system

Abstract

The system according to this embodiment aims to deeply understand the user's values ​​and behavioral patterns and provide real-time feedback. [Solution] The system according to the embodiment comprises a collection unit, a learning unit, and a feedback unit. The collection unit collects the user's conversation history, search history, and purchase history. The learning unit performs reinforcement learning based on the data collected by the collection unit. The feedback unit provides feedback using an AI agent generated by the learning unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that it was difficult to deeply understand the user's values and behavior patterns and provide real-time feedback.

[0005] The system according to the embodiment aims to deeply understand the user's values and behavior patterns and provide real-time feedback.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, a learning unit, and a feedback unit. The data collection unit collects the user's conversation history, search history, and purchase history. The learning unit performs reinforcement learning based on the data collected by the data collection unit. The feedback unit provides feedback using an AI agent generated by the learning unit. [Effects of the Invention]

[0007] The system according to this embodiment can deeply understand the user's values ​​and behavioral patterns and provide real-time feedback. [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 controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

[0019] The smart device 14 comprises a computer 36, a reception 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 reception device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​agent persona system according to an embodiment of the present invention is a tool that revolutionizes customer research in new product development. This system utilizes generative AI to perform reinforcement learning based on the user's conversation history, search history, and purchase history, and creates tens of thousands of AI agents. This allows for a deep understanding of the user's values ​​and behavioral patterns, and provides real-time feedback. In particular, a characteristic of reinforcement learning is that the output does not depend on the distribution of the training data, making it possible to flexibly respond to unknown scenarios and the evaluation of new products. By leveraging this characteristic and obtaining rapid feedback in the early stages of the development process, it is possible to rapidly run the verification cycle at the idea stage, and as a result, it becomes possible to launch innovative products into the market ahead of other companies, establishing a competitive advantage. For example, the AI ​​agent persona system collects the user's conversation history, search history, and purchase history. For example, it collects data such as the content of conversations on social media, search history on search engines, and purchase history on electronic payment systems. This allows for an understanding of the user's behavioral patterns and values. Next, reinforcement learning is performed based on the collected data to create tens of thousands of AI agents. Reinforcement learning allows agents to reinforce their behavior by receiving rewards, and imitates the user's values ​​and behavioral patterns. For example, if a user tends to purchase a particular product, the agent learns to behave similarly. Furthermore, using generative AI, it gains a deep understanding of user values ​​and behavioral patterns, providing real-time feedback. For instance, when evaluating a new product, the agent can simulate user reactions, allowing for rapid feedback in the early stages of the development process. This mechanism enables rapid and cost-effective evaluation of a product's market suitability, improving the product's success rate by providing feedback in the early stages of development. Moreover, due to the characteristics of reinforcement learning, it can flexibly respond to unknown scenarios and the evaluation of new products. In this way, using an AI agent persona system revolutionizes customer research in new product development, enabling rapid market entry and establishing a competitive advantage.This allows the AI ​​agent persona system to gain a deep understanding of user behavior patterns and provide real-time feedback.

[0029] The AI ​​agent persona system according to this embodiment comprises a collection unit, a learning unit, and a feedback unit. The collection unit collects the user's conversation history, search history, and purchase history. For example, the collection unit collects the content of conversations the user has on social media. For example, the collection unit collects the user's search history on search engines. For example, the collection unit collects the user's purchase history on electronic payment systems. The learning unit performs reinforcement learning based on the data collected by the collection unit. For example, the learning unit performs reinforcement learning based on the collected data and generates tens of thousands of AI agents. For example, the learning unit uses Q-learning as the reinforcement learning algorithm. For example, the learning unit uses SARSA as the reinforcement learning algorithm. For example, the learning unit uses deep reinforcement learning as the reinforcement learning algorithm. The feedback unit provides feedback using the AI ​​agents generated by the learning unit. For example, the feedback unit uses the generated AI agents to gain a deep understanding of the user's values ​​and behavioral patterns. For example, the feedback unit provides real-time feedback using the generated AI agents. The feedback unit, for example, uses the generated AI agent to evaluate the new product. This allows the AI ​​agent persona system according to the embodiment to gain a deep understanding of user behavior patterns and provide real-time feedback.

[0030] The data collection unit collects users' conversation history, search history, and purchase history. Specifically, the unit collects the content of conversations that users have on social media. This includes data in various formats, such as text messages, images, videos, and voice messages. The unit acquires this data in real time and uses it as foundational data to analyze users' communication patterns and interests. The unit also collects users' search history on search engines. This includes search keywords, click history of search results, and search times. This allows the unit to understand what kind of information users are looking for and what topics they are interested in. Furthermore, the unit collects users' purchase history on electronic payment systems. This includes the type of product purchased, purchase amount, purchase date and time, and purchase location. This allows for a detailed analysis of users' consumption behavior and purchasing trends. The unit centrally manages this data and makes it available to the learning and feedback units while ensuring security. The collected data is stored on a cloud server and encrypted as needed. This allows the unit to efficiently collect and manage data while protecting user privacy.

[0031] The learning unit performs reinforcement learning based on the data collected by the collection unit. Specifically, the learning unit generates tens of thousands of AI agents based on the collected data. These AI agents are designed to mimic the user's behavior patterns and values. The learning unit uses Q-learning, SARSA, and deep reinforcement learning as reinforcement learning algorithms. Q-learning is an algorithm that learns actions to maximize rewards for state-action pairs, while SARSA is an algorithm that considers action selection and its consequences during learning. Deep reinforcement learning is a type of reinforcement learning that can handle complex state spaces using neural networks. The learning unit applies these algorithms to analyze user behavior data and learn optimal behavior patterns. For example, it predicts what actions a user will take under specific conditions and evaluates the consequences of those actions. Based on these learning results, the learning unit updates the behavior model of the AI ​​agents to enable more accurate predictions. As a result, the learning unit can generate AI agents that mimic user behavior patterns with high accuracy and improve the overall system performance.

[0032] The Feedback Unit provides feedback using AI agents generated by the Learning Unit. Specifically, the Feedback Unit uses the generated AI agents to gain a deep understanding of the user's values ​​and behavioral patterns. This enables it to provide personalized feedback tailored to the user's needs and preferences. For example, the Feedback Unit uses AI agents to recommend content and products that the user might be interested in. The Feedback Unit also provides real-time feedback using the generated AI agents. This includes immediate advice and suggestions based on the user's actions. For example, when a user performs a specific search, it instantly presents relevant information and products. Furthermore, the Feedback Unit uses the generated AI agents to evaluate new products. This allows it to suggest product improvements and new features based on user reactions and feedback. The Feedback Unit collects this feedback and provides it to the Learning Unit, continuously improving the AI ​​agent's learning process. This enables the Feedback Unit to gain a deep understanding of user behavioral patterns and provide appropriate feedback in real time.

[0033] The data collection unit can collect conversation content on social media, search history on search engines, and purchase history on electronic payment systems. For example, the data collection unit can collect conversation content on social media. For example, the data collection unit can collect search history on search engines. For example, the data collection unit can collect purchase history on electronic payment systems. By collecting diverse user behavior data, more accurate analysis becomes possible. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input conversation content on social media into a generating AI and have the generating AI perform analysis of the conversation content.

[0034] The learning unit can perform reinforcement learning based on collected data and generate tens of thousands of AI agents. For example, the learning unit can perform reinforcement learning based on collected data. For example, the learning unit can generate tens of thousands of AI agents. For example, the learning unit can use Q-learning as a reinforcement learning algorithm. For example, the learning unit can use SARSA as a reinforcement learning algorithm. For example, the learning unit can use deep reinforcement learning as a reinforcement learning algorithm. This makes it possible to generate a large number of AI agents through reinforcement learning and imitate user behavior patterns. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input collected data into a generating AI and have the generating AI perform the generation of AI agents.

[0035] The feedback unit can use the generated AI agent to gain a deep understanding of the user's values ​​and behavioral patterns and provide real-time feedback. For example, the feedback unit can use the generated AI agent to gain a deep understanding of the user's values ​​and behavioral patterns. The feedback unit can use the generated AI agent to provide real-time feedback. For example, the feedback unit can use the generated AI agent to evaluate a new product. This allows for rapid product evaluation by gaining a deep understanding of the user's values ​​and behavioral patterns and providing real-time feedback. Some or all of the above-described processes in the feedback unit may be performed using AI, or not using AI. For example, the feedback unit can input the generated AI agent into the generating AI and have the generating AI perform the task of understanding the user's values ​​and behavioral patterns.

[0036] The feedback unit, when evaluating a new product, uses agents to simulate user reactions and obtains rapid feedback in the early stages of the development process. For example, when evaluating a new product, the feedback unit uses agents to simulate user reactions. The feedback unit obtains rapid feedback in the early stages of the development process. For example, the feedback unit uses agents to simulate user reactions and evaluate the product. This allows for rapid evaluation of the product's market suitability by obtaining rapid feedback in the early stages of the development process. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user reactions simulated by the agents into a generating AI and have the generating AI provide the feedback.

[0037] The learning unit, due to the characteristics of reinforcement learning, can flexibly respond to unknown scenarios and the evaluation of new products. The learning unit, for example, responds to unknown scenarios due to the characteristics of reinforcement learning. The learning unit, for example, responds to the evaluation of new products due to the characteristics of reinforcement learning. The learning unit, for example, responds flexibly to unknown scenarios and the evaluation of new products due to the characteristics of reinforcement learning. This improves the success rate of products by flexibly responding to unknown scenarios and the evaluation of new products. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the evaluation of unknown scenarios and new products into a generating AI and have the generating AI perform the evaluation.

[0038] The data collection unit can analyze the user's past behavior history and select the optimal data collection method. For example, the data collection unit prioritizes collecting data from devices the user has frequently used in the past. For example, if the user was active during a specific time period in the past, the data collection unit collects data during that time period. For example, the data collection unit analyzes the user's past behavior patterns and selects the most efficient data collection method. This allows for the selection of the optimal data collection method and efficient data collection by analyzing the user's past behavior history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's past behavior history into a generating AI and have the generating AI select the optimal data collection method.

[0039] The data collection unit can filter data based on the user's current areas of interest and lifestyle during collection. For example, the data collection unit prioritizes collecting data related to topics the user is currently interested in. For example, the data collection unit filters relevant data based on the user's lifestyle (e.g., traveling, working). For example, the data collection unit collects appropriate data based on the user's current activity (e.g., exercising, resting). This allows for the collection of highly relevant data by filtering data based on the user's current areas of interest and lifestyle. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's current areas of interest and lifestyle into a generating AI and have the generating AI perform data filtering.

[0040] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, if the user is in a specific region, the data collection unit will prioritize the collection of data related to that region. For example, if the user is traveling, the data collection unit will prioritize the collection of data related to the travel destination. For example, if the user is at home, the data collection unit will prioritize the collection of data related to the area around the user's home. This allows for efficient data collection by considering the user's geographical location information and prioritizing the collection of highly relevant data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant data.

[0041] The data collection unit can analyze the user's social media activity and collect relevant data during the collection process. For example, the data collection unit can collect data related to the content the user frequently posts on social media. For example, the data collection unit can collect data based on the activity of accounts the user follows. For example, the data collection unit can collect data related to groups and communities the user participates in. This allows for the efficient collection of relevant data by analyzing the user's social media activity. Some or all of the above-described processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's social media activity into a generating AI and have the generating AI perform the collection of relevant data.

[0042] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit optimizes the learning algorithm by setting optimal parameters based on past learning data. For example, the learning unit improves the learning algorithm by utilizing insights gained from past learning data. For example, the learning unit improves the accuracy of the learning algorithm by analyzing past learning data. As a result, the learning algorithm is optimized by referring to past learning data, and the accuracy of learning is improved. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0043] The learning unit can enhance learning based on user behavior patterns during the learning process. For example, the learning unit can analyze user behavior patterns and enhance the learning algorithm. For example, the learning unit can weight the learning data based on user behavior patterns. For example, the learning unit can adjust the parameters of the learning algorithm based on user behavior patterns. This improves the accuracy of learning by enhancing learning based on user behavior patterns. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user behavior patterns into a generating AI and have the generating AI perform the learning enhancement.

[0044] The learning unit can weight the training data based on when the collected data was submitted during training. For example, if the collected data is recently submitted, the learning unit will set a higher weight and reflect this in the training. For example, if the collected data is older, the learning unit will set a lower weight and reflect this in the training. The learning unit can dynamically adjust the weighting of the training data based on when the collected data was submitted. This improves the accuracy of training by weighting the training data based on when the collected data was submitted. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input the submission dates of the collected data into a generating AI and have the generating AI perform the weighting of the training data.

[0045] The learning unit can customize the learning algorithm during training by taking user attribute information into consideration. For example, the learning unit can customize the learning algorithm based on the user's age and gender. For example, the learning unit can customize the learning algorithm based on the user's occupation and hobbies. For example, the learning unit can customize the learning algorithm based on the user's place of residence and cultural background. By customizing the learning algorithm while taking user attribute information into consideration, the accuracy of learning is improved. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input user attribute information into a generating AI and have the generating AI perform the customization of the learning algorithm.

[0046] The feedback unit can adjust the level of detail of the feedback based on the user's values ​​and behavioral patterns. For example, the feedback unit can adjust the level of detail of the feedback based on the user's values. For example, the feedback unit can adjust the level of detail of the feedback based on the user's behavioral patterns. For example, the feedback unit can adjust the level of detail of the feedback by referring to the user's past feedback history. By adjusting the level of detail of the feedback based on the user's values ​​and behavioral patterns, the system can provide the user with the most appropriate feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's values ​​and behavioral patterns into a generating AI and have the generating AI perform the adjustment of the level of detail of the feedback.

[0047] The feedback unit can simulate the user's reaction during feedback and provide optimal feedback. For example, the feedback unit simulates optimal feedback based on the user's past reactions. For example, the feedback unit simulates optimal feedback considering the user's current situation. For example, the feedback unit simulates optimal feedback based on the user's attribute information. In this way, by simulating the user's reaction, optimal feedback can be provided. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input user reaction data into a generating AI and have the generating AI perform a feedback simulation.

[0048] The feedback unit can provide optimal feedback by considering the user's geographical location information when providing feedback. For example, if the user is in a specific region, the feedback unit will provide feedback relevant to that region. For example, if the user is traveling, the feedback unit will provide feedback relevant to the travel destination. For example, if the user is at home, the feedback unit will provide feedback relevant to the area around the user's home. In this way, by providing optimal feedback by considering the user's geographical location information, the feedback unit can provide the most suitable feedback for the user. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of providing optimal feedback.

[0049] The feedback unit can analyze the user's social media activity and provide relevant feedback when providing feedback. For example, the feedback unit can provide feedback related to the content the user frequently posts on social media. For example, the feedback unit can provide feedback based on the activity of accounts the user follows. For example, the feedback unit can provide feedback related to groups and communities the user participates in. In this way, relevant feedback can be provided by analyzing the user's social media activity. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's social media activity into a generating AI and have the generating AI perform the task of providing relevant feedback.

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

[0051] The data collection unit can optimize the data collection method according to the type and usage of the user's device when collecting user behavior data. For example, if the user is using a smartphone, the data collection unit can employ a data collection method specifically for smartphones. Similarly, if the user is using a personal computer, the data collection unit can employ a data collection method specifically for personal computers. Furthermore, if the user is using a wearable device, the data collection unit can optimize data collection from the wearable device. By optimizing the data collection method according to the type and usage of the user's device, more accurate and efficient data collection becomes possible.

[0052] The learning unit can weight user behavior data based on the user's lifestyle and daily routines when analyzing user behavior data. For example, if a user has a habit of jogging every morning, the learning unit can give a higher weight to data from that time. Similarly, if a user has time to relax in the evening, the learning unit can give a higher weight to data from that time. Furthermore, if a user engages in a specific activity on weekends, the learning unit can give a higher weight to data related to that activity. By weighting data based on the user's lifestyle and daily routines, more accurate learning becomes possible.

[0053] The data collection unit can incorporate features to protect user privacy when collecting user behavior data. For example, the data collection unit can anonymize user data during collection. Furthermore, the data collection unit can collect data only with the user's consent. In addition, the data collection unit can provide users with the option to stop data collection. This allows for data collection while protecting user privacy.

[0054] The feedback unit can analyze user behavior data and customize the content of feedback based on the user's behavior patterns. For example, if a user tends to perform a specific action at a specific time of day, the feedback unit can provide feedback related to that action. Similarly, if a user tends to perform a specific action in a specific location, the feedback unit can provide feedback related to that location. Furthermore, if a user tends to perform a specific action using a specific device, the feedback unit can provide feedback related to that device. This allows for more effective feedback by customizing the content of feedback based on the user's behavior patterns.

[0055] The learning unit can dynamically adjust its learning algorithm in response to changes in user behavior when analyzing user behavior data. For example, if a user starts a new hobby, the learning unit can prioritize learning data related to that hobby. Similarly, if a user starts a new job, the learning unit can prioritize learning data related to that job. Furthermore, if a user moves to a new living environment, the learning unit can prioritize learning data related to that environment. By dynamically adjusting the learning algorithm in response to changes in user behavior, the accuracy of learning can be improved.

[0056] The data collection unit can optimize the timing of data collection based on predictions of user behavior when collecting user behavior data. For example, if a user tends to perform a specific action during a specific time period, the data collection unit can collect data during that time period. Also, if a user tends to perform a specific action in a specific location, the data collection unit can collect data at that location. Furthermore, if a user tends to perform a specific action using a specific device, the data collection unit can collect data on that device. In this way, by optimizing the timing of data collection based on predictions of user behavior, data can be collected efficiently.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The data collection unit collects the user's conversation history, search history, and purchase history. For example, the data collection unit collects the user's conversation content on social media, search history on search engines, and purchase history on electronic payment systems. Step 2: The learning unit performs reinforcement learning based on the data collected by the collection unit. For example, the learning unit performs reinforcement learning based on the collected data and generates tens of thousands of AI agents. Reinforcement learning algorithms such as Q-learning, SARSA, and deep reinforcement learning can be used. Step 3: The feedback unit provides feedback using the AI ​​agent generated by the learning unit. For example, the feedback unit uses the generated AI agent to gain a deep understanding of the user's values ​​and behavioral patterns and provide real-time feedback. It can also evaluate new products.

[0059] (Example of form 2) The AI ​​agent persona system according to an embodiment of the present invention is a tool that revolutionizes customer research in new product development. This system utilizes generative AI to perform reinforcement learning based on the user's conversation history, search history, and purchase history, and creates tens of thousands of AI agents. This allows for a deep understanding of the user's values ​​and behavioral patterns, and provides real-time feedback. In particular, a characteristic of reinforcement learning is that the output does not depend on the distribution of the training data, making it possible to flexibly respond to unknown scenarios and the evaluation of new products. By leveraging this characteristic and obtaining rapid feedback in the early stages of the development process, it is possible to rapidly run the verification cycle at the idea stage, and as a result, it becomes possible to launch innovative products into the market ahead of other companies, establishing a competitive advantage. For example, the AI ​​agent persona system collects the user's conversation history, search history, and purchase history. For example, it collects data such as the content of conversations on social media, search history on search engines, and purchase history on electronic payment systems. This allows for an understanding of the user's behavioral patterns and values. Next, reinforcement learning is performed based on the collected data to create tens of thousands of AI agents. Reinforcement learning allows agents to reinforce their behavior by receiving rewards, and imitates the user's values ​​and behavioral patterns. For example, if a user tends to purchase a particular product, the agent learns to behave similarly. Furthermore, using generative AI, it gains a deep understanding of user values ​​and behavioral patterns, providing real-time feedback. For instance, when evaluating a new product, the agent can simulate user reactions, allowing for rapid feedback in the early stages of the development process. This mechanism enables rapid and cost-effective evaluation of a product's market suitability, improving the product's success rate by providing feedback in the early stages of development. Moreover, due to the characteristics of reinforcement learning, it can flexibly respond to unknown scenarios and the evaluation of new products. In this way, using an AI agent persona system revolutionizes customer research in new product development, enabling rapid market entry and establishing a competitive advantage.This allows the AI ​​agent persona system to gain a deep understanding of user behavior patterns and provide real-time feedback.

[0060] The AI ​​agent persona system according to this embodiment comprises a collection unit, a learning unit, and a feedback unit. The collection unit collects the user's conversation history, search history, and purchase history. For example, the collection unit collects the content of conversations the user has on social media. For example, the collection unit collects the user's search history on search engines. For example, the collection unit collects the user's purchase history on electronic payment systems. The learning unit performs reinforcement learning based on the data collected by the collection unit. For example, the learning unit performs reinforcement learning based on the collected data and generates tens of thousands of AI agents. For example, the learning unit uses Q-learning as the reinforcement learning algorithm. For example, the learning unit uses SARSA as the reinforcement learning algorithm. For example, the learning unit uses deep reinforcement learning as the reinforcement learning algorithm. The feedback unit provides feedback using the AI ​​agents generated by the learning unit. For example, the feedback unit uses the generated AI agents to gain a deep understanding of the user's values ​​and behavioral patterns. For example, the feedback unit provides real-time feedback using the generated AI agents. The feedback unit, for example, uses the generated AI agent to evaluate the new product. This allows the AI ​​agent persona system according to the embodiment to gain a deep understanding of user behavior patterns and provide real-time feedback.

[0061] The data collection unit collects users' conversation history, search history, and purchase history. Specifically, the unit collects the content of conversations that users have on social media. This includes data in various formats, such as text messages, images, videos, and voice messages. The unit acquires this data in real time and uses it as foundational data to analyze users' communication patterns and interests. The unit also collects users' search history on search engines. This includes search keywords, click history of search results, and search times. This allows the unit to understand what kind of information users are looking for and what topics they are interested in. Furthermore, the unit collects users' purchase history on electronic payment systems. This includes the type of product purchased, purchase amount, purchase date and time, and purchase location. This allows for a detailed analysis of users' consumption behavior and purchasing trends. The unit centrally manages this data and makes it available to the learning and feedback units while ensuring security. The collected data is stored on a cloud server and encrypted as needed. This allows the unit to efficiently collect and manage data while protecting user privacy.

[0062] The learning unit performs reinforcement learning based on the data collected by the collection unit. Specifically, the learning unit generates tens of thousands of AI agents based on the collected data. These AI agents are designed to mimic the user's behavior patterns and values. The learning unit uses Q-learning, SARSA, and deep reinforcement learning as reinforcement learning algorithms. Q-learning is an algorithm that learns actions to maximize rewards for state-action pairs, while SARSA is an algorithm that considers action selection and its consequences during learning. Deep reinforcement learning is a type of reinforcement learning that can handle complex state spaces using neural networks. The learning unit applies these algorithms to analyze user behavior data and learn optimal behavior patterns. For example, it predicts what actions a user will take under specific conditions and evaluates the consequences of those actions. Based on these learning results, the learning unit updates the behavior model of the AI ​​agents to enable more accurate predictions. As a result, the learning unit can generate AI agents that mimic user behavior patterns with high accuracy and improve the overall system performance.

[0063] The Feedback Unit provides feedback using AI agents generated by the Learning Unit. Specifically, the Feedback Unit uses the generated AI agents to gain a deep understanding of the user's values ​​and behavioral patterns. This enables it to provide personalized feedback tailored to the user's needs and preferences. For example, the Feedback Unit uses AI agents to recommend content and products that the user might be interested in. The Feedback Unit also provides real-time feedback using the generated AI agents. This includes immediate advice and suggestions based on the user's actions. For example, when a user performs a specific search, it instantly presents relevant information and products. Furthermore, the Feedback Unit uses the generated AI agents to evaluate new products. This allows it to suggest product improvements and new features based on user reactions and feedback. The Feedback Unit collects this feedback and provides it to the Learning Unit, continuously improving the AI ​​agent's learning process. This enables the Feedback Unit to gain a deep understanding of user behavioral patterns and provide appropriate feedback in real time.

[0064] The data collection unit can collect conversation content on social media, search history on search engines, and purchase history on electronic payment systems. For example, the data collection unit can collect conversation content on social media. For example, the data collection unit can collect search history on search engines. For example, the data collection unit can collect purchase history on electronic payment systems. By collecting diverse user behavior data, more accurate analysis becomes possible. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input conversation content on social media into a generating AI and have the generating AI perform analysis of the conversation content.

[0065] The learning unit can perform reinforcement learning based on collected data and generate tens of thousands of AI agents. For example, the learning unit can perform reinforcement learning based on collected data. For example, the learning unit can generate tens of thousands of AI agents. For example, the learning unit can use Q-learning as a reinforcement learning algorithm. For example, the learning unit can use SARSA as a reinforcement learning algorithm. For example, the learning unit can use deep reinforcement learning as a reinforcement learning algorithm. This makes it possible to generate a large number of AI agents through reinforcement learning and imitate user behavior patterns. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input collected data into a generating AI and have the generating AI perform the generation of AI agents.

[0066] The feedback unit can use the generated AI agent to gain a deep understanding of the user's values ​​and behavioral patterns and provide real-time feedback. For example, the feedback unit can use the generated AI agent to gain a deep understanding of the user's values ​​and behavioral patterns. The feedback unit can use the generated AI agent to provide real-time feedback. For example, the feedback unit can use the generated AI agent to evaluate a new product. This allows for rapid product evaluation by gaining a deep understanding of the user's values ​​and behavioral patterns and providing real-time feedback. Some or all of the above-described processes in the feedback unit may be performed using AI, or not using AI. For example, the feedback unit can input the generated AI agent into the generating AI and have the generating AI perform the task of understanding the user's values ​​and behavioral patterns.

[0067] The feedback unit, when evaluating a new product, uses agents to simulate user reactions and obtains rapid feedback in the early stages of the development process. For example, when evaluating a new product, the feedback unit uses agents to simulate user reactions. The feedback unit obtains rapid feedback in the early stages of the development process. For example, the feedback unit uses agents to simulate user reactions and evaluate the product. This allows for rapid evaluation of the product's market suitability by obtaining rapid feedback in the early stages of the development process. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user reactions simulated by the agents into a generating AI and have the generating AI provide the feedback.

[0068] The learning unit, due to the characteristics of reinforcement learning, can flexibly respond to unknown scenarios and the evaluation of new products. The learning unit, for example, responds to unknown scenarios due to the characteristics of reinforcement learning. The learning unit, for example, responds to the evaluation of new products due to the characteristics of reinforcement learning. The learning unit, for example, responds flexibly to unknown scenarios and the evaluation of new products due to the characteristics of reinforcement learning. This improves the success rate of products by flexibly responding to unknown scenarios and the evaluation of new products. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the evaluation of unknown scenarios and new products into a generating AI and have the generating AI perform the evaluation.

[0069] The data collection unit can estimate the user's emotions and adjust the timing of collecting conversation history, search history, and purchase history based on the estimated emotions. For example, if the user is stressed, the data collection unit can delay the collection timing to reduce the user's burden. For example, if the user is relaxed, the data collection unit can advance the collection timing to collect more data. For example, if the user is in a hurry, the data collection unit can optimize the collection timing to collect data quickly. This reduces the user's burden and allows for efficient data collection by adjusting the collection timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 data collection unit may be performed using AI, or not using AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI adjust the collection timing.

[0070] The data collection unit can analyze the user's past behavior history and select the optimal data collection method. For example, the data collection unit prioritizes collecting data from devices the user has frequently used in the past. For example, if the user was active during a specific time period in the past, the data collection unit collects data during that time period. For example, the data collection unit analyzes the user's past behavior patterns and selects the most efficient data collection method. This allows for the selection of the optimal data collection method and efficient data collection by analyzing the user's past behavior history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's past behavior history into a generating AI and have the generating AI select the optimal data collection method.

[0071] The data collection unit can filter data based on the user's current areas of interest and lifestyle during collection. For example, the data collection unit prioritizes collecting data related to topics the user is currently interested in. For example, the data collection unit filters relevant data based on the user's lifestyle (e.g., traveling, working). For example, the data collection unit collects appropriate data based on the user's current activity (e.g., exercising, resting). This allows for the collection of highly relevant data by filtering data based on the user's current areas of interest and lifestyle. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's current areas of interest and lifestyle into a generating AI and have the generating AI perform data filtering.

[0072] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated user emotions. For example, if the user is excited, the data collection unit will prioritize collecting data related to emotions. For example, if the user is calm, the data collection unit will prioritize collecting data related to long-term behavioral patterns. For example, if the user is tired, the data collection unit will prioritize collecting data related to short-term behavioral patterns. This allows for efficient data collection by prioritizing the data to be collected 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 data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of the data.

[0073] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, if the user is in a specific region, the data collection unit will prioritize the collection of data related to that region. For example, if the user is traveling, the data collection unit will prioritize the collection of data related to the travel destination. For example, if the user is at home, the data collection unit will prioritize the collection of data related to the area around the user's home. This allows for efficient data collection by considering the user's geographical location information and prioritizing the collection of highly relevant data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant data.

[0074] The data collection unit can analyze the user's social media activity and collect relevant data during the collection process. For example, the data collection unit can collect data related to the content the user frequently posts on social media. For example, the data collection unit can collect data based on the activity of accounts the user follows. For example, the data collection unit can collect data related to groups and communities the user participates in. This allows for the efficient collection of relevant data by analyzing the user's social media activity. Some or all of the above-described processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's social media activity into a generating AI and have the generating AI perform the collection of relevant data.

[0075] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is relaxed, the learning unit uses data related to relaxation for training. For example, if the user is stressed, the learning unit uses data related to stress reduction for training. For example, if the user is excited, the learning unit uses data related to excitement for training. This improves the accuracy of learning by selecting training data based on 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 AI, for example, or without AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI perform the selection of training data.

[0076] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit optimizes the learning algorithm by setting optimal parameters based on past learning data. For example, the learning unit improves the learning algorithm by utilizing insights gained from past learning data. For example, the learning unit improves the accuracy of the learning algorithm by analyzing past learning data. As a result, the learning algorithm is optimized by referring to past learning data, and the accuracy of learning is improved. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0077] The learning unit can enhance learning based on user behavior patterns during the learning process. For example, the learning unit can analyze user behavior patterns and enhance the learning algorithm. For example, the learning unit can weight the learning data based on user behavior patterns. For example, the learning unit can adjust the parameters of the learning algorithm based on user behavior patterns. This improves the accuracy of learning by enhancing learning based on user behavior patterns. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user behavior patterns into a generating AI and have the generating AI perform the learning enhancement.

[0078] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is relaxed, the learning unit increases the learning frequency to collect data. For example, if the user is stressed, the learning unit decreases the learning frequency to reduce the user's burden. For example, if the user is excited, the learning unit adjusts the learning frequency to collect optimal data. This allows for efficient learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using AI, or not using AI. For example, the learning unit can input user emotion data into the generative AI and have the generative AI adjust the learning frequency.

[0079] The learning unit can weight the training data based on when the collected data was submitted during training. For example, if the collected data is recently submitted, the learning unit will set a higher weight and reflect this in the training. For example, if the collected data is older, the learning unit will set a lower weight and reflect this in the training. The learning unit can dynamically adjust the weighting of the training data based on when the collected data was submitted. This improves the accuracy of training by weighting the training data based on when the collected data was submitted. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input the submission dates of the collected data into a generating AI and have the generating AI perform the weighting of the training data.

[0080] The learning unit can customize the learning algorithm during training by taking user attribute information into consideration. For example, the learning unit can customize the learning algorithm based on the user's age and gender. For example, the learning unit can customize the learning algorithm based on the user's occupation and hobbies. For example, the learning unit can customize the learning algorithm based on the user's place of residence and cultural background. By customizing the learning algorithm while taking user attribute information into consideration, the accuracy of learning is improved. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input user attribute information into a generating AI and have the generating AI perform the customization of the learning algorithm.

[0081] The feedback unit can estimate the user's emotions and adjust the way it presents the feedback based on those emotions. For example, if the user is nervous, the feedback unit provides simple and easily understandable feedback. If the user is relaxed, the feedback unit provides detailed feedback. If the user is in a hurry, the feedback unit provides concise feedback. By adjusting the way it presents the feedback based on the user's emotions, it can provide the user with the most appropriate feedback. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the feedback unit may be performed using AI or not. For example, the feedback unit can input user emotion data into the generative AI and have the generative AI adjust the way it presents the feedback.

[0082] The feedback unit can adjust the level of detail of the feedback based on the user's values ​​and behavioral patterns. For example, the feedback unit can adjust the level of detail of the feedback based on the user's values. For example, the feedback unit can adjust the level of detail of the feedback based on the user's behavioral patterns. For example, the feedback unit can adjust the level of detail of the feedback by referring to the user's past feedback history. By adjusting the level of detail of the feedback based on the user's values ​​and behavioral patterns, the system can provide the user with the most appropriate feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's values ​​and behavioral patterns into a generating AI and have the generating AI perform the adjustment of the level of detail of the feedback.

[0083] The feedback unit can simulate the user's reaction during feedback and provide optimal feedback. For example, the feedback unit simulates optimal feedback based on the user's past reactions. For example, the feedback unit simulates optimal feedback considering the user's current situation. For example, the feedback unit simulates optimal feedback based on the user's attribute information. In this way, by simulating the user's reaction, optimal feedback can be provided. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input user reaction data into a generating AI and have the generating AI perform a feedback simulation.

[0084] The feedback unit can estimate the user's emotions and determine the priority of feedback based on the estimated emotions. For example, if the user is excited, the feedback unit will prioritize providing feedback related to that emotion. For example, if the user is calm, the feedback unit will prioritize providing feedback related to long-term behavioral patterns. For example, if the user is tired, the feedback unit will prioritize providing feedback related to short-term behavioral patterns. This allows for efficient feedback delivery by prioritizing feedback based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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-described processes in the feedback unit may be performed using AI, or not using AI. For example, the feedback unit can input user emotion data into a generative AI and have the generative AI determine the priority of feedback.

[0085] The feedback unit can provide optimal feedback by considering the user's geographical location information when providing feedback. For example, if the user is in a specific region, the feedback unit will provide feedback relevant to that region. For example, if the user is traveling, the feedback unit will provide feedback relevant to the travel destination. For example, if the user is at home, the feedback unit will provide feedback relevant to the area around the user's home. In this way, by providing optimal feedback by considering the user's geographical location information, the feedback unit can provide the most suitable feedback for the user. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of providing optimal feedback.

[0086] The feedback unit can analyze the user's social media activity and provide relevant feedback when providing feedback. For example, the feedback unit can provide feedback related to the content the user frequently posts on social media. For example, the feedback unit can provide feedback based on the activity of accounts the user follows. For example, the feedback unit can provide feedback related to groups and communities the user participates in. In this way, relevant feedback can be provided by analyzing the user's social media activity. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the user's social media activity into a generating AI and have the generating AI perform the task of providing relevant feedback.

[0087] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0088] The data collection unit can optimize the data collection method according to the type and usage of the user's device when collecting user behavior data. For example, if the user is using a smartphone, the data collection unit can employ a data collection method specifically for smartphones. Similarly, if the user is using a personal computer, the data collection unit can employ a data collection method specifically for personal computers. Furthermore, if the user is using a wearable device, the data collection unit can optimize data collection from the wearable device. By optimizing the data collection method according to the type and usage of the user's device, more accurate and efficient data collection becomes possible.

[0089] The learning unit can weight user behavior data based on the user's lifestyle and daily routines when analyzing user behavior data. For example, if a user has a habit of jogging every morning, the learning unit can give a higher weight to data from that time. Similarly, if a user has time to relax in the evening, the learning unit can give a higher weight to data from that time. Furthermore, if a user engages in a specific activity on weekends, the learning unit can give a higher weight to data related to that activity. By weighting data based on the user's lifestyle and daily routines, more accurate learning becomes possible.

[0090] The feedback unit can estimate the user's emotions and adjust the timing of feedback based on those emotions. For example, if the user is stressed, the feedback unit can delay the timing of feedback to reduce the user's burden. Conversely, if the user is relaxed, the feedback unit can speed up the timing of feedback to provide more feedback. Furthermore, if the user is in a hurry, the feedback unit can optimize the timing of feedback to provide feedback quickly. In this way, by adjusting the timing of feedback according to the user's emotions, the system can provide the most appropriate feedback for the user.

[0091] The data collection unit can incorporate features to protect user privacy when collecting user behavior data. For example, the data collection unit can anonymize user data during collection. Furthermore, the data collection unit can collect data only with the user's consent. In addition, the data collection unit can provide users with the option to stop data collection. This allows for data collection while protecting user privacy.

[0092] The learning unit can estimate the user's emotions and adjust the learning algorithm based on those emotions. For example, if the user is relaxed, the learning unit can prioritize learning data related to relaxation. If the user is stressed, the learning unit can prioritize learning data related to stress reduction. Furthermore, if the user is excited, the learning unit can prioritize learning data related to excitement. By adjusting the learning algorithm based on the user's emotions, the accuracy of learning can be improved.

[0093] The feedback unit can analyze user behavior data and customize the content of feedback based on the user's behavior patterns. For example, if a user tends to perform a specific action at a specific time of day, the feedback unit can provide feedback related to that action. Similarly, if a user tends to perform a specific action in a specific location, the feedback unit can provide feedback related to that location. Furthermore, if a user tends to perform a specific action using a specific device, the feedback unit can provide feedback related to that device. This allows for more effective feedback by customizing the content of feedback based on the user's behavior patterns.

[0094] The data collection unit can estimate the user's emotions and adjust the frequency of data collection based on those emotions. For example, if the user is relaxed, the unit can increase the data collection frequency to collect more data. If the user is stressed, the unit can decrease the data collection frequency to reduce the user's burden. Furthermore, if the user is excited, the unit can adjust the data collection frequency to collect the optimal amount of data. In this way, by adjusting the data collection frequency based on the user's emotions, data can be collected efficiently.

[0095] The learning unit can dynamically adjust its learning algorithm in response to changes in user behavior when analyzing user behavior data. For example, if a user starts a new hobby, the learning unit can prioritize learning data related to that hobby. Similarly, if a user starts a new job, the learning unit can prioritize learning data related to that job. Furthermore, if a user moves to a new living environment, the learning unit can prioritize learning data related to that environment. By dynamically adjusting the learning algorithm in response to changes in user behavior, the accuracy of learning can be improved.

[0096] The feedback unit can estimate the user's emotions and adjust the content of the feedback based on those emotions. For example, if the user is relaxed, the feedback unit can provide detailed feedback. If the user is stressed, the feedback unit can provide simple and easy-to-understand feedback. Furthermore, if the user is agitated, the feedback unit can provide concise feedback. In this way, by adjusting the content of the feedback based on the user's emotions, the system can provide the most appropriate feedback for the user.

[0097] The data collection unit can optimize the timing of data collection based on predictions of user behavior when collecting user behavior data. For example, if a user tends to perform a specific action during a specific time period, the data collection unit can collect data during that time period. Also, if a user tends to perform a specific action in a specific location, the data collection unit can collect data at that location. Furthermore, if a user tends to perform a specific action using a specific device, the data collection unit can collect data on that device. In this way, by optimizing the timing of data collection based on predictions of user behavior, data can be collected efficiently.

[0098] The following briefly describes the processing flow for example form 2.

[0099] Step 1: The data collection unit collects the user's conversation history, search history, and purchase history. For example, the data collection unit collects the user's conversation content on social media, search history on search engines, and purchase history on electronic payment systems. Step 2: The learning unit performs reinforcement learning based on the data collected by the collection unit. For example, the learning unit performs reinforcement learning based on the collected data and generates tens of thousands of AI agents. Reinforcement learning algorithms such as Q-learning, SARSA, and deep reinforcement learning can be used. Step 3: The feedback unit provides feedback using the AI ​​agent generated by the learning unit. For example, the feedback unit uses the generated AI agent to gain a deep understanding of the user's values ​​and behavioral patterns and provide real-time feedback. It can also evaluate new products.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] Each of the multiple elements described above, including the data collection unit, learning unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit is implemented by the control unit 46A of the smart device 14 and collects the user's conversation history, search history, and purchase history. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs reinforcement learning based on the collected data to generate tens of thousands of AI agents. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides real-time feedback using the generated AI agents. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0104] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] Each of the multiple elements described above, including the data collection unit, learning unit, and feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit is implemented by the control unit 46A of the smart glasses 214 and collects the user's conversation history, search history, and purchase history. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs reinforcement learning based on the collected data to generate tens of thousands of AI agents. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides real-time feedback using the generated AI agents. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0120] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] Each of the multiple elements described above, including the data collection unit, learning unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit is implemented by the control unit 46A of the headset terminal 314 and collects the user's conversation history, search history, and purchase history. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs reinforcement learning based on the collected data to generate tens of thousands of AI agents. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides real-time feedback using the generated AI agents. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.).

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the 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.

[0150] 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.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is 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.

[0152] Each of the multiple elements described above, including the data collection unit, learning unit, and feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the data collection unit is implemented by the control unit 46A of the robot 414 and collects the user's conversation history, search history, and purchase history. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs reinforcement learning based on the collected data to generate tens of thousands of AI agents. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides real-time feedback using the generated AI agents. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] (Note 1) A system characterized by comprising: a collection unit that collects the user's conversation history, search history, and purchase history; a learning unit that performs reinforcement learning based on the data collected by the collection unit; and a feedback unit that provides feedback using an AI agent generated by the learning unit. (Note 2) The system described in Appendix 1 is characterized in that the collection unit collects conversation content on social media, search history on search engines, and purchase history on electronic payment systems. (Note 3) The system described in Appendix 1 is characterized in that the learning unit performs reinforcement learning based on the collected data and generates tens of thousands of AI agents. (Note 4) The system described in Appendix 1 is characterized in that the feedback unit uses a generated AI agent to deeply understand the user's values ​​and behavioral patterns and provides feedback in real time. (Note 5) The system described in Appendix 1 is characterized in that, when evaluating a new product, the feedback unit has an agent simulate user reactions and obtains rapid feedback in the early stages of the development process. (Note 6) The system described in Appendix 1 is characterized in that the learning unit can flexibly respond to unknown scenarios and evaluations of new products due to the characteristics of reinforcement learning. (Note 7) The system described in Appendix 1 is characterized in that the collection unit estimates the user's emotions and adjusts the timing of collecting conversation history, search history, and purchase history based on the estimated user emotions. (Note 8) The system described in Appendix 1 is characterized in that the collection unit analyzes the user's past behavior history and selects the optimal collection method. (Note 9) The system described in Appendix 1, wherein the data collection unit filters the data based on the user's current areas of interest and living situation during collection. (Note 10) The system according to Appendix 1, characterized in that the collection unit estimates the user's emotions and determines the priority of data to be collected based on the estimated user's emotions. (Note 11) The system described in Appendix 1 is characterized in that, during collection, the collection unit prioritizes the collection of highly relevant data, taking into account the user's geographical location information. (Note 12) The system described in Appendix 1 is characterized in that the collection unit analyzes the user's social media activity and collects relevant data during collection. (Note 13) The system according to Appendix 1, characterized in that the learning unit estimates the user's emotions and selects learning data based on the estimated user's emotions. (Note 14) The system described in Appendix 1, characterized in that the learning unit optimizes the learning algorithm by referring to past learning data during learning. (Note 15) The system according to Appendix 1, characterized in that the learning unit enhances learning based on the user's behavior patterns during learning. (Note 16) The system according to Appendix 1, characterized in that the learning unit estimates the user's emotions and adjusts the learning frequency based on the estimated user's emotions. (Note 17) The system described in Appendix 1 is characterized in that the learning unit weights the learning data based on the timing of data submission during the learning process. (Note 18) The system described in Appendix 1, characterized in that the learning unit customizes the learning algorithm during learning, taking into account the user's attribute information. (Note 19) The system according to Appendix 1, characterized in that the feedback unit estimates the user's emotions and adjusts the method of expressing the feedback based on the estimated user's emotions. (Note 20) The system according to Appendix 1, characterized in that the feedback unit adjusts the level of detail of the feedback based on the user's values ​​and behavioral patterns when providing feedback. (Note 21) The system according to Appendix 1, characterized in that the feedback unit simulates the user's reaction during feedback and provides optimal feedback. (Note 22) The system according to Appendix 1, characterized in that the feedback unit estimates the user's emotions and determines the priority of feedback based on the estimated user's emotions. (Note 23) The system according to Appendix 1, characterized in that the feedback unit provides optimal feedback by taking into account the user's geographical location information when providing feedback. (Note 24) The system according to Appendix 1, characterized in that the feedback unit analyzes the user's social media activity and provides relevant feedback at the time of feedback. [Explanation of symbols]

[0172] 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. A collection unit that collects the user's conversation history, search history, and purchase history, A learning unit that performs reinforcement learning based on the data collected by the aforementioned collection unit, The system includes a feedback unit that provides feedback using an AI agent generated by the learning unit. A system characterized by the following features.

2. The aforementioned collection unit is Collects conversation content on social media, search history on search engines, and purchase history on electronic payment systems. The system according to feature 1.

3. The aforementioned learning unit, Based on the collected data, reinforcement learning is performed to generate tens of thousands of AI agents. The system according to feature 1.

4. The aforementioned feedback unit is Using the generated AI agent, we gain a deep understanding of the user's values ​​and behavioral patterns, and provide real-time feedback. The system according to feature 1.

5. The aforementioned feedback unit is When evaluating a new product, agents simulate user reactions and provide rapid feedback early in the development process. The system according to feature 1.

6. The aforementioned learning unit, Due to the characteristics of reinforcement learning, it can flexibly respond to unknown scenarios and the evaluation of new products. The system according to feature 1.

7. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of collecting conversation history, search history, and purchase history based on the estimated user emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze the user's past behavior history and select the optimal data collection method. The system according to feature 1.

Images