System

Abstract

An object of a system according to an embodiment is to generate a behavior of an avatar in real time on the basis of a text or a touch event of a user and realize more natural touch.SOLUTION: A system includes a reception unit, an analysis unit, and a generation unit. The reception unit receives a user's text or touch event. The analysis unit analyzes the information received by the reception unit and estimates an intention of the user. The generation unit immediately generates a behavior of the avatar based on the intention estimated by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, there were limitations on how to interact with virtual avatars, such as standard responses and interaction patterns, as well as a limited number of response variations, making it difficult to achieve true interaction.

[0005] The system according to the embodiment aims to realize more natural interactions by generating avatar behavior in real time based on user text and touch events. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, and a generation unit. The reception unit receives text and touch events from a user. The analysis unit analyzes the information received by the reception unit and infers the user's intention. The generation unit instantly generates avatar behavior based on the intention inferred by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment generates avatar behavior in real time based on the user's text and touch events, enabling more natural interaction. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) An agent system according to an embodiment of the present invention is a system that accepts a user's text and touch events, analyzes them with a generation AI, and generates avatar behavior in real time. The agent system accepts the user's text and touch events, analyzes them with a generation AI, infers the user's intention, and generates avatar behavior in real time based on the user's intention. For example, the agent system accepts text and touch events such as a user saying "hello" or patting an avatar's head. The generation AI then analyzes this information and infers the user's intention. For example, when the user says "hello," the generation AI infers the avatar's behavior of returning the greeting with a smile. The agent system then generates avatar behavior in real time based on the inferred intention. For example, the generation AI dynamically generates avatar facial expressions and movements and displays them to the user in real time. In this way, the agent system generates avatar behavior in real time in response to the user's text and touch events, thereby achieving natural communication. In this way, the agent system generates avatar behavior in real time based on the user's text and touch events, thereby achieving natural communication. For example, if a user says to an avatar, "Let's play together," the generation AI analyzes that intention and generates an action in real time for the avatar to invite the user to play. Similarly, if the user shakes the avatar's hand, the generation AI analyzes that intention and generates an action in real time for the avatar to shake the hand back. This allows the agent system to overcome the limitations of conventional standard responses, interaction patterns, and the limited number of response variations, and generate avatar behaviors in real time that match the user's intentions, providing a richer communication experience.

[0029] The agent system according to the embodiment includes a reception unit, an analysis unit, and a generation unit. The reception unit receives user text and touch events. Examples of user text and touch events include, but are not limited to, chat messages, clicks, and swipes. The reception unit can receive, for example, text input by the user such as "hello" and a touch event such as patting an avatar's head. The reception unit can also receive voice input and gesture input. For example, the reception unit can receive a user's voice input of "hello" or a gesture of touching an avatar. The analysis unit analyzes the information received by the reception unit and infers the user's intention. The analysis unit infers the intention from the user's text and touch events using, for example, natural language processing technology or a machine learning algorithm. For example, if the user inputs "hello," the analysis unit infers that the avatar intends to return the greeting with a smile. The analysis unit can also infer a gesture that the avatar will be happy to make if the user pat the avatar's head. Furthermore, the analysis unit can infer the user's intention by taking into account the user's past interaction history and the current context. For example, the analysis unit can refer to the avatar's reaction when the user previously input "hello" and estimate a similar reaction this time. The generation unit generates the avatar's behavior in real time based on the intention estimated by the analysis unit. The generation unit dynamically generates the avatar's facial expressions and movements using, for example, image generation AI. For example, the generation unit generates an avatar's movement of smiling and returning a greeting in real time and displays it to the user. The generation unit can also generate an avatar's movement of shaking hands or an avatar's movement of inviting the user to play in real time. Furthermore, the generation unit can generate avatar behavior in real time that matches the user's intention. For example, if the user says "Let's play together," the generation unit generates an avatar's movement of inviting the user to play in real time. As a result, the agent system according to the embodiment can generate avatar behavior in real time based on the user's text and touch events, thereby achieving natural communication.Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may generate the behavior of an avatar using a generation AI model that receives the intention estimated by the analysis unit as input and outputs the behavior of the avatar.

[0030] The reception unit can analyze the user's past interaction history and select an appropriate reception method. The reception unit analyzes the user's past interaction history and selects the optimal reception method. For example, the reception unit can prioritize and suggest input methods (such as voice and text) that the user has frequently used in the past. The reception unit can also automatically recognize specific touch events performed by the user in the past and enable the user to easily accept similar events. Furthermore, the reception unit can predict and suggest an input method to be used during a specific time period based on the user's past interaction history. This can improve the user experience by providing the optimal reception method based on the past interaction history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past interaction history data into a generation AI and have the generation AI select the optimal reception method.

[0031] The reception unit can perform filtering based on the user's current context when receiving text or touch events. The reception unit performs filtering based on the user's current context (e.g., time of day or location) when receiving text or touch events. For example, if the user uses the device at night, the reception unit can provide an interface suitable for a dark environment. Also, if the user is in a specific location, the reception unit can preferentially display input options related to that location. Furthermore, if the user is on the move, the reception unit can provide an interface that is easy to operate. This makes it possible to provide a more appropriate interface by filtering according to the user's current context. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the user's current context data to the generation AI and have the generation AI perform the filtering process.

[0032] The reception unit can select an appropriate reception means according to the user's input method when receiving text or touch events. The reception unit selects the optimal reception means according to the user's input method (voice, text, gesture, etc.) when receiving text or touch events. For example, when the user gives instructions by voice, the reception unit can preferentially receive voice input. Also, when the user gives instructions by text, the reception unit can preferentially receive text input. Furthermore, when the user gives instructions by gesture, the reception unit can preferentially receive gesture input. This can improve the user experience by providing the optimal reception means according to the user's input method. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's input method data to the generation AI and cause the generation AI to select the optimal reception means.

[0033] When receiving text or touch events, the reception unit can prioritize receiving highly relevant events based on the user's geographical location information. When receiving text or touch events, the reception unit prioritizes receiving highly relevant events taking the user's geographical location information into consideration. For example, when the user is in a specific location, the reception unit prioritizes receiving events related to that location. Furthermore, when the user is traveling, the reception unit can prioritize receiving events related to the user's destination. Furthermore, when the user is at home, the reception unit can prioritize receiving events related to the user's home. This enables more appropriate responses by determining the priority of events based on the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information data to a generation AI and cause the generation AI to select highly relevant events.

[0034] The reception unit can analyze the user's social media activity and receive related events when receiving text or touch events. The reception unit can analyze the user's social media activity and receive related events when receiving text or touch events. For example, the reception unit can prioritize events related to places where the user has checked in on social media. The reception unit can also analyze the content of the user's social media posts and prioritize related events. Furthermore, the reception unit can prioritize related events by referring to the activities of the user's friends on social media. This enables more appropriate responses by receiving events based on the user's social media activity. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or can be performed without AI. For example, the reception unit can input the user's social media activity data into a generation AI and cause the generation AI to select related events.

[0035] The reception unit can change the reception method by reflecting the user's past feedback when receiving a text or touch event. The reception unit customizes the reception method by reflecting the user's past feedback when receiving a text or touch event. For example, the reception unit can preferentially provide reception methods that the user has previously preferred. It can also avoid reception methods that the user has previously dissatisfied with. Furthermore, the reception unit can suggest an optimal reception method based on the user's past feedback. This can improve the user experience by providing a reception method based on the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the reception method.

[0036] During analysis, the analysis unit can improve the accuracy of intent analysis based on the user's past interaction history. During analysis, the analysis unit improves the accuracy of intent analysis by referring to the user's past interaction history. For example, the analysis unit accurately estimates intent based on specific touch events performed by the user in the past. The analysis unit can also analyze intent by referring to the user's past text input history. Furthermore, the analysis unit can find specific patterns from the user's past interaction history and estimate intent. This enables more accurate intent estimation by improving the accuracy of intent analysis based on the past interaction history. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past interaction history data to the generation AI and cause the generation AI to improve the accuracy of intent analysis.

[0037] During analysis, the analysis unit can infer intent based on the user's current context. During analysis, the analysis unit infers intent based on the user's current context (e.g., time of day or location). For example, if the user uses the device at night, the analysis unit can prioritize analyzing intent related to nighttime. Also, if the user is in a specific location, the analysis unit can prioritize analyzing intent related to that location. Furthermore, if the user is moving, the analysis unit can prioritize analyzing intent related to movement. This enables more accurate intent analysis by estimating intent based on the user's current context. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's current context data to the generation AI and cause the generation AI to estimate the intent.

[0038] The analysis unit can apply different analysis algorithms depending on the user's input method during analysis. The analysis unit can apply different analysis algorithms depending on the user's input method (voice, text, gesture, etc.) during analysis. For example, if the user gives instructions by voice, the analysis unit can apply a voice analysis algorithm. If the user gives instructions by text, the analysis unit can apply a text analysis algorithm. Furthermore, if the user gives instructions by gesture, the analysis unit can apply a gesture analysis algorithm. This allows for more accurate analysis of the user's intentions by providing an analysis algorithm depending on the user's input method. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input user's input method data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0039] During analysis, the analysis unit can infer the intention based on the user's geographical location information. During analysis, the analysis unit infers the intention taking the user's geographical location information into consideration. For example, when the user is in a specific location, the analysis unit can prioritize analyzing intentions related to that location. Furthermore, when the user is traveling, the analysis unit can prioritize analyzing intentions related to traveling. Furthermore, when the user is at home, the analysis unit can prioritize analyzing intentions related to home. This enables more accurate analysis of intentions by estimating the intention based on the user's geographical location information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's geographical location information data to the generation AI and cause the generation AI to estimate the intention.

[0040] The analysis unit can analyze the user's social media activity and infer related intentions during analysis. The analysis unit can analyze the user's social media activity and infer related intentions during analysis. For example, the analysis unit can prioritize analysis of intentions related to places where the user has checked in on social media. The analysis unit can also analyze the content of the user's social media posts and prioritize analysis of related intentions. Furthermore, the analysis unit can prioritize analysis of related intentions by referring to the activities of the user's friends on social media. This enables more accurate analysis of intentions by estimating intentions based on the user's social media activity. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's social media activity data into a generation AI and cause the generation AI to estimate intentions.

[0041] The analysis unit can change the analysis method during analysis by reflecting the user's past feedback. The analysis unit can customize the analysis method during analysis by reflecting the user's past feedback. For example, the analysis unit can preferentially apply analysis methods that the user has previously preferred. Also, the analysis unit can avoid analysis methods that the user has previously dissatisfied with. Furthermore, the analysis unit can suggest an optimal analysis method based on the user's past feedback. This enables more accurate analysis of intent by providing an analysis method based on the user's past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past feedback data into the generation AI and have the generation AI customize the analysis method.

[0042] The generation unit can improve the accuracy of avatar behavior generation based on the user's past interaction history during generation. The generation unit improves the accuracy of avatar behavior generation by referring to the user's past interaction history during generation. For example, the generation unit accurately generates avatar behavior based on a specific touch event performed by the user in the past. The generation unit can also generate avatar behavior by referring to the user's past text input history. Furthermore, the generation unit can find specific patterns from the user's past interaction history and generate avatar behavior. This improves the accuracy of avatar behavior generation based on the past interaction history, enabling more natural communication. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input the user's past interaction history data into the generation AI and cause the generation AI to improve the accuracy of avatar behavior generation.

[0043] The generation unit can generate avatar behavior based on the user's current context at the time of generation. The generation unit generates avatar behavior based on the user's current context (e.g., time of day or location) at the time of generation. For example, if the user uses the device at night, the generation unit can generate avatar behavior related to nighttime. Also, if the user is in a specific location, the generation unit can generate avatar behavior related to that location. Furthermore, if the user is moving, the generation unit can generate avatar behavior related to movement. This enables more natural communication by generating avatar behavior based on the user's current context. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's current context data to the generation AI and cause the generation AI to generate avatar behavior.

[0044] The generation unit can apply different generation algorithms depending on the user's input method during generation. The generation unit can apply different generation algorithms depending on the user's input method (voice, text, gesture, etc.) during generation. For example, when a user gives instructions by voice, the generation unit can generate avatar behavior corresponding to the voice input. When a user gives instructions by text, the generation unit can generate avatar behavior corresponding to the text input. When a user gives instructions by gesture, the generation unit can generate avatar behavior corresponding to the gesture input. This enables more natural communication by providing a generation algorithm corresponding to the user's input method. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user's input method data to the generation AI and cause the generation AI to apply the generation algorithm.

[0045] The generation unit can generate avatar behavior based on the user's geographical location information at the time of generation. The generation unit generates avatar behavior taking the user's geographical location information into consideration at the time of generation. For example, if the user is in a specific location, the generation unit can generate avatar behavior related to that location. Also, if the user is moving, the generation unit can generate avatar behavior related to the movement. Furthermore, if the user is at home, the generation unit can generate avatar behavior related to the home. This enables more natural communication by generating avatar behavior based on the user's geographical location information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's geographical location information data to the generation AI and cause the generation AI to generate avatar behavior.

[0046] The generation unit can analyze the user's social media activity and generate the behavior of the related avatar at the time of generation. The generation unit can analyze the user's social media activity and generate the behavior of the related avatar at the time of generation. For example, the generation unit can generate the behavior of the avatar related to the place where the user checked in on social media. The generation unit can also analyze the content of the user's social media posts and generate the behavior of the related avatar. Furthermore, the generation unit can generate the behavior of the related avatar by referring to the activities of the user's friends on social media. This enables more natural communication by generating the behavior of the avatar based on the user's social media activity. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's social media activity data into the generation AI and cause the generation AI to generate the behavior of the avatar.

[0047] The generation unit can change the avatar behavior generation method by reflecting the user's past feedback at the time of generation. The generation unit can customize the avatar behavior generation method by reflecting the user's past feedback at the time of generation. For example, the generation unit can prioritize the generation of behaviors that the user has previously preferred. Also, the generation unit can avoid behaviors that the user has previously dissatisfied with. Furthermore, the generation unit can propose an optimal behavior generation method based on the user's past feedback. This enables more natural communication by providing an avatar behavior generation method based on the user's past feedback. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the avatar behavior generation method.

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

[0049] The generation unit can customize the behavior of the avatar based on the user's past purchasing history. For example, if the user has frequently purchased products from a specific brand in the past, the generation unit can generate avatar behavior related to that brand. Also, if the user has purchased products from a specific category in the past, the generation unit can generate avatar behavior related to that category. Furthermore, it is possible to find specific patterns from the user's purchasing history and customize the avatar's behavior. This makes it possible to generate avatar behavior based on the user's purchasing history, thereby providing a more personalized experience.

[0050] The reception unit can obtain the user's calendar information and provide an appropriate reception method based on the schedule. For example, if the user is in a meeting, the reception unit will avoid voice input and prioritize text input. Also, if the user is on the move, the reception unit can provide an interface that is easy to operate. Furthermore, the reception unit can continuously monitor the user's calendar information and adjust the reception method in real time. This makes it possible to provide an interface based on the user's schedule, resulting in a more appropriate user experience.

[0051] The generator can customize the behavior of the avatar based on the user's health data (e.g., step count and sleep data). For example, if the user is getting enough sleep, the generator can generate an energetic avatar behavior. Alternatively, if the user is not getting enough exercise, the generator can generate an avatar behavior that encourages exercise. Furthermore, the generator can continuously monitor the user's health data and adjust the avatar behavior in real time. This makes it possible to generate avatar behavior based on the user's health condition, providing a more personalized experience.

[0052] The reception unit can acquire the user's music playback history and provide an appropriate reception method based on the music being played. For example, if the user is playing relaxing music, the reception unit can provide detailed input options. On the other hand, if the user is playing fast-paced music, the reception unit can provide a simple interface. Furthermore, the reception unit can continuously monitor the user's music playback history and adjust the reception method in real time. This makes it possible to provide an interface based on the user's music playback status, resulting in a more appropriate user experience.

[0053] The generation unit can customize the behavior of the avatar based on the user's hobbies and interests. For example, if the user is interested in sports, the generation unit can generate avatar behavior related to sports. Also, if the user is interested in music, the generation unit can generate avatar behavior related to music. Furthermore, the user's hobbies and interests can be continuously monitored and the avatar behavior can be adjusted in real time. This makes it possible to generate avatar behavior based on the user's hobbies and interests, providing a more personalized experience.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The reception unit receives user text and touch events. User text and touch events include chat messages, clicks, swipes, voice input, and gesture input. For example, the reception unit can receive the user's text "Hello," a touch event of patting an avatar's head, a voice message saying "Hello," or a gesture of touching an avatar. Step 2: The analysis unit analyzes the information received by the reception unit and infers the user's intention. The analysis unit uses natural language processing technology and machine learning algorithms to infer the user's intention from the user's text and touch events. For example, if the user types "hello," the analysis unit infers the avatar's intention to return the greeting with a smile, and if the user pats the avatar's head, the analysis unit infers the avatar's happy behavior. The analysis unit can also infer the user's intention by taking into account the user's past interaction history and current context. Step 3: The generator generates the avatar's behavior in real time based on the intention estimated by the analyzer. The generator uses image generation AI to dynamically generate the avatar's facial expressions and movements. For example, it can generate in real time an avatar's movements to return a greeting with a smile, shake hands, or invite someone to play. The generator generates avatar behavior in real time that matches the user's intention, enabling natural communication.

[0056] (Example 2) An agent system according to an embodiment of the present invention is a system that accepts a user's text and touch events, analyzes them with a generation AI, and generates avatar behavior in real time. The agent system accepts the user's text and touch events, analyzes them with a generation AI, infers the user's intention, and generates avatar behavior in real time based on the user's intention. For example, the agent system accepts text and touch events such as a user saying "hello" or patting an avatar's head. The generation AI then analyzes this information and infers the user's intention. For example, when the user says "hello," the generation AI infers the avatar's behavior of returning the greeting with a smile. The agent system then generates avatar behavior in real time based on the inferred intention. For example, the generation AI dynamically generates avatar facial expressions and movements and displays them to the user in real time. In this way, the agent system generates avatar behavior in real time in response to the user's text and touch events, thereby achieving natural communication. In this way, the agent system generates avatar behavior in real time based on the user's text and touch events, thereby achieving natural communication. For example, if a user says to an avatar, "Let's play together," the generation AI analyzes that intention and generates an action in real time for the avatar to invite the user to play. Similarly, if the user shakes the avatar's hand, the generation AI analyzes that intention and generates an action in real time for the avatar to shake the hand back. This allows the agent system to overcome the limitations of conventional standard responses, interaction patterns, and the limited number of response variations, and generate avatar behaviors in real time that match the user's intentions, providing a richer communication experience.

[0057] The agent system according to the embodiment includes a reception unit, an analysis unit, and a generation unit. The reception unit receives user text and touch events. Examples of user text and touch events include, but are not limited to, chat messages, clicks, and swipes. The reception unit can receive, for example, text input by the user such as "hello" and a touch event such as patting an avatar's head. The reception unit can also receive voice input and gesture input. For example, the reception unit can receive a user's voice input of "hello" or a gesture of touching an avatar. The analysis unit analyzes the information received by the reception unit and infers the user's intention. The analysis unit infers the intention from the user's text and touch events using, for example, natural language processing technology or a machine learning algorithm. For example, if the user inputs "hello," the analysis unit infers that the avatar intends to return the greeting with a smile. The analysis unit can also infer a gesture that the avatar will be happy to make if the user pat the avatar's head. Furthermore, the analysis unit can infer the user's intention by taking into account the user's past interaction history and the current context. For example, the analysis unit can refer to the avatar's reaction when the user previously input "hello" and estimate a similar reaction this time. The generation unit generates the avatar's behavior in real time based on the intention estimated by the analysis unit. The generation unit dynamically generates the avatar's facial expressions and movements using, for example, image generation AI. For example, the generation unit generates an avatar's movement of smiling and returning a greeting in real time and displays it to the user. The generation unit can also generate an avatar's movement of shaking hands or an avatar's movement of inviting the user to play in real time. Furthermore, the generation unit can generate avatar behavior in real time that matches the user's intention. For example, if the user says "Let's play together," the generation unit generates an avatar's movement of inviting the user to play in real time. As a result, the agent system according to the embodiment can generate avatar behavior in real time based on the user's text and touch events, thereby achieving natural communication.Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may generate the behavior of an avatar using a generation AI model that receives the intention estimated by the analysis unit as input and outputs the behavior of the avatar.

[0058] The agent system includes a reception unit that estimates a user's emotion and adjusts the reception method for text and touch events based on the estimated user emotion. The reception unit estimates the user's emotion and adjusts the reception method for text and touch events based on the estimated user emotion. For example, if the user is stressed, the reception unit provides a simple interface and minimizes input steps. Alternatively, if the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input and quickly accept text and touch events. This allows for a more appropriate interface by adjusting the reception method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or without AI. For example, the reception unit may input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0059] The reception unit can analyze the user's past interaction history and select an appropriate reception method. The reception unit analyzes the user's past interaction history and selects the optimal reception method. For example, the reception unit can prioritize and suggest input methods (such as voice and text) that the user has frequently used in the past. The reception unit can also automatically recognize specific touch events performed by the user in the past and enable the user to easily accept similar events. Furthermore, the reception unit can predict and suggest an input method to be used during a specific time period based on the user's past interaction history. This can improve the user experience by providing the optimal reception method based on the past interaction history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past interaction history data into a generation AI and have the generation AI select the optimal reception method.

[0060] The reception unit can perform filtering based on the user's current context when receiving text or touch events. The reception unit performs filtering based on the user's current context (e.g., time of day or location) when receiving text or touch events. For example, if the user uses the device at night, the reception unit can provide an interface suitable for a dark environment. Also, if the user is in a specific location, the reception unit can preferentially display input options related to that location. Furthermore, if the user is on the move, the reception unit can provide an interface that is easy to operate. This makes it possible to provide a more appropriate interface by filtering according to the user's current context. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the user's current context data to the generation AI and have the generation AI perform the filtering process.

[0061] The reception unit can select an appropriate reception means according to the user's input method when receiving text or touch events. The reception unit selects the optimal reception means according to the user's input method (voice, text, gesture, etc.) when receiving text or touch events. For example, when the user gives instructions by voice, the reception unit can preferentially receive voice input. Also, when the user gives instructions by text, the reception unit can preferentially receive text input. Furthermore, when the user gives instructions by gesture, the reception unit can preferentially receive gesture input. This can improve the user experience by providing the optimal reception means according to the user's input method. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's input method data to the generation AI and cause the generation AI to select the optimal reception means.

[0062] The reception unit can estimate the user's emotions and prioritize events to be accepted based on the estimated user emotions. The reception unit can estimate the user's emotions and prioritize events to be accepted based on the estimated user emotions. For example, if the user is stressed, the reception unit can prioritize important events. If the user is relaxed, the reception unit can equally prioritize all events. If the user is in a hurry, the reception unit can prioritize urgent events. This enables more appropriate responses by prioritizing events according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using an AI, for example, or without an AI. For example, the reception unit can input the user's emotion data into the generation AI and have the generation AI set the event priorities.

[0063] When receiving text or touch events, the reception unit can prioritize receiving highly relevant events based on the user's geographical location information. When receiving text or touch events, the reception unit prioritizes receiving highly relevant events taking the user's geographical location information into consideration. For example, when the user is in a specific location, the reception unit prioritizes receiving events related to that location. Furthermore, when the user is traveling, the reception unit can prioritize receiving events related to the user's destination. Furthermore, when the user is at home, the reception unit can prioritize receiving events related to the user's home. This enables more appropriate responses by determining the priority of events based on the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information data to a generation AI and cause the generation AI to select highly relevant events.

[0064] The reception unit can analyze the user's social media activity and receive related events when receiving text or touch events. The reception unit can analyze the user's social media activity and receive related events when receiving text or touch events. For example, the reception unit can prioritize events related to places where the user has checked in on social media. The reception unit can also analyze the content of the user's social media posts and prioritize related events. Furthermore, the reception unit can prioritize related events by referring to the activities of the user's friends on social media. This enables more appropriate responses by receiving events based on the user's social media activity. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or can be performed without AI. For example, the reception unit can input the user's social media activity data into a generation AI and cause the generation AI to select related events.

[0065] The reception unit can change the reception method by reflecting the user's past feedback when receiving a text or touch event. The reception unit customizes the reception method by reflecting the user's past feedback when receiving a text or touch event. For example, the reception unit can preferentially provide reception methods that the user has previously preferred. It can also avoid reception methods that the user has previously dissatisfied with. Furthermore, the reception unit can suggest an optimal reception method based on the user's past feedback. This can improve the user experience by providing a reception method based on the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the reception method.

[0066] The analysis unit can estimate the user's emotions and change the intent analysis method based on the estimated user emotions. The analysis unit can estimate the user's emotions and adjust the intent analysis method based on the estimated user emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis to accurately estimate the user's intent. If the user is in a hurry, the analysis unit can perform a quick analysis to quickly estimate the user's intent. Furthermore, if the user is excited, the analysis unit can analyze the user's intent taking into account emotional fluctuations. This allows for more accurate intent estimation by providing an intent analysis method that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the intent analysis method.

[0067] During analysis, the analysis unit can improve the accuracy of intent analysis based on the user's past interaction history. During analysis, the analysis unit improves the accuracy of intent analysis by referring to the user's past interaction history. For example, the analysis unit accurately estimates intent based on specific touch events performed by the user in the past. The analysis unit can also analyze intent by referring to the user's past text input history. Furthermore, the analysis unit can find specific patterns from the user's past interaction history and estimate intent. This enables more accurate intent estimation by improving the accuracy of intent analysis based on the past interaction history. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past interaction history data to the generation AI and cause the generation AI to improve the accuracy of intent analysis.

[0068] During analysis, the analysis unit can infer intent based on the user's current context. During analysis, the analysis unit infers intent based on the user's current context (e.g., time of day or location). For example, if the user uses the device at night, the analysis unit can prioritize analyzing intent related to nighttime. Also, if the user is in a specific location, the analysis unit can prioritize analyzing intent related to that location. Furthermore, if the user is moving, the analysis unit can prioritize analyzing intent related to movement. This enables more accurate intent analysis by estimating intent based on the user's current context. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's current context data to the generation AI and cause the generation AI to estimate the intent.

[0069] The analysis unit can apply different analysis algorithms depending on the user's input method during analysis. The analysis unit can apply different analysis algorithms depending on the user's input method (voice, text, gesture, etc.) during analysis. For example, if the user gives instructions by voice, the analysis unit can apply a voice analysis algorithm. If the user gives instructions by text, the analysis unit can apply a text analysis algorithm. Furthermore, if the user gives instructions by gesture, the analysis unit can apply a gesture analysis algorithm. This allows for more accurate analysis of the user's intentions by providing an analysis algorithm depending on the user's input method. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input user's input method data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0070] The analysis unit can estimate the user's emotions and prioritize intentions based on the estimated user emotions. The analysis unit estimates the user's emotions and prioritizes intentions based on the estimated user emotions. For example, if the user is stressed, the analysis unit prioritizes important intentions. Furthermore, if the user is relaxed, the analysis unit can analyze all intentions equally. Furthermore, if the user is in a hurry, the analysis unit can prioritize urgent intentions. This enables more appropriate responses by prioritizing intentions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI prioritize the intentions.

[0071] During analysis, the analysis unit can infer the intention based on the user's geographical location information. During analysis, the analysis unit infers the intention taking the user's geographical location information into consideration. For example, when the user is in a specific location, the analysis unit can prioritize analyzing intentions related to that location. Furthermore, when the user is traveling, the analysis unit can prioritize analyzing intentions related to traveling. Furthermore, when the user is at home, the analysis unit can prioritize analyzing intentions related to home. This enables more accurate analysis of intentions by estimating the intention based on the user's geographical location information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's geographical location information data to the generation AI and cause the generation AI to estimate the intention.

[0072] The analysis unit can analyze the user's social media activity and infer related intentions during analysis. The analysis unit can analyze the user's social media activity and infer related intentions during analysis. For example, the analysis unit can prioritize analysis of intentions related to places where the user has checked in on social media. The analysis unit can also analyze the content of the user's social media posts and prioritize analysis of related intentions. Furthermore, the analysis unit can prioritize analysis of related intentions by referring to the activities of the user's friends on social media. This enables more accurate analysis of intentions by estimating intentions based on the user's social media activity. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's social media activity data into a generation AI and cause the generation AI to estimate intentions.

[0073] The analysis unit can change the analysis method during analysis by reflecting the user's past feedback. The analysis unit can customize the analysis method during analysis by reflecting the user's past feedback. For example, the analysis unit can preferentially apply analysis methods that the user has previously preferred. Also, the analysis unit can avoid analysis methods that the user has previously dissatisfied with. Furthermore, the analysis unit can suggest an optimal analysis method based on the user's past feedback. This enables more accurate analysis of intent by providing an analysis method based on the user's past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past feedback data into the generation AI and have the generation AI customize the analysis method.

[0074] The generation unit can estimate the user's emotion and change the avatar's behavior generation method based on the estimated user's emotion. The generation unit can estimate the user's emotion and adjust the avatar's behavior generation method based on the estimated user's emotion. For example, if the user is relaxed, the generation unit can generate avatar behavior that proceeds at a leisurely pace. If the user is in a hurry, the generation unit can generate avatar behavior that emphasizes quick movements. Furthermore, if the user is excited, the generation unit can generate avatar behavior that adds a visually stimulating effect. This enables more natural communication by providing an avatar behavior generation method that corresponds to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input user emotion data to the generation AI and cause the generation AI to adjust the method of generating the avatar's behavior.

[0075] The generation unit can improve the accuracy of avatar behavior generation based on the user's past interaction history during generation. The generation unit improves the accuracy of avatar behavior generation by referring to the user's past interaction history during generation. For example, the generation unit accurately generates avatar behavior based on a specific touch event performed by the user in the past. The generation unit can also generate avatar behavior by referring to the user's past text input history. Furthermore, the generation unit can find specific patterns from the user's past interaction history and generate avatar behavior. This improves the accuracy of avatar behavior generation based on the past interaction history, enabling more natural communication. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input the user's past interaction history data into the generation AI and cause the generation AI to improve the accuracy of avatar behavior generation.

[0076] The generation unit can generate avatar behavior based on the user's current context at the time of generation. The generation unit generates avatar behavior based on the user's current context (e.g., time of day or location) at the time of generation. For example, if the user uses the device at night, the generation unit can generate avatar behavior related to nighttime. Also, if the user is in a specific location, the generation unit can generate avatar behavior related to that location. Furthermore, if the user is moving, the generation unit can generate avatar behavior related to movement. This enables more natural communication by generating avatar behavior based on the user's current context. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's current context data to the generation AI and cause the generation AI to generate avatar behavior.

[0077] The generation unit can apply different generation algorithms depending on the user's input method during generation. The generation unit can apply different generation algorithms depending on the user's input method (voice, text, gesture, etc.) during generation. For example, when a user gives instructions by voice, the generation unit can generate avatar behavior corresponding to the voice input. When a user gives instructions by text, the generation unit can generate avatar behavior corresponding to the text input. When a user gives instructions by gesture, the generation unit can generate avatar behavior corresponding to the gesture input. This enables more natural communication by providing a generation algorithm corresponding to the user's input method. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user's input method data to the generation AI and cause the generation AI to apply the generation algorithm.

[0078] The generation unit can estimate the user's emotions and prioritize the avatar's behaviors based on the estimated user emotions. The generation unit can estimate the user's emotions and prioritize the avatar's behaviors based on the estimated user emotions. For example, if the user is stressed, the generation unit can prioritize relaxing behaviors. Also, if the user is relaxed, the generation unit can generate all behaviors equally. Furthermore, if the user is in a hurry, the generation unit can prioritize quick behaviors. This enables a more appropriate response by prioritizing the avatar's behaviors according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, an AI, or without an AI. For example, the generation unit can input the user's emotion data into the generation AI and cause the generation AI to prioritize the avatar's behaviors.

[0079] The generation unit can generate avatar behavior based on the user's geographical location information at the time of generation. The generation unit generates avatar behavior taking the user's geographical location information into consideration at the time of generation. For example, if the user is in a specific location, the generation unit can generate avatar behavior related to that location. Also, if the user is moving, the generation unit can generate avatar behavior related to the movement. Furthermore, if the user is at home, the generation unit can generate avatar behavior related to the home. This enables more natural communication by generating avatar behavior based on the user's geographical location information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's geographical location information data to the generation AI and cause the generation AI to generate avatar behavior.

[0080] The generation unit can analyze the user's social media activity and generate the behavior of the related avatar at the time of generation. The generation unit can analyze the user's social media activity and generate the behavior of the related avatar at the time of generation. For example, the generation unit can generate the behavior of the avatar related to the place where the user checked in on social media. The generation unit can also analyze the content of the user's social media posts and generate the behavior of the related avatar. Furthermore, the generation unit can generate the behavior of the related avatar by referring to the activities of the user's friends on social media. This enables more natural communication by generating the behavior of the avatar based on the user's social media activity. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's social media activity data into the generation AI and cause the generation AI to generate the behavior of the avatar.

[0081] The generation unit can change the avatar behavior generation method by reflecting the user's past feedback at the time of generation. The generation unit can customize the avatar behavior generation method by reflecting the user's past feedback at the time of generation. For example, the generation unit can prioritize the generation of behaviors that the user has previously preferred. Also, the generation unit can avoid behaviors that the user has previously dissatisfied with. Furthermore, the generation unit can propose an optimal behavior generation method based on the user's past feedback. This enables more natural communication by providing an avatar behavior generation method based on the user's past feedback. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the avatar behavior generation method. === Hard Collateral 1-1 === Each of the above-described elements, including the reception unit, analysis unit, generation unit, and emotion estimation function, is realized by, for example, at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives a user's text or touch events using a touch panel 38A or a microphone 38B of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's intention. The generation unit generates avatar behavior in real time using the control unit 46A of the smart device 14. The emotion estimation function is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's emotion. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and emotion estimation function is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives a user's text or touch events using the microphone 238 or touch panel of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's intention. The generation unit generates avatar behavior in real time by the control unit 46A of the smart glasses 214. The emotion estimation function is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's emotion. === Hard Collateral 1-3 === Each of the multiple elements including the above-described reception unit, analysis unit, generation unit, and emotion estimation function is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit receives user text and touch events using the microphone 238 or touch panel of the headset-type terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's intention. The generation unit generates avatar behavior in real time by the control unit 46A of the headset-type terminal 314. The emotion estimation function is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's emotion. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and emotion estimation function is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives user text and touch events using the microphone 238 or touch panel of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's intention. The generation unit generates avatar behavior in real time using the control unit 46A of the robot 414. The emotion estimation function is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's emotion.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The reception unit can acquire the user's biometric information (e.g., heart rate and electrodermal activity) and estimate the user's stress level. For example, if the user's heart rate is high, the reception unit can infer that the user is feeling stressed and provide a simple interface. Alternatively, if the user's electrodermal activity is low, the reception unit can infer that the user is relaxed and provide detailed input options. Furthermore, the reception unit can continuously monitor the user's biometric information and adjust the interface in real time. This makes it possible to provide an interface based on the user's biometric information, resulting in a more appropriate user experience.

[0084] The analysis unit can analyze the user's voice tone and speech rate to estimate the user's emotions. For example, if the user's voice tone is high and the speech rate is fast, the analysis unit can estimate that the user is excited and take prompt action. Alternatively, if the user's voice tone is low and the speech rate is slow, the analysis unit can estimate that the user is relaxed and provide a detailed explanation. Furthermore, the analysis unit can continuously analyze the user's voice data and detect changes in emotions in real time. This makes it possible to estimate emotions based on the user's voice characteristics, allowing for more appropriate responses.

[0085] The generation unit can customize the behavior of the avatar based on the user's past purchasing history. For example, if the user has frequently purchased products from a specific brand in the past, the generation unit can generate avatar behavior related to that brand. Also, if the user has purchased products from a specific category in the past, the generation unit can generate avatar behavior related to that category. Furthermore, it is possible to find specific patterns from the user's purchasing history and customize the avatar's behavior. This makes it possible to generate avatar behavior based on the user's purchasing history, thereby providing a more personalized experience.

[0086] The reception unit can obtain the user's calendar information and provide an appropriate reception method based on the schedule. For example, if the user is in a meeting, the reception unit will avoid voice input and prioritize text input. Also, if the user is on the move, the reception unit can provide an interface that is easy to operate. Furthermore, the reception unit can continuously monitor the user's calendar information and adjust the reception method in real time. This makes it possible to provide an interface based on the user's schedule, resulting in a more appropriate user experience.

[0087] The analysis unit can analyze the user's emotional expressions on social media and infer the user's emotions. For example, if the user posts positive things on social media, the analysis unit can infer that the user is relaxed and provide a detailed explanation. If the user posts negative things, the analysis unit can infer that the user is stressed and provide a simple interface. Furthermore, the analysis unit can continuously analyze the user's emotional expressions on social media and detect changes in emotions in real time. This makes it possible to infer emotions based on the user's social media activity, enabling more appropriate responses.

[0088] The generator can customize the behavior of the avatar based on the user's health data (e.g., step count and sleep data). For example, if the user is getting enough sleep, the generator can generate an energetic avatar behavior. Alternatively, if the user is not getting enough exercise, the generator can generate an avatar behavior that encourages exercise. Furthermore, the generator can continuously monitor the user's health data and adjust the avatar behavior in real time. This makes it possible to generate avatar behavior based on the user's health condition, providing a more personalized experience.

[0089] The reception unit can acquire the user's music playback history and provide an appropriate reception method based on the music being played. For example, if the user is playing relaxing music, the reception unit can provide detailed input options. On the other hand, if the user is playing fast-paced music, the reception unit can provide a simple interface. Furthermore, the reception unit can continuously monitor the user's music playback history and adjust the reception method in real time. This makes it possible to provide an interface based on the user's music playback status, resulting in a more appropriate user experience.

[0090] The analysis unit can analyze the content of a user's email and infer the user's emotions. For example, if the user is sending an email with positive content, the analysis unit can infer that the user is relaxed and provide a detailed explanation. If the user is sending an email with negative content, the analysis unit can infer that the user is stressed and provide a simple interface. Furthermore, the analysis unit can continuously analyze the content of a user's email and detect changes in emotions in real time. This makes it possible to infer emotions based on the content of the user's email, enabling more appropriate responses.

[0091] The generation unit can customize the behavior of the avatar based on the user's hobbies and interests. For example, if the user is interested in sports, the generation unit can generate avatar behavior related to sports. Also, if the user is interested in music, the generation unit can generate avatar behavior related to music. Furthermore, the user's hobbies and interests can be continuously monitored and the avatar behavior can be adjusted in real time. This makes it possible to generate avatar behavior based on the user's hobbies and interests, providing a more personalized experience.

[0092] The analysis unit can estimate emotions based on data acquired from the user's wearable device. For example, it can analyze the user's heart rate and electrodermal activity to estimate the user's stress level. It can also analyze the user's body temperature and breathing rate to estimate the user's level of relaxation. It can also continuously monitor data from the user's wearable device to detect changes in emotions in real time. This makes it possible to estimate emotions based on the user's biometric information, enabling more appropriate responses.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The reception unit receives user text and touch events. User text and touch events include chat messages, clicks, swipes, voice input, and gesture input. For example, the reception unit can receive the user's text "Hello," a touch event of patting an avatar's head, a voice message saying "Hello," or a gesture of touching an avatar. Step 2: The analysis unit analyzes the information received by the reception unit and infers the user's intention. The analysis unit uses natural language processing technology and machine learning algorithms to infer the user's intention from the user's text and touch events. For example, if the user types "hello," the analysis unit infers the avatar's intention to return the greeting with a smile, and if the user pats the avatar's head, the analysis unit infers the avatar's happy behavior. The analysis unit can also infer the user's intention by taking into account the user's past interaction history and current context. Step 3: The generator generates the avatar's behavior in real time based on the intention estimated by the analyzer. The generator uses image generation AI to dynamically generate the avatar's facial expressions and movements. For example, it can generate in real time an avatar's movements to return a greeting with a smile, shake hands, or invite someone to play. The generator generates avatar behavior in real time that matches the user's intention, enabling natural communication.

[0095] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0097] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0098] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0099] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0100] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0101] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0102] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0103] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0104] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0105] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0106] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0107] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0108] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0109] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0110] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0113] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0114] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0115] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0116] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0122] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0125] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0139] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0142] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0149] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0150] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0151] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0152] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0153] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0154] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0155] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0156] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0157] 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.

[0158] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0159] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0160] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0161] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0162] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0163] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0164] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0165] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0166] [Explanation of symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives user text and touch events; an analysis unit that analyzes the information received by the reception unit and infers the user's intention; a generation unit that instantly generates a behavior of an avatar based on the intention estimated by the analysis unit. A system characterized by:

2. The reception unit Estimate the user's emotions and change the way text and touch events are received based on the estimated user emotions.

2. The system of claim 1.

3. The reception unit Analyze the user's past interaction history and select the appropriate reception method 2. The system of claim 1.

4. The reception unit When receiving text or touch events, filter them based on the user's current context.

2. The system of claim 1.

5. The reception unit When accepting text or touch events, select the appropriate acceptance method depending on the user's input method.

2. The system of claim 1.

6. The reception unit Estimate the user's emotions and prioritize events based on the estimated user emotions.

2. The system of claim 1.

7. The reception unit When receiving text and touch events, prioritize events that are more relevant to the user based on their geographic location.

2. The system of claim 1.

8. The reception unit When receiving text or touch events, analyze the user's social media activity and receive related events.

2. The system of claim 1.

Images