System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting personal data from a user; means for storing and managing the personal data; means for normalizing and tagging the personal data; means for training a generative artificial intelligence model using the normalized and tagged personal data; means for generating an optimization output for the trained generative artificial intelligence model based on a user request; and means for delivering the optimization output to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] This invention aims to solve the problem that, as generative AI becomes increasingly commoditized, companies lose their competitive advantage simply by utilizing generative AI. In particular, conventional generative AI relies on public data, making it difficult to provide optimized output for individual users. Furthermore, there is often a lack of an environment for safely collecting, managing, and efficiently utilizing personal data, which limits the value of generative AI in providing actual services. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a means for collecting personal data from users, a means for storing and managing the personal data, a means for normalizing and tagging the personal data, a means for training a generative AI model using the normalized and tagged personal data, a means for the trained generative AI model to generate optimized output based on user requests, and a means for delivering the optimized output to user terminals, thereby realizing a system that effectively utilizes user data and provides information optimized for each individual user. This system enables companies to utilize their own personal data infrastructure to secure a competitive advantage and raise the barriers to entry for other companies.

[0006] "Personal data" is a general term for data associated with individual users, such as user behavioral history, purchase history, and location information.

[0007] A "generative AI model" is a model that allows artificial intelligence to learn from large amounts of data and generate new information and output.

[0008] "Normalization" is the process of standardizing and organizing acquired data according to certain standards and formats.

[0009] "Tagging" is the process of adding relevant attributes or categories to data to make it easier to search and classify.

[0010] "Training" is the process of repeatedly feeding data to an algorithm so that it learns and finds patterns and rules.

[0011] "Optimized output" is an output result that generates the most appropriate information and suggestions based on the user's individual needs and personal data.

[0012] "Storage and management" refers to the process of keeping collected data safe and ensuring that it is accessed and used appropriately as needed.

[0013] "Distribution" is the act of transmitting the generated output to a user terminal.

[0014] "User terminal" refers to an electronic device that is directly used by a user, such as a smartphone, PC, or tablet. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention relates to a system that collects personal data from users and provides optimized outputs using generative AI models. The system is composed of the following subsystems and processes:

[0037] Collection of Personal Data

[0038] With the user's permission, the server collects personal data from various services. For example, data such as purchase history, behavioral history, and location information is obtained from e-commerce sites and location information services via API. This allows detailed data on the user's behavior and preferences to be collected.

[0039] Data storage and management

[0040] The data management server securely stores and manages the collected data. Data is encrypted and access controls are applied to protect data security and privacy. Stored data is properly indexed for quick access when needed.

[0041] Data normalization and tagging

[0042] The data processing terminal normalizes and tags the collected personal data. For example, it converts acquired purchase history data into a unified format and assigns relevant categories and keywords. This process ensures data consistency and makes subsequent processing easier.

[0043] Training a private AI model

[0044] The learning server uses the normalized and tagged personal data to train a generative AI model that learns each user's patterns and preferences and generates optimal output based on them. The model is continuously updated and retrained as new user data is added.

[0045] Generating optimization output

[0046] The application server accepts user requests and uses the trained generative AI model to generate optimized output, such as personalized product recommendations based on past purchase and behavioral history when a user searches for new products. This output is customized to the user's specific needs.

[0047] Output Delivery

[0048] The distribution server distributes the generated optimized output to the user's device, which can be a smartphone, PC, or other device that appropriately displays the distributed output and provides it to the user.

[0049] Specific examples

[0050] For example, if a user searches for a specific product on an e-commerce site, the data collection server collects information about the user's past purchase history, recently visited locations, etc. After this data is normalized and tagged, the learning server uses it to update and train the AI ​​model.

[0051] When the user searches for a product again, the application server uses the trained AI model to generate optimal product recommendations based on the user's preferences and past behavior. The generated recommendation information is sent to the user's smartphone by the distribution server, allowing the user to view and purchase product information optimized for them.

[0052] In this manner, the system of the present invention can provide an output that is optimized for each user, thereby maintaining a company's competitive advantage.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, location information, etc. from various services (e.g., e-commerce sites, location information services) via API. This allows for detailed data on the user's behavior and preferences to be obtained.

[0056] Step 2:

[0057] The data management server securely stores and manages the collected personal data. The data management server encrypts the collected data and stores it with appropriate access control. This protects the security and privacy of the data while also ensuring that the data can be accessed quickly when needed.

[0058] Step 3:

[0059] The data processing terminal normalizes and tags the stored personal data. Specifically, the data processing terminal converts purchase history information into a unified format and assigns relevant categories and keywords. This process ensures data consistency and facilitates subsequent processing.

[0060] Step 4:

[0061] The learning server trains the generative AI model using normalized and tagged personal data. The learning server learns each user's data patterns and preferences and builds a model to generate optimal output based on them. This model is continuously updated and learns as new user data is added.

[0062] Step 5:

[0063] The application server accepts user requests and generates optimized output using the trained generative AI model. For example, if a user searches for a specific product, the application server provides optimized product recommendations based on past purchase history and behavioral history. This output is tailored to the user's specific needs.

[0064] Step 6:

[0065] The distribution server distributes the generated optimized output to the user's device. The distribution server sends the generated output in an appropriate format to the user's device, such as a smartphone or PC, for notification or display, allowing the user to receive optimized information and suggestions.

[0066] Step 7:

[0067] The user device displays the received output. The user device visually displays the received information, allowing the user to view and use optimized product information and suggestions. For example, the user can view a list of product recommendations optimized for them on their smartphone and can even purchase the products directly.

[0068] Through this series of steps, the system of the present invention provides optimized output for each user, enabling the company to maintain a competitive advantage.

[0069] Example 1

[0070] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0071] Conventional systems have struggled to generate personalized outputs that fully utilize users' personal data. They also face challenges in terms of data security, privacy protection, and continuous model updates. Furthermore, it has been difficult to create a system that can respond quickly and optimally to user requests.

[0072] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0073] In this invention, the server includes means for collecting personal data from a user, means for storing and managing the personal data, means for normalizing and tagging the personal data, means for training a generative artificial intelligence model using the normalized and tagged personal data, means for generating an optimized output from the trained generative artificial intelligence model based on a user request, means for delivering the optimized output to a user terminal, specific means for obtaining personal data through an API, encrypting and storing it, means for updating the generative artificial intelligence model based on past data, and specific means for processing requests input by the user.

[0074] This makes it possible to provide personalized output specific to each user, ensure data security and privacy, and continuously update models using the latest data, enabling quick and optimal responses to user requests.

[0075] "Personal data" refers to information related to a specific individual, such as a user's purchasing history, behavioral history, and location information.

[0076] "Acquisition through API" refers to the method of acquiring data from other services or systems via an application program interface (API).

[0077] "Encryption" is the process of transforming data using a specific algorithm into a format that cannot be easily deciphered by third parties.

[0078] "Normalization" means converting data into a consistent format and making it easier to process.

[0079] "Tagging" refers to assigning relevant categories and keywords to data to make it easier to search and classify.

[0080] A "generative artificial intelligence model" is a model that has been trained using machine learning or artificial intelligence algorithms to perform a specific task.

[0081] "Training" is the process of using collected data to teach an artificial intelligence model and improve its performance.

[0082] "Optimization output" refers to the recommendations and responses generated by an artificial intelligence model tailored to a user's individual needs.

[0083] A "server" is a computer system that provides services or processing power over a network.

[0084] A "user terminal" refers to a device such as a computer, smartphone, or tablet that is directly operated by a user.

[0085] A "user request" is a request or inquiry sent by a user to the system.

[0086] The present invention relates to a system that uses personal data collected from users to train a generative artificial intelligence model and generate optimized outputs based on user requests. A specific example of the system is described below.

[0087] This system mainly uses the following hardware and software. The hardware includes a data collection server, data management server, data processing terminal, learning server, application server, distribution server, and user terminal. The software uses APIs, encryption algorithms (e.g., AES-256), database software (e.g., MongoDB or PostgreSQL), and machine learning frameworks (e.g., PyTorch or TensorFlow).

[0088] First, the server collects personal data through API with the user's permission. The collected data includes purchase history, behavioral history, and location information. The collected data is encrypted by the server and stored on a data management server. This is to protect the security and privacy of the data.

[0089] The data processing terminal then normalizes the collected data and assigns tags to it. For example, it converts date and time data in different formats into a unified format and assigns categories such as "food" or "electronic devices" to purchase history data. This process ensures data consistency and makes subsequent processing easier.

[0090] The learning server uses the normalized and tagged data to train the generative artificial intelligence model. Specifically, it processes the data in batches and trains the model using a machine learning framework. Training is performed by adjusting hyperparameters such as the number of epochs and batch size. The model is continuously updated based on new data, so it is always possible to generate optimized outputs using the latest information.

[0091] The application server receives requests from users. For example, when a user sends a request to search for new products, the application server uses the trained generative artificial intelligence model to generate optimal product recommendations based on past purchase history and behavioral history.

[0092] The generated optimization output is sent to the user's device via the distribution server. The user's device is a device such as a smartphone or PC, which appropriately displays the distributed output and provides it to the user. For example, it may display recommendations for a new smartphone, allowing the user to view and purchase it.

[0093] For example, when a user searches for a new smartphone model on an e-commerce site, the server collects past purchase history and location information. This data is encrypted and stored on a data management server. A data processing terminal normalizes the data and assigns tags such as "electronic device" and "smartphone." The learning server then uses this data to train an AI model. When the user searches for a product again, the application server uses the model to generate optimal smartphone recommendations based on the user's preferences. This recommendation information is sent to the user's smartphone via a distribution server, allowing the user to view and purchase optimized product information on the screen.

[0094] An example of a prompt sentence to be input into a generative AI model is, "Based on past purchasing history, please suggest three smartphones that the user might be interested in."

[0095] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0096] Step 1:

[0097] Collecting personal data from users

[0098] The server collects the user's personal data through the API.

[0099] Input: User permission, API token

[0100] Processing: The server connects to the API of the e-commerce site or location information service to obtain data such as purchase history, behavioral history, and location information. This data is obtained in JSON format.

[0101] Output: Collected personal data (purchase history, behavioral history, location information, etc.)

[0102] Step 2:

[0103] Encryption and storage of personal data

[0104] The personal data collected by the server is encrypted and stored on a data management server.

[0105] Input: Collected personal data

[0106] Processing: The server encrypts the data using an encryption algorithm such as AES-256, then transfers the encrypted data to the data management server, where it is stored in a database (e.g., MongoDB or PostgreSQL).

[0107] Output: Encrypted personal data stored in a database

[0108] Step 3:

[0109] Normalizing and tagging personal data

[0110] The data processing terminal normalizes the collected and stored data and assigns the necessary tags.

[0111] Input: Encrypted personal data

[0112] Processing: The data processing terminal decodes the data and converts data in different formats into a unified format. For example, it unifies date and time data into ISO 8601 format. It also assigns category tags such as "food" and "electronic devices" to purchase history data.

[0113] Output: Normalized and tagged personal data

[0114] Step 4:

[0115] Training a generative AI model

[0116] The learning server uses the normalized and tagged data to train a generative AI model.

[0117] Input: Normalized and tagged personal data

[0118] Processing: The training server processes the data in batches and trains the model using a machine learning framework (such as PyTorch or TensorFlow). Hyperparameters such as the number of epochs and batch size are set and the model is trained multiple times.

[0119] Output: A trained generative AI model

[0120] Step 5:

[0121] Generating Optimization Output

[0122] The application server processes user requests and generates optimized outputs using the trained generative AI model.

[0123] Input: User request, trained generative AI model

[0124] Processing: The application server receives a request from the user. For example, when a user sends a request to search for new products, it generates personalized product recommendations based on their past purchase history and behavioral history.

[0125] Output: Optimized product recommendations

[0126] Step 6:

[0127] Delivering optimized output

[0128] A distribution server distributes the generated optimized output to the user terminal.

[0129] Input: Optimized product recommendations

[0130] Processing: The distribution server sends optimized recommendation information to the user's device, which can be a smartphone, PC, or other device.

[0131] Output: Optimized product recommendations displayed on the user's device

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] Traditional online shopping sites and similar services have struggled to fully utilize users' personal data to provide optimal product recommendations. This has limited the amount of useful information they can provide, and they have sought ways to improve user satisfaction. Furthermore, there has been a lack of effective methods for presenting special offers using location information in real time.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes means for collecting personal data from a user, means for storing and managing the personal data, means for normalizing and tagging the personal data, means for training a generative artificial intelligence model using the normalized and tagged personal data, means for generating an optimized output from the trained generative artificial intelligence model based on a user request, means for delivering the optimized output to a user terminal, means for recommending products based on the user's purchase history and browsing history, and means for presenting special offers using the user's location information. This enables personalized product recommendations that match the user's preferences and the presentation of special offers in real time, which is expected to improve the user experience.

[0137] "User" refers to an individual user of a particular system or service.

[0138] "Personal data" refers to information related to an individual, such as a user's purchase history, behavioral history, and location information.

[0139] "Purchase history" refers to products purchased by a user in the past and their detailed information.

[0140] "Behavioral history" refers to a record of a series of operations and activities performed by a user within the service.

[0141] "Location information" refers to data regarding a user's current or past location.

[0142] "Storage and management measures" refers to the mechanisms for safely storing personal data and for accessing and managing it as necessary.

[0143] "Normalization and tagging measures" refers to the process by which collected personal data is converted into a standard format and assigned relevant keywords and categories.

[0144] "Means for training a generative AI model" refers to the process of using normalized personal data to build and train a generative AI model to learn patterns that are unique to each user.

[0145] "Means for generating optimized outputs based on user requests" refers to a process for using a trained generative AI model to output optimal results in response to user inputs or requests.

[0146] "User terminal" refers to a device such as a smartphone or PC used by a user.

[0147] "Means for delivering" refers to a method for transferring the generated output to a user terminal and displaying it.

[0148] "Means for recommending products" refers to a system that selects and suggests products suitable for users based on personal data.

[0149] "Means for presenting special offers" refers to methods that utilize location information to provide advantageous proposals or coupons to users at specific locations or times.

[0150] The present invention is a system that collects personal data of users and uses a generative AI model to provide optimized output. Specific embodiments of the system are described in detail below.

[0151] Hardware and Software Configuration

[0152] The main hardware components of this system include servers and user terminals (smartphones, PCs, etc.). The roles of each component are as follows:

[0153] server:

[0154] Data collection server: Collects personal data such as user purchase history, behavioral history, and location information from various services via API.

[0155] Data Management Server: Securely stores and manages collected personal data, applying encryption and access controls.

[0156] Data processing server: Normalizes collected personal data and assigns tags such as categories and keywords.

[0157] Learning Server: Uses normalized and tagged data to train generative AI models to learn individual user patterns and preferences.

[0158] Application Server: Uses trained generative AI models to generate optimized outputs based on user requests.

[0159] Distribution server: distributes the generated output to user devices.

[0160] User device:

[0161] The system application is installed on the device that the user normally uses, such as a smartphone or PC, and displays the generated output.

[0162] Description of the main process

[0163] 1. Collection of Personal Data:

[0164] The server collects personal data such as the user's purchase history, behavioral history, and location information from various services with the user's permission. This data collection is done via API.

[0165] 2. Data Storage and Management:

[0166] The data management server encrypts and securely stores collected personal data, and data security is ensured through access control.

[0167] 3. Data normalization and tagging:

[0168] The data processing server converts the collected personal data into a unified format and maintains data consistency by assigning relevant categories and keywords.

[0169] 4. Training the generative AI model:

[0170] The learning server uses the normalized and tagged data to train a generative AI model, which learns individual user patterns and preferences and is continuously updated.

[0171] 5. Generating optimization outputs:

[0172] The application server accepts user requests and generates optimized outputs using a trained generative AI model.

[0173] 6. Output Delivery:

[0174] The distribution server distributes the generated optimized output to the user terminal, which then appropriately displays the distributed output and provides it to the user.

[0175] Specific examples

[0176] For example, if a user searches for a specific product on an e-commerce site, the following prompt sentences can be used to generate optimized product recommendations:

[0177] Example prompt sentence:

[0178] Please list 5 recommended products based on the user's purchase history. <User ID: 12345>

[0179] By inputting this prompt into a generative AI model, the system can recommend the best products for the user. If the user provides specific location information, special offers related to that location can also be presented. For example, if the user is near a specific electronics retailer, they will be notified of special offers and coupons.

[0180] In this way, the system of the present invention uses the user's personal data to provide personalized and optimized output, which is expected to improve the user experience.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1: Collecting personal data

[0183] The server collects personal data such as the user's purchase history, behavioral history, and location information from various services via API. Specifically, it obtains purchase history from the e-commerce site and the user's current location and visit history from the location information service. The input is the user's authentication information and API request, and the output is the collected personal data. The server temporarily stores this data.

[0184] Step 2: Store and manage your data

[0185] The server encrypts the collected personal data and stores it securely in a database. Access control is also applied during the storage process. The input is the personal data collected in step 1, and the output is the securely stored personal data.

[0186] Step 3: Normalize and tag the data

[0187] The data processing server converts the collected personal data into a unified format and assigns relevant categories and keywords, ensuring data consistency and facilitating subsequent processing. The input is the stored personal data, and the output is the normalized and tagged data.

[0188] Step 4: Training the generative AI model

[0189] The learning server uses the normalized and tagged data to train the generative AI model. The training process learns each user's patterns and preferences. The input is the normalized and tagged personal data, and the output is the trained generative AI model.

[0190] Step 5: Generate optimization output

[0191] The application server accepts user requests and generates optimized outputs using the trained generative AI model. For example, if a user searches for a specific product, it generates product recommendations based on the user's purchase history and behavioral history. The input is the user request and the trained AI model, and the output is optimized product recommendations.

[0192] Step 6: Delivering the output

[0193] The distribution server distributes the generated optimized output to the user's device. The distribution process involves real-time notifications and display of the optimized output on the user's smartphone or PC. The input is the optimized output, and the output is product recommendations and special offers displayed on the user's device.

[0194] This series of steps results in personalized product recommendations and special offers that enhance the user experience.

[0195] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0196] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and emotion engine. The system is composed of the following multiple subsystems and processes:

[0197] Collection of Personal Data

[0198] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, location information, etc. from various services (e.g., e-commerce sites, location-based services) via API. This data provides detailed information about the user's behavior and preferences.

[0199] Data storage and management

[0200] The data management server securely stores and manages the collected personal data. The data management server encrypts the collected data and stores it with appropriate access control. This ensures the security and privacy of the data while allowing it to be accessed quickly when needed.

[0201] Data normalization and tagging

[0202] The data processing terminal normalizes and tags the stored personal data. For example, this includes converting collected purchase history information into a consistent format and tagging it with relevant categories and keywords. This process ensures data consistency and makes subsequent processing easier.

[0203] Collecting Emotional Data

[0204] The emotion engine collects the user's emotional data. The emotion engine uses sensors and devices to analyze emotions from the user's facial expressions, voice tone, and text input. This data is also stored and managed along with other personal data.

[0205] Training a private AI model

[0206] The learning server uses the normalized and tagged personal and emotional data to train a generative AI model. This AI model learns each user's data patterns and preferences to generate optimal output. The model is continuously updated and retrained as new user data is added.

[0207] Generating optimization output

[0208] The application server accepts user requests and integrates the trained generative AI model with emotional data to generate optimized output. For example, if a user searches for a specific product, it provides optimized product recommendations based on past purchase history, behavioral history, and current emotional state. This output is tailored to the user's specific needs and emotional state.

[0209] Output Delivery

[0210] The distribution server distributes the generated optimized output to the user's device. The distribution server sends the generated output in an appropriate format to the user's device, such as a smartphone or PC, for notification or display, allowing the user to receive optimized information and suggestions.

[0211] Specific examples

[0212] For example, when a user searches for a specific product on an e-commerce site, the system works as follows: The data collection server collects information about the user's past purchase history, behavioral history, and recently visited places, and the emotion engine analyzes the user's current emotional state (e.g., stress level and satisfaction). This data is normalized and tagged.

[0213] The learning server uses this data to train the AI ​​model, and when the user searches for a product again, the application server generates optimized product recommendations based on the trained model and emotion data. The generated recommendation information is sent to the user's smartphone by the distribution server, allowing the user to view and purchase product information optimized for them.

[0214] In this way, the system of the present invention can provide an output optimized for each user, thereby maintaining a competitive advantage for the company. By providing a more refined output based on the user's emotions, it becomes possible to provide information that is optimal for a specific situation or timing.

[0215] The processing flow will be explained below.

[0216] Step 1:

[0217] With the user's permission, the server collects personal data. Specifically, the server obtains data such as the user's purchase history, behavioral history, and location information from various services (e.g., e-commerce sites, location-based services) via API. This allows for detailed data on the user's behavior and preferences to be obtained.

[0218] Step 2:

[0219] The data management server encrypts the collected personal data and stores it in a secure database. The data has appropriate access controls to protect privacy. This step ensures that the data is stored securely and can be retrieved when needed.

[0220] Step 3:

[0221] The data processing terminal normalizes the stored personal data and assigns categories and keywords. For example, purchase history data is converted into a unified format and tagged with "home appliances" or "books." This process maintains data consistency and makes it easier to use in subsequent processes.

[0222] Step 4:

[0223] The emotion engine collects the user's emotional data. The emotion engine analyzes the user's facial expressions, voice tone, and text input to collect data to identify the user's emotional state (e.g., "joy," "sadness," "stress") using cameras, microphones, and sensors.

[0224] Step 5:

[0225] The data management server also encrypts the emotion data collected from the emotion engine and stores it in a secure database, ensuring that emotion data is stored securely in the same way as personal data.

[0226] Step 6:

[0227] The learning server trains the generative AI model using normalized and tagged personal and emotional data. The learning server learns each user's patterns and preferences and builds a model to generate optimized outputs. The model is retrained each time new user data is added.

[0228] Step 7:

[0229] The application server receives requests from users. For example, when a user searches for a specific product, the application server generates optimized product recommendations based on past purchase history, behavioral history, and emotional data. The recommendations take into account the user's current emotional state.

[0230] Step 8:

[0231] The distribution server distributes the generated optimized output to the user's device. The output is distributed in an appropriate format and sent to the user's smartphone, PC, etc.

[0232] Step 9:

[0233] The user device displays the received output. The user device visually displays the optimized information and suggestions, allowing the user to use and view the information. For example, the user can check the product recommendation list optimized for them on their smartphone and purchase the product immediately.

[0234] Through this series of steps, the system of the present invention provides optimized output that is personalized for each user and based on their emotional state, allowing companies to maintain a competitive advantage.

[0235] Example 2

[0236] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0237] Conventional systems only provide output based on user behavioral and purchasing data, making it difficult to generate optimal output that takes the user's emotional state into account. Furthermore, they often lack the ability to uniformly handle data in different formats and provide insufficient security management. Therefore, there is a need for a system that can provide more precise and personalized output.

[0238] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data from a user, means for saving and managing the personal data, means for normalizing and tagging the personal data, means for collecting and analyzing emotion data, means for training a generative AI model using the normalized and tagged personal data and emotion data, means for generating an optimized output using the trained generative AI model and emotion data based on a user request, and means for delivering the optimized output to a user terminal. This makes it possible to quickly and safely provide more personalized and sophisticated output based on the user's behavioral data and emotion data.

[0239] "User" refers to an individual or corporation that uses the system.

[0240] "Personal data" refers to data that includes information about a user's specific behavior or preferences, such as purchase history, behavior history, and location information.

[0241] "Means of collection" refers to the ability to obtain data through interfaces such as APIs.

[0242] "Means of storage and management" refers to the ability to securely store and properly manage data using encryption and access control.

[0243] "Means for normalization and tagging" refers to the function of converting data of different formats into a unified format and assigning tags such as categories and keywords.

[0244] "Emotion data" refers to data that indicates the user's emotional state, such as information extracted from facial expressions, voice tones, and character input.

[0245] "Means for collecting and analyzing emotional data" refers to the function of detecting and analyzing the user's emotions using sensors or devices.

[0246] A "generative artificial intelligence model" refers to a model that uses machine learning techniques to learn user data patterns and preferences.

[0247] "Training" refers to the process of using collected data to train a generative artificial intelligence model.

[0248] "Optimized Output" refers to personalized results generated based on a generative artificial intelligence model and emotional data in response to a user's request.

[0249] "User request" refers to a search or information request made by a user to the system.

[0250] "Means for delivering" refers to the function of transferring and notifying the generated output to the user terminal.

[0251] "User terminal" refers to a device used by a user to access the system, such as a smartphone or PC.

[0252] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and emotion engine. This system is composed of multiple subsystems and processes as described below.

[0253] Collection of Personal Data

[0254] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, and location information from various services via API. This data provides detailed information about the user's behavior and preferences. For example, the server sends a request to an e-commerce site's API to obtain the user's purchase history data.

[0255] Data storage and management

[0256] The data management server securely stores and manages the collected personal data. The data management server encrypts the data using an encryption library (e.g., AES-256) and stores it in a database (e.g., MySQL). It also performs appropriate access control using a user authentication function (e.g., JWT token).

[0257] Data normalization and tagging

[0258] The data processing device normalizes and tags the stored personal data. For example, it unifies purchase history recorded in different formats and assigns relevant categories and keywords. This process uses a text classification algorithm (e.g., TF-IDF or Word2Vec).

[0259] Collecting Emotional Data

[0260] The emotion engine collects user emotional data. Using sensors and devices, emotions are analyzed from the user's facial expressions, voice tone, and text input. For example, a facial recognition camera captures the user's facial expressions and analyzes them with an emotion recognition algorithm (e.g., OpenFace). Voice tone is analyzed using a voice feature extraction algorithm (e.g., Librosa).

[0261] Training a private AI model

[0262] The learning server trains a generative AI model using the normalized and tagged personal and emotional data. This process uses machine learning libraries (e.g., TensorFlow and PyTorch). The trained model learns each user's data patterns and preferences and is retrained each time new data is added.

[0263] Generating optimization output

[0264] The application server accepts requests from users and generates optimized outputs by integrating the trained generative AI model with emotional data. For example, if a user searches for a specific product, it provides optimized product recommendations taking into account their past purchase history, behavioral history, and current emotional state. As a concrete example, the prompt sentence to be input to the generative AI model is shown below.

[0265] Example prompt sentence:

[0266] "Provide optimal product recommendations that match the user's recent searches and take into account his past purchase history and current emotional state."

[0267] Output Delivery

[0268] The distribution server distributes the generated optimized output to the user's device. The distribution server then sends the generated output in an appropriate format to the user's smartphone or PC for notification or display, allowing the user to receive optimized information and suggestions.

[0269] In this way, the system of the present invention can provide refined output for each user, enabling more personalized services, which helps companies maintain their competitive advantage and enables users to receive optimal information tailored to their specific situation and timing.

[0270] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0271] Step 1: Collecting personal data

[0272] With the user's permission, the server collects personal data, including purchase history, behavioral history, and location information.

[0273] Input: Data API endpoints from various services (e.g., e-commerce sites, location services).

[0274] How it works: The server sends a request to the API and gets back data in JSON format. For example, it accesses the endpoint "https: / / api.ecommerce.com / history?userid=12345".

[0275] Output: Purchase history and behavioral history data in JSON format.

[0276] Step 2: Store and manage your data

[0277] The data management server stores and manages the collected personal data, a process that includes data encryption and access control.

[0278] Input: Personal data collected in step 1.

[0279] Operation: The data management server encrypts the data using an encryption library (e.g., AES-256) and stores it in a database (e.g., MySQL). It also implements access control using user authentication functions (e.g., JWT tokens).

[0280] Output: Encrypted data stored securely in a database.

[0281] Step 3: Normalize and tag the data

[0282] The data processing terminal normalizes the stored personal data and assigns relevant categories and keywords.

[0283] Input: The encrypted data stored in step 2.

[0284] How it works: The data processing terminal runs a script that converts the data into a consistent format, for example standardizing different date formats to "YYYY-MM-DD" and tagging it using a text classification algorithm (e.g. TF-IDF or Word2Vec).

[0285] Output: Normalized and tagged data.

[0286] Step 4: Collecting emotion data

[0287] The emotion engine collects user emotional data by analyzing the user's facial expressions, tone of voice, and text input using sensors and devices.

[0288] Input: User's facial expression data, voice data, and text input data.

[0289] How it works: The emotion engine uses a facial recognition camera or microphone to analyze emotion data using facial expression recognition algorithms (e.g., OpenFace) and voice feature extraction algorithms (e.g., Librosa).

[0290] Output: Data indicating the user's emotional state.

[0291] Step 5: Train a private AI model

[0292] The learning server trains the generative AI model using normalized and tagged personal data and emotion data.

[0293] Input: Normalized and tagged data from step 3, sentiment data from step 4.

[0294] How it works: The learning server uses machine learning libraries (e.g., TensorFlow or PyTorch) to train generative AI models (e.g., Transformer models).

[0295] Output: A trained generative AI model.

[0296] Step 6: Generate optimization output

[0297] The application server accepts requests from users and integrates the trained generative AI model with emotion data to generate optimized outputs.

[0298] Input: User request, trained generative AI model, current emotion data.

[0299] How it works: The application server inputs prompt statements into the generative AI model and executes requests such as, "Please provide optimal product recommendations that match the user's recent search results, taking into account his past purchase history and current emotional state."

[0300] Output: An optimized product recommendation list.

[0301] Step 7: Delivering the output

[0302] A distribution server distributes the generated optimized output to the user terminal.

[0303] Input: The optimization output generated in step 6.

[0304] Operation: The distribution server sends the generated recommended product list in JSON format to an endpoint and distributes it to the user's device via a REST API. The user's device receives this information and sends a push notification or displays it on the screen.

[0305] Output: Optimized output notification delivered to user terminal.

[0306] (Application example 2)

[0307] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0308] Today's consumers are becoming increasingly diverse and tend to demand products and services tailored to their individual needs. However, conventional systems have difficulty making optimal recommendations that take into account not only a user's purchasing history, behavioral history, and location information, but also their emotional state. This can lead to issues such as reduced user satisfaction and lost sales opportunities.

[0309] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data from users, means for saving and managing the personal data, means for normalizing and tagging the personal data, means for training a generative AI model using the normalized and tagged personal data, means for generating an optimized output from the trained generative AI model based on a user request, means for delivering the optimized output to a user terminal, means for collecting and analyzing user emotion data, and means for optimizing recommendations using the emotion data. This makes it possible to respond to the diverse needs of users and provide individually optimized product recommendations and services.

[0310] "Means of collecting personal data from users" refers to means of obtaining individual data such as users' purchase history, behavioral history, and location information via APIs or sensors.

[0311] "Personal data" refers to data that indicates individual preferences and patterns, such as user behavior, purchasing history, and location information.

[0312] "Means for storage and management" refers to the means for securely storing collected personal data and encrypting and controlling access to it.

[0313] "Normalization and tagging measures" are measures that convert collected personal data into a consistent format and assign relevant categories and keywords.

[0314] "Means for training a generative artificial intelligence model" means means for using normalized and tagged personal data to train an artificial intelligence model to learn individual data patterns and preferences.

[0315] The "means for generating optimized output" refers to a means for using a trained artificial intelligence model to provide optimal recommendations and information based on user requests.

[0316] The "means for delivering" refers to a means for transmitting the generated optimization output to the user's terminal and for notifying or displaying the output.

[0317] "Means for collecting and analyzing emotional data" refers to means for collecting and analyzing the emotional state of a user by analyzing the user's facial expressions, tone of voice, etc. using sensors or devices.

[0318] "Means for optimizing recommendations" refers to means for using collected and analyzed emotional data to recommend and provide products and services that are most suited to the user's emotional state.

[0319] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and an emotion engine. This system is constructed using the following hardware and software:

[0320] Hardware and software used

[0321] Hardware

[0322] 1. Server: The server that collects, stores, and manages personal data from users.

[0323] 2. Data management server: A server that encrypts and stores data and controls access.

[0324] 3. Data processing terminal: A terminal that normalizes and tags personal data.

[0325] 4. Learning server: A server that trains AI models.

[0326] 5. Application Server: The server that generates and delivers the optimized output.

[0327] 6. Distribution server: A server that distributes the generated output to user terminals.

[0328] 7. User terminal: The device that receives the output, such as a smartphone or PC.

[0329] 8. Emotion Sensor: A device (camera, microphone, heart rate sensor, etc.) that collects user emotional data.

[0330] software

[0331] 1. Generative AI model: A model that generates optimized output based on personal data and emotional data.

[0332] 2. Emotion Recognizer: Software that analyzes the user's emotions.

[0333] 3. Recommendation Engine: Software that generates optimized output based on data.

[0334] System configuration

[0335] 1. Collection of Personal Data:

[0336] The server collects personal data such as users' purchase history, behavioral history, and location information. This data is obtained from various web services and apps via APIs.

[0337] 2. Data Storage and Management:

[0338] The data management server encrypts and securely stores collected personal data, and also implements appropriate access control to ensure data security.

[0339] 3. Data normalization and tagging:

[0340] The data processing terminal normalizes the personal data into a consistent format and tags it with relevant categories and keywords, a process that ensures data consistency.

[0341] 4. Emotional Data Collection and Analysis:

[0342] Emotion sensors and emotion recognition software (EmotionRecognizer) collect and analyze emotional data from users' facial expressions, voice tones, and text input. This data is stored along with other personal data.

[0343] 5. Training the AI ​​model:

[0344] The learning server uses the normalized and tagged personal and emotional data to train a generative AI model that learns each user's data patterns and preferences to generate optimized outputs.

[0345] 6. Generating optimization outputs:

[0346] The trained generative AI model generates optimized outputs based on user requests on the application server, which recommend optimal products and services taking into account the user's current emotional state.

[0347] 7. Output Delivery:

[0348] The distribution server distributes the generated optimization output to the user's device, allowing the user to receive optimized information and suggestions on their device, such as a smartphone or PC.

[0349] Specific examples

[0350] For example, when a user approaches the beverage section of a physical store, a push notification will be sent with the most suitable drink or promotion based on the user's past purchase history (e.g., coffee, energy drinks) and their emotional state at that moment (e.g., relaxed). This allows for product recommendations that are optimized for each user.

[0351] Prompt Sentence Examples

[0352] An example prompt is:

[0353] User ID: example_user_id

[0354] Past purchase history: Coffee, energy drinks

[0355] Current behavior history: Entered the beverage section

[0356] Emotional state: Relaxed

[0357] Generate the recommended output.

[0358] In this way, the system of the present invention responds to the diverse needs of users and realizes individually optimized product recommendations and service provision.

[0359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0360] Step 1:

[0361] The server collects personal data from users. Specifically, it obtains data such as purchase history, behavioral history, and location information from various web services and apps via APIs. A user ID is provided as input, and related data is collected based on that user ID. The output is a set of collected personal data.

[0362] Step 2:

[0363] The server transmits the collected personal data to the data management server, which securely stores and manages it. The data management server then encrypts the data and performs appropriate access control to ensure data security. The collected personal data is provided as input, and the encrypted and stored data is obtained as output.

[0364] Step 3:

[0365] The data processing terminal normalizes and tags the stored personal data by converting the data into a consistent format and assigning relevant categories and keywords. The input is the encrypted and stored personal data, and the output is the normalized and tagged data.

[0366] Step 4:

[0367] The server uses emotion sensors and emotion recognition software (EmotionRecognizer) to collect and analyze the user's emotion data. Specifically, it obtains emotion data by analyzing the user's facial expressions, voice tone, and text input obtained from the sensors. The input is the user's real-time behavior data, and the output is analyzed emotion data.

[0368] Step 5:

[0369] The learning server trains the generative AI model using normalized and tagged personal data and emotion data. Specifically, the AI ​​model learns each user's data patterns and preferences based on this data. Normalized and tagged personal data and emotion data are provided as input, and the trained AI model is obtained as output.

[0370] Step 6:

[0371] The application server uses the trained generative AI model to generate optimized output based on user requests. Specifically, it generates the most appropriate information, product recommendations, and service content based on the user's current emotional data and behavioral history. The trained AI model and real-time user data are provided as input, and the optimized output is obtained as output.

[0372] Step 7:

[0373] The distribution server distributes the optimized output to the user's device. Specifically, the generated output is sent to the user's device, such as a smartphone or PC, and displayed as a notification. The optimized output is provided as input, and the output is information, product recommendations, and service content displayed on the user's device.

[0374] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0375] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0376] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0377] [Second embodiment]

[0378] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0379] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0380] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0381] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0382] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0383] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0384] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0385] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0386] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0387] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0388] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0389] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0390] The present invention relates to a system that collects personal data from users and provides optimized outputs using generative AI models. The system is composed of the following subsystems and processes:

[0391] Collection of Personal Data

[0392] With the user's permission, the server collects personal data from various services. For example, data such as purchase history, behavioral history, and location information is obtained from e-commerce sites and location information services via API. This allows detailed data on the user's behavior and preferences to be collected.

[0393] Data storage and management

[0394] The data management server securely stores and manages the collected data. Data is encrypted and access controls are applied to protect data security and privacy. Stored data is properly indexed for quick access when needed.

[0395] Data normalization and tagging

[0396] The data processing terminal normalizes and tags the collected personal data. For example, it converts acquired purchase history data into a unified format and assigns relevant categories and keywords. This process ensures data consistency and makes subsequent processing easier.

[0397] Training a private AI model

[0398] The learning server uses the normalized and tagged personal data to train a generative AI model that learns each user's patterns and preferences and generates optimal output based on them. The model is continuously updated and retrained as new user data is added.

[0399] Generating optimization output

[0400] The application server accepts user requests and uses the trained generative AI model to generate optimized output, such as personalized product recommendations based on past purchase and behavioral history when a user searches for new products. This output is customized to the user's specific needs.

[0401] Output Delivery

[0402] The distribution server distributes the generated optimized output to the user's device, which can be a smartphone, PC, or other device that appropriately displays the distributed output and provides it to the user.

[0403] Specific examples

[0404] For example, if a user searches for a specific product on an e-commerce site, the data collection server collects information about the user's past purchase history, recently visited locations, etc. After this data is normalized and tagged, the learning server uses it to update and train the AI ​​model.

[0405] When the user searches for a product again, the application server uses the trained AI model to generate optimal product recommendations based on the user's preferences and past behavior. The generated recommendation information is sent to the user's smartphone by the distribution server, allowing the user to view and purchase product information optimized for them.

[0406] In this manner, the system of the present invention can provide an output that is optimized for each user, thereby maintaining a company's competitive advantage.

[0407] The processing flow will be explained below.

[0408] Step 1:

[0409] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, location information, etc. from various services (e.g., e-commerce sites, location information services) via API. This allows for detailed data on the user's behavior and preferences to be obtained.

[0410] Step 2:

[0411] The data management server securely stores and manages the collected personal data. The data management server encrypts the collected data and stores it with appropriate access control. This protects the security and privacy of the data while also ensuring that the data can be accessed quickly when needed.

[0412] Step 3:

[0413] The data processing terminal normalizes and tags the stored personal data. Specifically, the data processing terminal converts purchase history information into a unified format and assigns relevant categories and keywords. This process ensures data consistency and facilitates subsequent processing.

[0414] Step 4:

[0415] The learning server trains the generative AI model using normalized and tagged personal data. The learning server learns each user's data patterns and preferences and builds a model to generate optimal output based on them. This model is continuously updated and learns as new user data is added.

[0416] Step 5:

[0417] The application server accepts user requests and generates optimized output using the trained generative AI model. For example, if a user searches for a specific product, the application server provides optimized product recommendations based on past purchase history and behavioral history. This output is tailored to the user's specific needs.

[0418] Step 6:

[0419] The distribution server distributes the generated optimized output to the user's device. The distribution server sends the generated output in an appropriate format to the user's device, such as a smartphone or PC, for notification or display, allowing the user to receive optimized information and suggestions.

[0420] Step 7:

[0421] The user device displays the received output. The user device visually displays the received information, allowing the user to view and use optimized product information and suggestions. For example, the user can view a list of product recommendations optimized for them on their smartphone and can even purchase the products directly.

[0422] Through this series of steps, the system of the present invention provides optimized output for each user, enabling the company to maintain a competitive advantage.

[0423] Example 1

[0424] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0425] Conventional systems have struggled to generate personalized outputs that fully utilize users' personal data. They also face challenges in terms of data security, privacy protection, and continuous model updates. Furthermore, it has been difficult to create a system that can respond quickly and optimally to user requests.

[0426] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0427] In this invention, the server includes means for collecting personal data from a user, means for storing and managing the personal data, means for normalizing and tagging the personal data, means for training a generative artificial intelligence model using the normalized and tagged personal data, means for generating an optimized output from the trained generative artificial intelligence model based on a user request, means for delivering the optimized output to a user terminal, specific means for obtaining personal data through an API, encrypting and storing it, means for updating the generative artificial intelligence model based on past data, and specific means for processing requests input by the user.

[0428] This makes it possible to provide personalized output specific to each user, ensure data security and privacy, and continuously update models using the latest data, enabling quick and optimal responses to user requests.

[0429] "Personal data" refers to information related to a specific individual, such as a user's purchasing history, behavioral history, and location information.

[0430] "Acquisition through API" refers to the method of acquiring data from other services or systems via an application program interface (API).

[0431] "Encryption" is the process of transforming data using a specific algorithm into a format that cannot be easily deciphered by third parties.

[0432] "Normalization" means converting data into a consistent format and making it easier to process.

[0433] "Tagging" refers to assigning relevant categories and keywords to data to make it easier to search and classify.

[0434] A "generative artificial intelligence model" is a model that has been trained using machine learning or artificial intelligence algorithms to perform a specific task.

[0435] "Training" is the process of using collected data to teach an artificial intelligence model and improve its performance.

[0436] "Optimization output" refers to the recommendations and responses generated by an artificial intelligence model tailored to a user's individual needs.

[0437] A "server" is a computer system that provides services or processing power over a network.

[0438] A "user terminal" refers to a device such as a computer, smartphone, or tablet that is directly operated by a user.

[0439] A "user request" is a request or inquiry sent by a user to the system.

[0440] The present invention relates to a system that uses personal data collected from users to train a generative artificial intelligence model and generate optimized outputs based on user requests. A specific example of the system is described below.

[0441] This system mainly uses the following hardware and software. The hardware includes a data collection server, data management server, data processing terminal, learning server, application server, distribution server, and user terminal. The software uses APIs, encryption algorithms (e.g., AES-256), database software (e.g., MongoDB or PostgreSQL), and machine learning frameworks (e.g., PyTorch or TensorFlow).

[0442] First, the server collects personal data through API with the user's permission. The collected data includes purchase history, behavioral history, and location information. The collected data is encrypted by the server and stored on a data management server. This is to protect the security and privacy of the data.

[0443] The data processing terminal then normalizes the collected data and assigns tags to it. For example, it converts date and time data in different formats into a unified format and assigns categories such as "food" or "electronic devices" to purchase history data. This process ensures data consistency and makes subsequent processing easier.

[0444] The learning server uses the normalized and tagged data to train the generative artificial intelligence model. Specifically, it processes the data in batches and trains the model using a machine learning framework. Training is performed by adjusting hyperparameters such as the number of epochs and batch size. The model is continuously updated based on new data, so it is always possible to generate optimized outputs using the latest information.

[0445] The application server receives requests from users. For example, when a user sends a request to search for new products, the application server uses the trained generative artificial intelligence model to generate optimal product recommendations based on past purchase history and behavioral history.

[0446] The generated optimization output is sent to the user's device via the distribution server. The user's device is a device such as a smartphone or PC, which appropriately displays the distributed output and provides it to the user. For example, it may display recommendations for a new smartphone, allowing the user to view and purchase it.

[0447] For example, when a user searches for a new smartphone model on an e-commerce site, the server collects past purchase history and location information. This data is encrypted and stored on a data management server. A data processing terminal normalizes the data and assigns tags such as "electronic device" and "smartphone." The learning server then uses this data to train an AI model. When the user searches for a product again, the application server uses the model to generate optimal smartphone recommendations based on the user's preferences. This recommendation information is sent to the user's smartphone via a distribution server, allowing the user to view and purchase optimized product information on the screen.

[0448] An example of a prompt sentence to be input into a generative AI model is, "Based on past purchasing history, please suggest three smartphones that the user might be interested in."

[0449] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0450] Step 1:

[0451] Collecting personal data from users

[0452] The server collects the user's personal data through the API.

[0453] Input: User permission, API token

[0454] Processing: The server connects to the API of the e-commerce site or location information service to obtain data such as purchase history, behavioral history, and location information. This data is obtained in JSON format.

[0455] Output: Collected personal data (purchase history, behavioral history, location information, etc.)

[0456] Step 2:

[0457] Encryption and storage of personal data

[0458] The personal data collected by the server is encrypted and stored on a data management server.

[0459] Input: Collected personal data

[0460] Processing: The server encrypts the data using an encryption algorithm such as AES-256, then transfers the encrypted data to the data management server, where it is stored in a database (e.g., MongoDB or PostgreSQL).

[0461] Output: Encrypted personal data stored in a database

[0462] Step 3:

[0463] Normalizing and tagging personal data

[0464] The data processing terminal normalizes the collected and stored data and assigns the necessary tags.

[0465] Input: Encrypted personal data

[0466] Processing: The data processing terminal decodes the data and converts data in different formats into a unified format. For example, it unifies date and time data into ISO 8601 format. It also assigns category tags such as "food" and "electronic devices" to purchase history data.

[0467] Output: Normalized and tagged personal data

[0468] Step 4:

[0469] Training a generative AI model

[0470] The learning server uses the normalized and tagged data to train a generative AI model.

[0471] Input: Normalized and tagged personal data

[0472] Processing: The training server processes the data in batches and trains the model using a machine learning framework (such as PyTorch or TensorFlow). Hyperparameters such as the number of epochs and batch size are set and the model is trained multiple times.

[0473] Output: A trained generative AI model

[0474] Step 5:

[0475] Generating Optimization Output

[0476] The application server processes user requests and generates optimized outputs using the trained generative AI model.

[0477] Input: User request, trained generative AI model

[0478] Processing: The application server receives a request from the user. For example, when a user sends a request to search for new products, it generates personalized product recommendations based on their past purchase history and behavioral history.

[0479] Output: Optimized product recommendations

[0480] Step 6:

[0481] Delivering optimized output

[0482] A distribution server distributes the generated optimized output to the user terminal.

[0483] Input: Optimized product recommendations

[0484] Processing: The distribution server sends optimized recommendation information to the user's device, which can be a smartphone, PC, or other device.

[0485] Output: Optimized product recommendations displayed on the user's device

[0486] (Application example 1)

[0487] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0488] Traditional online shopping sites and similar services have struggled to fully utilize users' personal data to provide optimal product recommendations. This has limited the amount of useful information they can provide, and they have sought ways to improve user satisfaction. Furthermore, there has been a lack of effective methods for presenting special offers using location information in real time.

[0489] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0490] In this invention, the server includes means for collecting personal data from a user, means for storing and managing the personal data, means for normalizing and tagging the personal data, means for training a generative artificial intelligence model using the normalized and tagged personal data, means for generating an optimized output from the trained generative artificial intelligence model based on a user request, means for delivering the optimized output to a user terminal, means for recommending products based on the user's purchase history and browsing history, and means for presenting special offers using the user's location information. This enables personalized product recommendations that match the user's preferences and the presentation of special offers in real time, which is expected to improve the user experience.

[0491] "User" refers to an individual user of a particular system or service.

[0492] "Personal data" refers to information related to an individual, such as a user's purchase history, behavioral history, and location information.

[0493] "Purchase history" refers to products purchased by a user in the past and their detailed information.

[0494] "Behavioral history" refers to a record of a series of operations and activities performed by a user within the service.

[0495] "Location information" refers to data regarding a user's current or past location.

[0496] "Storage and management measures" refers to the mechanisms for safely storing personal data and for accessing and managing it as necessary.

[0497] "Normalization and tagging measures" refers to the process by which collected personal data is converted into a standard format and assigned relevant keywords and categories.

[0498] "Means for training a generative AI model" refers to the process of using normalized personal data to build and train a generative AI model to learn patterns that are unique to each user.

[0499] "Means for generating optimized outputs based on user requests" refers to a process for using a trained generative AI model to output optimal results in response to user inputs or requests.

[0500] "User terminal" refers to a device such as a smartphone or PC used by a user.

[0501] "Means for delivering" refers to a method for transferring the generated output to a user terminal and displaying it.

[0502] "Means for recommending products" refers to a system that selects and suggests products suitable for users based on personal data.

[0503] "Means for presenting special offers" refers to methods that utilize location information to provide advantageous proposals or coupons to users at specific locations or times.

[0504] The present invention is a system that collects personal data of users and uses a generative AI model to provide optimized output. Specific embodiments of the system are described in detail below.

[0505] Hardware and Software Configuration

[0506] The main hardware components of this system include servers and user terminals (smartphones, PCs, etc.). The roles of each component are as follows:

[0507] server:

[0508] Data collection server: Collects personal data such as user purchase history, behavioral history, and location information from various services via API.

[0509] Data Management Server: Securely stores and manages collected personal data, applying encryption and access controls.

[0510] Data processing server: Normalizes collected personal data and assigns tags such as categories and keywords.

[0511] Learning Server: Uses normalized and tagged data to train generative AI models to learn individual user patterns and preferences.

[0512] Application Server: Uses trained generative AI models to generate optimized outputs based on user requests.

[0513] Distribution server: distributes the generated output to user devices.

[0514] User device:

[0515] The system application is installed on the device that the user normally uses, such as a smartphone or PC, and displays the generated output.

[0516] Description of the main process

[0517] 1. Collection of Personal Data:

[0518] The server collects personal data such as the user's purchase history, behavioral history, and location information from various services with the user's permission. This data collection is done via API.

[0519] 2. Data Storage and Management:

[0520] The data management server encrypts and securely stores collected personal data, and data security is ensured through access control.

[0521] 3. Data normalization and tagging:

[0522] The data processing server converts the collected personal data into a unified format and maintains data consistency by assigning relevant categories and keywords.

[0523] 4. Training the generative AI model:

[0524] The learning server uses the normalized and tagged data to train a generative AI model, which learns individual user patterns and preferences and is continuously updated.

[0525] 5. Generating optimization outputs:

[0526] The application server accepts user requests and generates optimized outputs using a trained generative AI model.

[0527] 6. Output Delivery:

[0528] The distribution server distributes the generated optimized output to the user terminal, which then appropriately displays the distributed output and provides it to the user.

[0529] Specific examples

[0530] For example, if a user searches for a specific product on an e-commerce site, the following prompt sentences can be used to generate optimized product recommendations:

[0531] Example prompt sentence:

[0532] Please list 5 recommended products based on the user's purchase history. <User ID: 12345>

[0533] By inputting this prompt into a generative AI model, the system can recommend the best products for the user. If the user provides specific location information, special offers related to that location can also be presented. For example, if the user is near a specific electronics retailer, they will be notified of special offers and coupons.

[0534] In this way, the system of the present invention uses the user's personal data to provide personalized and optimized output, which is expected to improve the user experience.

[0535] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0536] Step 1: Collecting personal data

[0537] The server collects personal data such as the user's purchase history, behavioral history, and location information from various services via API. Specifically, it obtains purchase history from the e-commerce site and the user's current location and visit history from the location information service. The input is the user's authentication information and API request, and the output is the collected personal data. The server temporarily stores this data.

[0538] Step 2: Store and manage your data

[0539] The server encrypts the collected personal data and stores it securely in a database. Access control is also applied during the storage process. The input is the personal data collected in step 1, and the output is the securely stored personal data.

[0540] Step 3: Normalize and tag the data

[0541] The data processing server converts the collected personal data into a unified format and assigns relevant categories and keywords, ensuring data consistency and facilitating subsequent processing. The input is the stored personal data, and the output is the normalized and tagged data.

[0542] Step 4: Training the generative AI model

[0543] The learning server uses the normalized and tagged data to train the generative AI model. The training process learns each user's patterns and preferences. The input is the normalized and tagged personal data, and the output is the trained generative AI model.

[0544] Step 5: Generate optimization output

[0545] The application server accepts user requests and generates optimized outputs using the trained generative AI model. For example, if a user searches for a specific product, it generates product recommendations based on the user's purchase history and behavioral history. The input is the user request and the trained AI model, and the output is optimized product recommendations.

[0546] Step 6: Delivering the output

[0547] The distribution server distributes the generated optimized output to the user's device. The distribution process involves real-time notifications and display of the optimized output on the user's smartphone or PC. The input is the optimized output, and the output is product recommendations and special offers displayed on the user's device.

[0548] This series of steps results in personalized product recommendations and special offers that enhance the user experience.

[0549] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0550] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and emotion engine. The system is composed of the following multiple subsystems and processes:

[0551] Collection of Personal Data

[0552] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, location information, etc. from various services (e.g., e-commerce sites, location-based services) via API. This data provides detailed information about the user's behavior and preferences.

[0553] Data storage and management

[0554] The data management server securely stores and manages the collected personal data. The data management server encrypts the collected data and stores it with appropriate access control. This ensures the security and privacy of the data while allowing it to be accessed quickly when needed.

[0555] Data normalization and tagging

[0556] The data processing terminal normalizes and tags the stored personal data. For example, this includes converting collected purchase history information into a consistent format and tagging it with relevant categories and keywords. This process ensures data consistency and makes subsequent processing easier.

[0557] Collecting Emotional Data

[0558] The emotion engine collects the user's emotional data. The emotion engine uses sensors and devices to analyze emotions from the user's facial expressions, voice tone, and text input. This data is also stored and managed along with other personal data.

[0559] Training a private AI model

[0560] The learning server uses the normalized and tagged personal and emotional data to train a generative AI model. This AI model learns each user's data patterns and preferences to generate optimal output. The model is continuously updated and retrained as new user data is added.

[0561] Generating optimization output

[0562] The application server accepts user requests and integrates the trained generative AI model with emotional data to generate optimized output. For example, if a user searches for a specific product, it provides optimized product recommendations based on past purchase history, behavioral history, and current emotional state. This output is tailored to the user's specific needs and emotional state.

[0563] Output Delivery

[0564] The distribution server distributes the generated optimized output to the user's device. The distribution server sends the generated output in an appropriate format to the user's device, such as a smartphone or PC, for notification or display, allowing the user to receive optimized information and suggestions.

[0565] Specific examples

[0566] For example, when a user searches for a specific product on an e-commerce site, the system works as follows: The data collection server collects information about the user's past purchase history, behavioral history, and recently visited places, and the emotion engine analyzes the user's current emotional state (e.g., stress level and satisfaction). This data is normalized and tagged.

[0567] The learning server uses this data to train the AI ​​model, and when the user searches for a product again, the application server generates optimized product recommendations based on the trained model and emotion data. The generated recommendation information is sent to the user's smartphone by the distribution server, allowing the user to view and purchase product information optimized for them.

[0568] In this way, the system of the present invention can provide an output optimized for each user, thereby maintaining a competitive advantage for the company. By providing a more refined output based on the user's emotions, it becomes possible to provide information that is optimal for a specific situation or timing.

[0569] The processing flow will be explained below.

[0570] Step 1:

[0571] With the user's permission, the server collects personal data. Specifically, the server obtains data such as the user's purchase history, behavioral history, and location information from various services (e.g., e-commerce sites, location-based services) via API. This allows for detailed data on the user's behavior and preferences to be obtained.

[0572] Step 2:

[0573] The data management server encrypts the collected personal data and stores it in a secure database. The data has appropriate access controls to protect privacy. This step ensures that the data is stored securely and can be retrieved when needed.

[0574] Step 3:

[0575] The data processing terminal normalizes the stored personal data and assigns categories and keywords. For example, purchase history data is converted into a unified format and tagged with "home appliances" or "books." This process maintains data consistency and makes it easier to use in subsequent processes.

[0576] Step 4:

[0577] The emotion engine collects the user's emotional data. The emotion engine analyzes the user's facial expressions, voice tone, and text input to collect data to identify the user's emotional state (e.g., "joy," "sadness," "stress") using cameras, microphones, and sensors.

[0578] Step 5:

[0579] The data management server also encrypts the emotion data collected from the emotion engine and stores it in a secure database, ensuring that emotion data is stored securely in the same way as personal data.

[0580] Step 6:

[0581] The learning server trains the generative AI model using normalized and tagged personal and emotional data. The learning server learns each user's patterns and preferences and builds a model to generate optimized outputs. The model is retrained each time new user data is added.

[0582] Step 7:

[0583] The application server receives requests from users. For example, when a user searches for a specific product, the application server generates optimized product recommendations based on past purchase history, behavioral history, and emotional data. The recommendations take into account the user's current emotional state.

[0584] Step 8:

[0585] The distribution server distributes the generated optimized output to the user's device. The output is distributed in an appropriate format and sent to the user's smartphone, PC, etc.

[0586] Step 9:

[0587] The user device displays the received output. The user device visually displays the optimized information and suggestions, allowing the user to use and view the information. For example, the user can check the product recommendation list optimized for them on their smartphone and purchase the product immediately.

[0588] Through this series of steps, the system of the present invention provides optimized output that is personalized for each user and based on their emotional state, allowing companies to maintain a competitive advantage.

[0589] Example 2

[0590] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0591] Conventional systems only provide output based on user behavioral and purchasing data, making it difficult to generate optimal output that takes the user's emotional state into account. Furthermore, they often lack the ability to uniformly handle data in different formats and provide insufficient security management. Therefore, there is a need for a system that can provide more precise and personalized output.

[0592] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data from a user, means for saving and managing the personal data, means for normalizing and tagging the personal data, means for collecting and analyzing emotion data, means for training a generative AI model using the normalized and tagged personal data and emotion data, means for generating an optimized output using the trained generative AI model and emotion data based on a user request, and means for delivering the optimized output to a user terminal. This makes it possible to quickly and safely provide more personalized and sophisticated output based on the user's behavioral data and emotion data.

[0593] "User" refers to an individual or corporation that uses the system.

[0594] "Personal data" refers to data that includes information about a user's specific behavior or preferences, such as purchase history, behavior history, and location information.

[0595] "Means of collection" refers to the ability to obtain data through interfaces such as APIs.

[0596] "Means of storage and management" refers to the ability to securely store and properly manage data using encryption and access control.

[0597] "Means for normalization and tagging" refers to the function of converting data of different formats into a unified format and assigning tags such as categories and keywords.

[0598] "Emotion data" refers to data that indicates the user's emotional state, such as information extracted from facial expressions, voice tones, and character input.

[0599] "Means for collecting and analyzing emotional data" refers to the function of detecting and analyzing the user's emotions using sensors or devices.

[0600] A "generative artificial intelligence model" refers to a model that uses machine learning techniques to learn user data patterns and preferences.

[0601] "Training" refers to the process of using collected data to train a generative artificial intelligence model.

[0602] "Optimized Output" refers to personalized results generated based on a generative artificial intelligence model and emotional data in response to a user's request.

[0603] "User request" refers to a search or information request made by a user to the system.

[0604] "Means for delivering" refers to the function of transferring and notifying the generated output to the user terminal.

[0605] "User terminal" refers to a device used by a user to access the system, such as a smartphone or PC.

[0606] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and emotion engine. This system is composed of multiple subsystems and processes as described below.

[0607] Collection of Personal Data

[0608] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, and location information from various services via API. This data provides detailed information about the user's behavior and preferences. For example, the server sends a request to an e-commerce site's API to obtain the user's purchase history data.

[0609] Data storage and management

[0610] The data management server securely stores and manages the collected personal data. The data management server encrypts the data using an encryption library (e.g., AES-256) and stores it in a database (e.g., MySQL). It also performs appropriate access control using a user authentication function (e.g., JWT token).

[0611] Data normalization and tagging

[0612] The data processing device normalizes and tags the stored personal data. For example, it unifies purchase history recorded in different formats and assigns relevant categories and keywords. This process uses a text classification algorithm (e.g., TF-IDF or Word2Vec).

[0613] Collecting Emotional Data

[0614] The emotion engine collects user emotional data. Using sensors and devices, emotions are analyzed from the user's facial expressions, voice tone, and text input. For example, a facial recognition camera captures the user's facial expressions and analyzes them with an emotion recognition algorithm (e.g., OpenFace). Voice tone is analyzed using a voice feature extraction algorithm (e.g., Librosa).

[0615] Training a private AI model

[0616] The learning server trains a generative AI model using the normalized and tagged personal and emotional data. This process uses machine learning libraries (e.g., TensorFlow and PyTorch). The trained model learns each user's data patterns and preferences and is retrained each time new data is added.

[0617] Generating optimization output

[0618] The application server accepts requests from users and generates optimized outputs by integrating the trained generative AI model with emotional data. For example, if a user searches for a specific product, it provides optimized product recommendations taking into account their past purchase history, behavioral history, and current emotional state. As a concrete example, the prompt sentence to be input to the generative AI model is shown below.

[0619] Example prompt sentence:

[0620] "Provide optimal product recommendations that match the user's recent searches and take into account his past purchase history and current emotional state."

[0621] Output Delivery

[0622] The distribution server distributes the generated optimized output to the user's device. The distribution server then sends the generated output in an appropriate format to the user's smartphone or PC for notification or display, allowing the user to receive optimized information and suggestions.

[0623] In this way, the system of the present invention can provide refined output for each user, enabling more personalized services, which helps companies maintain their competitive advantage and enables users to receive optimal information tailored to their specific situation and timing.

[0624] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0625] Step 1: Collecting personal data

[0626] With the user's permission, the server collects personal data, including purchase history, behavioral history, and location information.

[0627] Input: Data API endpoints from various services (e.g., e-commerce sites, location services).

[0628] How it works: The server sends a request to the API and gets back data in JSON format. For example, it accesses the endpoint "https: / / api.ecommerce.com / history?userid=12345".

[0629] Output: Purchase history and behavioral history data in JSON format.

[0630] Step 2: Store and manage your data

[0631] The data management server stores and manages the collected personal data, a process that includes data encryption and access control.

[0632] Input: Personal data collected in step 1.

[0633] Operation: The data management server encrypts the data using an encryption library (e.g., AES-256) and stores it in a database (e.g., MySQL). It also implements access control using user authentication functions (e.g., JWT tokens).

[0634] Output: Encrypted data stored securely in a database.

[0635] Step 3: Normalize and tag the data

[0636] The data processing terminal normalizes the stored personal data and assigns relevant categories and keywords.

[0637] Input: The encrypted data stored in step 2.

[0638] How it works: The data processing terminal runs a script that converts the data into a consistent format, for example standardizing different date formats to "YYYY-MM-DD" and tagging it using a text classification algorithm (e.g. TF-IDF or Word2Vec).

[0639] Output: Normalized and tagged data.

[0640] Step 4: Collecting emotion data

[0641] The emotion engine collects user emotional data by analyzing the user's facial expressions, tone of voice, and text input using sensors and devices.

[0642] Input: User's facial expression data, voice data, and text input data.

[0643] How it works: The emotion engine uses a facial recognition camera or microphone to analyze emotion data using facial expression recognition algorithms (e.g., OpenFace) and voice feature extraction algorithms (e.g., Librosa).

[0644] Output: Data indicating the user's emotional state.

[0645] Step 5: Train a private AI model

[0646] The learning server trains the generative AI model using normalized and tagged personal data and emotion data.

[0647] Input: Normalized and tagged data from step 3, sentiment data from step 4.

[0648] How it works: The learning server uses machine learning libraries (e.g., TensorFlow or PyTorch) to train generative AI models (e.g., Transformer models).

[0649] Output: A trained generative AI model.

[0650] Step 6: Generate optimization output

[0651] The application server accepts requests from users and integrates the trained generative AI model with emotion data to generate optimized outputs.

[0652] Input: User request, trained generative AI model, current emotion data.

[0653] How it works: The application server inputs prompt statements into the generative AI model and executes requests such as, "Please provide optimal product recommendations that match the user's recent search results, taking into account his past purchase history and current emotional state."

[0654] Output: An optimized product recommendation list.

[0655] Step 7: Delivering the output

[0656] A distribution server distributes the generated optimized output to the user terminal.

[0657] Input: The optimization output generated in step 6.

[0658] Operation: The distribution server sends the generated recommended product list in JSON format to an endpoint and distributes it to the user's device via a REST API. The user's device receives this information and sends a push notification or displays it on the screen.

[0659] Output: Optimized output notification delivered to user terminal.

[0660] (Application example 2)

[0661] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0662] Today's consumers are becoming increasingly diverse and tend to demand products and services tailored to their individual needs. However, conventional systems have difficulty making optimal recommendations that take into account not only a user's purchasing history, behavioral history, and location information, but also their emotional state. This can lead to issues such as reduced user satisfaction and lost sales opportunities.

[0663] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data from users, means for saving and managing the personal data, means for normalizing and tagging the personal data, means for training a generative AI model using the normalized and tagged personal data, means for generating an optimized output from the trained generative AI model based on a user request, means for delivering the optimized output to a user terminal, means for collecting and analyzing user emotion data, and means for optimizing recommendations using the emotion data. This makes it possible to respond to the diverse needs of users and provide individually optimized product recommendations and services.

[0664] "Means of collecting personal data from users" refers to means of obtaining individual data such as users' purchase history, behavioral history, and location information via APIs or sensors.

[0665] "Personal data" refers to data that indicates individual preferences and patterns, such as user behavior, purchasing history, and location information.

[0666] "Means for storage and management" refers to the means for securely storing collected personal data and encrypting and controlling access to it.

[0667] "Normalization and tagging measures" are measures that convert collected personal data into a consistent format and assign relevant categories and keywords.

[0668] "Means for training a generative artificial intelligence model" means means for using normalized and tagged personal data to train an artificial intelligence model to learn individual data patterns and preferences.

[0669] The "means for generating optimized output" refers to a means for using a trained artificial intelligence model to provide optimal recommendations and information based on user requests.

[0670] The "means for delivering" refers to a means for transmitting the generated optimization output to the user's terminal and for notifying or displaying the output.

[0671] "Means for collecting and analyzing emotional data" refers to means for collecting and analyzing the emotional state of a user by analyzing the user's facial expressions, tone of voice, etc. using sensors or devices.

[0672] "Means for optimizing recommendations" refers to means for using collected and analyzed emotional data to recommend and provide products and services that are most suited to the user's emotional state.

[0673] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and an emotion engine. This system is constructed using the following hardware and software:

[0674] Hardware and software used

[0675] Hardware

[0676] 1. Server: The server that collects, stores, and manages personal data from users.

[0677] 2. Data management server: A server that encrypts and stores data and controls access.

[0678] 3. Data processing terminal: A terminal that normalizes and tags personal data.

[0679] 4. Learning server: A server that trains AI models.

[0680] 5. Application Server: The server that generates and delivers the optimized output.

[0681] 6. Distribution server: A server that distributes the generated output to user terminals.

[0682] 7. User terminal: The device that receives the output, such as a smartphone or PC.

[0683] 8. Emotion Sensor: A device (camera, microphone, heart rate sensor, etc.) that collects user emotional data.

[0684] software

[0685] 1. Generative AI model: A model that generates optimized output based on personal data and emotional data.

[0686] 2. Emotion Recognizer: Software that analyzes the user's emotions.

[0687] 3. Recommendation Engine: Software that generates optimized output based on data.

[0688] System configuration

[0689] 1. Collection of Personal Data:

[0690] The server collects personal data such as users' purchase history, behavioral history, and location information. This data is obtained from various web services and apps via APIs.

[0691] 2. Data Storage and Management:

[0692] The data management server encrypts and securely stores collected personal data, and also implements appropriate access control to ensure data security.

[0693] 3. Data normalization and tagging:

[0694] The data processing terminal normalizes the personal data into a consistent format and tags it with relevant categories and keywords, a process that ensures data consistency.

[0695] 4. Emotional Data Collection and Analysis:

[0696] Emotion sensors and emotion recognition software (EmotionRecognizer) collect and analyze emotional data from users' facial expressions, voice tones, and text input. This data is stored along with other personal data.

[0697] 5. Training the AI ​​model:

[0698] The learning server uses the normalized and tagged personal and emotional data to train a generative AI model that learns each user's data patterns and preferences to generate optimized outputs.

[0699] 6. Generating optimization outputs:

[0700] The trained generative AI model generates optimized outputs based on user requests on the application server, which recommend optimal products and services taking into account the user's current emotional state.

[0701] 7. Output Delivery:

[0702] The distribution server distributes the generated optimization output to the user's device, allowing the user to receive optimized information and suggestions on their device, such as a smartphone or PC.

[0703] Specific examples

[0704] For example, when a user approaches the beverage section of a physical store, a push notification will be sent with the most suitable drink or promotion based on the user's past purchase history (e.g., coffee, energy drinks) and their emotional state at that moment (e.g., relaxed). This allows for product recommendations that are optimized for each user.

[0705] Prompt Sentence Examples

[0706] An example prompt is:

[0707] User ID: example_user_id

[0708] Past purchase history: Coffee, energy drinks

[0709] Current behavior history: Entered the beverage section

[0710] Emotional state: Relaxed

[0711] Generate the recommended output.

[0712] In this way, the system of the present invention responds to the diverse needs of users and realizes individually optimized product recommendations and service provision.

[0713] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0714] Step 1:

[0715] The server collects personal data from users. Specifically, it obtains data such as purchase history, behavioral history, and location information from various web services and apps via APIs. A user ID is provided as input, and related data is collected based on that user ID. The output is a set of collected personal data.

[0716] Step 2:

[0717] The server transmits the collected personal data to the data management server, which securely stores and manages it. The data management server then encrypts the data and performs appropriate access control to ensure data security. The collected personal data is provided as input, and the encrypted and stored data is obtained as output.

[0718] Step 3:

[0719] The data processing terminal normalizes and tags the stored personal data by converting the data into a consistent format and assigning relevant categories and keywords. The input is the encrypted and stored personal data, and the output is the normalized and tagged data.

[0720] Step 4:

[0721] The server uses emotion sensors and emotion recognition software (EmotionRecognizer) to collect and analyze the user's emotion data. Specifically, it obtains emotion data by analyzing the user's facial expressions, voice tone, and text input obtained from the sensors. The input is the user's real-time behavior data, and the output is analyzed emotion data.

[0722] Step 5:

[0723] The learning server trains the generative AI model using normalized and tagged personal data and emotion data. Specifically, the AI ​​model learns each user's data patterns and preferences based on this data. Normalized and tagged personal data and emotion data are provided as input, and the trained AI model is obtained as output.

[0724] Step 6:

[0725] The application server uses the trained generative AI model to generate optimized output based on user requests. Specifically, it generates the most appropriate information, product recommendations, and service content based on the user's current emotional data and behavioral history. The trained AI model and real-time user data are provided as input, and the optimized output is obtained as output.

[0726] Step 7:

[0727] The distribution server distributes the optimized output to the user's device. Specifically, the generated output is sent to the user's device, such as a smartphone or PC, and displayed as a notification. The optimized output is provided as input, and the output is information, product recommendations, and service content displayed on the user's device.

[0728] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0729] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0730] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0731] [Third embodiment]

[0732] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0733] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0734] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0735] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0736] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0737] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0738] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0739] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0740] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0741] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0742] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0743] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0744] The present invention relates to a system that collects personal data from users and provides optimized outputs using generative AI models. The system is composed of the following subsystems and processes:

[0745] Collection of Personal Data

[0746] With the user's permission, the server collects personal data from various services. For example, data such as purchase history, behavioral history, and location information is obtained from e-commerce sites and location information services via API. This allows detailed data on the user's behavior and preferences to be collected.

[0747] Data storage and management

[0748] The data management server securely stores and manages the collected data. Data is encrypted and access controls are applied to protect data security and privacy. Stored data is properly indexed for quick access when needed.

[0749] Data normalization and tagging

[0750] The data processing terminal normalizes and tags the collected personal data. For example, it converts acquired purchase history data into a unified format and assigns relevant categories and keywords. This process ensures data consistency and makes subsequent processing easier.

[0751] Training a private AI model

[0752] The learning server uses the normalized and tagged personal data to train a generative AI model that learns each user's patterns and preferences and generates optimal output based on them. The model is continuously updated and retrained as new user data is added.

[0753] Generating optimization output

[0754] The application server accepts user requests and uses the trained generative AI model to generate optimized output, such as personalized product recommendations based on past purchase and behavioral history when a user searches for new products. This output is customized to the user's specific needs.

[0755] Output Delivery

[0756] The distribution server distributes the generated optimized output to the user's device, which can be a smartphone, PC, or other device that appropriately displays the distributed output and provides it to the user.

[0757] Specific examples

[0758] For example, if a user searches for a specific product on an e-commerce site, the data collection server collects information about the user's past purchase history, recently visited locations, etc. After this data is normalized and tagged, the learning server uses it to update and train the AI ​​model.

[0759] When the user searches for a product again, the application server uses the trained AI model to generate optimal product recommendations based on the user's preferences and past behavior. The generated recommendation information is sent to the user's smartphone by the distribution server, allowing the user to view and purchase product information optimized for them.

[0760] In this manner, the system of the present invention can provide an output that is optimized for each user, thereby maintaining a company's competitive advantage.

[0761] The processing flow will be explained below.

[0762] Step 1:

[0763] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, location information, etc. from various services (e.g., e-commerce sites, location information services) via API. This allows for detailed data on the user's behavior and preferences to be obtained.

[0764] Step 2:

[0765] The data management server securely stores and manages the collected personal data. The data management server encrypts the collected data and stores it with appropriate access control. This protects the security and privacy of the data while also ensuring that the data can be accessed quickly when needed.

[0766] Step 3:

[0767] The data processing terminal normalizes and tags the stored personal data. Specifically, the data processing terminal converts purchase history information into a unified format and assigns relevant categories and keywords. This process ensures data consistency and facilitates subsequent processing.

[0768] Step 4:

[0769] The learning server trains the generative AI model using normalized and tagged personal data. The learning server learns each user's data patterns and preferences and builds a model to generate optimal output based on them. This model is continuously updated and learns as new user data is added.

[0770] Step 5:

[0771] The application server accepts user requests and generates optimized output using the trained generative AI model. For example, if a user searches for a specific product, the application server provides optimized product recommendations based on past purchase history and behavioral history. This output is tailored to the user's specific needs.

[0772] Step 6:

[0773] The distribution server distributes the generated optimized output to the user's device. The distribution server sends the generated output in an appropriate format to the user's device, such as a smartphone or PC, for notification or display, allowing the user to receive optimized information and suggestions.

[0774] Step 7:

[0775] The user device displays the received output. The user device visually displays the received information, allowing the user to view and use optimized product information and suggestions. For example, the user can view a list of product recommendations optimized for them on their smartphone and can even purchase the products directly.

[0776] Through this series of steps, the system of the present invention provides optimized output for each user, enabling the company to maintain a competitive advantage.

[0777] Example 1

[0778] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0779] Conventional systems have struggled to generate personalized outputs that fully utilize users' personal data. They also face challenges in terms of data security, privacy protection, and continuous model updates. Furthermore, it has been difficult to create a system that can respond quickly and optimally to user requests.

[0780] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0781] In this invention, the server includes means for collecting personal data from a user, means for storing and managing the personal data, means for normalizing and tagging the personal data, means for training a generative artificial intelligence model using the normalized and tagged personal data, means for generating an optimized output from the trained generative artificial intelligence model based on a user request, means for delivering the optimized output to a user terminal, specific means for obtaining personal data through an API, encrypting and storing it, means for updating the generative artificial intelligence model based on past data, and specific means for processing requests input by the user.

[0782] This makes it possible to provide personalized output specific to each user, ensure data security and privacy, and continuously update models using the latest data, enabling quick and optimal responses to user requests.

[0783] "Personal data" refers to information related to a specific individual, such as a user's purchasing history, behavioral history, and location information.

[0784] "Acquisition through API" refers to the method of acquiring data from other services or systems via an application program interface (API).

[0785] "Encryption" is the process of transforming data using a specific algorithm into a format that cannot be easily deciphered by third parties.

[0786] "Normalization" means converting data into a consistent format and making it easier to process.

[0787] "Tagging" refers to assigning relevant categories and keywords to data to make it easier to search and classify.

[0788] A "generative artificial intelligence model" is a model that has been trained using machine learning or artificial intelligence algorithms to perform a specific task.

[0789] "Training" is the process of using collected data to teach an artificial intelligence model and improve its performance.

[0790] "Optimization output" refers to the recommendations and responses generated by an artificial intelligence model tailored to a user's individual needs.

[0791] A "server" is a computer system that provides services or processing power over a network.

[0792] A "user terminal" refers to a device such as a computer, smartphone, or tablet that is directly operated by a user.

[0793] A "user request" is a request or inquiry sent by a user to the system.

[0794] The present invention relates to a system that uses personal data collected from users to train a generative artificial intelligence model and generate optimized outputs based on user requests. A specific example of the system is described below.

[0795] This system mainly uses the following hardware and software. The hardware includes a data collection server, data management server, data processing terminal, learning server, application server, distribution server, and user terminal. The software uses APIs, encryption algorithms (e.g., AES-256), database software (e.g., MongoDB or PostgreSQL), and machine learning frameworks (e.g., PyTorch or TensorFlow).

[0796] First, the server collects personal data through API with the user's permission. The collected data includes purchase history, behavioral history, and location information. The collected data is encrypted by the server and stored on a data management server. This is to protect the security and privacy of the data.

[0797] The data processing terminal then normalizes the collected data and assigns tags to it. For example, it converts date and time data in different formats into a unified format and assigns categories such as "food" or "electronic devices" to purchase history data. This process ensures data consistency and makes subsequent processing easier.

[0798] The learning server uses the normalized and tagged data to train the generative artificial intelligence model. Specifically, it processes the data in batches and trains the model using a machine learning framework. Training is performed by adjusting hyperparameters such as the number of epochs and batch size. The model is continuously updated based on new data, so it is always possible to generate optimized outputs using the latest information.

[0799] The application server receives requests from users. For example, when a user sends a request to search for new products, the application server uses the trained generative artificial intelligence model to generate optimal product recommendations based on past purchase history and behavioral history.

[0800] The generated optimization output is sent to the user's device via the distribution server. The user's device is a device such as a smartphone or PC, which appropriately displays the distributed output and provides it to the user. For example, it may display recommendations for a new smartphone, allowing the user to view and purchase it.

[0801] For example, when a user searches for a new smartphone model on an e-commerce site, the server collects past purchase history and location information. This data is encrypted and stored on a data management server. A data processing terminal normalizes the data and assigns tags such as "electronic device" and "smartphone." The learning server then uses this data to train an AI model. When the user searches for a product again, the application server uses the model to generate optimal smartphone recommendations based on the user's preferences. This recommendation information is sent to the user's smartphone via a distribution server, allowing the user to view and purchase optimized product information on the screen.

[0802] An example of a prompt sentence to be input into a generative AI model is, "Based on past purchasing history, please suggest three smartphones that the user might be interested in."

[0803] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0804] Step 1:

[0805] Collecting personal data from users

[0806] The server collects the user's personal data through the API.

[0807] Input: User permission, API token

[0808] Processing: The server connects to the API of the e-commerce site or location information service to obtain data such as purchase history, behavioral history, and location information. This data is obtained in JSON format.

[0809] Output: Collected personal data (purchase history, behavioral history, location information, etc.)

[0810] Step 2:

[0811] Encryption and storage of personal data

[0812] The personal data collected by the server is encrypted and stored on a data management server.

[0813] Input: Collected personal data

[0814] Processing: The server encrypts the data using an encryption algorithm such as AES-256, then transfers the encrypted data to the data management server, where it is stored in a database (e.g., MongoDB or PostgreSQL).

[0815] Output: Encrypted personal data stored in a database

[0816] Step 3:

[0817] Normalizing and tagging personal data

[0818] The data processing terminal normalizes the collected and stored data and assigns the necessary tags.

[0819] Input: Encrypted personal data

[0820] Processing: The data processing terminal decodes the data and converts data in different formats into a unified format. For example, it unifies date and time data into ISO 8601 format. It also assigns category tags such as "food" and "electronic devices" to purchase history data.

[0821] Output: Normalized and tagged personal data

[0822] Step 4:

[0823] Training a generative AI model

[0824] The learning server uses the normalized and tagged data to train a generative AI model.

[0825] Input: Normalized and tagged personal data

[0826] Processing: The training server processes the data in batches and trains the model using a machine learning framework (such as PyTorch or TensorFlow). Hyperparameters such as the number of epochs and batch size are set and the model is trained multiple times.

[0827] Output: A trained generative AI model

[0828] Step 5:

[0829] Generating Optimization Output

[0830] The application server processes user requests and generates optimized outputs using the trained generative AI model.

[0831] Input: User request, trained generative AI model

[0832] Processing: The application server receives a request from the user. For example, when a user sends a request to search for new products, it generates personalized product recommendations based on their past purchase history and behavioral history.

[0833] Output: Optimized product recommendations

[0834] Step 6:

[0835] Delivering optimized output

[0836] A distribution server distributes the generated optimized output to the user terminal.

[0837] Input: Optimized product recommendations

[0838] Processing: The distribution server sends optimized recommendation information to the user's device, which can be a smartphone, PC, or other device.

[0839] Output: Optimized product recommendations displayed on the user's device

[0840] (Application example 1)

[0841] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0842] Traditional online shopping sites and similar services have struggled to fully utilize users' personal data to provide optimal product recommendations. This has limited the amount of useful information they can provide, and they have sought ways to improve user satisfaction. Furthermore, there has been a lack of effective methods for presenting special offers using location information in real time.

[0843] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0844] In this invention, the server includes means for collecting personal data from a user, means for storing and managing the personal data, means for normalizing and tagging the personal data, means for training a generative artificial intelligence model using the normalized and tagged personal data, means for generating an optimized output from the trained generative artificial intelligence model based on a user request, means for delivering the optimized output to a user terminal, means for recommending products based on the user's purchase history and browsing history, and means for presenting special offers using the user's location information. This enables personalized product recommendations that match the user's preferences and the presentation of special offers in real time, which is expected to improve the user experience.

[0845] "User" refers to an individual user of a particular system or service.

[0846] "Personal data" refers to information related to an individual, such as a user's purchase history, behavioral history, and location information.

[0847] "Purchase history" refers to products purchased by a user in the past and their detailed information.

[0848] "Behavioral history" refers to a record of a series of operations and activities performed by a user within the service.

[0849] "Location information" refers to data regarding a user's current or past location.

[0850] "Storage and management measures" refers to the mechanisms for safely storing personal data and for accessing and managing it as necessary.

[0851] "Normalization and tagging measures" refers to the process by which collected personal data is converted into a standard format and assigned relevant keywords and categories.

[0852] "Means for training a generative AI model" refers to the process of using normalized personal data to build and train a generative AI model to learn patterns that are unique to each user.

[0853] "Means for generating optimized outputs based on user requests" refers to a process for using a trained generative AI model to output optimal results in response to user inputs or requests.

[0854] "User terminal" refers to a device such as a smartphone or PC used by a user.

[0855] "Means for delivering" refers to a method for transferring the generated output to a user terminal and displaying it.

[0856] "Means for recommending products" refers to a system that selects and suggests products suitable for users based on personal data.

[0857] "Means for presenting special offers" refers to methods that utilize location information to provide advantageous proposals or coupons to users at specific locations or times.

[0858] The present invention is a system that collects personal data of users and uses a generative AI model to provide optimized output. Specific embodiments of the system are described in detail below.

[0859] Hardware and Software Configuration

[0860] The main hardware components of this system include servers and user terminals (smartphones, PCs, etc.). The roles of each component are as follows:

[0861] server:

[0862] Data collection server: Collects personal data such as user purchase history, behavioral history, and location information from various services via API.

[0863] Data Management Server: Securely stores and manages collected personal data, applying encryption and access controls.

[0864] Data processing server: Normalizes collected personal data and assigns tags such as categories and keywords.

[0865] Learning Server: Uses normalized and tagged data to train generative AI models to learn individual user patterns and preferences.

[0866] Application Server: Uses trained generative AI models to generate optimized outputs based on user requests.

[0867] Distribution server: distributes the generated output to user devices.

[0868] User device:

[0869] The system application is installed on the device that the user normally uses, such as a smartphone or PC, and displays the generated output.

[0870] Description of the main process

[0871] 1. Collection of Personal Data:

[0872] The server collects personal data such as the user's purchase history, behavioral history, and location information from various services with the user's permission. This data collection is done via API.

[0873] 2. Data Storage and Management:

[0874] The data management server encrypts and securely stores collected personal data, and data security is ensured through access control.

[0875] 3. Data normalization and tagging:

[0876] The data processing server converts the collected personal data into a unified format and maintains data consistency by assigning relevant categories and keywords.

[0877] 4. Training the generative AI model:

[0878] The learning server uses the normalized and tagged data to train a generative AI model, which learns individual user patterns and preferences and is continuously updated.

[0879] 5. Generating optimization outputs:

[0880] The application server accepts user requests and generates optimized outputs using a trained generative AI model.

[0881] 6. Output Delivery:

[0882] The distribution server distributes the generated optimized output to the user terminal, which then appropriately displays the distributed output and provides it to the user.

[0883] Specific examples

[0884] For example, if a user searches for a specific product on an e-commerce site, the following prompt sentences can be used to generate optimized product recommendations:

[0885] Example prompt sentence:

[0886] Please list 5 recommended products based on the user's purchase history. <User ID: 12345>

[0887] By inputting this prompt into a generative AI model, the system can recommend the best products for the user. If the user provides specific location information, special offers related to that location can also be presented. For example, if the user is near a specific electronics retailer, they will be notified of special offers and coupons.

[0888] In this way, the system of the present invention uses the user's personal data to provide personalized and optimized output, which is expected to improve the user experience.

[0889] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0890] Step 1: Collecting personal data

[0891] The server collects personal data such as the user's purchase history, behavioral history, and location information from various services via API. Specifically, it obtains purchase history from the e-commerce site and the user's current location and visit history from the location information service. The input is the user's authentication information and API request, and the output is the collected personal data. The server temporarily stores this data.

[0892] Step 2: Store and manage your data

[0893] The server encrypts the collected personal data and stores it securely in a database. Access control is also applied during the storage process. The input is the personal data collected in step 1, and the output is the securely stored personal data.

[0894] Step 3: Normalize and tag the data

[0895] The data processing server converts the collected personal data into a unified format and assigns relevant categories and keywords, ensuring data consistency and facilitating subsequent processing. The input is the stored personal data, and the output is the normalized and tagged data.

[0896] Step 4: Training the generative AI model

[0897] The learning server uses the normalized and tagged data to train the generative AI model. The training process learns each user's patterns and preferences. The input is the normalized and tagged personal data, and the output is the trained generative AI model.

[0898] Step 5: Generate optimization output

[0899] The application server accepts user requests and generates optimized outputs using the trained generative AI model. For example, if a user searches for a specific product, it generates product recommendations based on the user's purchase history and behavioral history. The input is the user request and the trained AI model, and the output is optimized product recommendations.

[0900] Step 6: Delivering the output

[0901] The distribution server distributes the generated optimized output to the user's device. The distribution process involves real-time notifications and display of the optimized output on the user's smartphone or PC. The input is the optimized output, and the output is product recommendations and special offers displayed on the user's device.

[0902] This series of steps results in personalized product recommendations and special offers that enhance the user experience.

[0903] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0904] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and emotion engine. The system is composed of the following multiple subsystems and processes:

[0905] Collection of Personal Data

[0906] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, location information, etc. from various services (e.g., e-commerce sites, location-based services) via API. This data provides detailed information about the user's behavior and preferences.

[0907] Data storage and management

[0908] The data management server securely stores and manages the collected personal data. The data management server encrypts the collected data and stores it with appropriate access control. This ensures the security and privacy of the data while allowing it to be accessed quickly when needed.

[0909] Data normalization and tagging

[0910] The data processing terminal normalizes and tags the stored personal data. For example, this includes converting collected purchase history information into a consistent format and tagging it with relevant categories and keywords. This process ensures data consistency and makes subsequent processing easier.

[0911] Collecting Emotional Data

[0912] The emotion engine collects the user's emotional data. The emotion engine uses sensors and devices to analyze emotions from the user's facial expressions, voice tone, and text input. This data is also stored and managed along with other personal data.

[0913] Training a private AI model

[0914] The learning server uses the normalized and tagged personal and emotional data to train a generative AI model. This AI model learns each user's data patterns and preferences to generate optimal output. The model is continuously updated and retrained as new user data is added.

[0915] Generating optimization output

[0916] The application server accepts user requests and integrates the trained generative AI model with emotional data to generate optimized output. For example, if a user searches for a specific product, it provides optimized product recommendations based on past purchase history, behavioral history, and current emotional state. This output is tailored to the user's specific needs and emotional state.

[0917] Output Delivery

[0918] The distribution server distributes the generated optimized output to the user's device. The distribution server sends the generated output in an appropriate format to the user's device, such as a smartphone or PC, for notification or display, allowing the user to receive optimized information and suggestions.

[0919] Specific examples

[0920] For example, when a user searches for a specific product on an e-commerce site, the system works as follows: The data collection server collects information about the user's past purchase history, behavioral history, and recently visited places, and the emotion engine analyzes the user's current emotional state (e.g., stress level and satisfaction). This data is normalized and tagged.

[0921] The learning server uses this data to train the AI ​​model, and when the user searches for a product again, the application server generates optimized product recommendations based on the trained model and emotion data. The generated recommendation information is sent to the user's smartphone by the distribution server, allowing the user to view and purchase product information optimized for them.

[0922] In this way, the system of the present invention can provide an output optimized for each user, thereby maintaining a competitive advantage for the company. By providing a more refined output based on the user's emotions, it becomes possible to provide information that is optimal for a specific situation or timing.

[0923] The processing flow will be explained below.

[0924] Step 1:

[0925] With the user's permission, the server collects personal data. Specifically, the server obtains data such as the user's purchase history, behavioral history, and location information from various services (e.g., e-commerce sites, location-based services) via API. This allows for detailed data on the user's behavior and preferences to be obtained.

[0926] Step 2:

[0927] The data management server encrypts the collected personal data and stores it in a secure database. The data has appropriate access controls to protect privacy. This step ensures that the data is stored securely and can be retrieved when needed.

[0928] Step 3:

[0929] The data processing terminal normalizes the stored personal data and assigns categories and keywords. For example, purchase history data is converted into a unified format and tagged with "home appliances" or "books." This process maintains data consistency and makes it easier to use in subsequent processes.

[0930] Step 4:

[0931] The emotion engine collects the user's emotional data. The emotion engine analyzes the user's facial expressions, voice tone, and text input to collect data to identify the user's emotional state (e.g., "joy," "sadness," "stress") using cameras, microphones, and sensors.

[0932] Step 5:

[0933] The data management server also encrypts the emotion data collected from the emotion engine and stores it in a secure database, ensuring that emotion data is stored securely in the same way as personal data.

[0934] Step 6:

[0935] The learning server trains the generative AI model using normalized and tagged personal and emotional data. The learning server learns each user's patterns and preferences and builds a model to generate optimized outputs. The model is retrained each time new user data is added.

[0936] Step 7:

[0937] The application server receives requests from users. For example, when a user searches for a specific product, the application server generates optimized product recommendations based on past purchase history, behavioral history, and emotional data. The recommendations take into account the user's current emotional state.

[0938] Step 8:

[0939] The distribution server distributes the generated optimized output to the user's device. The output is distributed in an appropriate format and sent to the user's smartphone, PC, etc.

[0940] Step 9:

[0941] The user device displays the received output. The user device visually displays the optimized information and suggestions, allowing the user to use and view the information. For example, the user can check the product recommendation list optimized for them on their smartphone and purchase the product immediately.

[0942] Through this series of steps, the system of the present invention provides optimized output that is personalized for each user and based on their emotional state, allowing companies to maintain a competitive advantage.

[0943] Example 2

[0944] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0945] Conventional systems only provide output based on user behavioral and purchasing data, making it difficult to generate optimal output that takes the user's emotional state into account. Furthermore, they often lack the ability to uniformly handle data in different formats and provide insufficient security management. Therefore, there is a need for a system that can provide more precise and personalized output.

[0946] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data from a user, means for saving and managing the personal data, means for normalizing and tagging the personal data, means for collecting and analyzing emotion data, means for training a generative AI model using the normalized and tagged personal data and emotion data, means for generating an optimized output using the trained generative AI model and emotion data based on a user request, and means for delivering the optimized output to a user terminal. This makes it possible to quickly and safely provide more personalized and sophisticated output based on the user's behavioral data and emotion data.

[0947] "User" refers to an individual or corporation that uses the system.

[0948] "Personal data" refers to data that includes information about a user's specific behavior or preferences, such as purchase history, behavior history, and location information.

[0949] "Means of collection" refers to the ability to obtain data through interfaces such as APIs.

[0950] "Means of storage and management" refers to the ability to securely store and properly manage data using encryption and access control.

[0951] "Means for normalization and tagging" refers to the function of converting data of different formats into a unified format and assigning tags such as categories and keywords.

[0952] "Emotion data" refers to data that indicates the user's emotional state, such as information extracted from facial expressions, voice tones, and character input.

[0953] "Means for collecting and analyzing emotional data" refers to the function of detecting and analyzing the user's emotions using sensors or devices.

[0954] A "generative artificial intelligence model" refers to a model that uses machine learning techniques to learn user data patterns and preferences.

[0955] "Training" refers to the process of using collected data to train a generative artificial intelligence model.

[0956] "Optimized Output" refers to personalized results generated based on a generative artificial intelligence model and emotional data in response to a user's request.

[0957] "User request" refers to a search or information request made by a user to the system.

[0958] "Means for delivering" refers to the function of transferring and notifying the generated output to the user terminal.

[0959] "User terminal" refers to a device used by a user to access the system, such as a smartphone or PC.

[0960] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and emotion engine. This system is composed of multiple subsystems and processes as described below.

[0961] Collection of Personal Data

[0962] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, and location information from various services via API. This data provides detailed information about the user's behavior and preferences. For example, the server sends a request to an e-commerce site's API to obtain the user's purchase history data.

[0963] Data storage and management

[0964] The data management server securely stores and manages the collected personal data. The data management server encrypts the data using an encryption library (e.g., AES-256) and stores it in a database (e.g., MySQL). It also performs appropriate access control using a user authentication function (e.g., JWT token).

[0965] Data normalization and tagging

[0966] The data processing device normalizes and tags the stored personal data. For example, it unifies purchase history recorded in different formats and assigns relevant categories and keywords. This process uses a text classification algorithm (e.g., TF-IDF or Word2Vec).

[0967] Collecting Emotional Data

[0968] The emotion engine collects user emotional data. Using sensors and devices, emotions are analyzed from the user's facial expressions, voice tone, and text input. For example, a facial recognition camera captures the user's facial expressions and analyzes them with an emotion recognition algorithm (e.g., OpenFace). Voice tone is analyzed using a voice feature extraction algorithm (e.g., Librosa).

[0969] Training a private AI model

[0970] The learning server trains a generative AI model using the normalized and tagged personal and emotional data. This process uses machine learning libraries (e.g., TensorFlow and PyTorch). The trained model learns each user's data patterns and preferences and is retrained each time new data is added.

[0971] Generating optimization output

[0972] The application server accepts requests from users and generates optimized outputs by integrating the trained generative AI model with emotional data. For example, if a user searches for a specific product, it provides optimized product recommendations taking into account their past purchase history, behavioral history, and current emotional state. As a concrete example, the prompt sentence to be input to the generative AI model is shown below.

[0973] Example prompt sentence:

[0974] "Provide optimal product recommendations that match the user's recent searches and take into account his past purchase history and current emotional state."

[0975] Output Delivery

[0976] The distribution server distributes the generated optimized output to the user's device. The distribution server then sends the generated output in an appropriate format to the user's smartphone or PC for notification or display, allowing the user to receive optimized information and suggestions.

[0977] In this way, the system of the present invention can provide refined output for each user, enabling more personalized services, which helps companies maintain their competitive advantage and enables users to receive optimal information tailored to their specific situation and timing.

[0978] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0979] Step 1: Collecting personal data

[0980] With the user's permission, the server collects personal data, including purchase history, behavioral history, and location information.

[0981] Input: Data API endpoints from various services (e.g., e-commerce sites, location services).

[0982] How it works: The server sends a request to the API and gets back data in JSON format. For example, it accesses the endpoint "https: / / api.ecommerce.com / history?userid=12345".

[0983] Output: Purchase history and behavioral history data in JSON format.

[0984] Step 2: Store and manage your data

[0985] The data management server stores and manages the collected personal data, a process that includes data encryption and access control.

[0986] Input: Personal data collected in step 1.

[0987] Operation: The data management server encrypts the data using an encryption library (e.g., AES-256) and stores it in a database (e.g., MySQL). It also implements access control using user authentication functions (e.g., JWT tokens).

[0988] Output: Encrypted data stored securely in a database.

[0989] Step 3: Normalize and tag the data

[0990] The data processing terminal normalizes the stored personal data and assigns relevant categories and keywords.

[0991] Input: The encrypted data stored in step 2.

[0992] How it works: The data processing terminal runs a script that converts the data into a consistent format, for example standardizing different date formats to "YYYY-MM-DD" and tagging it using a text classification algorithm (e.g. TF-IDF or Word2Vec).

[0993] Output: Normalized and tagged data.

[0994] Step 4: Collecting emotion data

[0995] The emotion engine collects user emotional data by analyzing the user's facial expressions, tone of voice, and text input using sensors and devices.

[0996] Input: User's facial expression data, voice data, and text input data.

[0997] How it works: The emotion engine uses a facial recognition camera or microphone to analyze emotion data using facial expression recognition algorithms (e.g., OpenFace) and voice feature extraction algorithms (e.g., Librosa).

[0998] Output: Data indicating the user's emotional state.

[0999] Step 5: Train a private AI model

[1000] The learning server trains the generative AI model using normalized and tagged personal data and emotion data.

[1001] Input: Normalized and tagged data from step 3, sentiment data from step 4.

[1002] How it works: The learning server uses machine learning libraries (e.g., TensorFlow or PyTorch) to train generative AI models (e.g., Transformer models).

[1003] Output: A trained generative AI model.

[1004] Step 6: Generate optimization output

[1005] The application server accepts requests from users and integrates the trained generative AI model with emotion data to generate optimized outputs.

[1006] Input: User request, trained generative AI model, current emotion data.

[1007] How it works: The application server inputs prompt statements into the generative AI model and executes requests such as, "Please provide optimal product recommendations that match the user's recent search results, taking into account his past purchase history and current emotional state."

[1008] Output: An optimized product recommendation list.

[1009] Step 7: Delivering the output

[1010] A distribution server distributes the generated optimized output to the user terminal.

[1011] Input: The optimization output generated in step 6.

[1012] Operation: The distribution server sends the generated recommended product list in JSON format to an endpoint and distributes it to the user's device via a REST API. The user's device receives this information and sends a push notification or displays it on the screen.

[1013] Output: Optimized output notification delivered to user terminal.

[1014] (Application example 2)

[1015] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1016] Today's consumers are becoming increasingly diverse and tend to demand products and services tailored to their individual needs. However, conventional systems have difficulty making optimal recommendations that take into account not only a user's purchasing history, behavioral history, and location information, but also their emotional state. This can lead to issues such as reduced user satisfaction and lost sales opportunities.

[1017] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data from users, means for saving and managing the personal data, means for normalizing and tagging the personal data, means for training a generative AI model using the normalized and tagged personal data, means for generating an optimized output from the trained generative AI model based on a user request, means for delivering the optimized output to a user terminal, means for collecting and analyzing user emotion data, and means for optimizing recommendations using the emotion data. This makes it possible to respond to the diverse needs of users and provide individually optimized product recommendations and services.

[1018] "Means of collecting personal data from users" refers to means of obtaining individual data such as users' purchase history, behavioral history, and location information via APIs or sensors.

[1019] "Personal data" refers to data that indicates individual preferences and patterns, such as user behavior, purchasing history, and location information.

[1020] "Means for storage and management" refers to the means for securely storing collected personal data and encrypting and controlling access to it.

[1021] "Normalization and tagging measures" are measures that convert collected personal data into a consistent format and assign relevant categories and keywords.

[1022] "Means for training a generative artificial intelligence model" means means for using normalized and tagged personal data to train an artificial intelligence model to learn individual data patterns and preferences.

[1023] The "means for generating optimized output" refers to a means for using a trained artificial intelligence model to provide optimal recommendations and information based on user requests.

[1024] The "means for delivering" refers to a means for transmitting the generated optimization output to the user's terminal and for notifying or displaying the output.

[1025] "Means for collecting and analyzing emotional data" refers to means for collecting and analyzing the emotional state of a user by analyzing the user's facial expressions, tone of voice, etc. using sensors or devices.

[1026] "Means for optimizing recommendations" refers to means for using collected and analyzed emotional data to recommend and provide products and services that are most suited to the user's emotional state.

[1027] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and an emotion engine. This system is constructed using the following hardware and software:

[1028] Hardware and software used

[1029] Hardware

[1030] 1. Server: The server that collects, stores, and manages personal data from users.

[1031] 2. Data management server: A server that encrypts and stores data and controls access.

[1032] 3. Data processing terminal: A terminal that normalizes and tags personal data.

[1033] 4. Learning server: A server that trains AI models.

[1034] 5. Application Server: The server that generates and delivers the optimized output.

[1035] 6. Distribution server: A server that distributes the generated output to user terminals.

[1036] 7. User terminal: The device that receives the output, such as a smartphone or PC.

[1037] 8. Emotion Sensor: A device (camera, microphone, heart rate sensor, etc.) that collects user emotional data.

[1038] software

[1039] 1. Generative AI model: A model that generates optimized output based on personal data and emotional data.

[1040] 2. Emotion Recognizer: Software that analyzes the user's emotions.

[1041] 3. Recommendation Engine: Software that generates optimized output based on data.

[1042] System configuration

[1043] 1. Collection of Personal Data:

[1044] The server collects personal data such as users' purchase history, behavioral history, and location information. This data is obtained from various web services and apps via APIs.

[1045] 2. Data Storage and Management:

[1046] The data management server encrypts and securely stores collected personal data, and also implements appropriate access control to ensure data security.

[1047] 3. Data normalization and tagging:

[1048] The data processing terminal normalizes the personal data into a consistent format and tags it with relevant categories and keywords, a process that ensures data consistency.

[1049] 4. Emotional Data Collection and Analysis:

[1050] Emotion sensors and emotion recognition software (EmotionRecognizer) collect and analyze emotional data from users' facial expressions, voice tones, and text input. This data is stored along with other personal data.

[1051] 5. Training the AI ​​model:

[1052] The learning server uses the normalized and tagged personal and emotional data to train a generative AI model that learns each user's data patterns and preferences to generate optimized outputs.

[1053] 6. Generating optimization outputs:

[1054] The trained generative AI model generates optimized outputs based on user requests on the application server, which recommend optimal products and services taking into account the user's current emotional state.

[1055] 7. Output Delivery:

[1056] The distribution server distributes the generated optimization output to the user's device, allowing the user to receive optimized information and suggestions on their device, such as a smartphone or PC.

[1057] Specific examples

[1058] For example, when a user approaches the beverage section of a physical store, a push notification will be sent with the most suitable drink or promotion based on the user's past purchase history (e.g., coffee, energy drinks) and their emotional state at that moment (e.g., relaxed). This allows for product recommendations that are optimized for each user.

[1059] Prompt Sentence Examples

[1060] An example prompt is:

[1061] User ID: example_user_id

[1062] Past purchase history: Coffee, energy drinks

[1063] Current behavior history: Entered the beverage section

[1064] Emotional state: Relaxed

[1065] Generate the recommended output.

[1066] In this way, the system of the present invention responds to the diverse needs of users and realizes individually optimized product recommendations and service provision.

[1067] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1068] Step 1:

[1069] The server collects personal data from users. Specifically, it obtains data such as purchase history, behavioral history, and location information from various web services and apps via APIs. A user ID is provided as input, and related data is collected based on that user ID. The output is a set of collected personal data.

[1070] Step 2:

[1071] The server transmits the collected personal data to the data management server, which securely stores and manages it. The data management server then encrypts the data and performs appropriate access control to ensure data security. The collected personal data is provided as input, and the encrypted and stored data is obtained as output.

[1072] Step 3:

[1073] The data processing terminal normalizes and tags the stored personal data by converting the data into a consistent format and assigning relevant categories and keywords. The input is the encrypted and stored personal data, and the output is the normalized and tagged data.

[1074] Step 4:

[1075] The server uses emotion sensors and emotion recognition software (EmotionRecognizer) to collect and analyze the user's emotion data. Specifically, it obtains emotion data by analyzing the user's facial expressions, voice tone, and text input obtained from the sensors. The input is the user's real-time behavior data, and the output is analyzed emotion data.

[1076] Step 5:

[1077] The learning server trains the generative AI model using normalized and tagged personal data and emotion data. Specifically, the AI ​​model learns each user's data patterns and preferences based on this data. Normalized and tagged personal data and emotion data are provided as input, and the trained AI model is obtained as output.

[1078] Step 6:

[1079] The application server uses the trained generative AI model to generate optimized output based on user requests. Specifically, it generates the most appropriate information, product recommendations, and service content based on the user's current emotional data and behavioral history. The trained AI model and real-time user data are provided as input, and the optimized output is obtained as output.

[1080] Step 7:

[1081] The distribution server distributes the optimized output to the user's device. Specifically, the generated output is sent to the user's device, such as a smartphone or PC, and displayed as a notification. The optimized output is provided as input, and the output is information, product recommendations, and service content displayed on the user's device.

[1082] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1083] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1084] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1085] [Fourth embodiment]

[1086] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1087] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1089] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1090] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1093] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1094] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1095] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1096] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1097] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1098] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1099] The present invention relates to a system that collects personal data from users and provides optimized outputs using generative AI models. The system is composed of the following subsystems and processes:

[1100] Collection of Personal Data

[1101] With the user's permission, the server collects personal data from various services. For example, data such as purchase history, behavioral history, and location information is obtained from e-commerce sites and location information services via API. This allows detailed data on the user's behavior and preferences to be collected.

[1102] Data storage and management

[1103] The data management server securely stores and manages the collected data. Data is encrypted and access controls are applied to protect data security and privacy. Stored data is properly indexed for quick access when needed.

[1104] Data normalization and tagging

[1105] The data processing terminal normalizes and tags the collected personal data. For example, it converts acquired purchase history data into a unified format and assigns relevant categories and keywords. This process ensures data consistency and makes subsequent processing easier.

[1106] Training a private AI model

[1107] The learning server uses the normalized and tagged personal data to train a generative AI model that learns each user's patterns and preferences and generates optimal output based on them. The model is continuously updated and retrained as new user data is added.

[1108] Generating optimization output

[1109] The application server accepts user requests and uses the trained generative AI model to generate optimized output, such as personalized product recommendations based on past purchase and behavioral history when a user searches for new products. This output is customized to the user's specific needs.

[1110] Output Delivery

[1111] The distribution server distributes the generated optimized output to the user's device, which can be a smartphone, PC, or other device that appropriately displays the distributed output and provides it to the user.

[1112] Specific examples

[1113] For example, if a user searches for a specific product on an e-commerce site, the data collection server collects information about the user's past purchase history, recently visited locations, etc. After this data is normalized and tagged, the learning server uses it to update and train the AI ​​model.

[1114] When the user searches for a product again, the application server uses the trained AI model to generate optimal product recommendations based on the user's preferences and past behavior. The generated recommendation information is sent to the user's smartphone by the distribution server, allowing the user to view and purchase product information optimized for them.

[1115] In this manner, the system of the present invention can provide an output that is optimized for each user, thereby maintaining a company's competitive advantage.

[1116] The processing flow will be explained below.

[1117] Step 1:

[1118] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, location information, etc. from various services (e.g., e-commerce sites, location information services) via API. This allows for detailed data on the user's behavior and preferences to be obtained.

[1119] Step 2:

[1120] The data management server securely stores and manages the collected personal data. The data management server encrypts the collected data and stores it with appropriate access control. This protects the security and privacy of the data while also ensuring that the data can be accessed quickly when needed.

[1121] Step 3:

[1122] The data processing terminal normalizes and tags the stored personal data. Specifically, the data processing terminal converts purchase history information into a unified format and assigns relevant categories and keywords. This process ensures data consistency and facilitates subsequent processing.

[1123] Step 4:

[1124] The learning server trains the generative AI model using normalized and tagged personal data. The learning server learns each user's data patterns and preferences and builds a model to generate optimal output based on them. This model is continuously updated and learns as new user data is added.

[1125] Step 5:

[1126] The application server accepts user requests and generates optimized output using the trained generative AI model. For example, if a user searches for a specific product, the application server provides optimized product recommendations based on past purchase history and behavioral history. This output is tailored to the user's specific needs.

[1127] Step 6:

[1128] The distribution server distributes the generated optimized output to the user's device. The distribution server sends the generated output in an appropriate format to the user's device, such as a smartphone or PC, for notification or display, allowing the user to receive optimized information and suggestions.

[1129] Step 7:

[1130] The user device displays the received output. The user device visually displays the received information, allowing the user to view and use optimized product information and suggestions. For example, the user can view a list of product recommendations optimized for them on their smartphone and can even purchase the products directly.

[1131] Through this series of steps, the system of the present invention provides optimized output for each user, enabling the company to maintain a competitive advantage.

[1132] Example 1

[1133] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1134] Conventional systems have struggled to generate personalized outputs that fully utilize users' personal data. They also face challenges in terms of data security, privacy protection, and continuous model updates. Furthermore, it has been difficult to create a system that can respond quickly and optimally to user requests.

[1135] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1136] In this invention, the server includes means for collecting personal data from a user, means for storing and managing the personal data, means for normalizing and tagging the personal data, means for training a generative artificial intelligence model using the normalized and tagged personal data, means for generating an optimized output from the trained generative artificial intelligence model based on a user request, means for delivering the optimized output to a user terminal, specific means for obtaining personal data through an API, encrypting and storing it, means for updating the generative artificial intelligence model based on past data, and specific means for processing requests input by the user.

[1137] This makes it possible to provide personalized output specific to each user, ensure data security and privacy, and continuously update models using the latest data, enabling quick and optimal responses to user requests.

[1138] "Personal data" refers to information related to a specific individual, such as a user's purchasing history, behavioral history, and location information.

[1139] "Acquisition through API" refers to the method of acquiring data from other services or systems via an application program interface (API).

[1140] "Encryption" is the process of transforming data using a specific algorithm into a format that cannot be easily deciphered by third parties.

[1141] "Normalization" means converting data into a consistent format and making it easier to process.

[1142] "Tagging" refers to assigning relevant categories and keywords to data to make it easier to search and classify.

[1143] A "generative artificial intelligence model" is a model that has been trained using machine learning or artificial intelligence algorithms to perform a specific task.

[1144] "Training" is the process of using collected data to teach an artificial intelligence model and improve its performance.

[1145] "Optimization output" refers to the recommendations and responses generated by an artificial intelligence model tailored to a user's individual needs.

[1146] A "server" is a computer system that provides services or processing power over a network.

[1147] A "user terminal" refers to a device such as a computer, smartphone, or tablet that is directly operated by a user.

[1148] A "user request" is a request or inquiry sent by a user to the system.

[1149] The present invention relates to a system that uses personal data collected from users to train a generative artificial intelligence model and generate optimized outputs based on user requests. A specific example of the system is described below.

[1150] This system mainly uses the following hardware and software. The hardware includes a data collection server, data management server, data processing terminal, learning server, application server, distribution server, and user terminal. The software uses APIs, encryption algorithms (e.g., AES-256), database software (e.g., MongoDB or PostgreSQL), and machine learning frameworks (e.g., PyTorch or TensorFlow).

[1151] First, the server collects personal data through API with the user's permission. The collected data includes purchase history, behavioral history, and location information. The collected data is encrypted by the server and stored on a data management server. This is to protect the security and privacy of the data.

[1152] The data processing terminal then normalizes the collected data and assigns tags to it. For example, it converts date and time data in different formats into a unified format and assigns categories such as "food" or "electronic devices" to purchase history data. This process ensures data consistency and makes subsequent processing easier.

[1153] The learning server uses the normalized and tagged data to train the generative artificial intelligence model. Specifically, it processes the data in batches and trains the model using a machine learning framework. Training is performed by adjusting hyperparameters such as the number of epochs and batch size. The model is continuously updated based on new data, so it is always possible to generate optimized outputs using the latest information.

[1154] The application server receives requests from users. For example, when a user sends a request to search for new products, the application server uses the trained generative artificial intelligence model to generate optimal product recommendations based on past purchase history and behavioral history.

[1155] The generated optimization output is sent to the user's device via the distribution server. The user's device is a device such as a smartphone or PC, which appropriately displays the distributed output and provides it to the user. For example, it may display recommendations for a new smartphone, allowing the user to view and purchase it.

[1156] For example, when a user searches for a new smartphone model on an e-commerce site, the server collects past purchase history and location information. This data is encrypted and stored on a data management server. A data processing terminal normalizes the data and assigns tags such as "electronic device" and "smartphone." The learning server then uses this data to train an AI model. When the user searches for a product again, the application server uses the model to generate optimal smartphone recommendations based on the user's preferences. This recommendation information is sent to the user's smartphone via a distribution server, allowing the user to view and purchase optimized product information on the screen.

[1157] An example of a prompt sentence to be input into a generative AI model is, "Based on past purchasing history, please suggest three smartphones that the user might be interested in."

[1158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1159] Step 1:

[1160] Collecting personal data from users

[1161] The server collects the user's personal data through the API.

[1162] Input: User permission, API token

[1163] Processing: The server connects to the API of the e-commerce site or location information service to obtain data such as purchase history, behavioral history, and location information. This data is obtained in JSON format.

[1164] Output: Collected personal data (purchase history, behavioral history, location information, etc.)

[1165] Step 2:

[1166] Encryption and storage of personal data

[1167] The personal data collected by the server is encrypted and stored on a data management server.

[1168] Input: Collected personal data

[1169] Processing: The server encrypts the data using an encryption algorithm such as AES-256, then transfers the encrypted data to the data management server, where it is stored in a database (e.g., MongoDB or PostgreSQL).

[1170] Output: Encrypted personal data stored in a database

[1171] Step 3:

[1172] Normalizing and tagging personal data

[1173] The data processing terminal normalizes the collected and stored data and assigns the necessary tags.

[1174] Input: Encrypted personal data

[1175] Processing: The data processing terminal decodes the data and converts data in different formats into a unified format. For example, it unifies date and time data into ISO 8601 format. It also assigns category tags such as "food" and "electronic devices" to purchase history data.

[1176] Output: Normalized and tagged personal data

[1177] Step 4:

[1178] Training a generative AI model

[1179] The learning server uses the normalized and tagged data to train a generative AI model.

[1180] Input: Normalized and tagged personal data

[1181] Processing: The training server processes the data in batches and trains the model using a machine learning framework (such as PyTorch or TensorFlow). Hyperparameters such as the number of epochs and batch size are set and the model is trained multiple times.

[1182] Output: A trained generative AI model

[1183] Step 5:

[1184] Generating Optimization Output

[1185] The application server processes user requests and generates optimized outputs using the trained generative AI model.

[1186] Input: User request, trained generative AI model

[1187] Processing: The application server receives a request from the user. For example, when a user sends a request to search for new products, it generates personalized product recommendations based on their past purchase history and behavioral history.

[1188] Output: Optimized product recommendations

[1189] Step 6:

[1190] Delivering optimized output

[1191] A distribution server distributes the generated optimized output to the user terminal.

[1192] Input: Optimized product recommendations

[1193] Processing: The distribution server sends optimized recommendation information to the user's device, which can be a smartphone, PC, or other device.

[1194] Output: Optimized product recommendations displayed on the user's device

[1195] (Application example 1)

[1196] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1197] Traditional online shopping sites and similar services have struggled to fully utilize users' personal data to provide optimal product recommendations. This has limited the amount of useful information they can provide, and they have sought ways to improve user satisfaction. Furthermore, there has been a lack of effective methods for presenting special offers using location information in real time.

[1198] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1199] In this invention, the server includes means for collecting personal data from a user, means for storing and managing the personal data, means for normalizing and tagging the personal data, means for training a generative artificial intelligence model using the normalized and tagged personal data, means for generating an optimized output from the trained generative artificial intelligence model based on a user request, means for delivering the optimized output to a user terminal, means for recommending products based on the user's purchase history and browsing history, and means for presenting special offers using the user's location information. This enables personalized product recommendations that match the user's preferences and the presentation of special offers in real time, which is expected to improve the user experience.

[1200] "User" refers to an individual user of a particular system or service.

[1201] "Personal data" refers to information related to an individual, such as a user's purchase history, behavioral history, and location information.

[1202] "Purchase history" refers to products purchased by a user in the past and their detailed information.

[1203] "Behavioral history" refers to a record of a series of operations and activities performed by a user within the service.

[1204] "Location information" refers to data regarding a user's current or past location.

[1205] "Storage and management measures" refers to the mechanisms for safely storing personal data and for accessing and managing it as necessary.

[1206] "Normalization and tagging measures" refers to the process by which collected personal data is converted into a standard format and assigned relevant keywords and categories.

[1207] "Means for training a generative AI model" refers to the process of using normalized personal data to build and train a generative AI model to learn patterns that are unique to each user.

[1208] "Means for generating optimized outputs based on user requests" refers to a process for using a trained generative AI model to output optimal results in response to user inputs or requests.

[1209] "User terminal" refers to a device such as a smartphone or PC used by a user.

[1210] "Means for delivering" refers to a method for transferring the generated output to a user terminal and displaying it.

[1211] "Means for recommending products" refers to a system that selects and suggests products suitable for users based on personal data.

[1212] "Means for presenting special offers" refers to methods that utilize location information to provide advantageous proposals or coupons to users at specific locations or times.

[1213] The present invention is a system that collects personal data of users and uses a generative AI model to provide optimized output. Specific embodiments of the system are described in detail below.

[1214] Hardware and Software Configuration

[1215] The main hardware components of this system include servers and user terminals (smartphones, PCs, etc.). The roles of each component are as follows:

[1216] server:

[1217] Data collection server: Collects personal data such as user purchase history, behavioral history, and location information from various services via API.

[1218] Data Management Server: Securely stores and manages collected personal data, applying encryption and access controls.

[1219] Data processing server: Normalizes collected personal data and assigns tags such as categories and keywords.

[1220] Learning Server: Uses normalized and tagged data to train generative AI models to learn individual user patterns and preferences.

[1221] Application Server: Uses trained generative AI models to generate optimized outputs based on user requests.

[1222] Distribution server: distributes the generated output to user devices.

[1223] User device:

[1224] The system application is installed on the device that the user normally uses, such as a smartphone or PC, and displays the generated output.

[1225] Description of the main process

[1226] 1. Collection of Personal Data:

[1227] The server collects personal data such as the user's purchase history, behavioral history, and location information from various services with the user's permission. This data collection is done via API.

[1228] 2. Data Storage and Management:

[1229] The data management server encrypts and securely stores collected personal data, and data security is ensured through access control.

[1230] 3. Data normalization and tagging:

[1231] The data processing server converts the collected personal data into a unified format and maintains data consistency by assigning relevant categories and keywords.

[1232] 4. Training the generative AI model:

[1233] The learning server uses the normalized and tagged data to train a generative AI model, which learns individual user patterns and preferences and is continuously updated.

[1234] 5. Generating optimization outputs:

[1235] The application server accepts user requests and generates optimized outputs using a trained generative AI model.

[1236] 6. Output Delivery:

[1237] The distribution server distributes the generated optimized output to the user terminal, which then appropriately displays the distributed output and provides it to the user.

[1238] Specific examples

[1239] For example, if a user searches for a specific product on an e-commerce site, the following prompt sentences can be used to generate optimized product recommendations:

[1240] Example prompt sentence:

[1241] Please list 5 recommended products based on the user's purchase history. <User ID: 12345>

[1242] By inputting this prompt into a generative AI model, the system can recommend the best products for the user. If the user provides specific location information, special offers related to that location can also be presented. For example, if the user is near a specific electronics retailer, they will be notified of special offers and coupons.

[1243] In this way, the system of the present invention uses the user's personal data to provide personalized and optimized output, which is expected to improve the user experience.

[1244] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1245] Step 1: Collecting personal data

[1246] The server collects personal data such as the user's purchase history, behavioral history, and location information from various services via API. Specifically, it obtains purchase history from the e-commerce site and the user's current location and visit history from the location information service. The input is the user's authentication information and API request, and the output is the collected personal data. The server temporarily stores this data.

[1247] Step 2: Store and manage your data

[1248] The server encrypts the collected personal data and stores it securely in a database. Access control is also applied during the storage process. The input is the personal data collected in step 1, and the output is the securely stored personal data.

[1249] Step 3: Normalize and tag the data

[1250] The data processing server converts the collected personal data into a unified format and assigns relevant categories and keywords, ensuring data consistency and facilitating subsequent processing. The input is the stored personal data, and the output is the normalized and tagged data.

[1251] Step 4: Training the generative AI model

[1252] The learning server uses the normalized and tagged data to train the generative AI model. The training process learns each user's patterns and preferences. The input is the normalized and tagged personal data, and the output is the trained generative AI model.

[1253] Step 5: Generate optimization output

[1254] The application server accepts user requests and generates optimized outputs using the trained generative AI model. For example, if a user searches for a specific product, it generates product recommendations based on the user's purchase history and behavioral history. The input is the user request and the trained AI model, and the output is optimized product recommendations.

[1255] Step 6: Delivering the output

[1256] The distribution server distributes the generated optimized output to the user's device. The distribution process involves real-time notifications and display of the optimized output on the user's smartphone or PC. The input is the optimized output, and the output is product recommendations and special offers displayed on the user's device.

[1257] This series of steps results in personalized product recommendations and special offers that enhance the user experience.

[1258] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1259] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and emotion engine. The system is composed of the following multiple subsystems and processes:

[1260] Collection of Personal Data

[1261] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, location information, etc. from various services (e.g., e-commerce sites, location-based services) via API. This data provides detailed information about the user's behavior and preferences.

[1262] Data storage and management

[1263] The data management server securely stores and manages the collected personal data. The data management server encrypts the collected data and stores it with appropriate access control. This ensures the security and privacy of the data while allowing it to be accessed quickly when needed.

[1264] Data normalization and tagging

[1265] The data processing terminal normalizes and tags the stored personal data. For example, this includes converting collected purchase history information into a consistent format and tagging it with relevant categories and keywords. This process ensures data consistency and makes subsequent processing easier.

[1266] Collecting Emotional Data

[1267] The emotion engine collects the user's emotional data. The emotion engine uses sensors and devices to analyze emotions from the user's facial expressions, voice tone, and text input. This data is also stored and managed along with other personal data.

[1268] Training a private AI model

[1269] The learning server uses the normalized and tagged personal and emotional data to train a generative AI model. This AI model learns each user's data patterns and preferences to generate optimal output. The model is continuously updated and retrained as new user data is added.

[1270] Generating optimization output

[1271] The application server accepts user requests and integrates the trained generative AI model with emotional data to generate optimized output. For example, if a user searches for a specific product, it provides optimized product recommendations based on past purchase history, behavioral history, and current emotional state. This output is tailored to the user's specific needs and emotional state.

[1272] Output Delivery

[1273] The distribution server distributes the generated optimized output to the user's device. The distribution server sends the generated output in an appropriate format to the user's device, such as a smartphone or PC, for notification or display, allowing the user to receive optimized information and suggestions.

[1274] Specific examples

[1275] For example, when a user searches for a specific product on an e-commerce site, the system works as follows: The data collection server collects information about the user's past purchase history, behavioral history, and recently visited places, and the emotion engine analyzes the user's current emotional state (e.g., stress level and satisfaction). This data is normalized and tagged.

[1276] The learning server uses this data to train the AI ​​model, and when the user searches for a product again, the application server generates optimized product recommendations based on the trained model and emotion data. The generated recommendation information is sent to the user's smartphone by the distribution server, allowing the user to view and purchase product information optimized for them.

[1277] In this way, the system of the present invention can provide an output optimized for each user, thereby maintaining a competitive advantage for the company. By providing a more refined output based on the user's emotions, it becomes possible to provide information that is optimal for a specific situation or timing.

[1278] The processing flow will be explained below.

[1279] Step 1:

[1280] With the user's permission, the server collects personal data. Specifically, the server obtains data such as the user's purchase history, behavioral history, and location information from various services (e.g., e-commerce sites, location-based services) via API. This allows for detailed data on the user's behavior and preferences to be obtained.

[1281] Step 2:

[1282] The data management server encrypts the collected personal data and stores it in a secure database. The data has appropriate access controls to protect privacy. This step ensures that the data is stored securely and can be retrieved when needed.

[1283] Step 3:

[1284] The data processing terminal normalizes the stored personal data and assigns categories and keywords. For example, purchase history data is converted into a unified format and tagged with "home appliances" or "books." This process maintains data consistency and makes it easier to use in subsequent processes.

[1285] Step 4:

[1286] The emotion engine collects the user's emotional data. The emotion engine analyzes the user's facial expressions, voice tone, and text input to collect data to identify the user's emotional state (e.g., "joy," "sadness," "stress") using cameras, microphones, and sensors.

[1287] Step 5:

[1288] The data management server also encrypts the emotion data collected from the emotion engine and stores it in a secure database, ensuring that emotion data is stored securely in the same way as personal data.

[1289] Step 6:

[1290] The learning server trains the generative AI model using normalized and tagged personal and emotional data. The learning server learns each user's patterns and preferences and builds a model to generate optimized outputs. The model is retrained each time new user data is added.

[1291] Step 7:

[1292] The application server receives requests from users. For example, when a user searches for a specific product, the application server generates optimized product recommendations based on past purchase history, behavioral history, and emotional data. The recommendations take into account the user's current emotional state.

[1293] Step 8:

[1294] The distribution server distributes the generated optimized output to the user's device. The output is distributed in an appropriate format and sent to the user's smartphone, PC, etc.

[1295] Step 9:

[1296] The user device displays the received output. The user device visually displays the optimized information and suggestions, allowing the user to use and view the information. For example, the user can check the product recommendation list optimized for them on their smartphone and purchase the product immediately.

[1297] Through this series of steps, the system of the present invention provides optimized output that is personalized for each user and based on their emotional state, allowing companies to maintain a competitive advantage.

[1298] Example 2

[1299] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1300] Conventional systems only provide output based on user behavioral and purchasing data, making it difficult to generate optimal output that takes the user's emotional state into account. Furthermore, they often lack the ability to uniformly handle data in different formats and provide insufficient security management. Therefore, there is a need for a system that can provide more precise and personalized output.

[1301] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data from a user, means for saving and managing the personal data, means for normalizing and tagging the personal data, means for collecting and analyzing emotion data, means for training a generative AI model using the normalized and tagged personal data and emotion data, means for generating an optimized output using the trained generative AI model and emotion data based on a user request, and means for delivering the optimized output to a user terminal. This makes it possible to quickly and safely provide more personalized and sophisticated output based on the user's behavioral data and emotion data.

[1302] "User" refers to an individual or corporation that uses the system.

[1303] "Personal data" refers to data that includes information about a user's specific behavior or preferences, such as purchase history, behavior history, and location information.

[1304] "Means of collection" refers to the ability to obtain data through interfaces such as APIs.

[1305] "Means of storage and management" refers to the ability to securely store and properly manage data using encryption and access control.

[1306] "Means for normalization and tagging" refers to the function of converting data of different formats into a unified format and assigning tags such as categories and keywords.

[1307] "Emotion data" refers to data that indicates the user's emotional state, such as information extracted from facial expressions, voice tones, and character input.

[1308] "Means for collecting and analyzing emotional data" refers to the function of detecting and analyzing the user's emotions using sensors or devices.

[1309] A "generative artificial intelligence model" refers to a model that uses machine learning techniques to learn user data patterns and preferences.

[1310] "Training" refers to the process of using collected data to train a generative artificial intelligence model.

[1311] "Optimized Output" refers to personalized results generated based on a generative artificial intelligence model and emotional data in response to a user's request.

[1312] "User request" refers to a search or information request made by a user to the system.

[1313] "Means for delivering" refers to the function of transferring and notifying the generated output to the user terminal.

[1314] "User terminal" refers to a device used by a user to access the system, such as a smartphone or PC.

[1315] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and emotion engine. This system is composed of multiple subsystems and processes as described below.

[1316] Collection of Personal Data

[1317] With the user's permission, the server collects personal data. Specifically, the server obtains the user's purchase history, behavioral history, and location information from various services via API. This data provides detailed information about the user's behavior and preferences. For example, the server sends a request to an e-commerce site's API to obtain the user's purchase history data.

[1318] Data storage and management

[1319] The data management server securely stores and manages the collected personal data. The data management server encrypts the data using an encryption library (e.g., AES-256) and stores it in a database (e.g., MySQL). It also performs appropriate access control using a user authentication function (e.g., JWT token).

[1320] Data normalization and tagging

[1321] The data processing device normalizes and tags the stored personal data. For example, it unifies purchase history recorded in different formats and assigns relevant categories and keywords. This process uses a text classification algorithm (e.g., TF-IDF or Word2Vec).

[1322] Collecting Emotional Data

[1323] The emotion engine collects user emotional data. Using sensors and devices, emotions are analyzed from the user's facial expressions, voice tone, and text input. For example, a facial recognition camera captures the user's facial expressions and analyzes them with an emotion recognition algorithm (e.g., OpenFace). Voice tone is analyzed using a voice feature extraction algorithm (e.g., Librosa).

[1324] Training a private AI model

[1325] The learning server trains a generative AI model using the normalized and tagged personal and emotional data. This process uses machine learning libraries (e.g., TensorFlow and PyTorch). The trained model learns each user's data patterns and preferences and is retrained each time new data is added.

[1326] Generating optimization output

[1327] The application server accepts requests from users and generates optimized outputs by integrating the trained generative AI model with emotional data. For example, if a user searches for a specific product, it provides optimized product recommendations taking into account their past purchase history, behavioral history, and current emotional state. As a concrete example, the prompt sentence to be input to the generative AI model is shown below.

[1328] Example prompt sentence:

[1329] "Provide optimal product recommendations that match the user's recent searches and take into account his past purchase history and current emotional state."

[1330] Output Delivery

[1331] The distribution server distributes the generated optimized output to the user's device. The distribution server then sends the generated output in an appropriate format to the user's smartphone or PC for notification or display, allowing the user to receive optimized information and suggestions.

[1332] In this way, the system of the present invention can provide refined output for each user, enabling more personalized services, which helps companies maintain their competitive advantage and enables users to receive optimal information tailored to their specific situation and timing.

[1333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1334] Step 1: Collecting personal data

[1335] With the user's permission, the server collects personal data, including purchase history, behavioral history, and location information.

[1336] Input: Data API endpoints from various services (e.g., e-commerce sites, location services).

[1337] How it works: The server sends a request to the API and gets back data in JSON format. For example, it accesses the endpoint "https: / / api.ecommerce.com / history?userid=12345".

[1338] Output: Purchase history and behavioral history data in JSON format.

[1339] Step 2: Store and manage your data

[1340] The data management server stores and manages the collected personal data, a process that includes data encryption and access control.

[1341] Input: Personal data collected in step 1.

[1342] Operation: The data management server encrypts the data using an encryption library (e.g., AES-256) and stores it in a database (e.g., MySQL). It also implements access control using user authentication functions (e.g., JWT tokens).

[1343] Output: Encrypted data stored securely in a database.

[1344] Step 3: Normalize and tag the data

[1345] The data processing terminal normalizes the stored personal data and assigns relevant categories and keywords.

[1346] Input: The encrypted data stored in step 2.

[1347] How it works: The data processing terminal runs a script that converts the data into a consistent format, for example standardizing different date formats to "YYYY-MM-DD" and tagging it using a text classification algorithm (e.g. TF-IDF or Word2Vec).

[1348] Output: Normalized and tagged data.

[1349] Step 4: Collecting emotion data

[1350] The emotion engine collects user emotional data by analyzing the user's facial expressions, tone of voice, and text input using sensors and devices.

[1351] Input: User's facial expression data, voice data, and text input data.

[1352] How it works: The emotion engine uses a facial recognition camera or microphone to analyze emotion data using facial expression recognition algorithms (e.g., OpenFace) and voice feature extraction algorithms (e.g., Librosa).

[1353] Output: Data indicating the user's emotional state.

[1354] Step 5: Train a private AI model

[1355] The learning server trains the generative AI model using normalized and tagged personal data and emotion data.

[1356] Input: Normalized and tagged data from step 3, sentiment data from step 4.

[1357] How it works: The learning server uses machine learning libraries (e.g., TensorFlow or PyTorch) to train generative AI models (e.g., Transformer models).

[1358] Output: A trained generative AI model.

[1359] Step 6: Generate optimization output

[1360] The application server accepts requests from users and integrates the trained generative AI model with emotion data to generate optimized outputs.

[1361] Input: User request, trained generative AI model, current emotion data.

[1362] How it works: The application server inputs prompt statements into the generative AI model and executes requests such as, "Please provide optimal product recommendations that match the user's recent search results, taking into account his past purchase history and current emotional state."

[1363] Output: An optimized product recommendation list.

[1364] Step 7: Delivering the output

[1365] A distribution server distributes the generated optimized output to the user terminal.

[1366] Input: The optimization output generated in step 6.

[1367] Operation: The distribution server sends the generated recommended product list in JSON format to an endpoint and distributes it to the user's device via a REST API. The user's device receives this information and sends a push notification or displays it on the screen.

[1368] Output: Optimized output notification delivered to user terminal.

[1369] (Application example 2)

[1370] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1371] Today's consumers are becoming increasingly diverse and tend to demand products and services tailored to their individual needs. However, conventional systems have difficulty making optimal recommendations that take into account not only a user's purchasing history, behavioral history, and location information, but also their emotional state. This can lead to issues such as reduced user satisfaction and lost sales opportunities.

[1372] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data from users, means for saving and managing the personal data, means for normalizing and tagging the personal data, means for training a generative AI model using the normalized and tagged personal data, means for generating an optimized output from the trained generative AI model based on a user request, means for delivering the optimized output to a user terminal, means for collecting and analyzing user emotion data, and means for optimizing recommendations using the emotion data. This makes it possible to respond to the diverse needs of users and provide individually optimized product recommendations and services.

[1373] "Means of collecting personal data from users" refers to means of obtaining individual data such as users' purchase history, behavioral history, and location information via APIs or sensors.

[1374] "Personal data" refers to data that indicates individual preferences and patterns, such as user behavior, purchasing history, and location information.

[1375] "Means for storage and management" refers to the means for securely storing collected personal data and encrypting and controlling access to it.

[1376] "Normalization and tagging measures" are measures that convert collected personal data into a consistent format and assign relevant categories and keywords.

[1377] "Means for training a generative artificial intelligence model" means means for using normalized and tagged personal data to train an artificial intelligence model to learn individual data patterns and preferences.

[1378] The "means for generating optimized output" refers to a means for using a trained artificial intelligence model to provide optimal recommendations and information based on user requests.

[1379] The "means for delivering" refers to a means for transmitting the generated optimization output to the user's terminal and for notifying or displaying the output.

[1380] "Means for collecting and analyzing emotional data" refers to means for collecting and analyzing the emotional state of a user by analyzing the user's facial expressions, tone of voice, etc. using sensors or devices.

[1381] "Means for optimizing recommendations" refers to means for using collected and analyzed emotional data to recommend and provide products and services that are most suited to the user's emotional state.

[1382] The present invention relates to a system that collects personal data from users and provides optimized output using a generative AI model and an emotion engine. This system is constructed using the following hardware and software:

[1383] Hardware and software used

[1384] Hardware

[1385] 1. Server: The server that collects, stores, and manages personal data from users.

[1386] 2. Data management server: A server that encrypts and stores data and controls access.

[1387] 3. Data processing terminal: A terminal that normalizes and tags personal data.

[1388] 4. Learning server: A server that trains AI models.

[1389] 5. Application Server: The server that generates and delivers the optimized output.

[1390] 6. Distribution server: A server that distributes the generated output to user terminals.

[1391] 7. User terminal: The device that receives the output, such as a smartphone or PC.

[1392] 8. Emotion Sensor: A device (camera, microphone, heart rate sensor, etc.) that collects user emotional data.

[1393] software

[1394] 1. Generative AI model: A model that generates optimized output based on personal data and emotional data.

[1395] 2. Emotion Recognizer: Software that analyzes the user's emotions.

[1396] 3. Recommendation Engine: Software that generates optimized output based on data.

[1397] System configuration

[1398] 1. Collection of Personal Data:

[1399] The server collects personal data such as users' purchase history, behavioral history, and location information. This data is obtained from various web services and apps via APIs.

[1400] 2. Data Storage and Management:

[1401] The data management server encrypts and securely stores collected personal data, and also implements appropriate access control to ensure data security.

[1402] 3. Data normalization and tagging:

[1403] The data processing terminal normalizes the personal data into a consistent format and tags it with relevant categories and keywords, a process that ensures data consistency.

[1404] 4. Emotional Data Collection and Analysis:

[1405] Emotion sensors and emotion recognition software (EmotionRecognizer) collect and analyze emotional data from users' facial expressions, voice tones, and text input. This data is stored along with other personal data.

[1406] 5. Training the AI ​​model:

[1407] The learning server uses the normalized and tagged personal and emotional data to train a generative AI model that learns each user's data patterns and preferences to generate optimized outputs.

[1408] 6. Generating optimization outputs:

[1409] The trained generative AI model generates optimized outputs based on user requests on the application server, which recommend optimal products and services taking into account the user's current emotional state.

[1410] 7. Output Delivery:

[1411] The distribution server distributes the generated optimization output to the user's device, allowing the user to receive optimized information and suggestions on their device, such as a smartphone or PC.

[1412] Specific examples

[1413] For example, when a user approaches the beverage section of a physical store, a push notification will be sent with the most suitable drink or promotion based on the user's past purchase history (e.g., coffee, energy drinks) and their emotional state at that moment (e.g., relaxed). This allows for product recommendations that are optimized for each user.

[1414] Prompt Sentence Examples

[1415] An example prompt is:

[1416] User ID: example_user_id

[1417] Past purchase history: Coffee, energy drinks

[1418] Current behavior history: Entered the beverage section

[1419] Emotional state: Relaxed

[1420] Generate the recommended output.

[1421] In this way, the system of the present invention responds to the diverse needs of users and realizes individually optimized product recommendations and service provision.

[1422] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1423] Step 1:

[1424] The server collects personal data from users. Specifically, it obtains data such as purchase history, behavioral history, and location information from various web services and apps via APIs. A user ID is provided as input, and related data is collected based on that user ID. The output is a set of collected personal data.

[1425] Step 2:

[1426] The server transmits the collected personal data to the data management server, which securely stores and manages it. The data management server then encrypts the data and performs appropriate access control to ensure data security. The collected personal data is provided as input, and the encrypted and stored data is obtained as output.

[1427] Step 3:

[1428] The data processing terminal normalizes and tags the stored personal data by converting the data into a consistent format and assigning relevant categories and keywords. The input is the encrypted and stored personal data, and the output is the normalized and tagged data.

[1429] Step 4:

[1430] The server uses emotion sensors and emotion recognition software (EmotionRecognizer) to collect and analyze the user's emotion data. Specifically, it obtains emotion data by analyzing the user's facial expressions, voice tone, and text input obtained from the sensors. The input is the user's real-time behavior data, and the output is analyzed emotion data.

[1431] Step 5:

[1432] The learning server trains the generative AI model using normalized and tagged personal data and emotion data. Specifically, the AI ​​model learns each user's data patterns and preferences based on this data. Normalized and tagged personal data and emotion data are provided as input, and the trained AI model is obtained as output.

[1433] Step 6:

[1434] The application server uses the trained generative AI model to generate optimized output based on user requests. Specifically, it generates the most appropriate information, product recommendations, and service content based on the user's current emotional data and behavioral history. The trained AI model and real-time user data are provided as input, and the optimized output is obtained as output.

[1435] Step 7:

[1436] The distribution server distributes the optimized output to the user's device. Specifically, the generated output is sent to the user's device, such as a smartphone or PC, and displayed as a notification. The optimized output is provided as input, and the output is information, product recommendations, and service content displayed on the user's device.

[1437] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1438] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1439] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1440] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1441] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1442] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1443] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1444] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1445] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1446] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1447] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1448] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1449] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1450] 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.

[1451] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1452] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1453] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1454] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1455] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1456] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1457] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1458] The following is further disclosed regarding the above embodiment.

[1459] (Claim 1)

[1460] means for collecting personal data from users;

[1461] means for storing and managing said personal data;

[1462] means for normalizing and tagging said personal data;

[1463] means for training a generative artificial intelligence model using the normalized and tagged personal data;

[1464] means for generating an optimized output based on a user request using the trained generative artificial intelligence model;

[1465] means for delivering the optimization output to a user terminal;

[1466] A system including:

[1467] (Claim 2)

[1468] The system according to claim 1, wherein the personal data includes purchase history, behavioral history, and location information.

[1469] (Claim 3)

[1470] 2. The system of claim 1, wherein the generative artificial intelligence model includes means for learning patterns that differ for each user.

[1471] "Example 1"

[1472] (Claim 1)

[1473] a means for collecting personal data from users;

[1474] means for storing and managing said personal data;

[1475] means for normalizing and tagging said personal data;

[1476] means for training a generative artificial intelligence model using the normalized and tagged personal data;

[1477] means for generating an optimized output based on a user request using the trained generative artificial intelligence model;

[1478] means for delivering the optimization output to a user terminal;

[1479] Specific means for obtaining, encrypting, and storing the personal data through API;

[1480] A means for updating the generative artificial intelligence model based on past data;

[1481] The specific means of processing the request entered by the user;

[1482] A system including:

[1483] (Claim 2)

[1484] The system of claim 1 , wherein the personal data includes purchase history, behavioral history, and location information.

[1485] (Claim 3)

[1486] 2. The system of claim 1, wherein the generative artificial intelligence model includes means for learning different patterns for each user and being continuously updated.

[1487] "Application Example 1"

[1488] (Claim 1)

[1489] means for collecting personal data from users;

[1490] means for storing and managing said personal data;

[1491] means for normalizing and tagging said personal data;

[1492] means for training a generative artificial intelligence model using the normalized and tagged personal data;

[1493] means for generating an optimized output based on a user request using the trained generative artificial intelligence model;

[1494] means for delivering the optimization output to a user terminal;

[1495] A means for recommending products based on a user's purchasing history and browsing history;

[1496] a means for using the user's location information to present special offers;

[1497] A system including:

[1498] (Claim 2)

[1499] The system according to claim 1, wherein the personal data includes purchase history, behavioral history, and location information.

[1500] (Claim 3)

[1501] 2. The system of claim 1, wherein the generative artificial intelligence model includes means for learning patterns that differ for each user and making personalized product recommendations.

[1502] "Example 2: Combining Emotion Engines"

[1503] (Claim 1)

[1504] means for collecting personal data from users;

[1505] means for storing and managing said personal data;

[1506] means for normalizing and tagging said personal data;

[1507] a means for collecting and analyzing emotion data;

[1508] means for training a generative artificial intelligence model using the normalized and tagged personal data and emotion data;

[1509] means for generating an optimized output based on the trained generative artificial intelligence model and emotion data as a user request;

[1510] means for delivering the optimization output to a user terminal;

[1511] A system including:

[1512] (Claim 2)

[1513] The system according to claim 1, wherein the personal data includes purchase history, behavioral history, and location information.

[1514] (Claim 3)

[1515] 10. The system of claim 1, wherein the generative artificial intelligence model includes means for learning different patterns and emotional states for different users.

[1516] "Application example 2 when combining emotion engines"

[1517] (Claim 1)

[1518] means for collecting personal data from users;

[1519] means for storing and managing said personal data;

[1520] means for normalizing and tagging said personal data;

[1521] means for training a generative artificial intelligence model using the normalized and tagged personal data;

[1522] means for generating an optimized output based on a user request using the trained generative artificial intelligence model;

[1523] means for delivering the optimization output to a user terminal;

[1524] means for collecting and analyzing user emotion data;

[1525] means for optimizing recommendations using the emotion data;

[1526] A system including:

[1527] (Claim 2)

[1528] The system according to claim 1, wherein the personal data includes purchase history, behavioral history, and location information.

[1529] (Claim 3)

[1530] 2. The system of claim 1, wherein the generative artificial intelligence model includes means for learning patterns that differ for each user. [Explanation of symbols]

[1531] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting personal data from users; means for storing and managing said personal data; means for normalizing and tagging said personal data; means for training a generative artificial intelligence model using the normalized and tagged personal data; means for generating an optimized output based on a user request using the trained generative artificial intelligence model; means for delivering the optimization output to a user terminal; A system including:

2. The system according to claim 1 , wherein the personal data includes purchase history, behavior history, and location information.

3. 2. The system of claim 1, wherein the generative artificial intelligence model includes means for learning patterns that differ for each user.

Images