emotions. The emotion recognition unit extracts the characteristics of the physical movements, and the AI ​​estimates emotions based on those characteristics. The emotion recognition unit can also capture the user's posture with a camera, and the AI ​​analyzes the changes in posture to estimate emotions. The emotion recognition unit extracts the characteristics of the posture, and the AI ​​estimates emotions based on those characteristics. Furthermore, the emotion recognition unit can simultaneously analyze the user's physical movements and posture, and the AI ​​can understand emotions in a comprehensive manner. The emotion recognition unit analyzes the characteristics of physical movements and posture in combination, and the AI ​​understands emotions based on that data. This allows for a deeper understanding of emotions by analyzing physical movements and posture. Some or all of the above-described processes in the emotion recognition unit may be performed using, for example, generative AI, or without using generative AI. For example, the emotion recognition unit inputs the user's physical movement data and posture data into a generating AI, which then analyzes that data to understand emotions.

[0063] The emotion recognition unit can estimate the user's emotions and adjust the timing of emotion recognition based on the estimated emotions. For example, if the user is stressed, the emotion recognition unit can reduce the frequency of emotion recognition to alleviate the burden. The emotion recognition unit monitors the user's emotional state and reduces the frequency of emotion recognition if the user is stressed. The emotion recognition unit can also increase the frequency of emotion recognition to collect more detailed data if the user is relaxed. The emotion recognition unit monitors the user's emotional state and increases the frequency of emotion recognition if the user is relaxed. Furthermore, if the user's emotions change rapidly, the emotion recognition unit can adjust the timing of emotion recognition in real time. The emotion recognition unit monitors the user's emotional state in real time and adjusts the timing of emotion recognition if the emotions change rapidly. By adjusting the timing of emotion recognition, the burden on the user can be reduced. Some or all of the above processing in the emotion recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the emotion recognition unit can input the user's emotional state data into a generative AI, and the generative AI can adjust the timing of emotion recognition based on that data.

[0064] The emotion recognition unit can recognize changes in emotion by considering the user's geographical location information during emotion recognition. For example, if the user is in a specific location, the emotion recognition unit recognizes the emotion by referring to emotion data associated with that location. The emotion recognition unit recognizes the emotion by referring to emotion data associated with that location based on geographical location information. The emotion recognition unit can also analyze the user's travel history and learn patterns of changes in emotion at specific locations. The emotion recognition unit analyzes the travel history and learns patterns of changes in emotion at specific locations. Furthermore, the emotion recognition unit can combine the user's current location with past emotion data to recognize changes in emotion in real time. The emotion recognition unit analyzes the combination of the current location and past emotion data to recognize changes in emotion in real time. This allows for more accurate recognition of changes in emotion by considering geographical location information. Some or all of the above processing in the emotion recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the emotion recognition unit can input the user's geographical location information data into a generative AI, and the generative AI can recognize changes in emotion based on that data.

[0065] The emotion recognition unit can analyze a user's social media activity and recognize changes in their emotions during emotion recognition. For example, the emotion recognition unit can analyze a user's social media posts and estimate their emotions from the content of the posts. The emotion recognition unit analyzes the content of the posts, and the AI ​​estimates the emotions based on that content. The emotion recognition unit can also analyze a user's social media reactions (likes, comments, etc.) and recognize changes in their emotions. The emotion recognition unit analyzes the reaction data, and the AI ​​recognizes changes in their emotions based on that data. Furthermore, the emotion recognition unit can analyze the time of day of a user's social media activity and recognize changes in their emotions at specific times. The emotion recognition unit analyzes the time of day of activity, and the AI ​​recognizes changes in their emotions based on that data. In this way, changes in emotions can be recognized by analyzing social media activity. Some or all of the above processing in the emotion recognition unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input the user's social media data into a generative AI, and the generative AI can recognize changes in their emotions based on that data.

[0066] The dialogue management unit can estimate the user's emotions and adjust the tone and content of the dialogue based on the estimated emotions. For example, if the user is sad, the dialogue management unit can make the tone of the dialogue gentle and provide comforting content. The dialogue management unit monitors the user's emotional state and, if sad, adjusts the tone of the dialogue gently and provides comforting content. The dialogue management unit can also make the tone of the dialogue brighter and provide content that shares the excitement if the user is excited. The dialogue management unit monitors the user's emotional state and, if excited, adjusts the tone of the dialogue brighter and provides content that shares the excitement. Furthermore, if the user is angry, the dialogue management unit can also calm the tone of the dialogue and provide content that responds calmly. The dialogue management unit monitors the user's emotional state and, if angry, calms the tone of the dialogue and provides content that responds calmly. This allows for more appropriate dialogue by adjusting the tone and content of the dialogue based on emotions. Some or all of the above processing in the dialogue management unit may be performed using, for example, generative AI, or not using generative AI. For example, the dialogue management unit can input user emotional state data into a generating AI, which can then adjust the tone and content of the dialogue based on that data.

[0067] The dialogue management unit can select the optimal dialogue method by referring to the user's past dialogue history during dialogue management. For example, the dialogue management unit can store the user's past dialogue history in a database, and the AI ​​can select the optimal dialogue method. The dialogue management unit refers to past dialogue history, and the AI ​​selects the optimal dialogue method based on that data. The dialogue management unit can also analyze the user's past dialogue history in chronological order, and the AI ​​can learn dialogue patterns. The dialogue management unit analyzes past dialogue history in chronological order, and the AI ​​learns dialogue patterns based on that data. Furthermore, the dialogue management unit can store the user's past dialogue history in the cloud, and the AI ​​can access it in real time to select the optimal dialogue method. The dialogue management unit stores past dialogue history in the cloud, and the AI ​​refers to that data in real time to select the optimal dialogue method. This allows the optimal dialogue method to be selected by referring to past dialogue history. Some or all of the above processes in the dialogue management unit may be performed using, for example, generative AI, or without using generative AI. For example, the dialogue management unit can input the user's past dialogue history data into a generating AI, which can then select the optimal dialogue method based on that data.

[0068] The dialogue management unit can customize dialogue content based on the user's current situation and interests during dialogue management. For example, the dialogue management unit can capture the user's current situation with sensors, and the AI ​​can customize the dialogue content based on that data. The dialogue management unit can also save the user's interests in a database, and the AI ​​can customize the dialogue content based on that data. Furthermore, the dialogue management unit can simultaneously analyze the user's current situation and interests, and the AI ​​can customize the dialogue content in a complex manner. This allows for more appropriate dialogue by customizing the dialogue content based on the current situation and interests. Some or all of the above-described processes in the dialogue management unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue management unit can input the user's current situation data and interest data into a generative AI, and the generative AI can customize the dialogue content based on that data.

[0069] The dialogue management unit can estimate the user's emotions and determine the priority of the dialogue based on the estimated emotions. For example, if the user is showing an urgent emotion, the dialogue management unit will set a higher priority for the dialogue. The dialogue management unit monitors the user's emotional state and sets a higher priority for the dialogue if the user is showing an urgent emotion. The dialogue management unit can also set a lower priority for the dialogue if the user is relaxed. The dialogue management unit monitors the user's emotional state and sets a lower priority for the dialogue if the user is relaxed. Furthermore, if the user's emotions change rapidly, the dialogue management unit can adjust the dialogue priority in real time. The dialogue management unit monitors the user's emotional state in real time and adjusts the dialogue priority if the emotions change rapidly. This allows for more appropriate dialogue by determining the priority of the dialogue based on emotions. Some or all of the above processing in the dialogue management unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue management unit can input the user's emotional state data into a generative AI, and the generative AI can determine the priority of the dialogue based on that data.

[0070] The dialogue management unit can adjust the dialogue content while considering the user's geographical location information during dialogue management. For example, if the user is in a specific location, the dialogue management unit provides information related to that location. The dialogue management unit provides information related to the location based on the geographical location information. The dialogue management unit can also analyze the user's movement history and customize the dialogue content for specific locations. The dialogue management unit analyzes the movement history and customizes the dialogue content for specific locations. Furthermore, the dialogue management unit can combine the user's current location and past dialogue history to adjust the dialogue content in real time. The dialogue management unit analyzes the current location and past dialogue history in combination and adjusts the dialogue content in real time. This allows for more appropriate adjustment of the dialogue content by considering geographical location information. Some or all of the above processing in the dialogue management unit may be performed using, for example, a generative AI, or without a generative AI. For example, the dialogue management unit can input the user's geographical location information data into a generative AI, and the generative AI can adjust the dialogue content based on that data.

[0071] The dialogue management unit can analyze the user's social media activity and adjust the dialogue content during dialogue management. For example, the dialogue management unit can analyze the user's social media posts and adjust the dialogue content based on the content of the posts. The dialogue management unit analyzes the content of the posts, and the AI ​​adjusts the dialogue content based on that content. The dialogue management unit can also analyze the user's social media reactions (likes, comments, etc.) and adjust the dialogue content. The dialogue management unit analyzes the reaction data, and the AI ​​adjusts the dialogue content based on that data. Furthermore, the dialogue management unit can analyze the time of day of the user's social media activity and adjust the dialogue content for specific time periods. The dialogue management unit analyzes the time of day of activity, and the AI ​​adjusts the dialogue content based on that data. In this way, by analyzing social media activity, the dialogue content can be adjusted more appropriately. Some or all of the above processing in the dialogue management unit may be performed using, for example, a generative AI, or without a generative AI. For example, the dialogue management unit can input the user's social media data into a generative AI, and the generative AI can adjust the dialogue content based on that data.

[0072] The personalization unit can estimate the user's emotions and adjust the personalization method based on the estimated emotions. For example, if the user is sad, the personalization unit can provide comforting content. The personalization unit monitors the user's emotional state and provides comforting content if the user is sad. The personalization unit can also provide content that shares the user's excitement if the user is excited. The personalization unit monitors the user's emotional state and provides content that shares the user's excitement if the user is excited. Furthermore, if the personalization unit is angry, it can provide content that responds calmly. The personalization unit monitors the user's emotional state and provides content that responds calmly if the user is angry. This allows for more appropriate interaction by adjusting the personalization method based on emotions. Some or all of the above processing in the personalization unit may be performed using, for example, generative AI, or not using generative AI. For example, the personalization unit can input the user's emotional state data into a generative AI, and the generative AI can adjust the personalization method based on that data.

[0073] The personalization unit can select the optimal personalization method by referring to the user's past interaction data during personalization. For example, the personalization unit can store the user's past interaction data in a database, and the AI ​​can select the optimal personalization method. The personalization unit refers to past interaction data, and the AI ​​selects the optimal personalization method based on that data. The personalization unit can also analyze the user's past interaction data in chronological order, and the AI ​​can learn personalization patterns. The personalization unit analyzes past interaction data in chronological order, and the AI ​​learns personalization patterns based on that data. Furthermore, the personalization unit can store the user's past interaction data in the cloud, and the AI ​​can access it in real time to select a personalization method. The personalization unit stores past interaction data in the cloud, and the AI ​​refers to that data in real time to select the optimal personalization method. This allows the optimal personalization method to be selected by referring to past interaction data. Some or all of the above processes in the personalization unit may be performed using, for example, generative AI, or without using generative AI. For example, the personalization unit can input the user's past interaction data into a generating AI, which can then select the optimal personalization method based on that data.

[0074] The personalization unit can customize the means of personalization based on the user's current lifestyle and interests during the personalization process. For example, the personalization unit can capture the user's current lifestyle using sensors, and the AI ​​can customize the means of personalization based on that data. The personalization unit can also store the user's interests in a database, and the AI ​​can customize the means of personalization based on that data. Furthermore, the personalization unit can simultaneously analyze the user's current lifestyle and interests, and the AI ​​can customize the means of personalization in a comprehensive manner. The personalization unit can simultaneously analyze the user's current lifestyle and interests, and the AI ​​can customize the means of personalization based on that data. This allows for more appropriate interaction by customizing the means of personalization based on the user's current lifestyle and interests. Some or all of the above-described processes in the personalization unit may be performed using, for example, generative AI, or without using generative AI. For example, the personalization unit inputs data on the user's current lifestyle and interests into a generating AI, which can then customize the personalization methods based on that data.

[0075] The personalization unit can estimate the user's emotions and determine personalization priorities based on those estimated emotions. For example, if the user is showing an urgent emotion, the personalization unit will set a higher priority for personalization. The personalization unit monitors the user's emotional state and sets a higher priority for personalization if the user is showing an urgent emotion. The personalization unit can also set a lower priority for personalization if the user is relaxed. The personalization unit monitors the user's emotional state and sets a lower priority for personalization if the user is relaxed. Furthermore, if the user's emotions change rapidly, the personalization unit can adjust the personalization priority in real time. The personalization unit monitors the user's emotional state in real time and adjusts the personalization priority if the emotions change rapidly. This allows for more appropriate interaction by determining personalization priorities based on emotions. Some or all of the above processing in the personalization unit may be performed using, for example, generative AI, or without generative AI. For example, the personalization unit can input the user's emotional state data into a generative AI, which can then determine personalization priorities based on that data.

[0076] The personalization unit can select the optimal personalization method by considering the user's geographical location information during personalization. For example, if the user is in a specific location, the personalization unit provides information related to that location. The personalization unit provides information related to that location based on geographical location information. The personalization unit can also analyze the user's movement history and customize the personalization method for specific locations. The personalization unit analyzes the movement history and customizes the personalization method for specific locations. Furthermore, the personalization unit can combine the user's current location with past interaction data to adjust the personalization method in real time. The personalization unit analyzes the current location with past interaction data and adjusts the personalization method in real time. This allows the personalization unit to select the optimal personalization method by considering geographical location information. Some or all of the above processing in the personalization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the personalization unit can input the user's geographical location information data into a generative AI, and the generative AI can select a personalization method based on that data.

[0077] The personalization unit can analyze a user's social media activity and suggest personalization methods during the personalization process. For example, the personalization unit can analyze a user's social media posts and suggest personalization methods based on the content of the posts. The personalization unit analyzes the content of the posts, and the AI ​​suggests personalization methods based on that content. The personalization unit can also analyze a user's social media reactions (likes, comments, etc.) and suggest personalization methods. The personalization unit analyzes the reaction data, and the AI ​​suggests personalization methods based on that data. Furthermore, the personalization unit can analyze the time of day of a user's social media activity and suggest personalization methods for specific time periods. The personalization unit analyzes the time of day of activity, and the AI ​​suggests personalization methods based on that data. In this way, by analyzing social media activity, the optimal personalization method can be suggested. Some or all of the above processing in the personalization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the personalization unit can input the user's social media data into a generative AI, and the generative AI can suggest personalization methods based on that data.

[0078] The Business Support Department can estimate a user's emotions and adjust the efficiency of business processes based on those estimated emotions. For example, if a user is feeling stressed, the Business Support Department can suggest a simpler process to reduce their burden. The Business Support Department monitors the user's emotional state and suggests a simpler process if they are feeling stressed. Furthermore, if a user is relaxed, the Business Support Department can suggest a more detailed process to improve efficiency. The Business Support Department monitors the user's emotional state and suggests a detailed process if they are relaxed. In addition, if a user's emotions change rapidly, the Business Support Department can adjust the efficiency of business processes in real time. The Business Support Department monitors the user's emotional state in real time and adjusts the efficiency of business processes if emotions change rapidly. This allows for more appropriate support by adjusting the efficiency of business processes based on emotions. Some or all of the above processes in the Business Support Department may be performed using, for example, generative AI, or without generative AI. For example, the Business Support Department can input user emotional state data into generative AI, which can then adjust the efficiency of business processes based on that data.

[0079] The Business Support Department can select the optimal support method by referring to the past business data of corporate clients when providing business support. For example, the Business Support Department can store the past business data of corporate clients in a database, and the AI ​​can select the optimal support method. The Business Support Department can refer to past business data, and the AI ​​can select the optimal support method based on that data. The Business Support Department can also analyze the past business data of corporate clients in chronological order, and the AI ​​can learn patterns of support methods. The Business Support Department can analyze past business data in chronological order, and the AI ​​can learn patterns of support methods based on that data. Furthermore, the Business Support Department can store the past business data of corporate clients in the cloud, and the AI ​​can access that data in real time to select the optimal support method. The Business Support Department can store past business data in the cloud, and the AI ​​can refer to that data in real time to select the optimal support method. This allows the optimal support method to be selected by referring to past business data. Some or all of the above processes in the Business Support Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Business Support Department can input the past business data of corporate clients into a generative AI, and the generative AI can select the optimal support method based on that data.

[0080] The Business Support Department can estimate the user's emotions and determine the priority of business support based on those emotions. For example, if the user is showing signs of urgency, the Business Support Department will set a higher priority for business support. The Business Support Department monitors the user's emotional state and sets a higher priority for business support if the user is showing signs of urgency. The Business Support Department can also set a lower priority for business support if the user is relaxed. The Business Support Department monitors the user's emotional state and sets a lower priority for business support if the user is relaxed. Furthermore, if the user's emotions change rapidly, the Business Support Department can adjust the priority of business support in real time. The Business Support Department monitors the user's emotional state in real time and adjusts the priority of business support if the emotions change rapidly. This allows for more appropriate support by determining the priority of business support based on emotions. Some or all of the above processes in the Business Support Department may be performed using, for example, generative AI, or not using generative AI. For example, the Business Support Department can input user emotional state data into a generative AI, which can then determine the priority of business support based on that data.

[0081] The Business Support Department can select the optimal support method when providing business support, taking into account the geographical location information of corporate clients. For example, if a corporate client is in a specific location, the Business Support Department can provide support methods relevant to that location. The Business Support Department provides support methods relevant to that location based on geographical location information. The Business Support Department can also analyze the corporate client's travel history and customize support methods for specific locations. The Business Support Department analyzes travel history and customizes support methods for specific locations. Furthermore, the Business Support Department can combine the corporate client's current location with past business data and adjust support methods in real time. The Business Support Department analyzes the combination of current location and past business data and adjusts support methods in real time. This allows for the selection of the optimal support method by considering geographical location information. Some or all of the above processing in the Business Support Department may be performed using, for example, a generative AI, or without a generative AI. For example, the Business Support Department can input the corporate client's geographical location data into a generative AI, and the generative AI can select a support method based on that data.

[0082] The Personal Support Unit can estimate the user's emotions and adjust methods for improving the quality of daily life based on those estimated emotions. For example, if the user is feeling stressed, the Personal Support Unit can suggest ways to relax. The Personal Support Unit monitors the user's emotional state and suggests ways to relax if the user is feeling stressed. Furthermore, if the user is relaxed, the Personal Support Unit can suggest even more comfortable methods. The Personal Support Unit monitors the user's emotional state and suggests even more comfortable methods if the user is relaxed. In addition, if the user's emotions change rapidly, the Personal Support Unit can adjust methods for improving the quality of daily life in real time. The Personal Support Unit monitors the user's emotional state in real time and adjusts methods for improving the quality of daily life if emotions change rapidly. This allows for more appropriate support by adjusting methods for improving the quality of daily life based on emotions. Some or all of the above processing in the Personal Support Unit may be performed using, for example, a generative AI, or without a generative AI. For example, the Personal Support Unit can input the user's emotional state data into a generative AI, which can then adjust methods for improving the quality of daily life based on that data.

[0083] The Personal Support Department can select the optimal support method by referring to the individual user's past life data when providing personal support. For example, the Personal Support Department can store the individual user's past life data in a database, and the AI ​​can select the optimal support method. The Personal Support Department can refer to past life data, and the AI ​​can select the optimal support method based on that data. The Personal Support Department can also analyze the individual user's past life data in chronological order, and the AI ​​can learn patterns of support methods. The Personal Support Department can analyze past life data in chronological order, and the AI ​​can learn patterns of support methods based on that data. Furthermore, the Personal Support Department can store the individual user's past life data in the cloud, and the AI ​​can access that data in real time to select the optimal support method. The Personal Support Department can store past life data in the cloud, and the AI ​​can refer to that data in real time to select the optimal support method. This allows the optimal support method to be selected by referring to past life data. Some or all of the above processes in the Personal Support Department may be performed using, for example, a generative AI, or without using a generative AI. For example, the Personal Support Department can input a user's past lifestyle data into a generating AI, which can then select the most suitable support method based on that data.

[0084] The Personal Support Unit can estimate the user's emotions and determine the priority of personal support based on those emotions. For example, if the user is showing an urgent emotion, the Personal Support Unit will set a higher priority for personal support. The Personal Support Unit monitors the user's emotional state and sets a higher priority for personal support if the user is showing an urgent emotion. The Personal Support Unit can also set a lower priority for personal support if the user is relaxed. The Personal Support Unit monitors the user's emotional state and sets a lower priority for personal support if the user is relaxed. Furthermore, if the user's emotions change rapidly, the Personal Support Unit can adjust the priority of personal support in real time. The Personal Support Unit monitors the user's emotional state in real time and adjusts the priority of personal support if the emotions change rapidly. This allows for more appropriate support by determining the priority of personal support based on emotions. Some or all of the above processing in the Personal Support Unit may be performed using, for example, generative AI, or without using generative AI. For example, the Personal Support Department can input user emotional state data into a generating AI, which can then use that data to determine the priority of personal support.

[0085] The Personal Support Unit can select the optimal support method when providing personal support, taking into account the geographical location information of the individual user. For example, if an individual user is in a specific location, the Personal Support Unit can provide support methods relevant to that location. The Personal Support Unit provides support methods relevant to that location based on geographical location information. The Personal Support Unit can also analyze the individual user's travel history and customize support methods for specific locations. The Personal Support Unit analyzes the travel history and customizes support methods for specific locations. Furthermore, the Personal Support Unit can combine the individual user's current location with past lifestyle data and adjust support methods in real time. The Personal Support Unit analyzes the combination of current location and past lifestyle data and adjusts support methods in real time. This allows for the selection of the optimal support method by considering geographical location information. Some or all of the above processing in the Personal Support Unit may be performed using, for example, a generative AI, or without a generative AI. For example, the Personal Support Unit can input the individual user's geographical location data into a generative AI, which can then select a support method based on that data.

[0086] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0087] The communication agent system may include a health management unit that estimates the user's emotions and monitors the user's health status based on those emotions. For example, if the user is feeling stressed, the health management unit can provide advice on stress reduction. The health management unit monitors the user's emotional state and suggests ways to relax if the user is stressed. Furthermore, if the user is relaxed, the health management unit can suggest activities to maintain their health. The health management unit monitors the user's emotional state in real time and adjusts the monitoring frequency if emotions change rapidly. This allows for more appropriate support of the user's health by providing health management based on emotions.

[0088] The communication agent system may include a learning support unit that estimates the user's emotions and manages the user's learning progress based on those emotions. For example, if the user is focused, the learning support unit may provide additional materials to deepen their understanding. The learning support unit monitors the user's emotional state and provides additional materials if the user is focused. Furthermore, if the user is tired, the learning support unit may suggest a break. The learning support unit monitors the user's emotional state and suggests a break if the user is tired. In addition, if the user's emotions change rapidly, the learning support unit may adjust the difficulty level of the learning material. This allows for improved user learning efficiency by providing learning support based on emotions.

[0089] The communication agent system may include a sleep management unit that estimates the user's emotions and manages the user's sleep state based on those emotions. For example, if the user is feeling anxious, the sleep management unit may provide relaxing music. The sleep management unit monitors the user's emotional state and provides relaxing music if the user is feeling anxious. Furthermore, if the user is relaxed, the sleep management unit can suggest a comfortable sleep environment. The sleep management unit monitors the user's emotional state in real time and provides advice to improve sleep quality if the user's emotions change rapidly. This allows for improved sleep quality by managing sleep based on emotions.

[0090] The communication agent system may include a meal management unit that estimates the user's emotions and manages the user's diet based on those emotions. For example, if the user is feeling stressed, the meal management unit might suggest meals that help reduce stress. The meal management unit monitors the user's emotional state and suggests meals that help reduce stress if the user is feeling stressed. Furthermore, if the user is relaxed, the meal management unit can suggest healthy meals. The meal management unit monitors the user's emotional state in real time and adjusts meals if emotions change rapidly. This allows for support of the user's health by managing their diet based on their emotions.

[0091] The communication agent system may include an exercise management unit that estimates the user's emotions and manages the user's exercise based on those emotions. For example, if the user is feeling stressed, the exercise management unit might suggest exercises that help relieve stress. The exercise management unit monitors the user's emotional state and suggests exercises that help relieve stress if the user is feeling stressed. Furthermore, if the user is relaxed, the exercise management unit can suggest exercises for maintaining health. The exercise management unit monitors the user's emotional state in real time and adjusts the exercise if the user's emotions change rapidly. This allows for support of the user's health by managing exercise based on their emotions.

[0092] Communication agent systems can achieve more natural dialogue by referencing the user's past dialogue history and learning dialogue patterns. For example, the dialogue management unit stores the user's past dialogue history in a database, and the AI ​​learns dialogue patterns based on that data. The dialogue management unit can also analyze the user's past dialogue history chronologically and predict the flow of the conversation. Furthermore, the dialogue management unit can store the user's past dialogue history in the cloud, and the AI ​​can access it in real time to learn dialogue patterns. This allows for more natural dialogue by referring to past dialogue history.

[0093] The communication agent system can customize the content of conversations based on the user's current situation and interests. For example, the conversation management unit can capture the user's current situation with sensors, and the AI ​​can customize the conversation content based on that data. The conversation management unit can also store the user's interests in a database, and the AI ​​can customize the conversation content based on that data. Furthermore, the conversation management unit can simultaneously analyze the user's current situation and interests, and the AI ​​can customize the conversation content in a comprehensive manner. This allows for more appropriate conversations by customizing the content based on the current situation and interests.

[0094] The communication agent system can adjust the content of conversations by taking into account the user's geographical location. For example, the conversation management unit can provide location-related information if the user is in a specific location. The conversation management unit can also analyze the user's movement history and customize the conversation content for specific locations. Furthermore, the conversation management unit can combine the user's current location with past conversation history to adjust the conversation content in real time. This allows for more appropriate adjustment of conversation content by considering geographical location information.

[0095] The communication agent system can analyze a user's social media activity and adjust the content of the conversation accordingly. For example, the conversation management unit can analyze a user's social media posts and adjust the conversation based on the content of those posts. The conversation management unit can also analyze a user's social media reactions (likes, comments, etc.) and adjust the conversation accordingly. Furthermore, the conversation management unit can analyze the time of day a user is active on social media and adjust the conversation for specific time periods. This allows for more appropriate adjustment of conversation content by analyzing social media activity.

[0096] A communication agent system can select the optimal personalization method by referring to a user's past interaction data. For example, the personalization unit can store the user's past interaction data in a database, and the AI ​​can select the optimal personalization method based on that data. The personalization unit can also analyze the user's past interaction data in chronological order and learn personalization patterns. Furthermore, the personalization unit can store the user's past interaction data in the cloud, and the AI ​​can access it in real time to select the personalization method. This allows the system to select the optimal personalization method by referring to past interaction data.

[0097] The following briefly describes the processing flow for example form 2.

[0098] Step 1: The emotion recognition unit understands the user's emotions. The emotion recognition unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. It can also analyze the tone of the user's voice using voice analysis technology and estimate their emotions. Furthermore, it can analyze the user's text messages using text analysis technology and estimate their emotions. For example, the emotion recognition unit can capture the user's facial expressions with a camera, and the AI ​​will analyze subtle changes in facial expressions to estimate their emotions. It can also collect the tone of the user's voice with a microphone, and the AI ​​will analyze the pitch and tempo of the voice to estimate their emotions. Furthermore, it can analyze the user's text messages, and the AI ​​will estimate their emotions from the content of the text. Step 2: The dialogue management unit performs advanced dialogue management based on the emotions understood by the emotion recognition unit. The dialogue management unit can understand the user's intent using natural language processing technology and generate appropriate responses. It can also manage the flow of the dialogue and conduct conversations in accordance with the user's intent. Furthermore, it can adjust the tone and content of the dialogue according to the user's emotions. For example, if the user is sad, the dialogue tone can be made gentle and comforting content can be provided. If the user is excited, the dialogue tone can be made cheerful and content that shares the excitement can be provided. Furthermore, if the user is angry, the dialogue tone can be made calm and content that responds calmly can be provided. Step 3: The personalization unit personalizes the interaction with the user based on the conversation conducted by the dialogue management unit. The personalization unit can learn the user's past behavior history, preferences, and interests using machine learning technology to personalize the interaction. It can also customize the interaction based on the user's current situation and interests. Furthermore, it can adjust the method of interaction based on the user's emotions. For example, if the user is sad, it can provide comforting content. If the user is excited, it can provide content that shares their excitement. Furthermore, if the user is angry, it can provide content that calms them down.

[0099] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0100] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0101] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0102] Each of the multiple elements described above, including the emotion recognition unit, dialogue management unit, personalization unit, business support unit, and personal support unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the emotion recognition unit uses the camera 42 and microphone 38B of the smart device 14 to detect the user's facial expressions and voice, and the control unit 46A recognizes emotions. The dialogue management unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and uses natural language processing technology to understand the user's intentions and generate appropriate responses. The personalization unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and uses machine learning technology to learn the user's past behavior history and preferences and personalize interactions. The business support unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and optimizes business flows and optimal resource allocation. The personal support unit is implemented in the control unit 46A of the smart device 14, for example, and provides support for health management, time management, and stress reduction. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0103] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0104] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0109] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0110] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0111] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0112] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0113] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0115] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0117] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements described above, including the emotion recognition unit, dialogue management unit, personalization unit, business support unit, and personal support unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the emotion recognition unit uses the camera 42 and microphone 238 of the smart glasses 214 to detect the user's facial expressions and voice, and the control unit 46A recognizes emotions. The dialogue management unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and uses natural language processing technology to understand the user's intentions and generate appropriate responses. The personalization unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and uses machine learning technology to learn the user's past behavior history and preferences and personalize interactions. The business support unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and optimizes business flows and optimal resource allocation. The personal support unit is implemented in the control unit 46A of the smart glasses 214, for example, and provides support for health management, time management, and stress reduction. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0119] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0120] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0122] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0123] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0125] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0126] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0127] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0128] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0129] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0130] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0133] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements described above, including the emotion recognition unit, dialogue management unit, personalization unit, business support unit, and personal support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the emotion recognition unit uses the camera 42 and microphone 238 of the headset terminal 314 to detect the user's facial expressions and voice, and the control unit 46A recognizes emotions. The dialogue management unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and uses natural language processing technology to understand the user's intentions and generate appropriate responses. The personalization unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and uses machine learning technology to learn the user's past behavior history and preferences and personalize interactions. The business support unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and optimizes business flows and optimal resource allocation. The personal support unit is implemented in the control unit 46A of the headset terminal 314, for example, and provides support for health management, time management, and stress reduction. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0135] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0136] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0143] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0144] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0145] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0146] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0148] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0150] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] Each of the multiple elements described above, including the emotion recognition unit, dialogue management unit, personalization unit, business support unit, and personal support unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the emotion recognition unit uses the camera 42 and microphone 238 of the robot 414 to detect the user's facial expressions and voice, and the control unit 46A recognizes emotions. The dialogue management unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and uses natural language processing technology to understand the user's intentions and generate appropriate responses. The personalization unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and uses machine learning technology to learn the user's past behavior history and preferences and personalize interactions. The business support unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and optimizes business flows and optimal resource allocation. The personal support unit is implemented in the control unit 46A of the robot 414, for example, and provides support for health management, time management, and stress reduction. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0152] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0154] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0155] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0156] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has 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 ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0160] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to 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] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0163] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0164] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0165] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0167] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0168] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0169] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0170] (Note 1) An emotion recognition unit that understands the user's emotions, A dialogue management unit that performs advanced dialogue management based on the emotions understood by the emotion recognition unit, A personalization unit that personalizes user interaction based on the dialogue conducted by the aforementioned dialogue management unit, Equipped with A system characterized by the following features. (Note 2) We have a business support department that provides corporate clients with business process efficiency improvements and enhanced customer service. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a personal support department that provides individual users with improved quality of life and entertainment. The system described in Appendix 1, characterized by the features described herein. (Note 4) The emotion recognition unit, Using emotion recognition technology to understand the user's emotions The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned dialogue management unit, Advanced dialogue management using natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 6) The personalization unit described above is Leveraging machine learning to personalize user interactions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The emotion recognition unit, The system analyzes the user's facial expressions and tone of voice, estimates their emotions, and improves the accuracy of emotion recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The emotion recognition unit, Referencing the user's past emotional data allows for a more accurate understanding of their current emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The emotion recognition unit, During emotion recognition, the system analyzes the user's body movements and posture to understand their emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The emotion recognition unit, It estimates the user's emotions and adjusts the timing of emotion recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The emotion recognition unit, When recognizing emotions, the system takes the user's geographical location into consideration to recognize changes in emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The emotion recognition unit, During emotion recognition, the system analyzes the user's social media activity and recognizes changes in their emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned dialogue management unit, It estimates the user's emotions and adjusts the tone and content of the conversation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned dialogue management unit, During dialogue management, the system selects the optimal dialogue method by referring to the user's past dialogue history. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned dialogue management unit, During dialogue management, the content of the dialogue is customized based on the user's current situation and interests. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned dialogue management unit, It estimates the user's emotions and determines the priority of the conversation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned dialogue management unit, During dialogue management, the content of the dialogue is adjusted taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned dialogue management unit, During conversation management, we analyze the user's social media activity and adjust the conversation content accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 19) The personalization unit described above is It estimates the user's emotions and adjusts the personalization method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The personalization unit described above is During personalization, the system references the user's past interaction data to select the optimal personalization method. The system described in Appendix 1, characterized by the features described herein. (Note 21) The personalization unit described above is During personalization, the means of personalization are customized based on the user's current lifestyle and interests. The system described in Appendix 1, characterized by the features described herein. (Note 22) The personalization unit described above is It estimates the user's emotions and determines personalization priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The personalization unit described above is When personalizing, the system selects the optimal personalization method by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The personalization unit described above is During personalization, the system analyzes the user's social media activity and suggests ways to personalize their experience. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned Business Support Department It estimates user emotions and adjusts how business processes are optimized based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned Business Support Department When providing business support, we select the optimal support method by referring to the corporate client's past business data. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned Business Support Department It estimates user emotions and determines business support priorities based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned Business Support Department When providing business support, we select the most suitable support method by considering the geographical location information of our corporate clients. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned Personal Support Department, It estimates the user's emotions and adjusts methods to improve the quality of daily life based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 30) The aforementioned Personal Support Department, When providing individual support, the system selects the most suitable support method by referring to the individual user's past lifestyle data. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned Personal Support Department, It estimates the user's emotions and determines the priority of personalized support based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned Personal Support Department, When providing individual support, the optimal support method is selected by considering the individual user's geographical location. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An emotion recognition unit that understands the user's emotions, A dialogue management unit that performs advanced dialogue management based on the emotions understood by the emotion recognition unit, A personalization unit that personalizes user interaction based on the dialogue conducted by the aforementioned dialogue management unit, Equipped with A system characterized by the following features.

2. We have a business support department that provides corporate clients with business process efficiency improvements and enhanced customer service. The system according to feature 1.

3. It has a personal support department that provides individual users with improved quality of life and entertainment. The system according to feature 1.

4. The emotion recognition unit, Using emotion recognition technology to understand the user's emotions The system according to feature 1.

5. The aforementioned dialogue management unit, Advanced dialogue management using natural language processing. The system according to feature 1.

6. The personalization unit described above is Leveraging machine learning to personalize user interactions. The system according to feature 1.

7. The emotion recognition unit, The system analyzes the user's facial expressions and tone of voice, estimates their emotions, and improves the accuracy of emotion recognition based on the estimated emotions. The system according to feature 1.

8. The emotion recognition unit, Referencing the user's past emotional data allows for a more accurate understanding of their current emotions. The system according to feature 1.

Images