system

Abstract

The system according to this embodiment aims to personalize the AI ​​agent according to the needs of individual users. [Solution] The system according to the embodiment comprises a base model unit, an additional learning unit, a memory unit, and a learning unit. The base model unit prepares a base model for the agent. The additional learning unit enables the base model unit to additionally learn a part of the model. The memory unit stores the user's actions and experiences. The learning unit learns based on the information stored by the memory unit, taking into account the user's instructions, responses, and preferences.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, AI agents have not been sufficiently personalized according to the needs of individual users, and there is room for improvement.

[0005] The system according to the embodiment aims to personalize an AI agent according to the needs of individual users.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a base model unit, an additional learning unit, a memory unit, and a learning unit. The base model unit prepares a base model for the agent. The additional learning unit enables the base model unit to additionally learn a part of the model. The memory unit stores the user's actions and experiences. The learning unit learns based on the information stored by the memory unit, taking into account the user's instructions, responses, and preferences. [Effects of the Invention]

[0007] The system according to this embodiment can personalize the AI ​​agent according to the needs of individual users. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An embodiment of the present invention provides a personalized AI agent system that offers an AI agent tailored to individual needs. While AI services are offered in various fields such as healthcare, education, law, and IT, these services are often generic and struggle to meet the individual needs of users. Furthermore, the widespread adoption of general-purpose AI raises concerns about mass unemployment among specialists and cultural mediocrity. The objective of the present invention is to solve these problems by providing a personalized AI agent tailored to individual needs. For example, the personalized AI agent system provides a model that forms the basis of the agent. For instance, it may include components such as natural language understanding, image / speech recognition, and sentiment analysis. The personalized AI agent system also allows for additional learning of parts of the model. For example, a less expensive version may include an output layer for transfer learning. Furthermore, the personalized AI agent system stores user behavior and experiences. For example, personal data is stored in isolated areas for each user and can be used for retrieval or learning. The personalized AI agent system also learns based on user instructions, responses, and preferences. For example, the user can change the agent's behavior by having it learn unfrozen parts of the model. In this way, by realizing a personalized AI agent, it is possible to provide services tailored to the individual needs of users and prevent mediocrity and model collapse caused by the widespread adoption of AI agents across society. As a result, the personalized AI agent system can provide services tailored to the individual needs of users.

[0029] The personal AI agent system according to this embodiment comprises a base model unit, an additional learning unit, a memory unit, and a learning unit. The base model unit prepares a base model for the agent. The base model unit includes components such as natural language understanding, image / speech recognition, and sentiment analysis. The base model unit can analyze user input using, for example, natural language understanding technology. The base model unit can analyze user image data using, for example, image recognition technology. The base model unit can analyze user emotions using, for example, sentiment analysis technology. The additional learning unit enables additional learning of a part of the model in the base model unit. The additional learning unit can perform transfer learning by adding an output layer, for example. The additional learning unit can perform additional learning of a part of the model using, for example, user data. The additional learning unit can optimize the model for a specific task, for example. The memory unit stores user behavior and experiences. The memory unit can store personal data in isolated areas for each user, for example. The memory unit can record user behavior history, for example. The memory unit can, for example, store the user's experience in a database. The learning unit learns based on the information stored by the memory unit, as well as the user's instructions, responses, and preferences. The learning unit can, for example, learn unfrozen parts of the model based on the user's instructions. The learning unit can, for example, adjust the model based on the user's responses. The learning unit can, for example, change the agent's behavior based on the user's preferences. As a result, the personalized AI agent system according to this embodiment can provide services that meet the individual needs of the user.

[0030] The foundational model unit prepares the model that forms the basis of the agent. The foundational model unit includes components such as natural language understanding, image and speech recognition, and sentiment analysis. Specifically, it can analyze user input using natural language understanding technology. Natural language understanding technology is a technology for analyzing text entered by the user and understanding its intent and meaning. For example, if a user enters "What's the weather like tomorrow?", the foundational model unit analyzes the question and obtains appropriate information to provide a weather forecast. It can also analyze the user's image data using image recognition technology. Image recognition technology is a technology for analyzing images uploaded by the user and understanding their content. For example, if a user uploads a picture of their pet, the foundational model unit analyzes the image and identifies the type and characteristics of the pet. It can also analyze the user's emotions using sentiment analysis technology. Sentiment analysis technology is a technology for reading emotions from the user's text and voice. For example, if a user enters "I'm very tired today," the foundational model unit reads the user's level of fatigue from the text and provides appropriate advice and support. This allows the foundational model unit to analyze diverse user input data and provide the agent with advanced understanding capabilities. Furthermore, the foundational model unit can combine these technologies to handle more complex tasks. For example, if a user uploads an image related to the weather while saying "Tell me tomorrow's weather," the foundational model unit can analyze both the text and the image to provide more accurate information. This enables the foundational model unit to respond flexibly to the diverse needs of users.

[0031] The additional learning unit enables the base model unit to further learn parts of the model. Specifically, it can perform transfer learning by adding an output layer. Transfer learning is a technique that adds new data to an existing model for training, allowing the model to be optimized for specific tasks. For example, if a user provides data related to a specific task, the additional learning unit can use that data to further learn parts of the model and build an agent specialized for that task. This allows the user to use a customized agent that meets their needs. Furthermore, the additional learning unit can further learn parts of the model using user data. For example, by training the agent with phrases and specific terms that the user uses daily, the agent can better adapt to the user's language and expressions. This makes communication between the agent and the user more natural and smooth. The additional learning unit can also optimize the model for specific tasks. For example, if a user uses a specific project management tool, the additional learning unit can train the agent with data related to that tool, enabling the agent to provide support for project management. This allows the agent to improve the user's work efficiency. Furthermore, the additional learning unit can continuously improve the model based on user feedback. For example, if a user provides feedback on the agent's response, the additional learning unit learns that feedback and improves the agent's response accuracy. This allows the additional learning unit to respond flexibly to user needs, enabling continuous improvement of the agent's performance.

[0032] The memory unit stores user behavior and experiences. Specifically, it can store personal data in isolated areas for each user. This allows for secure management of individual data while protecting user privacy. For example, by storing a user's past search and purchase history in the memory unit, the agent can understand the user's preferences and tendencies and provide more personalized services. The memory unit can record the user's behavioral history. For example, it can record the user's daily tasks and schedules, and the agent can use this information to set reminders and manage tasks. This allows users to efficiently manage their daily work. Furthermore, the memory unit can store user experiences in a database. For example, it can record information about events and projects the user has participated in in the past, and the agent can use this information to provide advice and support. This allows the agent to leverage the user's past experiences to provide more appropriate support. The memory unit also has security features to securely manage user data. For example, it protects user data from unauthorized access by encrypting data and controlling access. This allows users to use the agent with peace of mind. In addition, the memory unit can regularly back up user data to prevent data loss or corruption. This ensures that user data is always securely stored and quickly accessible when needed. The memory unit remembers user behavior and experiences, allowing agents to provide more personalized services and respond flexibly to user needs.

[0033] The learning unit learns based on user instructions, responses, and preferences, using information stored by the memory unit. Specifically, it can learn unfrozen parts of the model based on user instructions. For example, if a user instructs the agent to perform a specific task, the learning unit learns data related to that task, enabling the agent to perform the task more efficiently. This allows the agent to respond quickly and accurately to user instructions. Furthermore, the learning unit can adjust the model based on user responses. For example, if a user provides feedback on information or services provided by the agent, the learning unit adjusts the model based on that feedback, improving the agent's response accuracy. This allows the agent to provide services that meet user expectations. The learning unit can also change the agent's behavior based on user preferences. For example, if a user prefers a particular music genre, the learning unit learns this information, allowing the agent to recommend music that matches the user's preferences. This allows the agent to provide personalized services tailored to the user's preferences. In addition, the learning unit can learn user behavior patterns and tendencies, providing predictive support. For example, if a user has a habit of drinking coffee at a specific time every morning, the learning unit learns this information, allowing the agent to remind the user to prepare the coffee. This allows the agent to support the user's daily life and improve convenience. The learning unit continuously learns based on the user's instructions, responses, and preferences, improving the agent's performance and enabling it to provide services tailored to the user's individual needs.

[0034] The base model unit can include components such as natural language understanding, image and speech recognition, and sentiment analysis. For example, the base model unit can analyze user input using natural language understanding technology. For example, the base model unit can analyze user image data using image recognition technology. For example, the base model unit can analyze user emotions using sentiment analysis technology. This allows the base model unit to provide a wide range of functions by including diverse components. Natural language understanding technology is implemented using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Image recognition technology is implemented using techniques such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Sentiment analysis technology is implemented using techniques such as text-based sentiment analysis and speech-based sentiment analysis. Some or all of the above-described processes in the base model unit may be performed using, for example, generative AI, or without generative AI. For example, when the base model unit analyzes user input using natural language understanding technology, it can output the analysis results using generative AI.

[0035] The additional learning unit can perform transfer learning by adding an output layer. For example, by adding an output layer and performing transfer learning, the flexibility of the model is improved. The additional learning unit can, for example, further train a part of the model using user data. The additional learning unit can, for example, optimize the model for a specific task. This further improves the flexibility of the model by adding an output layer and performing transfer learning. Transfer learning is a technique that reuses a part of a previously trained model and adapts it to a new task. Some or all of the above processing in the additional learning unit may be performed using, for example, generative AI, or without generative AI. For example, the additional learning unit can input user data into a generative AI and further train a part of the model using the generative AI.

[0036] The memory unit can store personal data in isolated areas for each user, making it available for retrieval or learning. For example, the memory unit can store personal data in isolated areas for each user. For example, the memory unit can record a user's behavioral history. For example, the memory unit can store a user's experience in a database. This allows for the secure management and use of the user's personal data as needed. Isolated areas are implemented using technologies such as database partitioning and access control. Some or all of the above-described processes in the memory unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory unit can input a user's behavioral history into a generative AI and store the data using the generative AI.

[0037] The learning unit can change the agent's behavior by having the user themselves learn the unfrozen parts of the model. The learning unit can, for example, learn the unfrozen parts of the model based on user instructions. The learning unit can, for example, adjust the model based on user responses. The learning unit can, for example, change the agent's behavior based on user preferences. This allows the agent's behavior to be customized based on user instructions. Unfreezing is, for example, a technique that makes a specific layer of the model retrainable. Some or all of the above processing in the learning unit may be performed, for example, using generative AI, or without using generative AI. For example, the learning unit can input user instructions into generative AI and use generative AI to learn the unfrozen parts of the model.

[0038] The base model unit can analyze the user's past behavior history and select the optimal model configuration. For example, the base model unit can prioritize displaying functions that the user has frequently used in the past. For example, the base model unit can automatically select the optimal model configuration based on the user's past behavior patterns. For example, the base model unit can hide functions that the user has avoided in the past. This allows the system to provide the optimal model configuration based on the user's past behavior history. The optimal model configuration is selected based on criteria such as performance indicators or user behavior patterns. Some or all of the above processing in the base model unit may be performed using, for example, a generative AI, or without a generative AI. For example, the base model unit can input the user's past behavior history into a generative AI and use the generative AI to select the optimal model configuration.

[0039] The base model unit can dynamically change the model components based on the user's current areas of interest. For example, the base model unit can prioritize displaying components related to topics the user is currently interested in. For example, the base model unit can hide unnecessary components based on the user's current areas of interest. For example, the base model unit can update the model components in real time if the user's areas of interest change. This allows for dynamic changes to the model components according to the user's areas of interest. Areas of interest are identified by criteria such as survey results or past behavioral history. Some or all of the above processing in the base model unit may be performed using, for example, generative AI, or without generative AI. For example, the base model unit can input the user's current areas of interest into generative AI and dynamically change the model components using generative AI.

[0040] The base model unit can prioritize the use of highly relevant models, taking into account the user's geographical location information. For example, if the user is in a specific region, the base model unit can prioritize displaying information related to that region. For example, if the user is traveling, the base model unit can prioritize displaying information related to the travel destination. For example, if the user is at home, the base model unit can prioritize displaying information related to home. This allows the system to provide highly relevant information based on the user's geographical location information. Geographical location information is obtained based on criteria such as GPS data or IP address. Some or all of the above processing in the base model unit may be performed using, for example, a generative AI, or without a generative AI. For example, the base model unit can input the user's geographical location information into a generative AI and use the generative AI to prioritize the use of highly relevant models.

[0041] The foundation model unit can analyze a user's social media activity and select relevant models. For example, the foundation model unit can prioritize the use of models related to topics that the user frequently mentions on social media. For example, the foundation model unit can identify areas of interest from the user's social media activity and select models related to those areas. For example, the foundation model unit can select the optimal model based on the time of day the user is active on social media. This allows the system to provide the optimal model based on the user's social media activity. Social media activity is analyzed based on criteria such as post content and the number of likes. Some or all of the above processing in the foundation model unit may be performed using, for example, a generative AI, or without a generative AI. For example, the foundation model unit can input the user's social media activity into a generative AI and use the generative AI to select relevant models.

[0042] The additional learning unit can analyze the user's past learning history and select the optimal learning method. For example, the additional learning unit can prioritize the use of learning methods that were effective for the user in the past. For example, the additional learning unit can automatically select the optimal learning method from the user's past learning history. For example, the additional learning unit can hide learning methods that the user has avoided in the past. This allows the system to provide the optimal learning method based on the user's past learning history. The learning history is recorded based on criteria such as past learning data and learning results. Some or all of the above processing in the additional learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the additional learning unit can input the user's past learning history into a generative AI and use the generative AI to select the optimal learning method.

[0043] The additional learning unit can customize learning data based on the user's current lifestyle. For example, if the user is busy, the additional learning unit can provide data that can be learned in a short amount of time. For example, if the user is relaxed, the additional learning unit can provide detailed learning data. For example, if the user is working on a specific project, the additional learning unit can provide learning data related to that project. This allows for the provision of learning data tailored to the user's lifestyle. Lifestyle is identified by criteria such as survey results or behavioral patterns. Some or all of the processing described above in the additional learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the additional learning unit can input the user's current lifestyle into a generative AI and use the generative AI to customize the learning data.

[0044] The additional learning unit can prioritize learning highly relevant data by taking into account the user's geographical location information. For example, if the user is in a specific region, the additional learning unit can prioritize providing learning data related to that region. For example, if the user is traveling, the additional learning unit can prioritize providing learning data related to the travel destination. For example, if the user is at home, the additional learning unit can prioritize providing learning data related to home. This allows the system to provide highly relevant learning data based on the user's geographical location information. Highly relevant data is identified by criteria such as geographical location information and the user's behavioral patterns. Some or all of the processing described above in the additional learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the additional learning unit can input the user's geographical location information into a generative AI and use the generative AI to prioritize learning highly relevant data.

[0045] The additional learning unit can analyze the user's social media activity and learn relevant data. For example, the additional learning unit can prioritize providing learning data related to topics that the user frequently mentions on social media. For example, the additional learning unit can identify areas of interest from the user's social media activity and provide learning data related to those areas. For example, the additional learning unit can provide optimal learning data based on the time of day the user is active on social media. This allows for the provision of optimal learning data based on the user's social media activity. Social media activity is analyzed based on criteria such as post content and the number of likes. Some or all of the above processing in the additional learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the additional learning unit can input the user's social media activity into a generative AI and learn relevant data using the generative AI.

[0046] The memory unit can analyze the user's past behavior history and select the optimal data storage method. For example, the memory unit can prioritize saving data that the user has frequently accessed in the past. For example, the memory unit can automatically select the optimal data storage method based on the user's past behavior patterns. For example, the memory unit can hide data that the user has avoided in the past. This allows the system to provide the optimal data storage method based on the user's past behavior history. The data storage method is set based on criteria such as the database structure and access control. Some or all of the above processing in the memory unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory unit can input the user's past behavior history into a generative AI and use the generative AI to select the optimal data storage method.

[0047] The memory unit can change the data storage priority based on the user's current areas of interest. For example, the memory unit can prioritize saving data related to topics the user is currently interested in. For example, the memory unit can hide unnecessary data based on the user's current areas of interest. For example, the memory unit can update the data storage priority in real time if the user's areas of interest change. This allows for the provision of data storage priorities that correspond to the user's areas of interest. The storage priority is set based on criteria such as the importance of the data or the user's areas of interest. Some or all of the above processing in the memory unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the memory unit can input the user's current areas of interest into a generative AI and use the generative AI to change the data storage priority.

[0048] The memory unit can prioritize saving highly relevant data, taking into account the user's geographical location. For example, if the user is in a specific region, the memory unit can prioritize saving data related to that region. For example, if the user is traveling, the memory unit can prioritize saving data related to the travel destination. For example, if the user is at home, the memory unit can prioritize saving data related to home. This allows the system to provide highly relevant data based on the user's geographical location. Highly relevant data is identified by criteria such as geographical location and the user's behavioral patterns. Some or all of the above processing in the memory unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory unit can input the user's geographical location into a generative AI and use the generative AI to prioritize saving highly relevant data.

[0049] The memory unit can analyze the user's social media activity and store relevant data. For example, the memory unit can prioritize storing data related to topics that the user frequently mentions on social media. For example, the memory unit can identify areas of interest from the user's social media activity and store data related to those areas. For example, the memory unit can store optimal data based on the time of day the user is active on social media. This allows the system to provide optimal data based on the user's social media activity. Social media activity is analyzed based on criteria such as post content and the number of likes. Some or all of the above processing in the memory unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory unit can input the user's social media activity into a generative AI and use the generative AI to store relevant data.

[0050] The learning unit can analyze the user's past learning history and select the optimal learning method. For example, the learning unit can prioritize the use of learning methods that have been effective for the user in the past. For example, the learning unit can automatically select the optimal learning method from the user's past learning history. For example, the learning unit can hide learning methods that the user has avoided in the past. This allows the learning unit to provide the optimal learning method based on the user's past learning history. The learning history is recorded based on criteria such as past learning data and learning results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the user's past learning history into a generative AI and use the generative AI to select the optimal learning method.

[0051] The learning unit can customize learning data based on the user's current lifestyle. For example, if the user is busy, the learning unit can provide data that can be learned in a short amount of time. For example, if the user is relaxed, the learning unit can provide detailed learning data. For example, if the user is working on a specific project, the learning unit can provide learning data related to that project. This allows the learning unit to provide learning data that is tailored to the user's lifestyle. Lifestyle is identified by criteria such as survey results or behavioral patterns. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the user's current lifestyle into a generative AI and use the generative AI to customize the learning data.

[0052] The learning unit can prioritize learning highly relevant data by taking into account the user's geographical location. For example, if the user is in a specific region, the learning unit can prioritize providing learning data related to that region. For example, if the user is traveling, the learning unit can prioritize providing learning data related to the travel destination. For example, if the user is at home, the learning unit can prioritize providing learning data related to home. This allows the learning unit to provide highly relevant learning data based on the user's geographical location. Highly relevant data is identified by criteria such as geographical location and the user's behavioral patterns. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the user's geographical location into a generative AI and use the generative AI to prioritize learning highly relevant data.

[0053] The learning unit can analyze a user's social media activity and learn relevant data. For example, the learning unit can prioritize providing learning data related to topics that the user frequently mentions on social media. For example, the learning unit can identify areas of interest from a user's social media activity and provide learning data related to those areas. For example, the learning unit can provide optimal learning data based on the time of day a user is active on social media. This allows for the provision of optimal learning data based on the user's social media activity. Social media activity is analyzed based on criteria such as post content and the number of likes. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input a user's social media activity into a generative AI and learn relevant data using the generative AI.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] A personalized AI agent system can monitor a user's health status and adjust the agent's behavior based on that health data. For example, it can monitor the user's heart rate and blood pressure, and if abnormalities are detected, it can provide advice to help them relax. It can also analyze the user's sleep patterns and offer suggestions to improve sleep quality. Furthermore, it can record the user's diet and exercise data and provide advice to support healthy lifestyle habits. This allows for personalized support tailored to the user's health condition.

[0056] A personalized AI agent system can provide relevant information and content based on the user's hobbies and interests. For example, if a user is interested in music, it can provide information on new music releases and concerts. If a user is interested in movies, it can recommend the latest movies and other films. Furthermore, if a user is interested in sports, it can provide match results and information on athletes. By providing information tailored to the user's hobbies and interests, it can improve user satisfaction.

[0057] A personalized AI agent system can suggest the optimal learning method based on the user's learning style. For example, if a user prefers visual learning, it can provide learning materials that heavily utilize visual content. If a user prefers auditory learning, it can provide audio content. Furthermore, if a user prefers practical learning, it can provide tasks that allow them to learn by actually working with their hands. By providing the optimal learning method tailored to the user's learning style, the system can maximize learning effectiveness.

[0058] A personalized AI agent system can provide notifications and reminders at the optimal time based on the user's lifestyle. For example, if a user has a morning routine, important notifications can be provided during the morning hours. Similarly, if a user has a night owl routine, reminders can be provided during the evening hours. Furthermore, if the user's lifestyle changes, the timing of notifications and reminders can be adjusted in real time. This improves user convenience by providing notifications and reminders at the optimal time according to the user's lifestyle.

[0059] A personalized AI agent system can provide region-specific information and services based on the user's geographical location. For example, if the user is in a specific area, it can provide weather and traffic information for that area. If the user is traveling, it can provide tourist information and restaurant recommendations for their destination. Furthermore, if the user is at home, it can provide information on events and shops in the vicinity of their home. By providing region-specific information and services based on the user's geographical location, this system can improve user convenience.

[0060] A personalized AI agent system can predict future behavior and provide appropriate support based on a user's past activity history. For example, if a user has exercised during a specific time slot in the past, it can provide exercise reminders during that time. Similarly, if a user has shopped on a specific day of the week in the past, it can provide a shopping list for that day. Furthermore, if a user has participated in a specific event in the past, it can provide information about similar events. This improves user convenience by providing appropriate support based on the user's past activity history.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The foundation model unit prepares the model that will serve as the basis for the agent. The foundation model unit includes components such as natural language understanding, image and speech recognition, and sentiment analysis, and can analyze user input, image data, and emotions. Step 2: The additional learning unit enables the base model unit to further train a portion of the model. The additional learning unit can perform transfer learning by adding an output layer, further train a portion of the model using user data, or optimize the model for a specific task. Step 3: The memory unit stores the user's actions and experiences. The memory unit can store personal data in isolated areas for each user, record the user's behavior history, and save the user's experiences in a database. Step 4: The learning unit learns based on the information stored by the memory unit, taking into account the user's instructions, responses, and preferences. The learning unit can learn unfrozen parts of the model based on user instructions, adjust the model based on user responses, and change the agent's behavior based on user preferences.

[0063] (Example of form 2) An embodiment of the present invention provides a personalized AI agent system that offers an AI agent tailored to individual needs. While AI services are offered in various fields such as healthcare, education, law, and IT, these services are often generic and struggle to meet the individual needs of users. Furthermore, the widespread adoption of general-purpose AI raises concerns about mass unemployment among specialists and cultural mediocrity. The objective of the present invention is to solve these problems by providing a personalized AI agent tailored to individual needs. For example, the personalized AI agent system provides a model that forms the basis of the agent. For instance, it may include components such as natural language understanding, image / speech recognition, and sentiment analysis. The personalized AI agent system also allows for additional learning of parts of the model. For example, a less expensive version may include an output layer for transfer learning. Furthermore, the personalized AI agent system stores user behavior and experiences. For example, personal data is stored in isolated areas for each user and can be used for retrieval or learning. The personalized AI agent system also learns based on user instructions, responses, and preferences. For example, the user can change the agent's behavior by having it learn unfrozen parts of the model. In this way, by realizing a personalized AI agent, it is possible to provide services tailored to the individual needs of users and prevent mediocrity and model collapse caused by the widespread adoption of AI agents across society. As a result, the personalized AI agent system can provide services tailored to the individual needs of users.

[0064] The personal AI agent system according to this embodiment comprises a base model unit, an additional learning unit, a memory unit, and a learning unit. The base model unit prepares a base model for the agent. The base model unit includes components such as natural language understanding, image / speech recognition, and sentiment analysis. The base model unit can analyze user input using, for example, natural language understanding technology. The base model unit can analyze user image data using, for example, image recognition technology. The base model unit can analyze user emotions using, for example, sentiment analysis technology. The additional learning unit enables additional learning of a part of the model in the base model unit. The additional learning unit can perform transfer learning by adding an output layer, for example. The additional learning unit can perform additional learning of a part of the model using, for example, user data. The additional learning unit can optimize the model for a specific task, for example. The memory unit stores user behavior and experiences. The memory unit can store personal data in isolated areas for each user, for example. The memory unit can record user behavior history, for example. The memory unit can, for example, store the user's experience in a database. The learning unit learns based on the information stored by the memory unit, as well as the user's instructions, responses, and preferences. The learning unit can, for example, learn unfrozen parts of the model based on the user's instructions. The learning unit can, for example, adjust the model based on the user's responses. The learning unit can, for example, change the agent's behavior based on the user's preferences. As a result, the personalized AI agent system according to this embodiment can provide services that meet the individual needs of the user.

[0065] The foundational model unit prepares the model that forms the basis of the agent. The foundational model unit includes components such as natural language understanding, image and speech recognition, and sentiment analysis. Specifically, it can analyze user input using natural language understanding technology. Natural language understanding technology is a technology for analyzing text entered by the user and understanding its intent and meaning. For example, if a user enters "What's the weather like tomorrow?", the foundational model unit analyzes the question and obtains appropriate information to provide a weather forecast. It can also analyze the user's image data using image recognition technology. Image recognition technology is a technology for analyzing images uploaded by the user and understanding their content. For example, if a user uploads a picture of their pet, the foundational model unit analyzes the image and identifies the type and characteristics of the pet. It can also analyze the user's emotions using sentiment analysis technology. Sentiment analysis technology is a technology for reading emotions from the user's text and voice. For example, if a user enters "I'm very tired today," the foundational model unit reads the user's level of fatigue from the text and provides appropriate advice and support. This allows the foundational model unit to analyze diverse user input data and provide the agent with advanced understanding capabilities. Furthermore, the foundational model unit can combine these technologies to handle more complex tasks. For example, if a user uploads an image related to the weather while saying "Tell me tomorrow's weather," the foundational model unit can analyze both the text and the image to provide more accurate information. This enables the foundational model unit to respond flexibly to the diverse needs of users.

[0066] The additional learning unit enables the base model unit to further learn parts of the model. Specifically, it can perform transfer learning by adding an output layer. Transfer learning is a technique that adds new data to an existing model for training, allowing the model to be optimized for specific tasks. For example, if a user provides data related to a specific task, the additional learning unit can use that data to further learn parts of the model and build an agent specialized for that task. This allows the user to use a customized agent that meets their needs. Furthermore, the additional learning unit can further learn parts of the model using user data. For example, by training the agent with phrases and specific terms that the user uses daily, the agent can better adapt to the user's language and expressions. This makes communication between the agent and the user more natural and smooth. The additional learning unit can also optimize the model for specific tasks. For example, if a user uses a specific project management tool, the additional learning unit can train the agent with data related to that tool, enabling the agent to provide support for project management. This allows the agent to improve the user's work efficiency. Furthermore, the additional learning unit can continuously improve the model based on user feedback. For example, if a user provides feedback on the agent's response, the additional learning unit learns that feedback and improves the agent's response accuracy. This allows the additional learning unit to respond flexibly to user needs, enabling continuous improvement of the agent's performance.

[0067] The memory unit stores user behavior and experiences. Specifically, it can store personal data in isolated areas for each user. This allows for secure management of individual data while protecting user privacy. For example, by storing a user's past search and purchase history in the memory unit, the agent can understand the user's preferences and tendencies and provide more personalized services. The memory unit can record the user's behavioral history. For example, it can record the user's daily tasks and schedules, and the agent can use this information to set reminders and manage tasks. This allows users to efficiently manage their daily work. Furthermore, the memory unit can store user experiences in a database. For example, it can record information about events and projects the user has participated in in the past, and the agent can use this information to provide advice and support. This allows the agent to leverage the user's past experiences to provide more appropriate support. The memory unit also has security features to securely manage user data. For example, it protects user data from unauthorized access by encrypting data and controlling access. This allows users to use the agent with peace of mind. In addition, the memory unit can regularly back up user data to prevent data loss or corruption. This ensures that user data is always securely stored and quickly accessible when needed. The memory unit remembers user behavior and experiences, allowing agents to provide more personalized services and respond flexibly to user needs.

[0068] The learning unit learns based on user instructions, responses, and preferences, using information stored by the memory unit. Specifically, it can learn unfrozen parts of the model based on user instructions. For example, if a user instructs the agent to perform a specific task, the learning unit learns data related to that task, enabling the agent to perform the task more efficiently. This allows the agent to respond quickly and accurately to user instructions. Furthermore, the learning unit can adjust the model based on user responses. For example, if a user provides feedback on information or services provided by the agent, the learning unit adjusts the model based on that feedback, improving the agent's response accuracy. This allows the agent to provide services that meet user expectations. The learning unit can also change the agent's behavior based on user preferences. For example, if a user prefers a particular music genre, the learning unit learns this information, allowing the agent to recommend music that matches the user's preferences. This allows the agent to provide personalized services tailored to the user's preferences. In addition, the learning unit can learn user behavior patterns and tendencies, providing predictive support. For example, if a user has a habit of drinking coffee at a specific time every morning, the learning unit learns this information, allowing the agent to remind the user to prepare the coffee. This allows the agent to support the user's daily life and improve convenience. The learning unit continuously learns based on the user's instructions, responses, and preferences, improving the agent's performance and enabling it to provide services tailored to the user's individual needs.

[0069] The base model unit can include components such as natural language understanding, image and speech recognition, and sentiment analysis. For example, the base model unit can analyze user input using natural language understanding technology. For example, the base model unit can analyze user image data using image recognition technology. For example, the base model unit can analyze user emotions using sentiment analysis technology. This allows the base model unit to provide a wide range of functions by including diverse components. Natural language understanding technology is implemented using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Image recognition technology is implemented using techniques such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Sentiment analysis technology is implemented using techniques such as text-based sentiment analysis and speech-based sentiment analysis. Some or all of the above-described processes in the base model unit may be performed using, for example, generative AI, or without generative AI. For example, when the base model unit analyzes user input using natural language understanding technology, it can output the analysis results using generative AI.

[0070] The additional learning unit can perform transfer learning by adding an output layer. For example, by adding an output layer and performing transfer learning, the flexibility of the model is improved. The additional learning unit can, for example, further train a part of the model using user data. The additional learning unit can, for example, optimize the model for a specific task. This further improves the flexibility of the model by adding an output layer and performing transfer learning. Transfer learning is a technique that reuses a part of a previously trained model and adapts it to a new task. Some or all of the above processing in the additional learning unit may be performed using, for example, generative AI, or without generative AI. For example, the additional learning unit can input user data into a generative AI and further train a part of the model using the generative AI.

[0071] The memory unit can store personal data in isolated areas for each user, making it available for retrieval or learning. For example, the memory unit can store personal data in isolated areas for each user. For example, the memory unit can record a user's behavioral history. For example, the memory unit can store a user's experience in a database. This allows for the secure management and use of the user's personal data as needed. Isolated areas are implemented using technologies such as database partitioning and access control. Some or all of the above-described processes in the memory unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory unit can input a user's behavioral history into a generative AI and store the data using the generative AI.

[0072] The learning unit can change the agent's behavior by having the user themselves learn the unfrozen parts of the model. The learning unit can, for example, learn the unfrozen parts of the model based on user instructions. The learning unit can, for example, adjust the model based on user responses. The learning unit can, for example, change the agent's behavior based on user preferences. This allows the agent's behavior to be customized based on user instructions. Unfreezing is, for example, a technique that makes a specific layer of the model retrainable. Some or all of the above processing in the learning unit may be performed, for example, using generative AI, or without using generative AI. For example, the learning unit can input user instructions into generative AI and use generative AI to learn the unfrozen parts of the model.

[0073] The base model unit can estimate the user's emotions and adjust the initial settings of the base model based on the estimated user emotions. For example, if the user is stressed, the base model unit can apply settings to the base model that promote relaxation. For example, if the user is excited, the base model unit can apply settings to the base model that enhance concentration. For example, if the user is tired, the base model unit can adjust the base model to allow for simple and intuitive operation. This allows for a more personalized experience by providing initial settings that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the base model unit may be performed using a generative AI, or not using a generative AI. For example, the base model unit can input user emotion data into a generative AI and use the generative AI to adjust the initial settings of the base model.

[0074] The base model unit can analyze the user's past behavior history and select the optimal model configuration. For example, the base model unit can prioritize displaying functions that the user has frequently used in the past. For example, the base model unit can automatically select the optimal model configuration based on the user's past behavior patterns. For example, the base model unit can hide functions that the user has avoided in the past. This allows the system to provide the optimal model configuration based on the user's past behavior history. The optimal model configuration is selected based on criteria such as performance indicators or user behavior patterns. Some or all of the above processing in the base model unit may be performed using, for example, a generative AI, or without a generative AI. For example, the base model unit can input the user's past behavior history into a generative AI and use the generative AI to select the optimal model configuration.

[0075] The base model unit can dynamically change the model components based on the user's current areas of interest. For example, the base model unit can prioritize displaying components related to topics the user is currently interested in. For example, the base model unit can hide unnecessary components based on the user's current areas of interest. For example, the base model unit can update the model components in real time if the user's areas of interest change. This allows for dynamic changes to the model components according to the user's areas of interest. Areas of interest are identified by criteria such as survey results or past behavioral history. Some or all of the above processing in the base model unit may be performed using, for example, generative AI, or without generative AI. For example, the base model unit can input the user's current areas of interest into generative AI and dynamically change the model components using generative AI.

[0076] The base model unit can estimate the user's emotions and determine the priority of the base model based on the estimated user emotions. For example, if the user is relaxed, the base model unit can prioritize displaying functions related to relaxation. For example, if the user is stressed, the base model unit can prioritize displaying functions that help reduce stress. For example, if the user is focused, the base model unit can prioritize displaying functions that enhance concentration. By setting priorities according to the user's emotions, more appropriate functions can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative 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 processing in the base model unit may be performed using a generative AI, or not using a generative AI. For example, the base model unit can input user emotion data into a generative AI and use the generative AI to determine the priority of the base model.

[0077] The base model unit can prioritize the use of highly relevant models, taking into account the user's geographical location information. For example, if the user is in a specific region, the base model unit can prioritize displaying information related to that region. For example, if the user is traveling, the base model unit can prioritize displaying information related to the travel destination. For example, if the user is at home, the base model unit can prioritize displaying information related to home. This allows the system to provide highly relevant information based on the user's geographical location information. Geographical location information is obtained based on criteria such as GPS data or IP address. Some or all of the above processing in the base model unit may be performed using, for example, a generative AI, or without a generative AI. For example, the base model unit can input the user's geographical location information into a generative AI and use the generative AI to prioritize the use of highly relevant models.

[0078] The foundation model unit can analyze a user's social media activity and select relevant models. For example, the foundation model unit can prioritize the use of models related to topics that the user frequently mentions on social media. For example, the foundation model unit can identify areas of interest from the user's social media activity and select models related to those areas. For example, the foundation model unit can select the optimal model based on the time of day the user is active on social media. This allows the system to provide the optimal model based on the user's social media activity. Social media activity is analyzed based on criteria such as post content and the number of likes. Some or all of the above processing in the foundation model unit may be performed using, for example, a generative AI, or without a generative AI. For example, the foundation model unit can input the user's social media activity into a generative AI and use the generative AI to select relevant models.

[0079] The additional learning unit can estimate the user's emotions and adjust the timing of additional learning based on the estimated user emotions. For example, the additional learning unit can adjust the timing of additional learning if the user is relaxed. For example, the additional learning unit can delay the timing of additional learning if the user is stressed. For example, the additional learning unit can advance the timing of additional learning if the user is focused. This maximizes the learning effect by performing additional learning at a timing appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the additional learning unit may be performed using a generative AI, or not using a generative AI. For example, the additional learning unit can input user emotion data into a generative AI and use the generative AI to adjust the timing of additional learning.

[0080] The additional learning unit can analyze the user's past learning history and select the optimal learning method. For example, the additional learning unit can prioritize the use of learning methods that were effective for the user in the past. For example, the additional learning unit can automatically select the optimal learning method from the user's past learning history. For example, the additional learning unit can hide learning methods that the user has avoided in the past. This allows the system to provide the optimal learning method based on the user's past learning history. The learning history is recorded based on criteria such as past learning data and learning results. Some or all of the above processing in the additional learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the additional learning unit can input the user's past learning history into a generative AI and use the generative AI to select the optimal learning method.

[0081] The additional learning unit can customize learning data based on the user's current lifestyle. For example, if the user is busy, the additional learning unit can provide data that can be learned in a short amount of time. For example, if the user is relaxed, the additional learning unit can provide detailed learning data. For example, if the user is working on a specific project, the additional learning unit can provide learning data related to that project. This allows for the provision of learning data tailored to the user's lifestyle. Lifestyle is identified by criteria such as survey results or behavioral patterns. Some or all of the processing described above in the additional learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the additional learning unit can input the user's current lifestyle into a generative AI and use the generative AI to customize the learning data.

[0082] The additional learning unit can estimate the user's emotions and determine the priority of additional learning based on the estimated user emotions. For example, if the user is relaxed, the additional learning unit can prioritize providing learning data related to relaxation. For example, if the user is stressed, the additional learning unit can prioritize providing learning data that helps reduce stress. For example, if the user is focused, the additional learning unit can prioritize providing learning data that enhances concentration. This maximizes the learning effect by performing additional learning with priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the additional learning unit may be performed using a generative AI, for example, or without a generative AI. For example, the additional learning unit can input user emotion data into a generative AI and use the generative AI to determine the priority of additional learning.

[0083] The additional learning unit can prioritize learning highly relevant data by taking into account the user's geographical location information. For example, if the user is in a specific region, the additional learning unit can prioritize providing learning data related to that region. For example, if the user is traveling, the additional learning unit can prioritize providing learning data related to the travel destination. For example, if the user is at home, the additional learning unit can prioritize providing learning data related to home. This allows the system to provide highly relevant learning data based on the user's geographical location information. Highly relevant data is identified by criteria such as geographical location information and the user's behavioral patterns. Some or all of the processing described above in the additional learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the additional learning unit can input the user's geographical location information into a generative AI and use the generative AI to prioritize learning highly relevant data.

[0084] The additional learning unit can analyze the user's social media activity and learn relevant data. For example, the additional learning unit can prioritize providing learning data related to topics that the user frequently mentions on social media. For example, the additional learning unit can identify areas of interest from the user's social media activity and provide learning data related to those areas. For example, the additional learning unit can provide optimal learning data based on the time of day the user is active on social media. This allows for the provision of optimal learning data based on the user's social media activity. Social media activity is analyzed based on criteria such as post content and the number of likes. Some or all of the above processing in the additional learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the additional learning unit can input the user's social media activity into a generative AI and learn relevant data using the generative AI.

[0085] The memory unit can estimate the user's emotions and adjust how memory data is stored based on the estimated emotions. For example, if the user is relaxed, the memory unit can store detailed data. For example, if the user is stressed, the memory unit can store concise data. For example, if the user is focused, the memory unit can prioritize storing important data. This streamlines data management by providing a storage method that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the memory unit may be performed using a generative AI, or not. For example, the memory unit can input user emotion data into a generative AI and use the generative AI to adjust how memory data is stored.

[0086] The memory unit can analyze the user's past behavior history and select the optimal data storage method. For example, the memory unit can prioritize saving data that the user has frequently accessed in the past. For example, the memory unit can automatically select the optimal data storage method based on the user's past behavior patterns. For example, the memory unit can hide data that the user has avoided in the past. This allows the system to provide the optimal data storage method based on the user's past behavior history. The data storage method is set based on criteria such as the database structure and access control. Some or all of the above processing in the memory unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory unit can input the user's past behavior history into a generative AI and use the generative AI to select the optimal data storage method.

[0087] The memory unit can change the data storage priority based on the user's current areas of interest. For example, the memory unit can prioritize saving data related to topics the user is currently interested in. For example, the memory unit can hide unnecessary data based on the user's current areas of interest. For example, the memory unit can update the data storage priority in real time if the user's areas of interest change. This allows for the provision of data storage priorities that correspond to the user's areas of interest. The storage priority is set based on criteria such as the importance of the data or the user's areas of interest. Some or all of the above processing in the memory unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the memory unit can input the user's current areas of interest into a generative AI and use the generative AI to change the data storage priority.

[0088] The memory unit can estimate the user's emotions and adjust the retrieval method of memory data based on the estimated user emotions. For example, if the user is relaxed, the memory unit can provide detailed search results. For example, if the user is stressed, the memory unit can provide concise search results. For example, if the user is focused, the memory unit can prioritize displaying important search results. This makes data retrieval more efficient by providing a search method that is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the memory unit may be performed using a generative AI, or not. For example, the memory unit can input user emotion data into a generative AI and use the generative AI to adjust the retrieval method of memory data.

[0089] The memory unit can prioritize saving highly relevant data, taking into account the user's geographical location. For example, if the user is in a specific region, the memory unit can prioritize saving data related to that region. For example, if the user is traveling, the memory unit can prioritize saving data related to the travel destination. For example, if the user is at home, the memory unit can prioritize saving data related to home. This allows the system to provide highly relevant data based on the user's geographical location. Highly relevant data is identified by criteria such as geographical location and the user's behavioral patterns. Some or all of the above processing in the memory unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory unit can input the user's geographical location into a generative AI and use the generative AI to prioritize saving highly relevant data.

[0090] The memory unit can analyze the user's social media activity and store relevant data. For example, the memory unit can prioritize storing data related to topics that the user frequently mentions on social media. For example, the memory unit can identify areas of interest from the user's social media activity and store data related to those areas. For example, the memory unit can store optimal data based on the time of day the user is active on social media. This allows the system to provide optimal data based on the user's social media activity. Social media activity is analyzed based on criteria such as post content and the number of likes. Some or all of the above processing in the memory unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory unit can input the user's social media activity into a generative AI and use the generative AI to store relevant data.

[0091] The learning unit can estimate the user's emotions and adjust the learning algorithm based on the estimated user emotions. For example, if the user is relaxed, the learning unit can use a learning algorithm related to relaxation. For example, if the user is stressed, the learning unit can use a learning algorithm that helps reduce stress. For example, if the user is focused, the learning unit can use a learning algorithm that enhances concentration. This maximizes the learning effect by providing a learning algorithm that responds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative 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 processing in the learning unit may be performed using a generative AI, for example, or without a generative AI. For example, the learning unit can input user emotion data into a generative AI and adjust the learning algorithm using the generative AI.

[0092] The learning unit can analyze the user's past learning history and select the optimal learning method. For example, the learning unit can prioritize the use of learning methods that have been effective for the user in the past. For example, the learning unit can automatically select the optimal learning method from the user's past learning history. For example, the learning unit can hide learning methods that the user has avoided in the past. This allows the learning unit to provide the optimal learning method based on the user's past learning history. The learning history is recorded based on criteria such as past learning data and learning results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the user's past learning history into a generative AI and use the generative AI to select the optimal learning method.

[0093] The learning unit can customize learning data based on the user's current lifestyle. For example, if the user is busy, the learning unit can provide data that can be learned in a short amount of time. For example, if the user is relaxed, the learning unit can provide detailed learning data. For example, if the user is working on a specific project, the learning unit can provide learning data related to that project. This allows the learning unit to provide learning data that is tailored to the user's lifestyle. Lifestyle is identified by criteria such as survey results or behavioral patterns. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the user's current lifestyle into a generative AI and use the generative AI to customize the learning data.

[0094] The learning unit can estimate the user's emotions and determine learning priorities based on the estimated emotions. For example, if the user is relaxed, the learning unit can prioritize providing learning data related to relaxation. For example, if the user is stressed, the learning unit can prioritize providing learning data that helps reduce stress. For example, if the user is focused, the learning unit can prioritize providing learning data that enhances concentration. This maximizes learning effectiveness by prioritizing learning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using a generative AI, or not. For example, the learning unit can input user emotion data into a generative AI and use the generative AI to determine learning priorities.

[0095] The learning unit can prioritize learning highly relevant data by taking into account the user's geographical location. For example, if the user is in a specific region, the learning unit can prioritize providing learning data related to that region. For example, if the user is traveling, the learning unit can prioritize providing learning data related to the travel destination. For example, if the user is at home, the learning unit can prioritize providing learning data related to home. This allows the learning unit to provide highly relevant learning data based on the user's geographical location. Highly relevant data is identified by criteria such as geographical location and the user's behavioral patterns. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the user's geographical location into a generative AI and use the generative AI to prioritize learning highly relevant data.

[0096] The learning unit can analyze a user's social media activity and learn relevant data. For example, the learning unit can prioritize providing learning data related to topics that the user frequently mentions on social media. For example, the learning unit can identify areas of interest from a user's social media activity and provide learning data related to those areas. For example, the learning unit can provide optimal learning data based on the time of day a user is active on social media. This allows for the provision of optimal learning data based on the user's social media activity. Social media activity is analyzed based on criteria such as post content and the number of likes. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input a user's social media activity into a generative AI and learn relevant data using the generative AI.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] A personalized AI agent system can monitor a user's health status and adjust the agent's behavior based on that health data. For example, it can monitor the user's heart rate and blood pressure, and if abnormalities are detected, it can provide advice to help them relax. It can also analyze the user's sleep patterns and offer suggestions to improve sleep quality. Furthermore, it can record the user's diet and exercise data and provide advice to support healthy lifestyle habits. This allows for personalized support tailored to the user's health condition.

[0099] A personalized AI agent system can estimate a user's emotions and adjust its dialogue style based on those emotions. For example, if the user is sad, it can offer words of encouragement. If the user is angry, it can respond calmly and offer suggestions for problem-solving. Furthermore, if the user is happy, it can show empathy and engage in positive dialogue. This allows for appropriate dialogue tailored to the user's emotions, thereby improving user satisfaction.

[0100] A personalized AI agent system can provide relevant information and content based on the user's hobbies and interests. For example, if a user is interested in music, it can provide information on new music releases and concerts. If a user is interested in movies, it can recommend the latest movies and other films. Furthermore, if a user is interested in sports, it can provide match results and information on athletes. By providing information tailored to the user's hobbies and interests, it can improve user satisfaction.

[0101] A personalized AI agent system can suggest the optimal learning method based on the user's learning style. For example, if a user prefers visual learning, it can provide learning materials that heavily utilize visual content. If a user prefers auditory learning, it can provide audio content. Furthermore, if a user prefers practical learning, it can provide tasks that allow them to learn by actually working with their hands. By providing the optimal learning method tailored to the user's learning style, the system can maximize learning effectiveness.

[0102] A personalized AI agent system can estimate a user's emotions and adjust the agent's response speed based on those emotions. For example, if a user is anxious, a quick response can alleviate their anxiety. If a user is relaxed, a slower response pace can maintain that relaxed atmosphere. Furthermore, if a user is concentrating, a timely response can avoid interrupting their concentration. By providing an appropriate response speed tailored to the user's emotions, this system can improve user satisfaction.

[0103] A personalized AI agent system can provide notifications and reminders at the optimal time based on the user's lifestyle. For example, if a user has a morning routine, important notifications can be provided during the morning hours. Similarly, if a user has a night owl routine, reminders can be provided during the evening hours. Furthermore, if the user's lifestyle changes, the timing of notifications and reminders can be adjusted in real time. This improves user convenience by providing notifications and reminders at the optimal time according to the user's lifestyle.

[0104] A personalized AI agent system can estimate a user's emotions and adjust the agent's voice tone based on those emotions. For example, if the user is sad, the agent can speak in a gentle tone. If the user is angry, the agent can respond in a calm and composed tone. Furthermore, if the user is happy, the agent can speak in a bright and cheerful tone. By providing an appropriate voice tone according to the user's emotions, this system can improve user satisfaction.

[0105] A personalized AI agent system can provide region-specific information and services based on the user's geographical location. For example, if the user is in a specific area, it can provide weather and traffic information for that area. If the user is traveling, it can provide tourist information and restaurant recommendations for their destination. Furthermore, if the user is at home, it can provide information on events and shops in the vicinity of their home. By providing region-specific information and services based on the user's geographical location, this system can improve user convenience.

[0106] A personalized AI agent system can estimate a user's emotions and adjust the agent's suggestions based on those emotions. For example, if a user is feeling stressed, it can suggest relaxing activities. If a user is bored, it can suggest new hobbies or activities that pique their interest. Furthermore, if a user is concentrating, it can provide advice to help them maintain their focus. By providing appropriate suggestions tailored to the user's emotions, this system can improve user satisfaction.

[0107] A personalized AI agent system can predict future behavior and provide appropriate support based on a user's past activity history. For example, if a user has exercised during a specific time slot in the past, it can provide exercise reminders during that time. Similarly, if a user has shopped on a specific day of the week in the past, it can provide a shopping list for that day. Furthermore, if a user has participated in a specific event in the past, it can provide information about similar events. This improves user convenience by providing appropriate support based on the user's past activity history.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The foundation model unit prepares the model that will serve as the basis for the agent. The foundation model unit includes components such as natural language understanding, image and speech recognition, and sentiment analysis, and can analyze user input, image data, and emotions. Step 2: The additional learning unit enables the base model unit to further train a portion of the model. The additional learning unit can perform transfer learning by adding an output layer, further train a portion of the model using user data, or optimize the model for a specific task. Step 3: The memory unit stores the user's actions and experiences. The memory unit can store personal data in isolated areas for each user, record the user's behavior history, and save the user's experiences in a database. Step 4: The learning unit learns based on the information stored by the memory unit, taking into account the user's instructions, responses, and preferences. The learning unit can learn unfrozen parts of the model based on user instructions, adjust the model based on user responses, and change the agent's behavior based on user preferences.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements described above, including the base model unit, additional learning unit, memory unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the base model unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12, and includes components such as natural language understanding, image / speech recognition, and sentiment analysis. The additional learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and can perform transfer learning by adding an output layer. The memory unit is implemented by the storage 50 of the smart device 14 and the database 24 of the data processing unit 12, and stores the user's actions and experiences. The learning unit is implemented by the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing unit 12, and performs learning based on the user's instructions, responses, and preferences. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] 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.

[0116] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0117] 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.

[0118] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0123] 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.

[0124] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the base model unit, additional learning unit, memory unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the base model unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12, and includes components such as natural language understanding, image / speech recognition, and sentiment analysis. The additional learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and can perform transfer learning by adding an output layer. The memory unit is implemented by the storage 50 of the smart glasses 214 and the database 24 of the data processing unit 12, and stores the user's actions and experiences. The learning unit is implemented by the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12, and performs learning based on the user's instructions, responses, and preferences. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] 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.

[0138] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] 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.

[0140] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the base model unit, additional learning unit, memory unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the base model unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12, and includes components such as natural language understanding, image / speech recognition, and sentiment analysis. The additional learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and can perform transfer learning by adding an output layer. The memory unit is implemented by the storage 50 of the headset terminal 314 and the database 24 of the data processing unit 12, and stores the user's actions and experiences. The learning unit is implemented by the control unit 46A of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12, and performs learning based on the user's instructions, responses, and preferences. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] 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.

[0155] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] 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.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the base model unit, additional learning unit, memory unit, and learning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the base model unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12, and includes components such as natural language understanding, image / speech recognition, and sentiment analysis. The additional learning unit is implemented by the specific processing unit 290 of the data processing unit 12, and can perform transfer learning by adding an output layer. The memory unit is implemented by the storage 50 of the robot 414 and the database 24 of the data processing unit 12, and stores the user's actions and experiences. The learning unit is implemented by the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing unit 12, and performs learning based on the user's instructions, responses, and preferences. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0163] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] 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.

[0173] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] 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.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) The foundation model section prepares the base model for the agent, The base model unit includes an additional learning unit that enables additional learning of a part of the model, A memory unit that stores the user's actions and experiences, A learning unit that learns based on the user's instructions, responses, and preferences, based on the information stored in the memory unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned base model section is It includes components such as natural language understanding, image and speech recognition, and sentiment analysis. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned additional learning unit is Add an output layer and perform transfer learning. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned storage unit is Personal data is stored in an isolated area for each user and made available for retrieval or learning. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, By having the user themselves unfreeze parts of the model, the agent's behavior can be changed. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned base model section is It estimates the user's emotions and adjusts the initial settings of the base model based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned base model section is Analyze the user's past behavior history and select the optimal model configuration. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned base model section is Dynamically change the model's components based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned base model section is It estimates user sentiment and determines the priority of the underlying models based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned base model section is Prioritize the use of the most relevant model, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned base model section is Analyze users' social media activity and select relevant models. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned additional learning unit is It estimates the user's emotions and adjusts the timing of additional learning based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned additional learning unit is Analyze the user's past learning history and select the optimal learning method. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned additional learning unit is Customize training data based on the user's current lifestyle. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned additional learning unit is It estimates the user's emotions and determines the priority of additional learning based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned additional learning unit is Prioritize learning highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned additional learning unit is Analyze users' social media activity and learn from relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned storage unit is It estimates the user's emotions and adjusts how memory data is stored based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned storage unit is Analyze the user's past behavior history and select the optimal data storage method. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned storage unit is Change the data storage priority based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned storage unit is It estimates the user's emotions and adjusts how memory data is retrieved based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned storage unit is Prioritize saving highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned storage unit is Analyze users' social media activity and save relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning algorithm based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning unit, Analyze the user's past learning history and select the optimal learning method. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning unit, Customize training data based on the user's current lifestyle. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, It estimates the user's emotions and determines learning priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, Prioritize learning highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, Analyze users' social media activity and learn from relevant data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The foundation model section prepares the base model for the agent, The base model unit includes an additional learning unit that enables additional learning of a part of the model, A memory unit that stores the user's actions and experiences, A learning unit that learns based on the user's instructions, responses, and preferences, based on the information stored in the memory unit, Equipped with A system characterized by the following features.

2. The aforementioned base model section is It includes components such as natural language understanding, image and speech recognition, and sentiment analysis. The system according to feature 1.

3. The aforementioned additional learning unit is Add an output layer and perform transfer learning. The system according to feature 1.

4. The aforementioned storage unit is Personal data is stored in an isolated area for each user and made available for retrieval or learning. The system according to feature 1.

5. The aforementioned learning unit, By having the user themselves unfreeze parts of the model, the agent's behavior can be changed. The system according to feature 1.

6. The aforementioned base model section is It estimates the user's emotions and adjusts the initial settings of the base model based on the estimated user emotions. The system according to feature 1.

7. The aforementioned base model section is Analyze the user's past behavior history and select the optimal model configuration. The system according to feature 1.

8. The aforementioned base model section is Dynamically change the model's components based on the user's current areas of interest. The system according to feature 1.

9. The aforementioned base model section is It estimates user sentiment and determines the priority of the underlying models based on the estimated user sentiment. The system according to feature 1.

10. The aforementioned base model section is Prioritize the use of the most relevant model, taking into account the user's geographical location. The system according to feature 1.

Images