system

Abstract

The system according to this embodiment aims to securely store users' personal data and utilize it in cooperation with each AI agent. [Solution] The system according to the embodiment comprises a data collection unit, a data storage unit, an API integration unit, and a fine-tuning unit. The data collection unit collects the user's personal data. The data storage unit securely stores the data collected by the data collection unit. The API integration unit integrates the data stored by the data storage unit with each AI agent via API. The fine-tuning unit uses the data integrated by the API integration unit to fine-tune the AI ​​agents.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the secure storage of user personal data and its utilization in cooperation with each AI agent have not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to securely store user personal data and utilize it in cooperation with each AI agent.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, a data storage unit, an API integration unit, and a fine-tuning unit. The data collection unit collects the user's personal data. The data storage unit securely stores the data collected by the data collection unit. The API integration unit integrates the data stored by the data storage unit with each AI agent via API. The fine-tuning unit uses the data integrated by the API integration unit to fine-tune the AI ​​agents. [Effects of the Invention]

[0007] The system according to this embodiment can securely store users' personal data and use it in conjunction with each AI agent. [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 labeled 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. ​​​​​​The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The Common Personal Database Platform (PDB) system according to an embodiment of the present invention is a system that simplifies the fine-tuning of AI agents by securely accumulating personal data such as users' consumption behavior, preferences, and internet browsing history, and linking with each AI agent via API. This system eliminates the need for users to input data from scratch when using a new AI agent. First, personal data such as users' consumption behavior, preferences, and internet browsing history are collected. This data is securely stored in data centers located throughout the country. Next, API linkage is established with each AI agent to share the accumulated data. This allows each AI agent to perform fine-tuning using the user's personal data. For example, when a user uses a new e-commerce AI agent, the consumption behavior data accumulated in the PDB can be used to recommend products that match the user's preferences. Also, when using a medical AI agent, the health data accumulated in the PDB can be used to provide the user with optimal health management advice. This mechanism allows users to easily use multiple AI agents and minimizes discrepancies in output due to differences in data volume between each AI agent. Furthermore, companies can use PDB to obtain highly confidential marketing data from personal databases and utilize it in their marketing strategies. This service is offered to B2C customers as a database usage fee (annual license) and to B2B customers as a usage fee for highly confidential marketing data from personal databases. In addition, a freemium model is adopted, offering free users a data capacity limit of 20GB and up to 5 API connections, while premium users receive a data capacity limit of 1TB and unlimited API connections. This enables the Common Personal Database Platform (PDB) system to efficiently collect, store, connect, and fine-tune users' personal data.

[0029] The common personal database platform (PDB) system according to this embodiment comprises a data collection unit, a data storage unit, an API integration unit, and a fine-tuning unit. The data collection unit collects the user's personal data. The user's personal data includes, but is not limited to, names, addresses, email addresses, and behavioral history. The data collection unit collects, for example, website browsing history. The data collection unit can also collect the user's purchase history. Furthermore, the data collection unit can collect the user's preferences. For example, the data collection unit collects information on products viewed by the user to understand the user's preferences. The data storage unit securely stores the data collected by the data collection unit. The data storage unit protects the data using, for example, encryption technology. The data storage unit can also perform access control to prevent unauthorized access to the data. Furthermore, the data storage unit can perform data backups. For example, the data storage unit periodically creates data backups to prevent data loss. The API integration unit integrates the data stored by the data storage unit with each AI agent via API. The API integration unit integrates data using, for example, a RESTful API. It can also integrate data using a SOAP API. Furthermore, it can integrate data using GraphQL. For example, the API integration unit provides user personal data to each AI agent. The fine-tuning unit uses the data integrated by the API integration unit to fine-tune the AI ​​agents. For example, the fine-tuning unit adjusts the AI ​​agent parameters using machine learning algorithms. It can also adjust the AI ​​agent parameters using deep learning algorithms. Furthermore, it can adjust the AI ​​agent parameters using reinforcement learning algorithms. For example, the fine-tuning unit takes user personal data as input and optimizes the output of the AI ​​agent.As a result, the common personal database platform (PDB) system according to this embodiment can efficiently collect, store, link, and fine-tune users' personal data.

[0030] The data collection unit collects users' personal data. This personal data includes, but is not limited to, names, addresses, email addresses, and browsing history. For example, the data collection unit collects website browsing history. Specifically, it collects detailed information such as the URLs of web pages visited, the time spent on each page, and the links clicked. The data collection unit can also collect users' purchase history. For example, it collects information such as items purchased on online shopping sites, the date and time of purchase, the purchase amount, and the payment method. Furthermore, the data collection unit can collect user preferences. For example, it collects information on products viewed by users to understand their preferences. Specifically, it collects information on product categories frequently viewed, reviews of products rated, and products added to the cart but not purchased. This allows the data collection unit to gain a detailed understanding of user behavior patterns and preferences, and to collect foundational data for providing personalized services. In addition, the data collection unit can also collect user device information and location information. For example, the system collects information such as the type of device the user is using, the OS version, the type of browser, the IP address, and GPS location information to understand the user's environment and range of activity. This allows the data collection unit to comprehensively collect diverse user data and gather foundational data for providing personalized services.

[0031] The data storage unit securely stores the data collected by the data collection unit. The data storage unit protects the data using, for example, encryption technology. Specifically, the collected data is encrypted using strong encryption algorithms such as AES (Advanced Encryption Standard) to ensure data confidentiality. The data storage unit can also implement access control to prevent unauthorized access to the data. For example, it implements user authentication and access rights management to strictly restrict which users and systems can access the data. Furthermore, the data storage unit can perform data backups. For example, it regularly creates data backups to prevent data loss. Specifically, data backups are stored on multiple servers in different physical locations, enabling data recovery even in the event of disasters or system failures. This allows the data storage unit to store collected data in a safe and reliable manner, ensuring data protection and availability. Additionally, the data storage unit can perform data validation and integrity checks to maintain data integrity. For example, it checks data format and value ranges during data entry to prevent the storage of fraudulent data. It also records data change history, allowing for tracking of changes if they occur. This allows the data storage unit to maintain data integrity and reliability, thereby improving the overall data quality of the system.

[0032] The API Integration Unit connects data stored by the Data Storage Unit to each AI agent via API. For example, the API Integration Unit uses RESTful APIs to connect data. Specifically, it uses the HTTP protocol to retrieve, send, update, and delete data through methods such as GET, POST, PUT, and DELETE. The API Integration Unit can also connect data using SOAP APIs. SOAP (Simple Object Access Protocol) is an XML-based messaging protocol that enables data exchange between different platforms. Furthermore, the API Integration Unit can also connect data using GraphQL. GraphQL is a query language that allows clients to precisely specify and retrieve the data they need. For example, the API Integration Unit provides each AI agent with user personal data. Specifically, the AI ​​agents retrieve data such as the user's name, address, email address, and behavioral history, and use this data to provide personalized services to the user. This allows the API Integration Unit to efficiently and flexibly connect data and quickly provide the data that AI agents need. Furthermore, the API Integration Unit can implement authentication and encryption to ensure security during data connection. For example, authentication using OAuth 2.0 is performed to verify access permissions when data is exchanged. Furthermore, communication is encrypted using SSL / TLS to prevent data eavesdropping and tampering. This enables the API integration unit to achieve secure and reliable data exchange, improving the overall system security.

[0033] The fine-tuning unit uses data linked by the API integration unit to fine-tune the AI ​​agent. For example, the fine-tuning unit adjusts the AI ​​agent's parameters using machine learning algorithms. Specifically, it retrains the AI ​​agent's model using collected user data to improve prediction accuracy and response performance. The fine-tuning unit can also adjust the AI ​​agent's parameters using deep learning algorithms. Deep learning is a learning method that uses multi-layered neural networks and can perform complex pattern recognition and prediction. Furthermore, the fine-tuning unit can also adjust the AI ​​agent's parameters using reinforcement learning algorithms. Reinforcement learning is a method in which an agent learns optimal behavior through interaction with the environment, improving its adaptability in dynamic environments. For example, the fine-tuning unit takes user personal data as input and optimizes the AI ​​agent's output. Specifically, it personalizes the services and content provided by the AI ​​agent based on user preferences and behavioral patterns to improve the user experience. This allows the fine-tuning unit to continuously improve the AI ​​agent's performance and provide high-quality services to users. Furthermore, the fine-tuning unit evaluates and validates the model to prevent overfitting and bias. For example, cross-validation and holdout validation are used to evaluate the generalization performance of the model, and the model is modified or retrained as needed. This allows the fine-tuning unit to not only improve the performance of the AI ​​agent but also ensure its reliability and fairness.

[0034] The Common Personal Database Platform (PDB) system includes a marketing data acquisition unit that retrieves highly confidential marketing data from personal databases. The marketing data acquisition unit can, for example, acquire customer purchase history. For example, it can collect information on products that customers have previously purchased. The marketing data acquisition unit can also acquire personal preference information. For example, it can understand the product categories that customers prefer. Furthermore, the marketing data acquisition unit can acquire customer behavior history. For example, it can collect information on websites that customers have visited. This allows for the efficient acquisition of marketing data. Some or all of the above-described processes in the marketing data acquisition unit may be performed using AI, or not. For example, the marketing data acquisition unit can input customer purchase history data into a generating AI and have the generating AI extract customer preference information.

[0035] The Common Personal Database Platform (PDB) system includes a Marketing Strategy Provisioning Unit that provides marketing strategies using data acquired by the Marketing Data Acquisition Unit. The Marketing Strategy Provisioning Unit can, for example, define target audiences. For example, the Marketing Strategy Provisioning Unit defines target audiences based on customer preference information. The Marketing Strategy Provisioning Unit can also determine how to deliver advertisements. For example, the Marketing Strategy Provisioning Unit determines the timing of advertisement delivery based on customer behavior history. Furthermore, the Marketing Strategy Provisioning Unit can also determine the content of marketing campaigns. For example, the Marketing Strategy Provisioning Unit sets the campaign content based on customer purchase history. This enables the efficient provision of marketing strategies. Some or all of the above-described processes in the Marketing Strategy Provisioning Unit may be performed using AI, for example, or without AI. For example, the Marketing Strategy Provisioning Unit can input customer preference information into a generating AI and have the generating AI perform the target audience definition.

[0036] The Common Personal Database Platform (PDB) system includes a free user management unit that manages the data capacity and number of API connections for free users. The free user management unit can, for example, limit the data capacity of free users. For instance, it can set a data capacity limit of 20GB for free users. It can also limit the number of API connections for free users. For example, it can set a limit of 5 API connections for free users. Furthermore, the free user management unit can monitor the data usage of free users. For example, it can notify free users when they reach their data capacity limit. This allows for efficient management of the data capacity and number of API connections for free users. Some or all of the above-described processes in the free user management unit may be performed using AI, or not. For example, the free user management unit can input the data usage of free users into a generating AI and have the generating AI implement data capacity limits.

[0037] The Common Personal Database Platform (PDB) system includes a Premium User Management Unit that manages the data capacity and API integration count of premium users. The Premium User Management Unit manages, for example, the data capacity of premium users. For instance, it sets a data capacity limit of 1TB for premium users. The Premium User Management Unit can also manage the number of API integrations for premium users. For example, it sets an unlimited limit on the number of API integrations for premium users. Furthermore, the Premium User Management Unit can monitor the data usage of premium users. For example, it notifies premium users when they reach their data capacity limit. This allows for efficient management of premium users' data capacity and API integration count. Some or all of the above-described processes in the Premium User Management Unit may be performed using, for example, AI, or not. For example, the Premium User Management Unit can input the data usage of premium users into a generating AI and have the generating AI implement data capacity limits.

[0038] The Common Personal Database Platform (PDB) system has a data collection unit that analyzes a user's past behavioral history and selects the optimal data collection method. For example, the data collection unit prioritizes collecting data from websites that the user has frequently visited in the past. For example, the data collection unit collects relevant data based on the user's past purchase history. The data collection unit can also analyze the user's past search history and collect data in areas of interest. For example, the data collection unit analyzes the user's behavioral patterns and selects the optimal data collection method. This allows for the selection of the optimal data collection method by analyzing the user's past behavioral 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 behavioral history data into a generating AI and have the generating AI select the optimal data collection method.

[0039] The Common Personal Database Platform (PDB) system allows the data collection unit to filter data based on the user's current areas of interest during data collection. For example, the data collection unit prioritizes collecting data related to topics the user is currently interested in. For instance, it might filter data based on the content of websites the user has recently visited. It can also collect data based on topics in online communities the user participates in. For example, the data collection unit identifies the user's areas of interest and prioritizes collecting relevant data. This allows for the collection of more relevant data by filtering data based on the user's current areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input user area of ​​interest data into a generating AI and have the generating AI perform the data filtering.

[0040] The Common Personal Database Platform (PDB) system prioritizes the collection of highly relevant data by considering the user's geographical location when collecting data. For example, the data collection unit prioritizes the collection of weather information for the user's current location. For example, the data collection unit collects event information related to places the user is visiting. The data collection unit can also collect data on nearby stores and services based on the user's location. For example, the data collection unit identifies the user's geographical location and prioritizes the collection of relevant data. This allows for the collection of more relevant data by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location data into a generating AI and have the generating AI perform the data collection.

[0041] The Common Personal Database Platform (PDB) system has a data collection unit that analyzes users' social media activity and collects relevant data during data collection. For example, the data collection unit collects data related to content shared by users on social media. For example, the data collection unit collects data based on posts from accounts that users follow. The data collection unit can also collect data related to groups and events that users participate in. For example, the data collection unit identifies users' social media activity and prioritizes the collection of relevant data. This allows for the efficient collection of relevant data by analyzing users' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input user social media activity data into a generating AI and have the generating AI perform the data collection.

[0042] The Common Personal Database Platform (PDB) system adjusts the level of detail in data storage based on data importance when the data is stored. For example, the data storage unit stores important data in detail, while storing less important data in a simplified manner. The data storage unit can also adjust the frequency of storage according to data importance. For example, the data storage unit evaluates data importance and adjusts the level of detail in storage. This improves storage efficiency by adjusting the level of detail in storage based on data importance. Some or all of the above processing in the data storage unit may be performed using AI, for example, or without AI. For example, the data storage unit can input data importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in storage.

[0043] The Common Personal Database Platform (PDB) system applies different storage algorithms depending on the data category when storing data in its data storage unit. For example, the data storage unit applies a compression algorithm to text data for storage. For example, the data storage unit stores image data in the optimal format. The data storage unit can also store video data in a format suitable for streaming. For example, the data storage unit identifies the data category and applies the appropriate storage algorithm. This improves data storage efficiency by applying different storage algorithms depending on the data category. Some or all of the above processing in the data storage unit may be performed using AI, for example, or without AI. For example, the data storage unit can input data category data into a generating AI and have the generating AI perform the application of the storage algorithm.

[0044] The Common Personal Database Platform (PDB) system has a data storage unit that determines storage priorities based on the data submission date when storing data. For example, the data storage unit prioritizes storing the most recent data. For example, it postpones storing older data. The data storage unit can also adjust the storage frequency based on the submission date. For example, the data storage unit evaluates the data submission date and determines the storage priority. This allows for the priority storage of the most recent data by determining the storage priority based on the data submission date. Some or all of the above processing in the data storage unit may be performed using AI, for example, or not using AI. For example, the data storage unit can input data submission date data into a generating AI and have the generating AI perform the determination of storage priorities.

[0045] The Common Personal Database Platform (PDB) system's data storage unit adjusts the storage order based on data relevance during data storage. For example, the data storage unit prioritizes storing highly relevant data. For example, it postpones storing less relevant data. The data storage unit can also adjust the storage frequency based on data relevance. For example, the data storage unit evaluates data relevance and adjusts the storage order. This allows for the priority storage of highly relevant data by adjusting the storage order based on data relevance. Some or all of the above processing in the data storage unit may be performed using AI, for example, or without AI. For example, the data storage unit can input data relevance data into a generating AI and have the generating AI perform the adjustment of the storage order.

[0046] The Common Personal Database Platform (PDB) system's API integration unit improves the accuracy of API integration by considering the interrelationships between data. For example, the API integration unit analyzes the interrelationships between data and integrates related data. For example, the API integration unit determines the priority of integration based on the interrelationships between data. The API integration unit can also adjust the frequency of integration by considering the interrelationships between data. For example, the API integration unit evaluates the interrelationships between data and improves the accuracy of integration. This improves the accuracy of integration by considering the interrelationships between data. Some or all of the above processing in the API integration unit may be performed using AI, for example, or without AI. For example, the API integration unit can input data interrelationship data into a generating AI and have the generating AI perform the improvement of integration accuracy.

[0047] The Common Personal Database Platform (PDB) system's API integration unit considers the attribute information of data submitters when performing API integration. For example, the API integration unit determines the priority of integration based on the attribute information of the data submitters. For example, the API integration unit adjusts the frequency of integration considering the attribute information of the data submitters. The API integration unit can also adjust the level of detail of integration based on the attribute information of the data submitters. For example, the API integration unit evaluates the attribute information of the data submitters and performs integration. This improves the accuracy of integration by considering the attribute information of the data submitters. Some or all of the above processing in the API integration unit may be performed using AI, for example, or without AI. For example, the API integration unit can input the attribute information data of the data submitters into a generating AI and have the generating AI perform the integration.

[0048] The Common Personal Database Platform (PDB) system's API integration unit considers the geographical distribution of data when performing API integration. For example, the API integration unit determines the priority of integration based on the geographical distribution of data. For example, the API integration unit adjusts the frequency of integration considering the geographical distribution of data. The API integration unit can also adjust the level of detail of integration based on the geographical distribution of data. For example, the API integration unit evaluates the geographical distribution of data and performs integration. This improves the accuracy of integration by considering the geographical distribution of data. Some or all of the above processing in the API integration unit may be performed using AI, for example, or without AI. For example, the API integration unit can input geographical distribution data into a generating AI and have the generating AI perform the integration.

[0049] The Common Personal Database Platform (PDB) system's API integration unit improves the accuracy of API integration by referencing relevant data literature during API integration. For example, the API integration unit improves the accuracy of integration by referencing relevant data literature. For example, the API integration unit determines the priority of integration based on the relevant data literature. The API integration unit can also adjust the frequency of integration by considering the relevant data literature. For example, the API integration unit evaluates the relevant data literature and performs integration. This improves the accuracy of integration by referencing the relevant data literature. Some or all of the above processing in the API integration unit may be performed using AI, for example, or without AI. For example, the API integration unit can input data-related literature data into a generating AI and have the generating AI perform the integration.

[0050] The Common Personal Database Platform (PDB) system's fine-tuning unit selects the optimal tuning method by referring to historical data during the fine-tuning process. For example, the fine-tuning unit analyzes historical data to select the optimal tuning method. For example, the fine-tuning unit determines tuning priorities based on historical data. The fine-tuning unit can also adjust the tuning frequency by referring to historical data. For example, the fine-tuning unit evaluates historical data to select the optimal tuning method. This allows the optimal tuning method to be selected by referring to historical data. Some or all of the above processes in the fine-tuning unit may be performed using AI, or without AI. For example, the fine-tuning unit can input historical data into a generating AI and have the generating AI select the optimal tuning method.

[0051] The Common Personal Database Platform (PDB) system's fine-tuning unit applies different tuning methods to each data category during the fine-tuning process. For example, the fine-tuning unit applies the optimal tuning method to text data. For example, the fine-tuning unit applies a tuning method suitable for image processing to image data. The fine-tuning unit can also apply a tuning method suitable for video processing to video data. For example, the fine-tuning unit identifies the data category and applies the appropriate tuning method. This improves the accuracy of fine-tuning by applying different tuning methods to each data category. Some or all of the above-described processes in the fine-tuning unit may be performed using AI, for example, or without AI. For example, the fine-tuning unit can input data category data into a generating AI and have the generating AI execute the application of tuning methods.

[0052] The Common Personal Database Platform (PDB) system's fine-tuning unit determines tuning priorities based on data submission timing during the fine-tuning process. For example, the fine-tuning unit prioritizes fine-tuning the most recent data. For example, it postpones fine-tuning older data. The fine-tuning unit can also adjust the frequency of fine-tuning based on submission timing. For example, the fine-tuning unit evaluates data submission timing and determines tuning priorities. This allows for prioritizing fine-tuning of the most recent data by determining tuning priorities based on data submission timing. Some or all of the above-described processes in the fine-tuning unit may be performed using AI, for example, or without AI. For example, the fine-tuning unit can input data submission timing data into a generating AI and have the generating AI determine the tuning priorities.

[0053] The Common Personal Database Platform (PDB) system's fine-tuning unit adjusts the tuning order based on data relevance during the fine-tuning process. For example, the fine-tuning unit prioritizes fine-tuning highly relevant data. For example, it postpones fine-tuning less relevant data. The fine-tuning unit can also adjust the frequency of fine-tuning based on data relevance. For example, the fine-tuning unit evaluates data relevance and adjusts the tuning order. This allows for prioritizing fine-tuning of highly relevant data by adjusting the tuning order based on data relevance. Some or all of the above-described processes in the fine-tuning unit may be performed using AI, for example, or without AI. For example, the fine-tuning unit can input data relevance data into a generating AI and have the generating AI perform the adjustment of the tuning order.

[0054] The Common Personal Database Platform (PDB) system allows the marketing data acquisition unit to select the optimal acquisition method by referring to past marketing data when acquiring marketing data. For example, the marketing data acquisition unit analyzes past marketing data to select the optimal acquisition method. For example, the marketing data acquisition unit determines the acquisition priority based on past marketing data. The marketing data acquisition unit can also adjust the acquisition frequency by referring to past marketing data. For example, the marketing data acquisition unit evaluates past marketing data to select the optimal acquisition method. This allows the optimal data acquisition method to be selected by referring to past marketing data. Some or all of the above processing in the marketing data acquisition unit may be performed using AI, or not. For example, the marketing data acquisition unit can input past marketing data into a generating AI and have the generating AI select the optimal acquisition method.

[0055] The Common Personal Database Platform (PDB) system's marketing data acquisition unit determines the acquisition priority based on the data submission date when acquiring marketing data. For example, the marketing data acquisition unit prioritizes acquiring the most recent marketing data. For example, it prioritizes acquiring older marketing data. The marketing data acquisition unit can also adjust the acquisition frequency based on the submission date. For example, the marketing data acquisition unit evaluates the data submission date and determines the acquisition priority. This allows for the acquisition of the most recent data by prioritizing acquisition based on the data submission date. Some or all of the above processing in the marketing data acquisition unit may be performed using AI, for example, or not using AI. For example, the marketing data acquisition unit can input data submission date data into a generating AI and have the generating AI perform the determination of acquisition priority.

[0056] The Common Personal Database Platform (PDB) system allows the Marketing Strategy Provider to select the optimal strategy by referring to past marketing data when providing marketing strategies. For example, the Marketing Strategy Provider can analyze past marketing data to select the optimal strategy. For example, the Marketing Strategy Provider can determine strategy priorities based on past marketing data. The Marketing Strategy Provider can also adjust the frequency of strategies by referring to past marketing data. For example, the Marketing Strategy Provider can evaluate past marketing data to select the optimal strategy. This allows for the selection of the optimal strategy by referring to past marketing data. Some or all of the above processes in the Marketing Strategy Provider may be performed using AI, or not. For example, the Marketing Strategy Provider can input past marketing data into a generating AI and have the generating AI select the optimal strategy.

[0057] The Common Personal Database Platform (PDB) system allows the Marketing Strategy Provider to prioritize strategies based on data submission timing when providing marketing strategies. For example, the Marketing Strategy Provider may prioritize providing the most recent marketing strategies. For example, it may postpone providing older marketing strategies. The Marketing Strategy Provider can also adjust the frequency of strategies based on submission timing. For example, it may evaluate data submission timing and determine strategy priorities. This allows for the priority provision of the most recent strategies by prioritizing strategies based on data submission timing. Some or all of the above processes in the Marketing Strategy Provider may be performed using AI, or not. For example, the Marketing Strategy Provider can input data submission timing data into a generating AI and have the generating AI determine strategy priorities.

[0058] The Common Personal Database Platform (PDB) system allows the free user management unit to select the optimal management method by referring to past usage history when managing free users. For example, the free user management unit analyzes past usage history and selects the optimal management method. For example, the free user management unit determines management priorities based on past usage history. The free user management unit can also adjust the frequency of management by referring to past usage history. For example, the free user management unit evaluates past usage history and selects the optimal management method. This allows the optimal management method to be selected by referring to past usage history. Some or all of the above processes in the free user management unit may be performed using AI, for example, or without AI. For example, the free user management unit can input past usage history data into a generating AI and have the generating AI select the optimal management method.

[0059] The Common Personal Database Platform (PDB) system's free user management unit selects the optimal management method when managing free users, taking into account the user's device information. For example, the free user management unit selects the optimal management method based on the user's device information. For example, the free user management unit determines management priorities considering the user's device information. Furthermore, the free user management unit can adjust the frequency of management based on the user's device information. For example, the free user management unit evaluates the user's device information and selects the optimal management method. This allows for the selection of the optimal management method by considering the user's device information. Some or all of the above-described processes in the free user management unit may be performed using AI, or not. For example, the free user management unit can input user device information data into a generating AI and have the generating AI select the optimal management method.

[0060] The Common Personal Database Platform (PDB) system allows the premium user management unit to select the optimal management method by referring to past usage history when managing premium users. For example, the premium user management unit analyzes past usage history and selects the optimal management method. For example, the premium user management unit determines management priorities based on past usage history. The premium user management unit can also adjust the frequency of management by referring to past usage history. For example, the premium user management unit evaluates past usage history and selects the optimal management method. This allows the optimal management method to be selected by referring to past usage history. Some or all of the above processes in the premium user management unit may be performed using AI, for example, or not using AI. For example, the premium user management unit can input past usage history data into a generating AI and have the generating AI perform the selection of the optimal management method.

[0061] The Common Personal Database Platform (PDB) system's premium user management unit selects the optimal management method when managing premium users, taking into account the user's device information. For example, the premium user management unit selects the optimal management method based on the user's device information. For example, the premium user management unit determines management priorities considering the user's device information. Furthermore, the premium user management unit can adjust the frequency of management based on the user's device information. For example, the premium user management unit evaluates the user's device information and selects the optimal management method. This allows for the selection of the optimal management method by considering the user's device information. Some or all of the above processes in the premium user management unit may be performed using AI, or not. For example, the premium user management unit can input user device information data into a generating AI and have the generating AI select the optimal management method.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The Common Personal Database Platform (PDB) system allows the data collection unit to analyze a user's past behavior history and select the optimal data collection method. For example, it can prioritize data collection from websites the user has frequently visited in the past. It can also collect relevant data based on the user's past purchase history. Furthermore, it can analyze the user's past search history and collect data in areas of interest. In this way, the system can select the optimal data collection method by analyzing the user's past behavior history.

[0064] The Common Personal Database Platform (PDB) system allows the data collection unit to filter data based on the user's current areas of interest during the data collection process. For example, it can prioritize the collection of data related to topics the user is currently interested in. It can also filter data based on the content of websites the user has recently visited. Furthermore, it can collect data based on topics in online communities the user participates in. This allows for the collection of more relevant data by filtering data based on the user's current areas of interest.

[0065] The Common Personal Database Platform (PDB) system allows the data collection unit to prioritize the collection of highly relevant data by considering the user's geographical location. For example, it can prioritize the collection of weather information for the user's current location. It can also collect event information related to places the user is visiting. Furthermore, it can collect data on nearby stores and services based on the user's location. In this way, by considering the user's geographical location when collecting data, more relevant data can be collected.

[0066] The Common Personal Database Platform (PDB) system allows the data storage unit to adjust the level of detail stored based on the importance of the data. For example, important data can be stored in detail, while less important data can be stored in a simplified form. Furthermore, the frequency of storage can be adjusted according to the importance of the data. This allows for improved storage efficiency by adjusting the level of detail based on the importance of the data.

[0067] The Common Personal Database Platform (PDB) system allows the data storage unit to apply different storage algorithms depending on the data category during data storage. For example, text data can be stored using a compression algorithm. Image data can be stored in the optimal format. Furthermore, video data can be stored in a format suitable for streaming. By applying different storage algorithms depending on the data category, data storage efficiency can be improved.

[0068] The Common Personal Database Platform (PDB) system allows the data storage unit to prioritize data retention based on submission date. For example, the most recent data can be saved first, while older data can be saved later. Furthermore, the retention frequency can be adjusted based on submission date. This allows for priority storage of the most recent data by determining retention based on submission date.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The data collection unit collects the user's personal data. This personal data includes the user's name, address, email address, and browsing history. For example, the data collection unit can collect website browsing history, purchase history, and preferences. Step 2: The data storage unit securely stores the data collected by the data collection unit. The data storage unit protects the data using encryption technology and implements access control to prevent unauthorized access. It also creates regular data backups to prevent data loss. Step 3: The API integration unit connects the data stored by the data storage unit to each AI agent via API. The API integration unit uses RESTful APIs, SOAP APIs, GraphQL, etc., to connect the data. For example, it provides user personal data to each AI agent. Step 4: The fine-tuning unit uses the data linked by the API integration unit to fine-tune the AI ​​agent. The fine-tuning unit adjusts the AI ​​agent's parameters using machine learning algorithms, deep learning algorithms, and reinforcement learning algorithms. For example, it takes user personal data as input and optimizes the AI ​​agent's output.

[0071] (Example of form 2) The Common Personal Database Platform (PDB) system according to an embodiment of the present invention is a system that simplifies the fine-tuning of AI agents by securely accumulating personal data such as users' consumption behavior, preferences, and internet browsing history, and linking with each AI agent via API. This system eliminates the need for users to input data from scratch when using a new AI agent. First, personal data such as users' consumption behavior, preferences, and internet browsing history are collected. This data is securely stored in data centers located throughout the country. Next, API linkage is established with each AI agent to share the accumulated data. This allows each AI agent to perform fine-tuning using the user's personal data. For example, when a user uses a new e-commerce AI agent, the consumption behavior data accumulated in the PDB can be used to recommend products that match the user's preferences. Also, when using a medical AI agent, the health data accumulated in the PDB can be used to provide the user with optimal health management advice. This mechanism allows users to easily use multiple AI agents and minimizes discrepancies in output due to differences in data volume between each AI agent. Furthermore, companies can use PDB to obtain highly confidential marketing data from personal databases and utilize it in their marketing strategies. This service is offered to B2C customers as a database usage fee (annual license) and to B2B customers as a usage fee for highly confidential marketing data from personal databases. In addition, a freemium model is adopted, offering free users a data capacity limit of 20GB and up to 5 API connections, while premium users receive a data capacity limit of 1TB and unlimited API connections. This enables the Common Personal Database Platform (PDB) system to efficiently collect, store, connect, and fine-tune users' personal data.

[0072] The common personal database platform (PDB) system according to this embodiment comprises a data collection unit, a data storage unit, an API integration unit, and a fine-tuning unit. The data collection unit collects the user's personal data. The user's personal data includes, but is not limited to, names, addresses, email addresses, and behavioral history. The data collection unit collects, for example, website browsing history. The data collection unit can also collect the user's purchase history. Furthermore, the data collection unit can collect the user's preferences. For example, the data collection unit collects information on products viewed by the user to understand the user's preferences. The data storage unit securely stores the data collected by the data collection unit. The data storage unit protects the data using, for example, encryption technology. The data storage unit can also perform access control to prevent unauthorized access to the data. Furthermore, the data storage unit can perform data backups. For example, the data storage unit periodically creates data backups to prevent data loss. The API integration unit integrates the data stored by the data storage unit with each AI agent via API. The API integration unit integrates data using, for example, a RESTful API. It can also integrate data using a SOAP API. Furthermore, it can integrate data using GraphQL. For example, the API integration unit provides user personal data to each AI agent. The fine-tuning unit uses the data integrated by the API integration unit to fine-tune the AI ​​agents. For example, the fine-tuning unit adjusts the AI ​​agent parameters using machine learning algorithms. It can also adjust the AI ​​agent parameters using deep learning algorithms. Furthermore, it can adjust the AI ​​agent parameters using reinforcement learning algorithms. For example, the fine-tuning unit takes user personal data as input and optimizes the output of the AI ​​agent.As a result, the common personal database platform (PDB) system according to this embodiment can efficiently collect, store, link, and fine-tune users' personal data.

[0073] The data collection unit collects users' personal data. This personal data includes, but is not limited to, names, addresses, email addresses, and browsing history. For example, the data collection unit collects website browsing history. Specifically, it collects detailed information such as the URLs of web pages visited, the time spent on each page, and the links clicked. The data collection unit can also collect users' purchase history. For example, it collects information such as items purchased on online shopping sites, the date and time of purchase, the purchase amount, and the payment method. Furthermore, the data collection unit can collect user preferences. For example, it collects information on products viewed by users to understand their preferences. Specifically, it collects information on product categories frequently viewed, reviews of products rated, and products added to the cart but not purchased. This allows the data collection unit to gain a detailed understanding of user behavior patterns and preferences, and to collect foundational data for providing personalized services. In addition, the data collection unit can also collect user device information and location information. For example, the system collects information such as the type of device the user is using, the OS version, the type of browser, the IP address, and GPS location information to understand the user's environment and range of activity. This allows the data collection unit to comprehensively collect diverse user data and gather foundational data for providing personalized services.

[0074] The data storage unit securely stores the data collected by the data collection unit. The data storage unit protects the data using, for example, encryption technology. Specifically, the collected data is encrypted using strong encryption algorithms such as AES (Advanced Encryption Standard) to ensure data confidentiality. The data storage unit can also implement access control to prevent unauthorized access to the data. For example, it implements user authentication and access rights management to strictly restrict which users and systems can access the data. Furthermore, the data storage unit can perform data backups. For example, it regularly creates data backups to prevent data loss. Specifically, data backups are stored on multiple servers in different physical locations, enabling data recovery even in the event of disasters or system failures. This allows the data storage unit to store collected data in a safe and reliable manner, ensuring data protection and availability. Additionally, the data storage unit can perform data validation and integrity checks to maintain data integrity. For example, it checks data format and value ranges during data entry to prevent the storage of fraudulent data. It also records data change history, allowing for tracking of changes if they occur. This allows the data storage unit to maintain data integrity and reliability, thereby improving the overall data quality of the system.

[0075] The API Integration Unit connects data stored by the Data Storage Unit to each AI agent via API. For example, the API Integration Unit uses RESTful APIs to connect data. Specifically, it uses the HTTP protocol to retrieve, send, update, and delete data through methods such as GET, POST, PUT, and DELETE. The API Integration Unit can also connect data using SOAP APIs. SOAP (Simple Object Access Protocol) is an XML-based messaging protocol that enables data exchange between different platforms. Furthermore, the API Integration Unit can also connect data using GraphQL. GraphQL is a query language that allows clients to precisely specify and retrieve the data they need. For example, the API Integration Unit provides each AI agent with user personal data. Specifically, the AI ​​agents retrieve data such as the user's name, address, email address, and behavioral history, and use this data to provide personalized services to the user. This allows the API Integration Unit to efficiently and flexibly connect data and quickly provide the data that AI agents need. Furthermore, the API Integration Unit can implement authentication and encryption to ensure security during data connection. For example, authentication using OAuth 2.0 is performed to verify access permissions when data is exchanged. Furthermore, communication is encrypted using SSL / TLS to prevent data eavesdropping and tampering. This enables the API integration unit to achieve secure and reliable data exchange, improving the overall system security.

[0076] The fine-tuning unit uses data linked by the API integration unit to fine-tune the AI ​​agent. For example, the fine-tuning unit adjusts the AI ​​agent's parameters using machine learning algorithms. Specifically, it retrains the AI ​​agent's model using collected user data to improve prediction accuracy and response performance. The fine-tuning unit can also adjust the AI ​​agent's parameters using deep learning algorithms. Deep learning is a learning method that uses multi-layered neural networks and can perform complex pattern recognition and prediction. Furthermore, the fine-tuning unit can also adjust the AI ​​agent's parameters using reinforcement learning algorithms. Reinforcement learning is a method in which an agent learns optimal behavior through interaction with the environment, improving its adaptability in dynamic environments. For example, the fine-tuning unit takes user personal data as input and optimizes the AI ​​agent's output. Specifically, it personalizes the services and content provided by the AI ​​agent based on user preferences and behavioral patterns to improve the user experience. This allows the fine-tuning unit to continuously improve the AI ​​agent's performance and provide high-quality services to users. Furthermore, the fine-tuning unit evaluates and validates the model to prevent overfitting and bias. For example, cross-validation and holdout validation are used to evaluate the generalization performance of the model, and the model is modified or retrained as needed. This allows the fine-tuning unit to not only improve the performance of the AI ​​agent but also ensure its reliability and fairness.

[0077] The Common Personal Database Platform (PDB) system includes a marketing data acquisition unit that retrieves highly confidential marketing data from personal databases. The marketing data acquisition unit can, for example, acquire customer purchase history. For example, it can collect information on products that customers have previously purchased. The marketing data acquisition unit can also acquire personal preference information. For example, it can understand the product categories that customers prefer. Furthermore, the marketing data acquisition unit can acquire customer behavior history. For example, it can collect information on websites that customers have visited. This allows for the efficient acquisition of marketing data. Some or all of the above-described processes in the marketing data acquisition unit may be performed using AI, or not. For example, the marketing data acquisition unit can input customer purchase history data into a generating AI and have the generating AI extract customer preference information.

[0078] The Common Personal Database Platform (PDB) system includes a Marketing Strategy Provisioning Unit that provides marketing strategies using data acquired by the Marketing Data Acquisition Unit. The Marketing Strategy Provisioning Unit can, for example, define target audiences. For example, the Marketing Strategy Provisioning Unit defines target audiences based on customer preference information. The Marketing Strategy Provisioning Unit can also determine how to deliver advertisements. For example, the Marketing Strategy Provisioning Unit determines the timing of advertisement delivery based on customer behavior history. Furthermore, the Marketing Strategy Provisioning Unit can also determine the content of marketing campaigns. For example, the Marketing Strategy Provisioning Unit sets the campaign content based on customer purchase history. This enables the efficient provision of marketing strategies. Some or all of the above-described processes in the Marketing Strategy Provisioning Unit may be performed using AI, for example, or without AI. For example, the Marketing Strategy Provisioning Unit can input customer preference information into a generating AI and have the generating AI perform the target audience definition.

[0079] The Common Personal Database Platform (PDB) system includes a free user management unit that manages the data capacity and number of API connections for free users. The free user management unit can, for example, limit the data capacity of free users. For instance, it can set a data capacity limit of 20GB for free users. It can also limit the number of API connections for free users. For example, it can set a limit of 5 API connections for free users. Furthermore, the free user management unit can monitor the data usage of free users. For example, it can notify free users when they reach their data capacity limit. This allows for efficient management of the data capacity and number of API connections for free users. Some or all of the above-described processes in the free user management unit may be performed using AI, or not. For example, the free user management unit can input the data usage of free users into a generating AI and have the generating AI implement data capacity limits.

[0080] The Common Personal Database Platform (PDB) system includes a Premium User Management Unit that manages the data capacity and API integration count of premium users. The Premium User Management Unit manages, for example, the data capacity of premium users. For instance, it sets a data capacity limit of 1TB for premium users. The Premium User Management Unit can also manage the number of API integrations for premium users. For example, it sets an unlimited limit on the number of API integrations for premium users. Furthermore, the Premium User Management Unit can monitor the data usage of premium users. For example, it notifies premium users when they reach their data capacity limit. This allows for efficient management of premium users' data capacity and API integration count. Some or all of the above-described processes in the Premium User Management Unit may be performed using, for example, AI, or not. For example, the Premium User Management Unit can input the data usage of premium users into a generating AI and have the generating AI implement data capacity limits.

[0081] The Common Personal Database Platform (PDB) system has a data collection unit that estimates the user's emotions and adjusts the timing of data collection based on the estimated emotions. For example, the data collection unit will reduce data collection if the user is stressed. For example, the data collection unit will collect data when the user is relaxed. The data collection unit can also collect data in real time and reflect it immediately if the user is excited. Furthermore, the data collection unit can pause data collection if the user is tired and resume it after the user has rested. For example, the data collection unit will monitor the user's emotional state in real time and adjust the timing of data collection according to changes in emotions. This allows for more appropriate data collection by adjusting the timing of data collection 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 or not using AI. For example, the data collection unit can input user emotion data into a generating AI and have the generating AI adjust the timing of data collection.

[0082] The Common Personal Database Platform (PDB) system has a data collection unit that analyzes a user's past behavioral history and selects the optimal data collection method. For example, the data collection unit prioritizes collecting data from websites that the user has frequently visited in the past. For example, the data collection unit collects relevant data based on the user's past purchase history. The data collection unit can also analyze the user's past search history and collect data in areas of interest. For example, the data collection unit analyzes the user's behavioral patterns and selects the optimal data collection method. This allows for the selection of the optimal data collection method by analyzing the user's past behavioral 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 behavioral history data into a generating AI and have the generating AI select the optimal data collection method.

[0083] The Common Personal Database Platform (PDB) system allows the data collection unit to filter data based on the user's current areas of interest during data collection. For example, the data collection unit prioritizes collecting data related to topics the user is currently interested in. For instance, it might filter data based on the content of websites the user has recently visited. It can also collect data based on topics in online communities the user participates in. For example, the data collection unit identifies the user's areas of interest and prioritizes collecting relevant data. This allows for the collection of more relevant data by filtering data based on the user's current areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input user area of ​​interest data into a generating AI and have the generating AI perform the data filtering.

[0084] The Common Personal Database Platform (PDB) system has a data collection unit that estimates the user's emotions and determines the priority of data to collect based on the estimated emotions. For example, if the user is relaxed, the data collection unit prioritizes collecting detailed data. For example, if the user is in a hurry, the data collection unit prioritizes collecting only important data. The data collection unit can also prioritize collecting real-time fluctuating data if the user is excited. For example, the data collection unit monitors the user's emotional state in real time and determines data priority according to changes in emotion. This allows for more appropriate data collection by determining the priority of data to collect 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 or not using AI. For example, the data collection unit can input user emotion data into the generative AI and have the generative AI perform the determination of data priority.

[0085] The Common Personal Database Platform (PDB) system prioritizes the collection of highly relevant data by considering the user's geographical location when collecting data. For example, the data collection unit prioritizes the collection of weather information for the user's current location. For example, the data collection unit collects event information related to places the user is visiting. The data collection unit can also collect data on nearby stores and services based on the user's location. For example, the data collection unit identifies the user's geographical location and prioritizes the collection of relevant data. This allows for the collection of more relevant data by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location data into a generating AI and have the generating AI perform the data collection.

[0086] The Common Personal Database Platform (PDB) system has a data collection unit that analyzes users' social media activity and collects relevant data during data collection. For example, the data collection unit collects data related to content shared by users on social media. For example, the data collection unit collects data based on posts from accounts that users follow. The data collection unit can also collect data related to groups and events that users participate in. For example, the data collection unit identifies users' social media activity and prioritizes the collection of relevant data. This allows for the efficient collection of relevant data by analyzing users' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input user social media activity data into a generating AI and have the generating AI perform the data collection.

[0087] The Common Personal Database Platform (PDB) system uses a data storage unit to estimate the user's emotions and adjust the data storage method based on the estimated emotions. For example, if the user is relaxed, the data storage unit stores detailed data. For example, if the user is in a hurry, the data storage unit stores only essential data. The data storage unit can also store data that fluctuates in real time if the user is excited. For example, the data storage unit monitors the user's emotional state in real time and adjusts the data storage method according to changes in emotions. This allows for more appropriate data storage by adjusting the data storage method 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 storage unit may be performed using AI or not using AI. For example, the data storage unit can input user emotion data into the generative AI and have the generative AI adjust the data storage method.

[0088] The Common Personal Database Platform (PDB) system adjusts the level of detail in data storage based on data importance when the data is stored. For example, the data storage unit stores important data in detail, while storing less important data in a simplified manner. The data storage unit can also adjust the frequency of storage according to data importance. For example, the data storage unit evaluates data importance and adjusts the level of detail in storage. This improves storage efficiency by adjusting the level of detail in storage based on data importance. Some or all of the above processing in the data storage unit may be performed using AI, for example, or without AI. For example, the data storage unit can input data importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in storage.

[0089] The Common Personal Database Platform (PDB) system applies different storage algorithms depending on the data category when storing data in its data storage unit. For example, the data storage unit applies a compression algorithm to text data for storage. For example, the data storage unit stores image data in the optimal format. The data storage unit can also store video data in a format suitable for streaming. For example, the data storage unit identifies the data category and applies the appropriate storage algorithm. This improves data storage efficiency by applying different storage algorithms depending on the data category. Some or all of the above processing in the data storage unit may be performed using AI, for example, or without AI. For example, the data storage unit can input data category data into a generating AI and have the generating AI perform the application of the storage algorithm.

[0090] The Common Personal Database Platform (PDB) system uses a data storage unit to estimate the user's emotions and adjust the data retention period based on the estimated emotions. For example, the data storage unit stores data for a longer period if the user is relaxed, for a shorter period if the user is in a hurry, and for a shorter period if the user is excited, as data fluctuates in real time. For example, the data storage unit monitors the user's emotional state in real time and adjusts the data retention period according to changes in emotion. This allows for more appropriate data storage by adjusting the data retention period 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 may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data storage unit may be performed using AI or not. For example, the data storage unit can input user emotion data into the generative AI and have the generative AI adjust the data retention period.

[0091] The Common Personal Database Platform (PDB) system has a data storage unit that determines storage priorities based on the data submission date when storing data. For example, the data storage unit prioritizes storing the most recent data. For example, it postpones storing older data. The data storage unit can also adjust the storage frequency based on the submission date. For example, the data storage unit evaluates the data submission date and determines the storage priority. This allows for the priority storage of the most recent data by determining the storage priority based on the data submission date. Some or all of the above processing in the data storage unit may be performed using AI, for example, or not using AI. For example, the data storage unit can input data submission date data into a generating AI and have the generating AI perform the determination of storage priorities.

[0092] The Common Personal Database Platform (PDB) system's data storage unit adjusts the storage order based on data relevance during data storage. For example, the data storage unit prioritizes storing highly relevant data. For example, it postpones storing less relevant data. The data storage unit can also adjust the storage frequency based on data relevance. For example, the data storage unit evaluates data relevance and adjusts the storage order. This allows for the priority storage of highly relevant data by adjusting the storage order based on data relevance. Some or all of the above processing in the data storage unit may be performed using AI, for example, or without AI. For example, the data storage unit can input data relevance data into a generating AI and have the generating AI perform the adjustment of the storage order.

[0093] The Common Personal Database Platform (PDB) system uses an API integration unit to estimate the user's emotions and adjust the API integration criteria based on the estimated emotions. For example, if the user is relaxed, the API integration unit integrates detailed data. For example, if the user is in a hurry, the API integration unit integrates only essential data. The API integration unit can also integrate data that changes in real time if the user is excited. For example, the API integration unit monitors the user's emotional state in real time and adjusts the API integration criteria according to changes in emotions. This allows for more appropriate data integration by adjusting the API integration criteria 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 API integration unit may be performed using AI or not. For example, the API integration unit can input user emotion data into a generative AI and have the generative AI adjust the API integration criteria.

[0094] The Common Personal Database Platform (PDB) system's API integration unit improves the accuracy of API integration by considering the interrelationships between data. For example, the API integration unit analyzes the interrelationships between data and integrates related data. For example, the API integration unit determines the priority of integration based on the interrelationships between data. The API integration unit can also adjust the frequency of integration by considering the interrelationships between data. For example, the API integration unit evaluates the interrelationships between data and improves the accuracy of integration. This improves the accuracy of integration by considering the interrelationships between data. Some or all of the above processing in the API integration unit may be performed using AI, for example, or without AI. For example, the API integration unit can input data interrelationship data into a generating AI and have the generating AI perform the improvement of integration accuracy.

[0095] The Common Personal Database Platform (PDB) system's API integration unit considers the attribute information of data submitters when performing API integration. For example, the API integration unit determines the priority of integration based on the attribute information of the data submitters. For example, the API integration unit adjusts the frequency of integration considering the attribute information of the data submitters. The API integration unit can also adjust the level of detail of integration based on the attribute information of the data submitters. For example, the API integration unit evaluates the attribute information of the data submitters and performs integration. This improves the accuracy of integration by considering the attribute information of the data submitters. Some or all of the above processing in the API integration unit may be performed using AI, for example, or without AI. For example, the API integration unit can input the attribute information data of the data submitters into a generating AI and have the generating AI perform the integration.

[0096] The Common Personal Database Platform (PDB) system uses an API integration unit to estimate the user's emotions and adjust the order in which API integration results are displayed based on the estimated emotions. For example, if the user is relaxed, the API integration unit prioritizes displaying detailed results. For example, if the user is in a hurry, the API integration unit prioritizes displaying only important results. The API integration unit can also prioritize displaying results that change in real time if the user is excited. For example, the API integration unit monitors the user's emotional state in real time and adjusts the order in which results are displayed according to changes in emotions. This allows for more appropriate result display by adjusting the order in which API integration results are displayed 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 API integration unit may be performed using AI or not using AI. For example, the API integration unit can input user emotion data into the generative AI and have the generative AI adjust the order in which results are displayed.

[0097] The Common Personal Database Platform (PDB) system's API integration unit considers the geographical distribution of data when performing API integration. For example, the API integration unit determines the priority of integration based on the geographical distribution of data. For example, the API integration unit adjusts the frequency of integration considering the geographical distribution of data. The API integration unit can also adjust the level of detail of integration based on the geographical distribution of data. For example, the API integration unit evaluates the geographical distribution of data and performs integration. This improves the accuracy of integration by considering the geographical distribution of data. Some or all of the above processing in the API integration unit may be performed using AI, for example, or without AI. For example, the API integration unit can input geographical distribution data into a generating AI and have the generating AI perform the integration.

[0098] The Common Personal Database Platform (PDB) system's API integration unit improves the accuracy of API integration by referencing relevant data literature during API integration. For example, the API integration unit improves the accuracy of integration by referencing relevant data literature. For example, the API integration unit determines the priority of integration based on the relevant data literature. The API integration unit can also adjust the frequency of integration by considering the relevant data literature. For example, the API integration unit evaluates the relevant data literature and performs integration. This improves the accuracy of integration by referencing the relevant data literature. Some or all of the above processing in the API integration unit may be performed using AI, for example, or without AI. For example, the API integration unit can input data-related literature data into a generating AI and have the generating AI perform the integration.

[0099] The Common Personal Database Platform (PDB) system has a fine-tuning unit that estimates the user's emotions and adjusts the fine-tuning method based on the estimated emotions. For example, if the user is relaxed, the fine-tuning unit performs detailed fine-tuning. For example, if the user is in a hurry, the fine-tuning unit fine-tunes only the important parts. The fine-tuning unit can also fine-tune data that fluctuates in real time if the user is excited. For example, the fine-tuning unit monitors the user's emotional state in real time and adjusts the fine-tuning method according to changes in emotions. This allows for more appropriate fine-tuning by adjusting the fine-tuning method 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 fine-tuning unit may be performed using AI or not using AI. For example, the fine-tuning unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the fine-tuning method.

[0100] The Common Personal Database Platform (PDB) system's fine-tuning unit selects the optimal tuning method by referring to historical data during the fine-tuning process. For example, the fine-tuning unit analyzes historical data to select the optimal tuning method. For example, the fine-tuning unit determines tuning priorities based on historical data. The fine-tuning unit can also adjust the tuning frequency by referring to historical data. For example, the fine-tuning unit evaluates historical data to select the optimal tuning method. This allows the optimal tuning method to be selected by referring to historical data. Some or all of the above processes in the fine-tuning unit may be performed using AI, or without AI. For example, the fine-tuning unit can input historical data into a generating AI and have the generating AI select the optimal tuning method.

[0101] The Common Personal Database Platform (PDB) system's fine-tuning unit applies different tuning methods to each data category during the fine-tuning process. For example, the fine-tuning unit applies the optimal tuning method to text data. For example, the fine-tuning unit applies a tuning method suitable for image processing to image data. The fine-tuning unit can also apply a tuning method suitable for video processing to video data. For example, the fine-tuning unit identifies the data category and applies the appropriate tuning method. This improves the accuracy of fine-tuning by applying different tuning methods to each data category. Some or all of the above-described processes in the fine-tuning unit may be performed using AI, for example, or without AI. For example, the fine-tuning unit can input data category data into a generating AI and have the generating AI execute the application of tuning methods.

[0102] The Common Personal Database Platform (PDB) system has a fine-tuning unit that estimates the user's emotions and determines the priority of fine-tuning based on the estimated emotions. For example, if the user is relaxed, the fine-tuning unit prioritizes detailed fine-tuning. For example, if the user is in a hurry, the fine-tuning unit prioritizes fine-tuning only the important parts. The fine-tuning unit can also prioritize fine-tuning data that is fluctuating in real time if the user is excited. For example, the fine-tuning unit monitors the user's emotional state in real time and determines the priority of fine-tuning according to changes in emotions. This allows for more appropriate fine-tuning by determining the priority of fine-tuning 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 fine-tuning unit may be performed using AI, for example, or without AI. For example, the fine-tuning unit can input user emotion data into the generating AI and have the generating AI determine the priorities for fine-tuning.

[0103] The Common Personal Database Platform (PDB) system's fine-tuning unit determines tuning priorities based on data submission timing during the fine-tuning process. For example, the fine-tuning unit prioritizes fine-tuning the most recent data. For example, it postpones fine-tuning older data. The fine-tuning unit can also adjust the frequency of fine-tuning based on submission timing. For example, the fine-tuning unit evaluates data submission timing and determines tuning priorities. This allows for prioritizing fine-tuning of the most recent data by determining tuning priorities based on data submission timing. Some or all of the above-described processes in the fine-tuning unit may be performed using AI, for example, or without AI. For example, the fine-tuning unit can input data submission timing data into a generating AI and have the generating AI determine the tuning priorities.

[0104] The Common Personal Database Platform (PDB) system's fine-tuning unit adjusts the tuning order based on data relevance during the fine-tuning process. For example, the fine-tuning unit prioritizes fine-tuning highly relevant data. For example, it postpones fine-tuning less relevant data. The fine-tuning unit can also adjust the frequency of fine-tuning based on data relevance. For example, the fine-tuning unit evaluates data relevance and adjusts the tuning order. This allows for prioritizing fine-tuning of highly relevant data by adjusting the tuning order based on data relevance. Some or all of the above-described processes in the fine-tuning unit may be performed using AI, for example, or without AI. For example, the fine-tuning unit can input data relevance data into a generating AI and have the generating AI perform the adjustment of the tuning order.

[0105] The Common Personal Database Platform (PDB) system uses a marketing data acquisition unit to estimate the user's emotions and adjust the method of acquiring marketing data based on the estimated emotions. For example, if the user is relaxed, the marketing data acquisition unit acquires detailed marketing data. For example, if the user is in a hurry, the marketing data acquisition unit acquires only essential marketing data. The marketing data acquisition unit can also acquire real-time fluctuating marketing data if the user is excited. For example, the marketing data acquisition unit monitors the user's emotional state in real time and adjusts the method of acquiring marketing data according to changes in emotions. This allows for more appropriate data acquisition by adjusting the method of acquiring marketing data 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the marketing data acquisition unit may be performed using AI, for example, or without AI. For example, the marketing data acquisition unit can input user sentiment data into a generating AI and have the generating AI adjust the method of acquiring marketing data.

[0106] The Common Personal Database Platform (PDB) system allows the marketing data acquisition unit to select the optimal acquisition method by referring to past marketing data when acquiring marketing data. For example, the marketing data acquisition unit analyzes past marketing data to select the optimal acquisition method. For example, the marketing data acquisition unit determines the acquisition priority based on past marketing data. The marketing data acquisition unit can also adjust the acquisition frequency by referring to past marketing data. For example, the marketing data acquisition unit evaluates past marketing data to select the optimal acquisition method. This allows the optimal data acquisition method to be selected by referring to past marketing data. Some or all of the above processing in the marketing data acquisition unit may be performed using AI, or not. For example, the marketing data acquisition unit can input past marketing data into a generating AI and have the generating AI select the optimal acquisition method.

[0107] The Common Personal Database Platform (PDB) system uses a marketing data acquisition unit to estimate the user's emotions and prioritize marketing data based on the estimated emotions. For example, if the user is relaxed, the marketing data acquisition unit prioritizes acquiring detailed marketing data. For example, if the user is in a hurry, the marketing data acquisition unit prioritizes acquiring only important marketing data. The marketing data acquisition unit can also prioritize acquiring real-time fluctuating marketing data if the user is excited. For example, the marketing data acquisition unit monitors the user's emotional state in real time and prioritizes marketing data according to changes in emotion. This allows for more appropriate data acquisition by prioritizing marketing data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the marketing data acquisition unit may be performed using AI or not using AI. For example, the marketing data acquisition unit can input user sentiment data into a generating AI, which can then perform the task of determining the priority of the marketing data.

[0108] The Common Personal Database Platform (PDB) system's marketing data acquisition unit determines the acquisition priority based on the data submission date when acquiring marketing data. For example, the marketing data acquisition unit prioritizes acquiring the most recent marketing data. For example, it prioritizes acquiring older marketing data. The marketing data acquisition unit can also adjust the acquisition frequency based on the submission date. For example, the marketing data acquisition unit evaluates the data submission date and determines the acquisition priority. This allows for the acquisition of the most recent data by prioritizing acquisition based on the data submission date. Some or all of the above processing in the marketing data acquisition unit may be performed using AI, for example, or not using AI. For example, the marketing data acquisition unit can input data submission date data into a generating AI and have the generating AI perform the determination of acquisition priority.

[0109] The Common Personal Database Platform (PDB) system allows the marketing strategy provider to estimate the user's emotions and adjust the delivery method of the marketing strategy based on the estimated emotions. For example, if the user is relaxed, the marketing strategy provider will provide a detailed marketing strategy. For example, if the user is in a hurry, the marketing strategy provider will provide only the essential marketing strategies. The marketing strategy provider can also provide a real-time, fluctuating marketing strategy if the user is excited. For example, the marketing strategy provider will monitor the user's emotional state in real time and adjust the delivery method of the marketing strategy in response to changes in emotions. This allows for the delivery of more appropriate strategies by adjusting the delivery method of the marketing strategy 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the marketing strategy provider may be performed using AI or not using AI. For example, the marketing strategy provision department can input user sentiment data into a generating AI and have the AI ​​adjust the method of providing marketing strategies.

[0110] The Common Personal Database Platform (PDB) system allows the Marketing Strategy Provider to select the optimal strategy by referring to past marketing data when providing marketing strategies. For example, the Marketing Strategy Provider can analyze past marketing data to select the optimal strategy. For example, the Marketing Strategy Provider can determine strategy priorities based on past marketing data. The Marketing Strategy Provider can also adjust the frequency of strategies by referring to past marketing data. For example, the Marketing Strategy Provider can evaluate past marketing data to select the optimal strategy. This allows for the selection of the optimal strategy by referring to past marketing data. Some or all of the above processes in the Marketing Strategy Provider may be performed using AI, or not. For example, the Marketing Strategy Provider can input past marketing data into a generating AI and have the generating AI select the optimal strategy.

[0111] The Common Personal Database Platform (PDB) system allows the marketing strategy provider to estimate the user's emotions and prioritize marketing strategies based on those emotions. For example, if the user is relaxed, the marketing strategy provider will prioritize detailed marketing strategies. For example, if the user is in a hurry, the marketing strategy provider will prioritize only essential marketing strategies. The marketing strategy provider can also prioritize real-time, fluctuating marketing strategies if the user is excited. For example, the marketing strategy provider can monitor the user's emotional state in real time and prioritize marketing strategies according to changes in emotion. This allows for the provision of more appropriate strategies by prioritizing marketing strategies according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the marketing strategy provider may be performed using AI or not using AI. For example, the marketing strategy provision department can input user sentiment data into a generating AI and have the AI ​​determine the priorities of its marketing strategy.

[0112] The Common Personal Database Platform (PDB) system allows the Marketing Strategy Provider to prioritize strategies based on data submission timing when providing marketing strategies. For example, the Marketing Strategy Provider may prioritize providing the most recent marketing strategies. For example, it may postpone providing older marketing strategies. The Marketing Strategy Provider can also adjust the frequency of strategies based on submission timing. For example, it may evaluate data submission timing and determine strategy priorities. This allows for the priority provision of the most recent strategies by prioritizing strategies based on data submission timing. Some or all of the above processes in the Marketing Strategy Provider may be performed using AI, or not. For example, the Marketing Strategy Provider can input data submission timing data into a generating AI and have the generating AI determine strategy priorities.

[0113] The Common Personal Database Platform (PDB) system uses a free user management unit to estimate a user's emotions and adjust the free user's data capacity based on the estimated emotions. For example, the free user management unit increases data capacity when a user is relaxed, or decreases it when a user is in a hurry. It can also provide real-time fluctuating data capacity when a user is excited. For example, the free user management unit monitors the user's emotional state in real time and adjusts data capacity according to changes in emotion. This allows for more appropriate data management by adjusting the free user's data capacity 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 may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the free user management unit may be performed using AI or not. For example, the free user management unit can input user emotion data into a generative AI and have the generative AI adjust the data capacity.

[0114] The Common Personal Database Platform (PDB) system allows the free user management unit to select the optimal management method by referring to past usage history when managing free users. For example, the free user management unit analyzes past usage history and selects the optimal management method. For example, the free user management unit determines management priorities based on past usage history. The free user management unit can also adjust the frequency of management by referring to past usage history. For example, the free user management unit evaluates past usage history and selects the optimal management method. This allows the optimal management method to be selected by referring to past usage history. Some or all of the above processes in the free user management unit may be performed using AI, for example, or without AI. For example, the free user management unit can input past usage history data into a generating AI and have the generating AI select the optimal management method.

[0115] The Common Personal Database Platform (PDB) system uses a free user management unit to estimate a user's emotions and adjust the number of API connections for free users based on the estimated emotions. For example, the free user management unit increases the number of API connections when a user is relaxed. For example, it decreases the number of API connections when a user is in a hurry. The free user management unit can also provide a real-time fluctuating number of API connections when a user is excited. For example, the free user management unit monitors the user's emotional state in real time and adjusts the number of API connections according to changes in emotions. This allows for more appropriate API connections by adjusting the number of API connections for free users according to their 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 free user management unit may be performed using AI or not using AI. For example, the free user management unit can input user sentiment data into a generating AI and have the AI ​​adjust the number of API connections.

[0116] The Common Personal Database Platform (PDB) system's free user management unit selects the optimal management method when managing free users, taking into account the user's device information. For example, the free user management unit selects the optimal management method based on the user's device information. For example, the free user management unit determines management priorities considering the user's device information. Furthermore, the free user management unit can adjust the frequency of management based on the user's device information. For example, the free user management unit evaluates the user's device information and selects the optimal management method. This allows for the selection of the optimal management method by considering the user's device information. Some or all of the above-described processes in the free user management unit may be performed using AI, or not. For example, the free user management unit can input user device information data into a generating AI and have the generating AI select the optimal management method.

[0117] The Common Personal Database Platform (PDB) system has a premium user management unit that estimates the user's emotions and adjusts the premium user's data capacity based on the estimated emotions. For example, the premium user management unit increases data capacity when the user is relaxed, or decreases it when the user is in a hurry. It can also provide real-time fluctuating data capacity when the user is excited. For example, the premium user management unit monitors the user's emotional state in real time and adjusts data capacity according to changes in emotions. This allows for more appropriate data management by adjusting the premium user's data capacity 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 premium user management unit may be performed using AI or not. For example, the premium user management unit can input user emotion data into a generative AI and have the generative AI perform the data capacity adjustment.

[0118] The Common Personal Database Platform (PDB) system allows the premium user management unit to select the optimal management method by referring to past usage history when managing premium users. For example, the premium user management unit analyzes past usage history and selects the optimal management method. For example, the premium user management unit determines management priorities based on past usage history. The premium user management unit can also adjust the frequency of management by referring to past usage history. For example, the premium user management unit evaluates past usage history and selects the optimal management method. This allows the optimal management method to be selected by referring to past usage history. Some or all of the above processes in the premium user management unit may be performed using AI, for example, or not using AI. For example, the premium user management unit can input past usage history data into a generating AI and have the generating AI perform the selection of the optimal management method.

[0119] The Common Personal Database Platform (PDB) system has a premium user management unit that estimates the user's emotions and adjusts the number of API connections for premium users based on the estimated emotions. For example, the premium user management unit increases the number of API connections when the user is relaxed. For example, it decreases the number of API connections when the user is in a hurry. The premium user management unit can also provide a real-time fluctuating number of API connections when the user is excited. For example, the premium user management unit monitors the user's emotional state in real time and adjusts the number of API connections according to changes in emotions. This allows for more appropriate API connections by adjusting the number of API connections for premium users according to their 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 premium user management unit may be performed using AI or not using AI. For example, the premium user management department can input user sentiment data into a generating AI and have the AI ​​adjust the number of API connections.

[0120] The Common Personal Database Platform (PDB) system's premium user management unit selects the optimal management method when managing premium users, taking into account the user's device information. For example, the premium user management unit selects the optimal management method based on the user's device information. For example, the premium user management unit determines management priorities considering the user's device information. Furthermore, the premium user management unit can adjust the frequency of management based on the user's device information. For example, the premium user management unit evaluates the user's device information and selects the optimal management method. This allows for the selection of the optimal management method by considering the user's device information. Some or all of the above processes in the premium user management unit may be performed using AI, or not. For example, the premium user management unit can input user device information data into a generating AI and have the generating AI select the optimal management method.

[0121] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0122] The Common Personal Database Platform (PDB) system allows the data collection unit to estimate the user's emotions and adjust the timing of data collection based on those estimates. For example, if a user is stressed, data collection can be kept to a minimum. It can also be collected when the user is relaxed. Furthermore, if the user is excited, data can be collected in real time and reflected immediately. This allows for more appropriate data collection by adjusting the timing of data collection according to the user's emotions.

[0123] The Common Personal Database Platform (PDB) system allows the data collection unit to analyze a user's past behavior history and select the optimal data collection method. For example, it can prioritize data collection from websites the user has frequently visited in the past. It can also collect relevant data based on the user's past purchase history. Furthermore, it can analyze the user's past search history and collect data in areas of interest. In this way, the system can select the optimal data collection method by analyzing the user's past behavior history.

[0124] The Common Personal Database Platform (PDB) system allows the data collection unit to filter data based on the user's current areas of interest during the data collection process. For example, it can prioritize the collection of data related to topics the user is currently interested in. It can also filter data based on the content of websites the user has recently visited. Furthermore, it can collect data based on topics in online communities the user participates in. This allows for the collection of more relevant data by filtering data based on the user's current areas of interest.

[0125] The Common Personal Database Platform (PDB) system allows the data collection unit to estimate the user's emotions and prioritize the data to be collected based on those emotions. For example, if the user is relaxed, detailed data can be prioritized. If the user is in a hurry, only essential data can be prioritized. Furthermore, if the user is agitated, real-time, fluctuating data can be prioritized. This allows for more appropriate data collection by prioritizing data collection according to the user's emotions.

[0126] The Common Personal Database Platform (PDB) system allows the data collection unit to prioritize the collection of highly relevant data by considering the user's geographical location. For example, it can prioritize the collection of weather information for the user's current location. It can also collect event information related to places the user is visiting. Furthermore, it can collect data on nearby stores and services based on the user's location. In this way, by considering the user's geographical location when collecting data, more relevant data can be collected.

[0127] The Common Personal Database Platform (PDB) system can also estimate the user's emotions and adjust how data is stored based on that estimation. For example, if the user is relaxed, detailed data can be stored. If the user is in a hurry, only essential data can be stored. Furthermore, if the user is excited, real-time, fluctuating data can be stored. This allows for more appropriate data storage by adjusting how data is stored according to the user's emotions.

[0128] The Common Personal Database Platform (PDB) system allows the data storage unit to adjust the level of detail stored based on the importance of the data. For example, important data can be stored in detail, while less important data can be stored in a simplified form. Furthermore, the frequency of storage can be adjusted according to the importance of the data. This allows for improved storage efficiency by adjusting the level of detail based on the importance of the data.

[0129] The Common Personal Database Platform (PDB) system allows the data storage unit to apply different storage algorithms depending on the data category during data storage. For example, text data can be stored using a compression algorithm. Image data can be stored in the optimal format. Furthermore, video data can be stored in a format suitable for streaming. By applying different storage algorithms depending on the data category, data storage efficiency can be improved.

[0130] The Common Personal Database Platform (PDB) system can also estimate the user's emotions in its data storage unit and adjust the data retention period based on the estimated emotions. For example, if the user is relaxed, the data can be stored for a longer period. If the user is in a hurry, the data can be stored for a shorter period. Furthermore, if the user is excited, real-time fluctuating data can be stored for a shorter period. This allows for more appropriate data storage by adjusting the data retention period according to the user's emotions.

[0131] The Common Personal Database Platform (PDB) system allows the data storage unit to prioritize data retention based on submission date. For example, the most recent data can be saved first, while older data can be saved later. Furthermore, the retention frequency can be adjusted based on submission date. This allows for priority storage of the most recent data by determining retention based on submission date.

[0132] The following briefly describes the processing flow for example form 2.

[0133] Step 1: The data collection unit collects the user's personal data. This personal data includes the user's name, address, email address, and browsing history. For example, the data collection unit can collect website browsing history, purchase history, and preferences. Step 2: The data storage unit securely stores the data collected by the data collection unit. The data storage unit protects the data using encryption technology and implements access control to prevent unauthorized access. It also creates regular data backups to prevent data loss. Step 3: The API integration unit connects the data stored by the data storage unit to each AI agent via API. The API integration unit uses RESTful APIs, SOAP APIs, GraphQL, etc., to connect the data. For example, it provides user personal data to each AI agent. Step 4: The fine-tuning unit uses the data linked by the API integration unit to fine-tune the AI ​​agent. The fine-tuning unit adjusts the AI ​​agent's parameters using machine learning algorithms, deep learning algorithms, and reinforcement learning algorithms. For example, it takes user personal data as input and optimizes the AI ​​agent's output.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] Each of the multiple elements described above, including the data collection unit, data storage unit, API linkage unit, and fine-tuning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit collects the user's personal data using the camera 42 and microphone 38B of the smart device 14 and processes the data with the control unit 46A. The data storage unit securely stores the data in the database 24 of the data processing unit 12. The API linkage unit links data with each AI agent via the communication I / F 26 of the data processing unit 12. The fine-tuning unit performs fine-tuning of the AI ​​agent using the specific processing unit 290 of the data processing unit 12. 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.

[0138] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] Each of the multiple elements described above, including the data collection unit, data storage unit, API linkage unit, and fine-tuning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects the user's personal data using the camera 42 and microphone 238 of the smart glasses 214 and processes the data with the control unit 46A. The data storage unit securely stores the data in the database 24 of the data processing unit 12. The API linkage unit links data with each AI agent via the communication I / F 26 of the data processing unit 12. The fine-tuning unit performs fine-tuning of the AI ​​agent using the specific processing unit 290 of the data processing unit 12. 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.

[0154] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] Each of the multiple elements described above, including the data collection unit, data storage unit, API linkage unit, and fine-tuning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects the user's personal data using the camera 42 and microphone 238 of the headset terminal 314 and processes the data with the control unit 46A. The data storage unit securely stores the data in the database 24 of the data processing unit 12. The API linkage unit links data with each AI agent via the communication I / F 26 of the data processing unit 12. The fine-tuning unit performs fine-tuning of the AI ​​agent using the specific processing unit 290 of the data processing unit 12. 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.

[0170] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.).

[0183] 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.

[0184] 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.

[0185] 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.

[0186] Each of the multiple elements described above, including the data collection unit, data storage unit, API linkage unit, and fine-tuning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the data collection unit collects the user's personal data using the camera 42 and microphone 238 of the robot 414 and processes the data with the control unit 46A. The data storage unit securely stores the data in the database 24 of the data processing unit 12. The API linkage unit links data with each AI agent via the communication I / F 26 of the data processing unit 12. The fine-tuning unit performs fine-tuning of the AI ​​agent using the specific processing unit 290 of the data processing unit 12. 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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."

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] (Note 1) A data collection unit that collects users' personal data, A data storage unit securely stores the data collected by the aforementioned data collection unit, The data stored by the aforementioned data storage unit is connected to each AI agent via an API, and the API connection unit connects the data stored by the data storage unit to each AI agent. A fine-tuning unit that uses the data linked by the aforementioned API linking unit to perform fine-tuning of the AI ​​agent, Equipped with A system characterized by the following features. (Note 2) It includes a marketing data acquisition unit that retrieves highly confidential marketing data from personal databases. The system described in Appendix 1, characterized by the features described herein. (Note 3) The system includes a marketing strategy provision unit that provides marketing strategies using the data acquired by the aforementioned marketing data acquisition unit. The system described in Appendix 2, characterized by the features described herein. (Note 4) It includes a free user management section that manages the data capacity and number of API connections for free users. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a premium user management unit that manages the data capacity and number of API connections for premium users. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned data acquisition unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned data acquisition unit is Analyze the user's past behavior history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned data acquisition unit is When collecting data, filtering is performed based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned data acquisition unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned data acquisition unit is When collecting data, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned data acquisition unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 12) The data storage unit is We estimate the user's emotions and adjust how data is stored based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The data storage unit is When storing data, adjust the level of detail stored based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The data storage unit is When accumulating data, different storage algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 15) The data storage unit is We estimate the user's sentiment and adjust the data retention period based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The data storage unit is When accumulating data, the priority of saving is determined based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The data storage unit is When accumulating data, adjust the saving order based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned API integration unit is We estimate the user's emotions and adjust the API integration criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned API integration unit is When integrating with APIs, we improve the accuracy of the integration by considering the interrelationships between data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned API integration unit is When integrating with an API, the system takes into account the attribute information of the data submitter. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned API integration unit is It estimates the user's emotions and adjusts the order in which API integration results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned API integration unit is When integrating with an API, the geographical distribution of the data should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned API integration unit is When integrating with APIs, we improve the accuracy of the integration by referring to relevant literature for the data. The system described in Appendix 1, characterized by the features described herein. (Note 24) The fine-tuning unit is It estimates the user's emotions and adjusts the fine-tuning method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The fine-tuning unit is During fine-tuning, the optimal tuning method is selected by referring to past data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The fine-tuning unit is During fine-tuning, different tuning methods are applied to each data category. The system described in Appendix 1, characterized by the features described herein. (Note 27) The fine-tuning unit is It estimates the user's emotions and determines the priority of fine-tuning based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The fine-tuning unit is During fine-tuning, tuning priorities are determined based on the timing of data submission. The system described in Appendix 1, characterized by the features described herein. (Note 29) The fine-tuning unit is During fine-tuning, the tuning order is adjusted based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned marketing data acquisition unit, We estimate user sentiment and adjust how marketing data is collected based on that estimated sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned marketing data acquisition unit, When acquiring marketing data, we select the optimal acquisition method by referring to past marketing data. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned marketing data acquisition unit, It estimates user sentiment and prioritizes marketing data based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned marketing data acquisition unit, When acquiring marketing data, prioritize the data acquisition based on when it was submitted. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned marketing strategy provision department, We estimate user sentiment and adjust the way we deliver marketing strategies based on that estimated sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned marketing strategy provision department, When providing a marketing strategy, we select the optimal strategy by referring to past marketing data. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned marketing strategy provision department, We estimate user sentiment and prioritize marketing strategies based on that estimated sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned marketing strategy provision department, When providing a marketing strategy, prioritize the strategy based on the timing of data submission. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned free user management unit is: It estimates the user's emotions and adjusts the data capacity for free users based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned free user management unit is: When managing free users, the system selects the optimal management method by referring to past usage history. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned free user management unit is: The system estimates user sentiment and adjusts the number of free users allowed to connect via API based on the estimated sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned free user management unit is: When managing free users, the optimal management method is selected considering the user's device information. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned premium user management department, It estimates user sentiment and adjusts premium user data capacity based on the estimated sentiment. The system described in Appendix 5, characterized by the features described herein. (Note 43) The aforementioned premium user management department, When managing premium users, the system selects the optimal management method by referring to past usage history. The system described in Appendix 5, characterized by the features described herein. (Note 44) The aforementioned premium user management department, The system estimates user sentiment and adjusts the number of API connections for premium users based on the estimated sentiment. The system described in Appendix 5, characterized by the features described herein. (Note 45) The aforementioned premium user management department, When managing premium users, the optimal management method is selected considering the user's device information. The system described in Appendix 5, characterized by the features described herein. [Explanation of Symbols]

[0206] 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 data collection unit that collects users' personal data, A data storage unit securely stores the data collected by the aforementioned data collection unit, The data stored by the aforementioned data storage unit is linked to each AI agent via API by an API integration unit, A fine-tuning unit that uses the data linked by the API linking unit to perform fine-tuning of the AI ​​agent, Equipped with A system characterized by the following features.

2. It includes a marketing data acquisition unit that retrieves highly confidential marketing data from personal databases. The system according to feature 1.

3. The system includes a marketing strategy provision unit that provides marketing strategies using the data acquired by the aforementioned marketing data acquisition unit. The system according to feature 2.

4. It includes a free user management section that manages the data capacity and number of API connections for free users. The system according to feature 1.

5. It includes a premium user management unit that manages the data capacity and number of API connections for premium users. The system according to feature 1.

6. The aforementioned data acquisition unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system according to feature 1.

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

8. The aforementioned data acquisition unit is When collecting data, filtering is performed based on the user's current areas of interest. The system according to feature 1.

9. The aforementioned data acquisition unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system according to feature 1.

Images