JP7852004B2 - system - Google Patents

Description

The technology disclosed herein relates to a system.

Patent Document 1 discloses a persona chatbot control method performed by at least one processor, comprising the steps of: receiving a user utterance; adding the user utterance to a prompt containing instructions related to a description of the chatbot's character; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Japanese Patent Publication No. 2022-180282

Current technologies do not adequately generate avatars based on user messages and call interactions, and there is room for improvement.

The system according to this embodiment aims to generate an avatar based on user messages and call exchanges, and to facilitate interaction.

The system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, and a dialogue unit. The collection unit collects user messages or call exchanges. The analysis unit analyzes the information collected by the collection unit and extracts user characteristics. The generation unit generates an avatar based on the characteristics extracted by the analysis unit. The dialogue unit allows the avatar generated by the generation unit to engage in dialogue.

The system according to this embodiment can generate an avatar based on user messages and call exchanges, and engage in dialogue with it.

This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. This shows an emotion map where multiple emotions are mapped. This shows an emotion map where multiple emotions are mapped.

An example of an embodiment of the system relating to the technology of this disclosure will be described below with reference to the attached drawings.

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

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

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

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

In the following embodiments, the coded communication interface (I/F) is an interface including a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi®, or Bluetooth®.

In the following embodiments, "A and/or B" is synonymous with "at least one of A and B." That is, "A and/or B" means that A alone, B alone, or a combination of A and B may be used. Furthermore, the same concept applies when expressing three or more things linked by "and/or" in this specification.

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

As shown in Figure 1, the data processing system 10 comprises a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to the bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. The storage 32 stores a specific processing program 56. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

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

(Example of form 1)
The interactive avatar system according to an embodiment of the present invention is a system that collects user messages and call exchanges, and a generating AI analyzes the user's characteristics to generate an anthropomorphic avatar. This interactive avatar system can generate an interactive avatar that reflects the user's characteristics and can engage in conversations on behalf of the user in times of emergency. For example, it collects user messages and call exchanges, and the generating AI analyzes the user's speaking style and expression characteristics. Next, the generating AI generates an avatar based on the analyzed characteristics, and this avatar engages in conversations on behalf of the user. This allows the user to live their daily life with peace of mind. Thus, the interactive avatar system can generate an avatar that reflects the user's characteristics and can engage in conversations on behalf of the user in times of emergency.

The interactive avatar system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, and a dialogue unit. The collection unit collects user messages or call exchanges. The collection unit can collect data such as text messages, voice calls, and video calls. The collection unit collects the content of messages and calls sent by the user in detail and provides this data to the analysis unit. The analysis unit analyzes the collected data and extracts user characteristics. The analysis unit analyzes the characteristics of the user's way of speaking and expression using, for example, natural language processing technology. The analysis unit extracts words, phrases, and speaking tone that the user frequently uses. The generation unit generates an avatar based on the characteristics extracted by the analysis unit. The generation unit generates an avatar that reflects the user's characteristics using a generation AI. The generation AI generates the avatar's dialogue content using, for example, a text generation AI (e.g., LLM). The generation unit can generate 3D models, 2D characters, voice-only avatars, etc., that reflect the user's characteristics. The dialogue unit has the generated avatar engage in dialogue on behalf of the user. The dialogue unit conducts conversations using methods such as text chat, voice chat, and video chat. The dialogue unit can use generative AI to conduct conversations that reflect the user's characteristics. As a result, the dialogue avatar system according to this embodiment can generate an avatar that reflects the user's characteristics and conduct conversations on behalf of the user in times of emergency. For example, the dialogue unit can have the generated avatar conduct a conversation on behalf of the user and respond appropriately. This allows the user to live their daily life with peace of mind.

The data collection unit collects user messages and call interactions. For example, the collection unit can collect data from text messages, voice calls, and video calls. Specifically, in the case of text messages, it acquires the text information sent by the user in real time; in the case of voice calls, it records the call content and stores it as audio data; and in the case of video calls, it collects both video and audio to obtain detailed information such as the user's facial expressions and tone of voice. This data is centrally managed by the data collection unit and provided to the analysis unit. The data collection unit can use encryption technology to protect privacy when collecting data. For example, collected data is encrypted at the time of collection to prevent unauthorized access by third parties until it is transmitted to the analysis unit. Furthermore, the data collection unit has a mechanism to collect data only after obtaining the user's consent, and can stop collection if the user refuses data collection. This allows the data collection unit to efficiently collect necessary data while protecting user privacy. In addition, the data collection unit is equipped with high-speed data transfer technology to provide collected data to the analysis unit in real time, thereby improving the overall system response speed.

The analysis unit analyzes the collected data and extracts user characteristics. For example, the analysis unit uses natural language processing technology to analyze the characteristics of the user's speech and expression. Specifically, in the case of text messages, it performs morphological and grammatical analysis to identify words and phrases that the user frequently uses. In the case of voice calls, it uses speech recognition technology to convert voice data into text and analyzes that text data. It can also extract features such as voice tone, speaking speed, and emotional expression from the voice data. In the case of video calls, it uses video analysis technology to analyze the user's facial expressions and gestures, and infers the user's emotions and intentions based on this information. The analysis unit integrates these analysis results to comprehensively understand the user's characteristics. Furthermore, the analysis unit can learn user behavior patterns and preferences by utilizing past data and user history information. For example, based on past conversation history, it can predict how the user will react in specific situations and provide information to realize more natural conversations. In addition, the analysis unit can use anomaly detection algorithms to detect unusual user behavior or statements and issue warnings as needed. This allows the analysis unit to accurately understand user characteristics and improve the overall dialogue quality of the system.

The generation unit generates avatars based on features extracted by the analysis unit. The generation unit uses a generation AI to create avatars that reflect the user's characteristics. Specifically, it uses a text generation AI (e.g., LLM) to generate the avatar's dialogue. The generation AI learns the user's speaking style and expressive characteristics and generates natural dialogue based on that. For example, it can generate dialogue incorporating words and phrases frequently used by the user, creating avatar statements that resemble the user's speaking style. The generation unit can also generate 3D models, 2D characters, and voice-only avatars that reflect the user's characteristics. In the case of 3D models, it can generate avatars that reproduce the user's appearance and facial expressions and operate them in real time. In the case of 2D characters, it generates illustrations and animations that reflect the user's characteristics and displays them during dialogue. In the case of voice-only avatars, it uses speech synthesis technology that reflects the user's voice characteristics to achieve natural voice dialogue. The generation unit provides these generation results to the dialogue unit, preparing it to engage in dialogue on behalf of the user. Furthermore, the generation unit can evaluate the quality of the generated avatars and make corrections or improvements as needed. For example, if the generated dialogue is unnatural or does not accurately reflect the user's characteristics, it will regenerate the avatar to improve its quality. This allows the generation unit to produce high-quality avatars that accurately reflect the user's characteristics, thereby improving the overall dialogue quality of the system.

The dialogue unit uses a generated avatar to interact on behalf of the user. The dialogue unit engages in conversations using methods such as text chat, voice chat, and video chat. Specifically, in the case of text chat, it sends text messages generated by a generative AI on behalf of the user and engages in conversation with the other party. In the case of voice chat, it plays voice generated using speech synthesis technology and engages in conversation on behalf of the user. In the case of video chat, it displays a generated 3D model or 2D character and engages in conversation while it operates in real time. The dialogue unit can use generative AI to conduct conversations that reflect the user's characteristics. For example, it can generate dialogue content incorporating words and phrases frequently used by the user and create avatar statements that resemble the user's speaking style. Furthermore, the dialogue unit can incorporate new dialogue content generated by the generative AI in real time as the conversation progresses. This enables the dialogue unit to achieve natural and smooth conversations and respond appropriately on behalf of the user. In addition, the dialogue unit can record the content and progress of the conversation and provide this information to the analysis and generation units later. This allows for continuous improvement of the overall dialogue quality of the system through feedback. For example, if the content of the dialogue is inappropriate or does not accurately reflect the user's characteristics, the analysis and generation units can correct or improve it based on that information. This allows the dialogue unit to conduct high-quality conversations on behalf of the user, improving the overall reliability and satisfaction of the system.

The collection unit can collect user messages or call content. For example, the collection unit can collect data such as text messages, voice calls, and video calls. The collection unit meticulously collects the content of messages and calls sent by the user and provides this data to the analysis unit. This allows for the understanding of user characteristics by collecting user messages and call content. Some or all of the processing described above in the collection unit may be performed using AI, or without AI. For example, the collection unit can input user messages and call content into AI, which can then analyze the data.

The analysis unit can analyze the collected data and extract characteristics of the user's speech or expression. For example, the analysis unit uses natural language processing techniques to analyze the user's speech and expression characteristics. The analysis unit extracts frequently used words, phrases, and speech tone. By extracting these characteristics, it is possible to generate an avatar that reflects the user's features. Some or all of the above-described processing in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the collected data into AI, which can then analyze the data.

The generation unit can generate avatars based on extracted features. The generation unit uses a generation AI to generate avatars that reflect the user's characteristics. The generation AI, for example, uses a text generation AI (e.g., LLM) to generate the avatar's dialogue. The generation unit can generate 3D models, 2D characters, or voice-only avatars that reflect the user's characteristics. This allows the generation unit to provide avatars that reflect the user's characteristics by generating avatars based on extracted features. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or without using a generation AI. For example, the generation unit can input extracted features into a generation AI, which can then generate an avatar.

The dialogue unit allows a generated avatar to engage in dialogue on behalf of the user. The dialogue unit conducts dialogue using methods such as text chat, voice dialogue, and video dialogue. The dialogue unit can use a generation AI to conduct dialogue that reflects the user's characteristics. This allows the generated avatar to engage in dialogue on behalf of the user, enabling appropriate responses in emergencies. Some or all of the above-described processes in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the generated avatar into the AI, which can then conduct the dialogue.

The dialogue unit can use algorithms to respond in the event of an emergency. For example, the dialogue unit can take appropriate action in an emergency using emergency response scenarios and the AI technology it employs. This allows it to take appropriate action on behalf of the user by using algorithms designed for appropriate responses in emergencies. Some or all of the above-described processes in the dialogue unit may be performed using AI, or not. For example, the dialogue unit can input emergency response scenarios into the AI, which can then perform the response.

The data collection unit can analyze the user's past messages and call history and select a collection method. For example, the collection unit can prioritize collecting data from messaging and calling apps that the user frequently used in the past. Furthermore, the collection unit can concentrate data collection on specific time periods based on the user's past messages and call history. In addition, the collection unit can analyze the user's past communication patterns and select the most effective collection method. This allows the optimal collection method to be selected by analyzing the user's past messages and call history. Some or all of the above processing in the collection unit may be performed using AI, or without AI. For example, the collection unit can input the user's past messages and call history into AI, which can then select a collection method.

The data collection unit can filter messages and call content based on the user's current lifestyle and areas of interest. For example, if the user is at work, the unit can prioritize collecting work-related messages and call content. Similarly, if the user is engaged in a hobby, the unit can collect messages and call content related to that hobby. Furthermore, if the user is traveling, the unit can collect travel-related messages and call content. This allows for the collection of more relevant data by filtering based on the user's lifestyle and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input the user's lifestyle and areas of interest into the AI, which can then perform the filtering.

The data collection unit can prioritize the collection of highly relevant content based on the user's geographical location when collecting messages and call content. For example, if the user is in a specific region, the data collection unit can prioritize the collection of messages and call content related to that region. Furthermore, if the user is traveling, the data collection unit can prioritize the collection of messages and call content related to their travel destination. Additionally, if the user is at home, the data collection unit can prioritize the collection of messages and call content related to their home. This allows for the priority collection of highly relevant data by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input the user's geographical location information into AI, which can then prioritize the collection of highly relevant content.

The data collection unit can analyze the user's social media activity and collect relevant content when collecting messages and call content. For example, the collection unit can prioritize collecting messages and call content with people the user frequently interacts with on social media. It can also collect messages and call content related to topics the user shows interest in on social media. Furthermore, it can collect messages and call content related to groups and communities the user participates in on social media. This allows for the collection of relevant content by analyzing the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input the user's social media activity into AI, which can then collect relevant content.

The analysis unit can adjust the level of detail of the analysis based on the importance of the message or call content during the analysis. For example, the analysis unit can perform a detailed analysis of high-importance messages or call content, extracting features down to the finest detail. Conversely, for low-importance messages or call content, the analysis unit can perform a simplified analysis, extracting only the main features. Furthermore, for urgent messages or call content, the analysis unit can perform a rapid analysis, immediately extracting features. This allows for efficient analysis by adjusting the level of detail based on the importance of the message or call content. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the importance of the message or call content into the AI, which can then adjust the level of detail of the analysis.

The analysis unit can apply different analysis algorithms depending on the category of the message or call content during analysis. For example, the analysis unit can apply an algorithm that analyzes formal expressions and technical terms to business-related messages and calls. It can also apply an algorithm that analyzes casual expressions and everyday language to private messages and calls. Furthermore, it can apply an algorithm for rapid response to urgent messages and calls. By applying different analysis algorithms depending on the category of the message or call content, more accurate analysis can be achieved. Some or all of the above processing in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the category of the message or call content into the AI, which can then apply different analysis algorithms.

The analysis unit can determine the priority of analysis based on the submission timing of messages and call content. For example, the analysis unit can prioritize the analysis of recently sent messages and call content. It can also prioritize the analysis of messages and call content sent within a specific time period. Furthermore, it can prioritize the analysis of messages and call content of high urgency. This allows for efficient analysis by determining the priority of analysis based on the submission timing of messages and call content. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the submission timing of messages and call content into the AI, which can then determine the analysis priority.

The analysis unit can adjust the order of analysis based on the relevance of messages and call content during the analysis process. For example, the analysis unit can prioritize the analysis of highly relevant messages and call content. It can also postpone the analysis of less relevant messages and call content. Furthermore, the analysis unit can prioritize the analysis of messages and call content related to specific topics. This allows for efficient analysis by adjusting the order of analysis based on the relevance of messages and call content. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the relevance of messages and call content into the AI, which can then adjust the order of analysis.

The generation unit can adjust the level of detail of the avatar based on the importance of the user's characteristics during avatar generation. For example, if the user's characteristics are clear, the generation unit can generate a detailed avatar. If the user's characteristics are ambiguous, the generation unit can generate a simplified avatar. Furthermore, if the user's characteristics are diverse, the generation unit can generate an avatar that emphasizes the main characteristics. This allows for the generation of a more appropriate avatar by adjusting the level of detail based on the importance of the user's characteristics. Some or all of the above processing in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the importance of the user's characteristics into the AI, which can then adjust the level of detail of the avatar.

The generation unit can apply different generation algorithms depending on the user's category when generating avatars. For example, the generation unit can apply a generation algorithm with formal expressions and actions to avatars for business use. It can also apply a generation algorithm with casual expressions and actions to avatars for private use. Furthermore, it can apply a generation algorithm for rapid response to avatars in emergencies. By applying different generation algorithms according to the user's category, a more appropriate avatar can be generated. Some or all of the above processing in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the user's category into the AI, which can then apply different generation algorithms.

The generation unit can determine the generation priority based on the user's past avatar usage history when generating avatars. For example, the generation unit can prioritize the reflection of features in avatars frequently used by the user in the past. Furthermore, the generation unit can predict and generate avatars to be used during specific time periods based on the user's past avatar usage history. In addition, the generation unit can analyze the user's past avatar usage patterns and generate the most effective avatar. This allows for the generation of more appropriate avatars by determining the generation priority based on the user's past avatar usage history. Some or all of the above-described processes in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the user's past avatar usage history into AI, which can then determine the generation priority.

The generation unit can improve the accuracy of avatar generation by referring to the user's relevant data. For example, the generation unit can adjust the avatar's appearance and personality by referring to the user's social media profile and posts. It can also adjust the avatar's speech patterns and expressions by referring to the user's past messages and call content. Furthermore, the generation unit can customize the avatar's characteristics based on the user's hobbies and interests. This allows for improved generation accuracy by referring to the user's relevant data. Some or all of the above-described processes in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the user's relevant data into AI, which can then improve the generation accuracy.

The dialogue unit can select a dialogue method by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can incorporate expressions and phrases that the user has previously used frequently. Furthermore, the dialogue unit can select a dialogue method for a specific topic based on the user's past dialogue history. In addition, the dialogue unit can analyze the user's past dialogue patterns and select the most effective dialogue method. This allows the optimal dialogue method to be selected by referring to the user's past dialogue history. Some or all of the above processing in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the user's past dialogue history into AI, which can then select a dialogue method.

The dialogue unit can customize the dialogue method based on the user's current situation during a conversation. For example, if the user is at work, the dialogue unit can engage in a businesslike conversation. If the user is relaxed, it can engage in a casual conversation. Furthermore, if the user is in an emergency, the dialogue unit can engage in a quick and concise conversation. This allows for more appropriate conversations by customizing the dialogue method based on the user's current situation. Some or all of the above processing in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the user's current situation into the AI, which can then customize the dialogue method.

The dialogue unit can select the optimal dialogue method during a conversation, taking into account the user's geographical location. For example, if the user is in a specific region, the dialogue unit can provide information related to that region. Furthermore, if the user is traveling, the dialogue unit can provide information related to their travel destination. Additionally, if the user is at home, the dialogue unit can provide information related to their home. This allows the dialogue unit to select the optimal dialogue method by considering the user's geographical location. Some or all of the above processing in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the user's geographical location information into the AI, which can then select the optimal dialogue method.

The dialogue unit can analyze the user's social media activity during a conversation and suggest appropriate dialogue methods. For example, the dialogue unit can prioritize conversations with individuals the user frequently interacts with on social media. It can also conduct conversations related to topics the user has shown interest in on social media. Furthermore, it can conduct conversations related to groups and communities the user participates in on social media. This allows the dialogue unit to suggest the most suitable dialogue method by analyzing the user's social media activity. Some or all of the above processing in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the user's social media activity into AI, which can then suggest dialogue methods.

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

The interactive avatar system can further collect user health data and reflect it in the avatar's dialogue. For example, the data collection unit can collect heart rate and sleep data from the user's wearable device. The analysis unit can analyze this data to understand the user's health status. The generation unit can provide health advice through the avatar based on the user's health status. The dialogue unit can engage in conversations that encourage relaxation or exercise, depending on the user's health condition. This allows for more personalized support by providing dialogue that takes the user's health status into consideration.

The data collection unit can collect user environmental data and reflect it in the avatar's dialogue. For example, the data collection unit can collect environmental data such as temperature, humidity, and noise levels around the user. The analysis unit can analyze this data to understand the user's environmental conditions. The generation unit can provide advice to help the avatar maintain a comfortable environment based on the user's environmental conditions. The dialogue unit can engage in appropriate dialogue according to the user's environmental conditions. This allows for dialogue that considers the user's environmental conditions, thereby supporting a more comfortable life.

The analysis unit can analyze the user's hobbies and interests and reflect them in the avatar's dialogue. For example, the analysis unit can analyze data on keywords the user has previously searched for and websites they have visited. Based on this data, the generation unit can provide the avatar with topics related to the user's hobbies and interests. The dialogue unit can suggest relevant information and activities according to the user's hobbies and interests. This allows for more engaging dialogue by considering the user's interests.

The generation unit can customize the avatar's dialogue by referencing the user's past dialogue history. For example, the generation unit can incorporate expressions and phrases that the user has previously favored into the avatar's dialogue. The dialogue unit can select a dialogue method for a specific topic based on the user's past dialogue history. Furthermore, the generation unit can analyze the user's past dialogue patterns and select the most effective dialogue method. This allows for more personalized dialogue by referencing the user's past dialogue history.

The dialogue unit can customize the avatar's conversation content by considering the user's geographical location. For example, if the user is in a specific region, the dialogue unit can provide information relevant to that region. If the user is traveling, the dialogue unit can provide information relevant to their travel destination. Furthermore, if the user is at home, the dialogue unit can provide information relevant to their home. This allows for more relevant conversations by considering the user's geographical location.

The following briefly describes the processing flow for example 1.

Step 1: The collection unit collects user messages or call interactions. The collection unit can collect data such as text messages, voice calls, and video calls. The collection unit collects detailed information about the messages and calls sent by the user and provides this data to the analysis unit.
Step 2: The analysis unit analyzes the collected data and extracts user characteristics. For example, the analysis unit uses natural language processing technology to analyze the characteristics of the user's speech and expressions. The analysis unit extracts words, phrases, and speaking tone that the user frequently uses.
Step 3: The generation unit generates an avatar based on the features extracted by the analysis unit. The generation unit uses a generation AI to generate an avatar that reflects the user's characteristics. The generation AI uses, for example, a text generation AI (e.g., LLM) to generate the avatar's dialogue. The generation unit can generate 3D models, 2D characters, or voice-only avatars that reflect the user's characteristics.
Step 4: The dialogue unit has the generated avatar interact on behalf of the user. The dialogue unit interacts using methods such as text chat, voice dialogue, or video dialogue. The dialogue unit can use generation AI to conduct dialogue that reflects the user's characteristics. As a result, the dialogue avatar system according to the embodiment can generate an avatar that reflects the user's characteristics and interact on behalf of the user in times of emergency.

(Example of form 2)
The interactive avatar system according to an embodiment of the present invention is a system that collects user messages and call exchanges, and a generating AI analyzes the user's characteristics to generate an anthropomorphic avatar. This interactive avatar system can generate an interactive avatar that reflects the user's characteristics and can engage in conversations on behalf of the user in times of emergency. For example, it collects user messages and call exchanges, and the generating AI analyzes the user's speaking style and expression characteristics. Next, the generating AI generates an avatar based on the analyzed characteristics, and this avatar engages in conversations on behalf of the user. This allows the user to live their daily life with peace of mind. Thus, the interactive avatar system can generate an avatar that reflects the user's characteristics and can engage in conversations on behalf of the user in times of emergency.

The interactive avatar system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, and a dialogue unit. The collection unit collects user messages or call exchanges. The collection unit can collect data such as text messages, voice calls, and video calls. The collection unit collects the content of messages and calls sent by the user in detail and provides this data to the analysis unit. The analysis unit analyzes the collected data and extracts user characteristics. The analysis unit analyzes the characteristics of the user's way of speaking and expression using, for example, natural language processing technology. The analysis unit extracts words, phrases, and speaking tone that the user frequently uses. The generation unit generates an avatar based on the characteristics extracted by the analysis unit. The generation unit generates an avatar that reflects the user's characteristics using a generation AI. The generation AI generates the avatar's dialogue content using, for example, a text generation AI (e.g., LLM). The generation unit can generate 3D models, 2D characters, voice-only avatars, etc., that reflect the user's characteristics. The dialogue unit has the generated avatar engage in dialogue on behalf of the user. The dialogue unit conducts conversations using methods such as text chat, voice chat, and video chat. The dialogue unit can use generative AI to conduct conversations that reflect the user's characteristics. As a result, the dialogue avatar system according to this embodiment can generate an avatar that reflects the user's characteristics and conduct conversations on behalf of the user in times of emergency. For example, the dialogue unit can have the generated avatar conduct a conversation on behalf of the user and respond appropriately. This allows the user to live their daily life with peace of mind.

The data collection unit collects user messages and call interactions. For example, the collection unit can collect data from text messages, voice calls, and video calls. Specifically, in the case of text messages, it acquires the text information sent by the user in real time; in the case of voice calls, it records the call content and stores it as audio data; and in the case of video calls, it collects both video and audio to obtain detailed information such as the user's facial expressions and tone of voice. This data is centrally managed by the data collection unit and provided to the analysis unit. The data collection unit can use encryption technology to protect privacy when collecting data. For example, collected data is encrypted at the time of collection to prevent unauthorized access by third parties until it is transmitted to the analysis unit. Furthermore, the data collection unit has a mechanism to collect data only after obtaining the user's consent, and can stop collection if the user refuses data collection. This allows the data collection unit to efficiently collect necessary data while protecting user privacy. In addition, the data collection unit is equipped with high-speed data transfer technology to provide collected data to the analysis unit in real time, thereby improving the overall system response speed.

The analysis unit analyzes the collected data and extracts user characteristics. For example, the analysis unit uses natural language processing technology to analyze the characteristics of the user's speech and expression. Specifically, in the case of text messages, it performs morphological and grammatical analysis to identify words and phrases that the user frequently uses. In the case of voice calls, it uses speech recognition technology to convert voice data into text and analyzes that text data. It can also extract features such as voice tone, speaking speed, and emotional expression from the voice data. In the case of video calls, it uses video analysis technology to analyze the user's facial expressions and gestures, and infers the user's emotions and intentions based on this information. The analysis unit integrates these analysis results to comprehensively understand the user's characteristics. Furthermore, the analysis unit can learn user behavior patterns and preferences by utilizing past data and user history information. For example, based on past conversation history, it can predict how the user will react in specific situations and provide information to realize more natural conversations. In addition, the analysis unit can use anomaly detection algorithms to detect unusual user behavior or statements and issue warnings as needed. This allows the analysis unit to accurately understand user characteristics and improve the overall dialogue quality of the system.

The generation unit generates avatars based on features extracted by the analysis unit. The generation unit uses a generation AI to create avatars that reflect the user's characteristics. Specifically, it uses a text generation AI (e.g., LLM) to generate the avatar's dialogue. The generation AI learns the user's speaking style and expressive characteristics and generates natural dialogue based on that. For example, it can generate dialogue incorporating words and phrases frequently used by the user, creating avatar statements that resemble the user's speaking style. The generation unit can also generate 3D models, 2D characters, and voice-only avatars that reflect the user's characteristics. In the case of 3D models, it can generate avatars that reproduce the user's appearance and facial expressions and operate them in real time. In the case of 2D characters, it generates illustrations and animations that reflect the user's characteristics and displays them during dialogue. In the case of voice-only avatars, it uses speech synthesis technology that reflects the user's voice characteristics to achieve natural voice dialogue. The generation unit provides these generation results to the dialogue unit, preparing it to engage in dialogue on behalf of the user. Furthermore, the generation unit can evaluate the quality of the generated avatars and make corrections or improvements as needed. For example, if the generated dialogue is unnatural or does not accurately reflect the user's characteristics, it will regenerate the avatar to improve its quality. This allows the generation unit to produce high-quality avatars that accurately reflect the user's characteristics, thereby improving the overall dialogue quality of the system.

The dialogue unit uses a generated avatar to interact on behalf of the user. The dialogue unit engages in conversations using methods such as text chat, voice chat, and video chat. Specifically, in the case of text chat, it sends text messages generated by a generative AI on behalf of the user and engages in conversation with the other party. In the case of voice chat, it plays voice generated using speech synthesis technology and engages in conversation on behalf of the user. In the case of video chat, it displays a generated 3D model or 2D character and engages in conversation while it operates in real time. The dialogue unit can use generative AI to conduct conversations that reflect the user's characteristics. For example, it can generate dialogue content incorporating words and phrases frequently used by the user and create avatar statements that resemble the user's speaking style. Furthermore, the dialogue unit can incorporate new dialogue content generated by the generative AI in real time as the conversation progresses. This enables the dialogue unit to achieve natural and smooth conversations and respond appropriately on behalf of the user. In addition, the dialogue unit can record the content and progress of the conversation and provide this information to the analysis and generation units later. This allows for continuous improvement of the overall dialogue quality of the system through feedback. For example, if the content of the dialogue is inappropriate or does not accurately reflect the user's characteristics, the analysis and generation units can correct or improve it based on that information. This allows the dialogue unit to conduct high-quality conversations on behalf of the user, improving the overall reliability and satisfaction of the system.

The collection unit can collect user messages or call content. For example, the collection unit can collect data such as text messages, voice calls, and video calls. The collection unit meticulously collects the content of messages and calls sent by the user and provides this data to the analysis unit. This allows for the understanding of user characteristics by collecting user messages and call content. Some or all of the processing described above in the collection unit may be performed using AI, or without AI. For example, the collection unit can input user messages and call content into AI, which can then analyze the data.

The analysis unit can analyze the collected data and extract characteristics of the user's speech or expression. For example, the analysis unit uses natural language processing techniques to analyze the user's speech and expression characteristics. The analysis unit extracts frequently used words, phrases, and speech tone. By extracting these characteristics, it is possible to generate an avatar that reflects the user's features. Some or all of the above-described processing in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the collected data into AI, which can then analyze the data.

The generation unit can generate avatars based on extracted features. The generation unit uses a generation AI to generate avatars that reflect the user's characteristics. The generation AI, for example, uses a text generation AI (e.g., LLM) to generate the avatar's dialogue. The generation unit can generate 3D models, 2D characters, or voice-only avatars that reflect the user's characteristics. This allows the generation unit to provide avatars that reflect the user's characteristics by generating avatars based on extracted features. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or without using a generation AI. For example, the generation unit can input extracted features into a generation AI, which can then generate an avatar.

The dialogue unit allows a generated avatar to engage in dialogue on behalf of the user. The dialogue unit conducts dialogue using methods such as text chat, voice dialogue, and video dialogue. The dialogue unit can use a generation AI to conduct dialogue that reflects the user's characteristics. This allows the generated avatar to engage in dialogue on behalf of the user, enabling appropriate responses in emergencies. Some or all of the above-described processes in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the generated avatar into the AI, which can then conduct the dialogue.

The dialogue unit can use algorithms to respond in the event of an emergency. For example, the dialogue unit can take appropriate action in an emergency using emergency response scenarios and the AI technology it employs. This allows it to take appropriate action on behalf of the user by using algorithms designed for appropriate responses in emergencies. Some or all of the above-described processes in the dialogue unit may be performed using AI, or not. For example, the dialogue unit can input emergency response scenarios into the AI, which can then perform the response.

The data collection unit can estimate the user's emotions and adjust the timing of message and call content collection based on the estimated emotions. The data collection unit estimates the user's emotions using technologies such as voice analysis, facial recognition, and text analysis. If the user is stressed, the data collection unit can temporarily stop collecting messages and call content and resume collection when the user is relaxed. Furthermore, if the user is relaxed, the data collection unit can actively collect messages and call content to obtain detailed data. Additionally, if the user is in a hurry, the data collection unit can prioritize the collection of important messages and call content in a short amount of time. This allows for data collection at a more appropriate time by adjusting the collection timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit inputs user emotion data into a generating AI, which can then adjust the data collection timing.

The data collection unit can analyze the user's past messages and call history and select a collection method. For example, the collection unit can prioritize collecting data from messaging and calling apps that the user frequently used in the past. Furthermore, the collection unit can concentrate data collection on specific time periods based on the user's past messages and call history. In addition, the collection unit can analyze the user's past communication patterns and select the most effective collection method. This allows the optimal collection method to be selected by analyzing the user's past messages and call history. Some or all of the above processing in the collection unit may be performed using AI, or without AI. For example, the collection unit can input the user's past messages and call history into AI, which can then select a collection method.

The data collection unit can filter messages and call content based on the user's current lifestyle and areas of interest. For example, if the user is at work, the unit can prioritize collecting work-related messages and call content. Similarly, if the user is engaged in a hobby, the unit can collect messages and call content related to that hobby. Furthermore, if the user is traveling, the unit can collect travel-related messages and call content. This allows for the collection of more relevant data by filtering based on the user's lifestyle and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input the user's lifestyle and areas of interest into the AI, which can then perform the filtering.

The data collection unit can estimate the user's emotions and determine the priority of messages and call content to collect based on the estimated emotions. The data collection unit estimates the user's emotions using technologies such as voice analysis, facial recognition, and text analysis. If the user is stressed, the data collection unit can prioritize collecting high-priority messages and call content. If the user is relaxed, the data collection unit can collect all messages and call content equally. Furthermore, if the user is in a hurry, the data collection unit can prioritize collecting urgent messages and call content. This allows for the priority collection of important data by determining the priority of messages and call content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input user emotion data into a generating AI, which can then determine the priority of data collection.

The data collection unit can prioritize the collection of highly relevant content based on the user's geographical location when collecting messages and call content. For example, if the user is in a specific region, the data collection unit can prioritize the collection of messages and call content related to that region. Furthermore, if the user is traveling, the data collection unit can prioritize the collection of messages and call content related to their travel destination. Additionally, if the user is at home, the data collection unit can prioritize the collection of messages and call content related to their home. This allows for the priority collection of highly relevant data by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input the user's geographical location information into AI, which can then prioritize the collection of highly relevant content.

The data collection unit can analyze the user's social media activity and collect relevant content when collecting messages and call content. For example, the collection unit can prioritize collecting messages and call content with people the user frequently interacts with on social media. It can also collect messages and call content related to topics the user shows interest in on social media. Furthermore, it can collect messages and call content related to groups and communities the user participates in on social media. This allows for the collection of relevant content by analyzing the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input the user's social media activity into AI, which can then collect relevant content.

The analysis unit can estimate the user's emotions and analyze the characteristics of their speech and expression based on the estimated emotions. The analysis unit estimates the user's emotions using technologies such as speech analysis, facial recognition, and text analysis. When the user is relaxed, the analysis unit can analyze a calm tone and slow speaking style. When the user is stressed, the analysis unit can analyze a fast pace and strong tone of speech. Furthermore, when the user is excited, the analysis unit can analyze emotionally rich expressions and emphasized words. This allows for the extraction of more accurate characteristics by analyzing the characteristics of speech and expression based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input user emotion data into a generating AI, which can then analyze the characteristics of the user's speech and expressions.

The analysis unit can adjust the level of detail of the analysis based on the importance of the message or call content during the analysis. For example, the analysis unit can perform a detailed analysis of high-importance messages or call content, extracting features down to the finest detail. Conversely, for low-importance messages or call content, the analysis unit can perform a simplified analysis, extracting only the main features. Furthermore, for urgent messages or call content, the analysis unit can perform a rapid analysis, immediately extracting features. This allows for efficient analysis by adjusting the level of detail based on the importance of the message or call content. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the importance of the message or call content into the AI, which can then adjust the level of detail of the analysis.

The analysis unit can apply different analysis algorithms depending on the category of the message or call content during analysis. For example, the analysis unit can apply an algorithm that analyzes formal expressions and technical terms to business-related messages and calls. It can also apply an algorithm that analyzes casual expressions and everyday language to private messages and calls. Furthermore, the analysis unit can apply an algorithm for rapid response to urgent messages and calls. By applying different analysis algorithms depending on the category of the message or call content, more accurate analysis can be achieved. Some or all of the above processing in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the category of the message or call content into the AI, which can then apply different analysis algorithms.

The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated emotions. The analysis unit estimates the user's emotions using technologies such as voice analysis, facial recognition, and text analysis. If the user is stressed, the analysis unit can prioritize the analysis of high-priority messages and call content. If the user is relaxed, the analysis unit can analyze all messages and call content equally. Furthermore, if the user is in a hurry, the analysis unit can prioritize the analysis of urgent messages and call content. This allows for the prioritization of important data by determining the analysis priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input user emotion data into the generative AI, which can then determine the analysis priority.

The analysis unit can determine the priority of analysis based on the submission timing of messages and call content. For example, the analysis unit can prioritize the analysis of recently sent messages and call content. It can also prioritize the analysis of messages and call content sent within a specific time period. Furthermore, it can prioritize the analysis of messages and call content of high urgency. This allows for efficient analysis by determining the priority of analysis based on the submission timing of messages and call content. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the submission timing of messages and call content into the AI, which can then determine the analysis priority.

The analysis unit can adjust the order of analysis based on the relevance of messages and call content during the analysis process. For example, the analysis unit can prioritize the analysis of highly relevant messages and call content. It can also postpone the analysis of less relevant messages and call content. Furthermore, the analysis unit can prioritize the analysis of messages and call content related to specific topics. This allows for efficient analysis by adjusting the order of analysis based on the relevance of messages and call content. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input the relevance of messages and call content into the AI, which can then adjust the order of analysis.

The generation unit can estimate the user's emotions and adjust the avatar's expression based on the estimated emotions. The generation unit estimates the user's emotions using technologies such as voice analysis, facial recognition, and text analysis. If the user is relaxed, the generation unit can generate an avatar with calm facial expressions and movements. If the user is stressed, the generation unit can generate an avatar with calm facial expressions and movements. Furthermore, if the user is excited, the generation unit can generate an avatar with lively facial expressions and movements. This allows for the generation of a more appropriate avatar by adjusting the avatar's expression based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, or not. For example, the generation unit can input user emotion data into the generation AI, which can then adjust the avatar's expression.

The generation unit can adjust the level of detail of the avatar based on the importance of the user's characteristics during avatar generation. For example, if the user's characteristics are clear, the generation unit can generate a detailed avatar. If the user's characteristics are ambiguous, the generation unit can generate a simplified avatar. Furthermore, if the user's characteristics are diverse, the generation unit can generate an avatar that emphasizes the main characteristics. This allows for the generation of a more appropriate avatar by adjusting the level of detail based on the importance of the user's characteristics. Some or all of the above processing in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the importance of the user's characteristics into the AI, which can then adjust the level of detail of the avatar.

The generation unit can apply different generation algorithms depending on the user's category when generating avatars. For example, the generation unit can apply a generation algorithm with formal expressions and actions to avatars for business use. It can also apply a generation algorithm with casual expressions and actions to avatars for private use. Furthermore, it can apply a generation algorithm for rapid response to avatars in emergencies. By applying different generation algorithms according to the user's category, a more appropriate avatar can be generated. Some or all of the above processing in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the user's category into the AI, which can then apply different generation algorithms.

The generation unit can estimate the user's emotions and adjust the avatar's appearance and actions based on the estimated emotions. The generation unit estimates the user's emotions using technologies such as voice analysis, facial recognition, and text analysis. If the user is relaxed, the generation unit can generate an avatar with calm facial expressions and actions. If the user is stressed, the generation unit can generate an avatar with calm facial expressions and actions. Furthermore, if the user is excited, the generation unit can generate an avatar with lively facial expressions and actions. This allows for the generation of a more appropriate avatar by adjusting its appearance and actions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, or without AI. For example, the generation unit inputs user emotion data into the generation AI, which can then adjust the avatar's appearance and movements.

The generation unit can determine the generation priority based on the user's past avatar usage history when generating avatars. For example, the generation unit can prioritize the reflection of features in avatars frequently used by the user in the past. Furthermore, the generation unit can predict and generate avatars to be used during specific time periods based on the user's past avatar usage history. In addition, the generation unit can analyze the user's past avatar usage patterns and generate the most effective avatar. This allows for the generation of more appropriate avatars by determining the generation priority based on the user's past avatar usage history. Some or all of the above-described processes in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the user's past avatar usage history into AI, which can then determine the generation priority.

The generation unit can improve the accuracy of avatar generation by referring to the user's relevant data. For example, the generation unit can adjust the avatar's appearance and personality by referring to the user's social media profile and posts. It can also adjust the avatar's speech patterns and expressions by referring to the user's past messages and call content. Furthermore, the generation unit can customize the avatar's characteristics based on the user's hobbies and interests. This allows for improved generation accuracy by referring to the user's relevant data. Some or all of the above-described processes in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the user's relevant data into AI, which can then improve the generation accuracy.

The dialogue unit can estimate the user's emotions and adjust the dialogue's presentation based on those emotions. The dialogue unit estimates the user's emotions using technologies such as speech analysis, facial recognition, and text analysis. If the user is relaxed, the dialogue unit can engage in dialogue in a calm tone. If the user is stressed, the dialogue unit can engage in dialogue in a calm tone. Furthermore, if the user is excited, the dialogue unit can engage in dialogue in an active tone. This allows for more appropriate dialogue by adjusting the dialogue's presentation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the dialogue unit may be performed using AI, or not. For example, the dialogue unit can input user emotion data into the generative AI, which can then adjust the dialogue's presentation.

The dialogue unit can select a dialogue method by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can incorporate expressions and phrases that the user has previously used frequently. Furthermore, the dialogue unit can select a dialogue method for a specific topic based on the user's past dialogue history. In addition, the dialogue unit can analyze the user's past dialogue patterns and select the most effective dialogue method. This allows the optimal dialogue method to be selected by referring to the user's past dialogue history. Some or all of the above processing in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the user's past dialogue history into AI, which can then select a dialogue method.

The dialogue unit can customize the dialogue method based on the user's current situation during a conversation. For example, if the user is at work, the dialogue unit can engage in a businesslike conversation. If the user is relaxed, it can engage in a casual conversation. Furthermore, if the user is in an emergency, the dialogue unit can engage in a quick and concise conversation. This allows for more appropriate conversations by customizing the dialogue method based on the user's current situation. Some or all of the above processing in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the user's current situation into the AI, which can then customize the dialogue method.

The dialogue unit can estimate the user's emotions and determine the priority of conversations based on those emotions. The dialogue unit estimates the user's emotions using technologies such as voice analysis, facial recognition, and text analysis. If the user is stressed, the dialogue unit prioritizes high-priority conversations. If the user is relaxed, the dialogue unit distributes all conversations equally. Furthermore, if the user is in a hurry, the dialogue unit prioritizes urgent conversations. This allows for prioritizing important conversations based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using AI, or not. For example, the dialogue unit can input user emotion data into a generative AI, which can then determine the priority of conversations.

The dialogue unit can select the optimal dialogue method during a conversation, taking into account the user's geographical location. For example, if the user is in a specific region, the dialogue unit can provide information related to that region. Furthermore, if the user is traveling, the dialogue unit can provide information related to their travel destination. Additionally, if the user is at home, the dialogue unit can provide information related to their home. This allows the dialogue unit to select the optimal dialogue method by considering the user's geographical location. Some or all of the above processing in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the user's geographical location information into the AI, which can then select the optimal dialogue method.

The dialogue unit can analyze the user's social media activity during a conversation and suggest appropriate dialogue methods. For example, the dialogue unit can prioritize conversations with individuals the user frequently interacts with on social media. It can also conduct conversations related to topics the user has shown interest in on social media. Furthermore, it can conduct conversations related to groups and communities the user participates in on social media. This allows the dialogue unit to suggest the most suitable dialogue method by analyzing the user's social media activity. Some or all of the above processing in the dialogue unit may be performed using AI, or without AI. For example, the dialogue unit can input the user's social media activity into AI, which can then suggest dialogue methods.

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

The interactive avatar system can further collect user health data and reflect it in the avatar's dialogue. For example, the data collection unit can collect heart rate and sleep data from the user's wearable device. The analysis unit can analyze this data to understand the user's health status. Based on the user's health status, the avatar can provide health-related advice. The dialogue unit can engage in conversations that encourage relaxation or exercise, depending on the user's health condition. This allows for more personalized support by providing dialogue that takes the user's health status into consideration.

The data collection unit can collect user environmental data and reflect it in the avatar's dialogue. For example, the data collection unit can collect environmental data such as temperature, humidity, and noise levels around the user. The analysis unit can analyze this data to understand the user's environmental conditions. The generation unit can provide advice to help the avatar maintain a comfortable environment based on the user's environmental conditions. The dialogue unit can engage in appropriate dialogue according to the user's environmental conditions. This allows for dialogue that considers the user's environmental conditions, thereby supporting a more comfortable life.

The analysis unit can analyze the user's hobbies and interests and reflect them in the avatar's dialogue. For example, the analysis unit can analyze data on keywords the user has searched for in the past and websites they have visited. Based on this data, the generation unit can provide the avatar with topics related to the user's hobbies and interests. The dialogue unit can suggest relevant information and activities according to the user's hobbies and interests. This allows for more engaging dialogue by considering the user's interests.

The generation unit can customize the avatar's dialogue by referencing the user's past dialogue history. For example, the generation unit can incorporate expressions and phrases that the user has previously favored into the avatar's dialogue. The dialogue unit can select a dialogue method for a specific topic based on the user's past dialogue history. Furthermore, the generation unit can analyze the user's past dialogue patterns and select the most effective dialogue method. This allows for more personalized dialogue by referencing the user's past dialogue history.

The dialogue unit can customize the avatar's conversation content by considering the user's geographical location. For example, if the user is in a specific region, the dialogue unit can provide information relevant to that region. If the user is traveling, the dialogue unit can provide information relevant to their travel destination. Furthermore, if the user is at home, the dialogue unit can provide information relevant to their home. This allows for more relevant conversations by considering the user's geographical location.

The data collection unit can estimate the user's emotions and adjust the type of data collected based on those emotions. For example, if the user is stressed, the unit can collect music or video data to help them relax. If the user is relaxed, the unit can collect data that is helpful for learning or working. Furthermore, if the user is excited, the unit can collect entertainment-related data. This allows for the provision of more relevant data by adjusting the type of data collected based on the user's emotions.

The analysis unit can estimate the user's emotions and adjust the level of detail of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit can perform a detailed analysis to identify the cause of the stress. If the user is relaxed, the analysis unit can perform a simplified analysis and extract only the main features. Furthermore, if the user is excited, the analysis unit can perform a rapid analysis and immediately extract features. This allows for more appropriate analysis by adjusting the level of detail based on the user's emotions.

The generation unit can estimate the user's emotions and adjust the avatar's appearance and actions based on those emotions. For example, if the user is relaxed, the generation unit can generate an avatar with a calm expression and actions. Similarly, if the user is stressed, it can generate an avatar with a calm expression and actions. Furthermore, if the user is excited, it can generate an avatar with an energetic expression and actions. This allows for the generation of a more appropriate avatar by adjusting its appearance and actions based on the user's emotions.

The dialogue unit can estimate the user's emotions and adjust the dialogue's presentation based on those emotions. For example, if the user is relaxed, the dialogue unit can use a calm tone. If the user is stressed, it can use a calm tone. Furthermore, if the user is excited, it can use a lively tone. This allows for more appropriate dialogue by adjusting the presentation based on the user's emotions.

The dialogue unit can estimate the user's emotions and prioritize conversations based on those emotions. For example, if the user is stressed, the dialogue unit can prioritize high-priority conversations. If the user is relaxed, the dialogue unit can distribute all conversations equally. Furthermore, if the user is in a hurry, the dialogue unit can prioritize urgent conversations. This allows for prioritizing important conversations based on the user's emotions.

The following briefly describes the processing flow for example 2.

Step 1: The collection unit collects user messages or call interactions. The collection unit can collect data such as text messages, voice calls, and video calls. The collection unit collects detailed information about the messages and calls sent by the user and provides this data to the analysis unit.
Step 2: The analysis unit analyzes the collected data and extracts user characteristics. For example, the analysis unit uses natural language processing technology to analyze the characteristics of the user's speech and expressions. The analysis unit extracts words, phrases, and speaking tone that the user frequently uses.
Step 3: The generation unit generates an avatar based on the features extracted by the analysis unit. The generation unit uses a generation AI to generate an avatar that reflects the user's characteristics. The generation AI uses, for example, a text generation AI (e.g., LLM) to generate the avatar's dialogue. The generation unit can generate 3D models, 2D characters, or voice-only avatars that reflect the user's characteristics.
Step 4: The dialogue unit has the generated avatar interact on behalf of the user. The dialogue unit interacts using methods such as text chat, voice dialogue, or video dialogue. The dialogue unit can use generation AI to conduct dialogue that reflects the user's characteristics. As a result, the dialogue avatar system according to the embodiment can generate an avatar that reflects the user's characteristics and interact on behalf of the user in times of emergency.

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

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

Furthermore, the processing performed 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 it may also be executed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Also, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or external devices.

Each of the multiple elements described above, including the data collection unit, analysis unit, generation unit, and dialogue unit, is implemented in at least one of the following: the smart device 14 and the data processing unit 12. For example, the data collection unit collects user messages and call interactions using the camera 42 and microphone 38B of the smart device 14. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes the collected data to extract user characteristics. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and generates an avatar reflecting the user's characteristics using generation AI. The dialogue unit is implemented, for example, by the control unit 46A of the smart device 14, and the generated avatar engages in dialogue on behalf of the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

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

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

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

The microphone 238 receives user voice commands and other information. The microphone 238 captures the user's voice, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

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

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

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

The processor 28 reads a specific processing program 56 from the storage 32 and executes the read program on the RAM 30. The specific processing is achieved by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

Furthermore, other devices besides the data processing device 12 may also possess the data generation model 58. For example, a server device may possess the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device possessing the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (e.g., a mobile phone, robot, home appliance, etc.).

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

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

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, or it may be executed by both 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 necessary for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or external devices.

Each of the multiple elements described above, including the data collection unit, analysis unit, generation unit, and dialogue unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects user messages and call interactions using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes the collected data to extract user characteristics. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and generates an avatar reflecting the user's characteristics using generation AI. The dialogue unit is implemented, for example, by the control unit 46A of the smart glasses 214, and the generated avatar engages in dialogue on behalf of the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

As shown in Figure 5, the data processing system 310 comprises a data processing device 12 and a headset-type terminal 314. An example of the data processing device 12 is a server.

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

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

The microphone 238 receives user voice commands and other information. The microphone 238 captures the user's voice, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

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

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

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

The processor 28 reads a specific processing program 56 from the storage 32 and executes the read program on the RAM 30. The specific processing is achieved by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

Furthermore, other devices besides the data processing device 12 may also possess the data generation model 58. For example, a server device may possess the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device possessing the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (e.g., a mobile phone, robot, home appliance, etc.).

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

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

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 terminal 314, or it may be executed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

Each of the multiple elements described above, including the data collection unit, analysis unit, generation unit, and dialogue unit, is implemented in at least one of the following: the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects user messages and call interactions using the camera 42 and microphone 238 of the headset terminal 314. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes the collected data to extract user characteristics. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and generates an avatar reflecting the user's characteristics using generation AI. The dialogue unit is implemented, for example, by the control unit 46A of the headset terminal 314, and the generated avatar engages in dialogue on behalf of the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

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

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

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

The microphone 238 receives user voice commands and other information. The microphone 238 captures the user's voice, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

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

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

The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

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

The processor 28 reads a specific processing program 56 from the storage 32 and executes the read program on the RAM 30. The specific processing is achieved by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

Furthermore, other devices besides the data processing device 12 may also possess the data generation model 58. For example, a server device may possess the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device possessing the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (e.g., a mobile phone, robot, home appliance, etc.).

The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input regarding the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

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 both 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 necessary for processing from the robot 414 or external devices, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or external devices.

Each of the multiple elements described above, including the data collection unit, analysis unit, generation unit, and dialogue unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the data collection unit collects user messages and call interactions using the camera 42 and microphone 238 of the robot 414. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and analyzes the collected data to extract user characteristics. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and generates an avatar reflecting the user's characteristics using generation AI. The dialogue unit is implemented, for example, by the control unit 46A of the robot 414, and the generated avatar engages in dialogue on behalf of the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, namely an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

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

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

The inner part of the Emotion Map 400 represents inner thoughts, while the outer part represents actions. Therefore, the further you go from the outer edge of the Emotion Map 400, the more visible (expressed through actions) your emotions become.

Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort; when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort; when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a Brain Physiological Signal Analysis System for Speech Emotion Recognition and Emotion, Tokushima University, Doctoral Dissertation: https://ci.nii.ac.jp/naid/500000375379). The left half of the emotion map displays emotions belonging to the "response" region, where sensation is dominant. The right half of the emotion map displays emotions belonging to the "situation" region, where situational awareness is dominant.

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

The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassurance," "peace of mind," and "reassurance" have similar emotion values.

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

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

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.

Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, nor is it necessary to store the entirety of the specific processing program 56 in the storage device 32. It is acceptable to store only a portion of the specific processing program 56.

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

The hardware resource performing a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource performing the specific process may consist of a single processor.

Examples of configurations using a single processor include, firstly, a configuration where one or more CPUs and software are combined to form a single processor, which functions as a hardware resource for executing specific processing. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources for executing specific processing, on a single IC chip, as exemplified by SoC (System-on-a-chip). Thus, specific processing is realized using one or more of the above-mentioned types of processors as hardware resources.

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

Furthermore, although the above examples were described separately as the first to fourth embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset-type terminal 314, and robot 414 are examples, and they may be combined, or other devices may be used. Furthermore, although the above examples were described separately as Embodiment Example 1 and Embodiment Example 2, these may be combined.

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

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

(Note 1)
A collection unit that collects user messages or call exchanges,
An analysis unit analyzes the information collected by the aforementioned collection unit and extracts user characteristics,
A generation unit generates an avatar based on the features extracted by the analysis unit,
A system comprising: a dialogue unit in which the avatar generated by the generation unit engages in dialogue.
(Note 2)
The aforementioned collection unit is
The system described in Appendix 1, characterized by collecting user messages or call content.
(Note 3)
The aforementioned analysis unit,
The system described in Appendix 1, characterized by analyzing collected data and extracting characteristics of the user's speaking style or expression.
(Note 4)
The generating unit is
The system described in Appendix 1, characterized by generating an avatar based on extracted features.
(Note 5)
The aforementioned dialogue unit,
The system described in Appendix 1, characterized in that the generated avatar engages in dialogue on behalf of the user.
(Note 6)
The aforementioned dialogue unit,
The system described in Appendix 1, characterized by using an algorithm for responding in the event of an emergency.
(Note 7)
The aforementioned collection unit is
The system described in Appendix 1, characterized by estimating the user's emotions and adjusting the timing of collecting messages and call content based on the estimated user emotions.
(Note 8)
The aforementioned collection unit is
The system described in Appendix 1, characterized by analyzing the user's past messages and call history and selecting a collection method.
(Note 9)
The aforementioned collection unit is
The system described in Appendix 1, characterized in that when collecting messages and call content, it filters based on the user's current living situation and areas of interest.
(Note 10)
The aforementioned collection unit is
The system described in Appendix 1, characterized by estimating the user's emotions and determining the priority of messages and call content to be collected based on the estimated user emotions.
(Note 11)
The aforementioned collection unit is
The system described in Appendix 1, characterized in that when collecting messages and call content, it prioritizes the collection of highly relevant content based on the user's geographical location information.
(Note 12)
The aforementioned collection unit is
The system described in Appendix 1, characterized in that, when collecting messages or call content, it analyzes the user's social media activity and collects relevant content.
(Note 13)
The aforementioned analysis unit,
The system described in Appendix 1, characterized by estimating the user's emotions and analyzing the characteristics of their speech and expression based on the estimated user emotions.
(Note 14)
The aforementioned analysis unit,
The system described in Appendix 1, characterized in that, during analysis, the level of detail of the analysis is adjusted based on the importance of the message or call content.
(Note 15)
The aforementioned analysis unit,
The system described in Appendix 1, characterized in that different analysis algorithms are applied during analysis depending on the category of the message or call content.
(Note 16)
The aforementioned analysis unit,
The system described in Appendix 1, characterized by estimating the user's emotions and determining the priority of analysis based on the estimated user emotions.
(Note 17)
The aforementioned analysis unit,
The system described in Appendix 1, characterized in that, during analysis, the priority of analysis is determined based on the timing of submission of messages and call content.
(Note 18)
The aforementioned analysis unit,
The system described in Appendix 1, characterized in that, during analysis, the order of analysis is adjusted based on the relevance of messages and call content.
(Note 19)
The generating unit is
The system described in Appendix 1, characterized by estimating the user's emotions and adjusting the avatar's representation based on the estimated user emotions.
(Note 20)
The generating unit is
The system described in Appendix 1, characterized in that, when generating an avatar, the level of detail of the avatar is adjusted based on the importance of the user's characteristics.
(Note 21)
The generating unit is
The system described in Appendix 1, characterized in that it applies different generation algorithms depending on the user's category when generating avatars.
(Note 22)
The generating unit is
The system described in Appendix 1, characterized by estimating the user's emotions and adjusting the appearance and behavior of the avatar based on the estimated user emotions.
(Note 23)
The generating unit is
The system described in Appendix 1, characterized in that, when generating avatars, it determines the priority of avatar generation based on the user's past avatar usage history.
(Note 24)
The generating unit is
The system described in Appendix 1, characterized in that it improves the accuracy of avatar generation by referring to the user's related data during avatar generation.
(Note 25)
The aforementioned dialogue unit,
The system described in Appendix 1, characterized by estimating the user's emotions and adjusting the way the dialogue is expressed based on the estimated user emotions.
(Note 26)
The aforementioned dialogue unit,
The system described in Appendix 1, characterized in that, during a conversation, it selects a conversation method by referring to the user's past conversation history.
(Note 27)
The aforementioned dialogue unit,
The system described in Appendix 1, characterized in that, during a conversation, the means of the conversation are customized based on the user's current situation.
(Note 28)
The aforementioned dialogue unit,
The system described in Appendix 1, characterized by estimating the user's emotions and determining the priority of the conversation based on the estimated user emotions.
(Note 29)
The aforementioned dialogue unit,
The system described in Appendix 1, characterized in that it selects the optimal dialogue method during dialogue, taking into account the user's geographical location information.
(Note 30)
The aforementioned dialogue unit,
The system described in Appendix 1, characterized in that it analyzes the user's social media activity during a dialogue and proposes a means of dialogue.

10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset terminal 414 Robot

Claims (6)

A collection unit that collects user messages or call exchanges,
An analysis unit analyzes the information collected by the aforementioned collection unit and extracts user characteristics,
A generation unit generates an avatar based on the features extracted by the analysis unit,
The system comprises a dialogue unit in which the avatar generated by the generation unit engages in dialogue ,
The analysis unit estimates the user's emotions and performs a detailed analysis if it estimates the user is feeling stressed, and performs a simplified analysis if it estimates the user is relaxed.
system. The aforementioned collection unit is
The system according to claim 1, characterized by collecting user messages or call content. The aforementioned analysis unit,
The system according to claim 1, characterized by analyzing the collected data and extracting the characteristics of the user's way of speaking or expression. The aforementioned dialogue unit,
The system according to claim 1, characterized in that it uses an algorithm for responding in the event of an emergency. The aforementioned collection unit is
The system according to claim 1, characterized in that it estimates the user's emotions and adjusts the timing of collecting messages and call content based on the estimated user emotions. The aforementioned collection unit is
The system according to claim 1, characterized by analyzing the user's past messages and call history and selecting a collection method.