System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving a request from a user; means for collecting personal data of the user; means for transmitting the collected personal data to a server; means for retrieving additional personal data from a database; means for providing the retrieved personal data to a generative AI model; means for receiving an optimal recommendation generated by the generative AI model; means for transmitting the received recommendation to the user; and means for displaying the recommendation on the user.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] Using conventional generative AI technology alone poses the challenge of losing competitive advantage, as other companies can obtain the same output using similar methods. Furthermore, output based solely on general data without utilizing personal data makes it difficult to provide optimal recommendations to users. Therefore, how to combine and effectively utilize personal data will be the key to corporate competitiveness in the near future. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: means for receiving a request from a user; means for collecting personal data of the user; means for transmitting the collected personal data to a server; means for acquiring additional personal data from a database; means for providing the acquired personal data to a generative AI model; means for receiving optimal recommendations generated by the generative AI model; means for transmitting the received recommendations to the user's terminal; and means for displaying the recommendations on the user's terminal. This system generates outputs that are individually optimized for each user, enabling companies to enhance their competitive advantage.

[0006] "User" refers to each individual who uses this system.

[0007] A "request" refers to a request for information or assistance made by a user to the system.

[0008] "Personal data" refers to personal information about a user, including browsing history, ratings, location information, etc.

[0009] "Terminal" means an electronic device used by a user to enter requests and receive output from the system.

[0010] "Server" refers to a centralized management system that receives and processes data from terminals and provides the data to the generating AI.

[0011] "Database" refers to a storage device or system for storing and managing personal data.

[0012] A "generative AI model" refers to an artificial intelligence model that analyzes collected personal data and generates optimal suggestions and outputs for users.

[0013] "Recommendation" refers to the optimal suggestions or information provided to the user by the generative AI model.

[0014] "Display" refers to the act of the terminal visually providing the recommendation to the user. [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] This invention relates to a system that utilizes personal data based on user requests and uses generative AI to provide optimal output. This system collects personal data based on the user's specific needs, provides it to a generative AI model, and generates optimal suggestions and recommendations, which are then presented to the user.

[0037] Accepting requests from users

[0038] The user uses the application to input a request such as "Tell me the next movie I should watch." The device receives this request and collects personal data such as the user's viewing history and ratings.

[0039] Collection and transmission of personal data

[0040] The device collects the user's operation log and input data and sends it to the server. At this time, the collected personal data is properly formatted and provided in a format that the server can easily analyze.

[0041] Data acquisition and analysis by the server

[0042] The server receives the data sent from the device, retrieves additional personal data from the database, and integrates this data. The server then provides the integrated personal data to the generative AI model.

[0043] Generative AI model generates output

[0044] The generative AI model analyzes the user's personal data and generates output that best suits the user's needs. For example, if a user requests, "What movie should I watch next?", the generative AI model will take into account viewing history and ratings to recommend an appropriate movie.

[0045] Sending and viewing recommendations

[0046] The server receives the recommendations generated by the generative AI model. The server then sends the recommendations to the device. The device displays the received recommendations to the user. The user then selects the next movie to watch based on the displayed recommendations.

[0047] Specific examples

[0048] For example, consider the case where a user uses this system to request, "What book should I read next?" The device collects the user's reading history, past ratings and reviews, etc., and sends this to the server. The server retrieves additional information from the database and provides it to the generative AI model. The generative AI model analyzes this data and generates a list of books that the user might be interested in. The server sends the generated list to the device, which displays it to the user. In this way, the user can easily select their next reading preference.

[0049] With the above-mentioned configuration, the present invention can effectively utilize the user's personal data to generate individually optimized output, thereby significantly increasing a company's competitive advantage.

[0050] The processing flow will be explained below.

[0051] Step 1: User enters request

[0052] A user launches a movie recommendation app and types, "What movie should I watch next?"

[0053] Step 2: The terminal receives user input

[0054] The terminal receives the user's request.

[0055] The terminal collects personal data such as the user's past viewing history and ratings from the terminal's cache or database.

[0056] Step 3: The device sends the data to the server

[0057] The device formats the personal data collected and the user's request into JSON format.

[0058] The terminal sends the formatted data to the server.

[0059] Step 4: The server receives the data

[0060] The server receives the JSON data sent from the device.

[0061] The server analyzes the received data and identifies the required personal data corresponding to the request content.

[0062] Step 5: The server retrieves additional data from the database

[0063] The server retrieves additional personal data from the database (e.g., recent viewing history and ratings).

[0064] The server merges the additional data it retrieves with the existing data.

[0065] Step 6: The server invokes the generative AI model

[0066] The server provides the integrated personal data to the generative AI model.

[0067] The server calls the API of the generated AI model and provides personal data as an argument.

[0068] Step 7: The generative AI model generates the output

[0069] The generative AI model analyzes the provided data and generates an optimal list of movies to watch next based on the user's viewing history and ratings.

[0070] The recommendation list generated by the generative AI model is returned to the server in JSON format.

[0071] Step 8: The server receives the output of the generated AI.

[0072] The server receives the recommendation list returned by the generative AI model.

[0073] The server cleans up the received recommendation list and formats it as needed.

[0074] Step 9: Server sends output to terminal

[0075] The server sends the formatted recommendation list to the terminal.

[0076] Step 10: The terminal displays the output to the user

[0077] The terminal receives the recommendation list received from the server and visually displays it to the user.

[0078] The user selects the next movie to watch from the displayed list.

[0079] In this way, specific actions at each step allow the user to receive individually optimized output.

[0080] Example 1

[0081] 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."

[0082] Conventional recommendation systems have been unable to effectively utilize users' personal data, making it difficult to provide optimal recommendations tailored to user needs. Collecting and analyzing personal data also takes time and effort, reducing system efficiency. To address these issues, a system is needed that can quickly and efficiently collect and analyze personal data based on user requests and provide optimal output using a generative AI model.

[0083] 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.

[0084] In this invention, the server includes means for accepting requests from users, means for collecting personal data of users, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for the terminal to appropriately format the collected personal data, means for the server to integrate the data and input it into the generative AI model, and means for the generative AI model to analyze and generate output. This makes it possible to effectively utilize the user's personal data and quickly and efficiently provide individually optimized recommendation results.

[0085] "User request" refers to the wishes or requests that a user inputs into the system.

[0086] "Personal data" refers to data related to individual attributes and behavior, such as personal information about a user, behavioral history, and evaluation information.

[0087] "Terminal" is a general term for devices operated by users, including smartphones, tablets, and personal computers.

[0088] A "server" refers to a computer system that manages and processes data on a network, and is responsible for integrating and analyzing data from multiple terminals.

[0089] A "database" is a collection of data that is systematically organized and stored, and is used to store personal data and various other information for easy searching and retrieval.

[0090] "Generative AI models" refer to algorithms and trained data models that use artificial intelligence technology to analyze users' personal data and generate optimal outputs.

[0091] "Formatting" means the process of putting data into a particular form or structure to make it easier to analyze or communicate.

[0092] "Recommendations" refer to information and suggestions presented as a result of analysis by a generative AI model, and are provided in a form optimized to meet the user's needs.

[0093] "Output" refers to the results or proposals that a generative AI model ultimately generates after analysis, including various information and lists provided to users.

[0094] "Integration" refers to the process of bringing together data from different sources to make it consistent and improve the accuracy of analysis and recommendations.

[0095] This invention is a system that utilizes personal data based on user requests and uses a generative AI model to provide optimal output. The system aims to collect and analyze personal data that meets the user's needs and provide highly accurate recommendations to the user. The entire system is mainly composed of four main components: a terminal, a server, a database, and a generative AI model.

[0096] The user uses the device to input a request such as "Tell me what movie I should watch next." The device receives this request and collects personal data such as the user's past viewing history and ratings. This collected data is then appropriately formatted and sent to the server.

[0097] The server receives the data sent from the device and temporarily stores it in a buffer. Then, if additional data is needed, it retrieves additional personal data from the database and aggregates this data. This brings all relevant data into one unified dataset, ready to be fed to the generative AI model.

[0098] The generative AI model analyzes the user's personal data and generates an output that best suits the user's needs. This output is based on the data and algorithms that the generative AI model has learned. When a user requests, "Tell me what movie I should watch next," the generative AI model takes into account viewing history and ratings to generate a list of optimal movie recommendations.

[0099] The server receives the recommendations generated by the generative AI model and sends them to the device. The device then displays the recommendations to the user. The user can then select the next movie to watch by looking at the displayed recommendations. Through this process, the user receives the best recommendations based on their preferences and past behavioral history.

[0100] Specific examples

[0101] For example, consider the case where a user uses this system to request, "What book should I read next?" The device collects the user's reading history, past ratings, and reviews, and sends this to the server. The server retrieves additional reading data from the database, integrates it, and then provides it to the generative AI model. The generative AI model analyzes this data and generates a list of books that the user might be interested in. The server sends the generated list of books to the device, which displays it to the user. The user can then select the next book to read based on the displayed list.

[0102] Prompt Sentence Examples

[0103] Tell me what movie I should watch next

[0104] What books do you recommend?

[0105] Tell me where I should travel next

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Step 1:

[0108] The user inputs a request. The user inputs a request using a device. Specifically, the user inputs a request such as "Tell me the next movie I should watch" through an application on a smartphone or tablet. This input is captured by the device. The input data is saved in text format as a prompt sentence.

[0109] Step 2:

[0110] The device collects personal data. The device retrieves user operation logs, viewing history, and rating data from an internal database or cache. This includes movies the user has previously viewed and their ratings. The collected data is formatted in an easy-to-parse format (e.g., JSON).

[0111] Step 3:

[0112] The device sends the collected personal data to the server. The device then sends the formatted personal data to the cloud server using a secure protocol such as HTTPS. The sent data includes the request prompt and the personal data.

[0113] Step 4:

[0114] The server receives the data sent from the device. The server temporarily stores the received data in a buffer and stores it in the appropriate data storage. The input data is personal data and a request prompt. This prepares the server for analysis and additional data acquisition.

[0115] Step 5:

[0116] The server retrieves additional personal data from the database. The server executes SQL queries to retrieve additional personal data related to the user from the database, including past browsing history, ratings, and related user rating data. The retrieved data is consolidated on the server.

[0117] Step 6:

[0118] The server provides the integrated data to the generative AI model. The server integrates the data acquired from the device with additional data from the database and provides it to the generative AI model (e.g., GPT-4). The input data is the integrated personal dataset. This allows the generative AI model to efficiently begin analysis.

[0119] Step 7:

[0120] The generative AI model generates recommendation results. The generative AI model analyzes the integrated personal data and generates output that best suits the user's needs. Specifically, it generates a list of movie recommendations based on viewing history and ratings. The output data is a list of recommended movies.

[0121] Step 8:

[0122] The server receives the recommendation results from the generative AI model. The server receives and stores the generated recommendation results in a data format such as JSON, which prepares the recommendation results for transmission to the device.

[0123] Step 9:

[0124] The server sends the recommendation results to the terminal. The server then sends the received recommendation results to the terminal using a secure protocol such as HTTPS. The input data is the recommendation result data, which is sent to the terminal as output.

[0125] Step 10:

[0126] The device displays the recommended results to the user. The device displays the recommended results received from the server to the user. Specifically, a list of recommended movies is displayed on the smartphone application screen. The user can refer to this list and select the next movie to watch.

[0127] (Application example 1)

[0128] 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."

[0129] Conventional content recommendation systems have not been able to fully utilize users' personal data, making it difficult to recommend optimal content to users. Furthermore, there is a lack of a means to effectively analyze users' past viewing history and rating data, generate prompts, and provide optimal recommendations based on those prompts. This often leaves users dissatisfied because they are unable to easily find content that matches their preferences.

[0130] 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.

[0131] In this invention, the server includes means for receiving a request from a user, means for collecting personal data of the user, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for providing prompt sentences generated based on the user's past viewing history and rating data to the generative AI model, and means for transmitting recommendation results generated from the prompt sentences to the server before displaying them to the user. This makes it possible to effectively utilize the user's personal data and provide individually optimized content to the user.

[0132] The "means for receiving requests from a user" is a function for receiving requests or questions input by a user through an application.

[0133] "Means for collecting user personal data" refers to a function that collects personal information such as the user's past behavioral history, ratings, and location information.

[0134] "Means for transmitting collected personal data to a server" refers to a function that transfers personal information collected from a user's terminal to a server via a network.

[0135] "Means for obtaining additional personal data from the database" refers to the function of retrieving necessary additional information from other related databases stored on the server.

[0136] "Means for providing acquired personal data to a generative AI model" refers to the function of handing over collected and acquired personal data to an AI model for analytical processing.

[0137] "Means for receiving optimal recommendations generated by a generative AI model" refers to a function for receiving recommendation results created by a generative AI model.

[0138] The "means for transmitting the received recommendation to the user's terminal" is a function for transferring the received recommendation results to the user's terminal.

[0139] The "means for displaying recommendations on the user's terminal" is a function for visually displaying the recommendation results on the user's terminal.

[0140] "Means for providing prompt sentences generated based on the user's past viewing history and rating data to a generative AI model" is a function for providing prompt sentences generated based on the user's past viewing history and rating data to an AI model.

[0141] The "means for sending the recommendation results generated from the prompt sentence to the server before displaying them to the user" is a function that returns the generated recommendation results to the server for confirmation or additional processing before displaying them to the user.

[0142] This invention relates to a system that utilizes personal data based on user requests and uses generative AI to provide optimal output. This system aims to recommend optimal content based on user viewing history and rating data, particularly for content distribution services.

[0143] Program Overview

[0144] This system mainly consists of the following process: First, the user inputs a request using a smartphone application. This request is for recommendations of movies, TV shows, etc. to watch next. The device receives this request, collects the user's past viewing history and rating data, and sends them to the server.

[0145] Hardware and software used

[0146] Hardware: Smartphone

[0147] Software: Python 3.x, Requests library, Flask (server side)

[0148] Processing flow

[0149] The server receives the user's personal data and retrieves additional personal data from the database. The collected and retrieved personal data is then provided to the generative AI model to generate prompt sentences. Based on the generated prompt sentences, the generative AI model recommends optimal content.

[0150] Prompt Sentence Examples

[0151] For example, if user "MovieFan123" requests "What movie should I watch next?", the following prompt will be generated:

[0152] "The user with user ID MovieFan123's viewing history includes The Matrix, Inception, and Interstellar, with ratings of 5, 4, and 5, respectively. Recommend the next best movie for this user."

[0153] Based on this, the generative AI model recommends a list of content (e.g., "Blade Runner 2049," "The Terminator," "Eternal Sunshine of the Spotless Mind") and sends it to the server, which then sends the recommendations to the user's device, which then displays them to the user.

[0154] Specific examples

[0155] As a concrete example, suppose a user requests an application, "What movie should I watch next?" The system generates a prompt based on the user's viewing history and rating data (e.g., "The Matrix" 5, "Inception" 4, "Interstellar" 5) and provides it to the generative AI model. Based on this data, the generative AI model recommends "Blade Runner 2049," "The Terminator," and "Eternal Sunshine of the Spotless Mind." The server sends the recommendation results to the user's smartphone, and the application displays them to the user. This allows the user to easily select the next movie to watch.

[0156] This process makes it possible to effectively utilize the user's personal data and provide individually optimized content.

[0157] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0158] Step 1:

[0159] A user types a request into a smartphone application, sending a request such as "Tell me what movie I should watch next."

[0160] Input: User request

[0161] Output: Request string

[0162] Specific operation: The user uses the app interface to enter a request and presses the send button.

[0163] Step 2:

[0164] The device collects and stores the user's viewing history and rating data.

[0165] Input: User viewing history and rating data

[0166] Output: Formatted personal data

[0167] What it does: The app retrieves the user's past viewing history and rating data from a local database or cloud service and formats it into a usable format.

[0168] Step 3:

[0169] The terminal transmits the collected personal data to the server.

[0170] Input: Formatted personal data

[0171] Output: Data request sent to the server

[0172] Specific operation: The device sends the collected data to the specified API endpoint using an HTTP request, etc.

[0173] Step 4:

[0174] The server retrieves the additional personal data from the database.

[0175] Input: Personal data submitted

[0176] Output: Consolidated personal data

[0177] Specific operation: Based on the data received by the server, related additional data is retrieved from the database using a query and integrated.

[0178] Step 5:

[0179] The server provides the integrated personal data to the generative AI model to generate prompt sentences.

[0180] Input: Integrated personal data

[0181] Output: Generated prompt statement

[0182] How it works: The server analyzes the integrated data and generates effective prompts for the generative AI model. The prompts are created in text format based on past viewing history and rating data.

[0183] Step 6:

[0184] A generative AI model generates optimal recommendations based on the prompt.

[0185] Input: prompt statement

[0186] Output: A list of recommendations

[0187] How it works: The generative AI model analyzes the prompt and uses algorithms and learned data to generate optimal recommendations.

[0188] Step 7:

[0189] The server sends the recommendation results received from the generative AI model to the user's device.

[0190] Input: List of recommended results

[0191] Output: Recommendation results sent to the user's device

[0192] Specific operation: The server sends the recommendation results to the user's device using a secure communication method.

[0193] Step 8:

[0194] The terminal displays the recommendation results to the user.

[0195] Input: List of recommended results

[0196] Output: Displayed recommendation results

[0197] Specific operation: The user's device receives the recommendation results and displays them on the screen. Specifically, the titles and ratings of the recommended movies are displayed in an easy-to-read format.

[0198] This allows users to easily find content that suits their preferences and select what to watch next.

[0199] 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.

[0200] This invention relates to a system that utilizes personal data based on user requests and combines it with an emotion engine to provide optimal output using generative AI. This system collects and analyzes personal data and emotion data according to the user's specific needs and emotions, and provides this to a generative AI model to generate optimal suggestions and recommendations, which are then presented to the user.

[0201] Accepting requests from users

[0202] The user uses the application to input a request such as "Tell me the next movie I should watch." The device receives this request and collects personal data such as the user's past viewing history, ratings, and current emotional state.

[0203] Emotion recognition by emotion engine

[0204] The device analyzes the user's voice, facial expressions, text input, etc., and uses an emotion engine to recognize the user's current emotion. The recognized emotion data is sent to the server as personal data.

[0205] Collection and transmission of personal and emotional data

[0206] The device collects the user's operation log, input data, and emotional data, and sends it to the server, where it is properly formatted and provided in a format that the server can easily analyze.

[0207] Data acquisition and analysis by the server

[0208] The server receives the data sent from the device, retrieves additional personal data from a database, and integrates this data. The server then provides the integrated data to the generative AI model.

[0209] Generative AI model generates output

[0210] The generative AI model analyzes the user's personal and emotional data to generate an output that best suits the user's needs and emotions. For example, if a user requests, "Tell me the next movie I should watch," the generative AI model will consider their viewing history, ratings, and emotional state to recommend an appropriate movie.

[0211] Sending and viewing recommendations

[0212] The server receives the recommendations generated by the generative AI model. The server then sends the recommendations to the device. The device displays the received recommendations to the user. The user then selects the next movie to watch based on the displayed recommendations.

[0213] Specific examples

[0214] For example, consider the case where a user uses this system to request, "Tell me the next movie I should watch." The device collects the user's viewing history, ratings, and emotional state analyzed from speech and facial expressions, and sends this to the server. The server retrieves additional information from the database and provides it to the generative AI model. The generative AI model analyzes this data and generates a list of movies that the user might be interested in. The server sends the generated list to the device, which displays it to the user. In this way, the user can easily select the next viewing content that suits their preferences.

[0215] With the above configuration, the present invention can effectively utilize personal data and emotional data to generate individually optimized output, thereby significantly increasing a company's competitive advantage.

[0216] The processing flow will be explained below.

[0217] Step 1: User enters request

[0218] A user launches a movie recommendation app and types, "What movie should I watch next?"

[0219] Step 2: The terminal receives user input

[0220] The terminal receives the user's request.

[0221] The device collects personal data such as the user's past viewing history and ratings from the device's cache or local database.

[0222] Step 3: The device uses the emotion engine to recognize emotions.

[0223] The device analyzes the user's voice, facial expressions, and text input, and uses an emotion engine to recognize their current emotional state.

[0224] The recognized emotion data is recorded as personal data.

[0225] Step 4: The device sends the data to the server

[0226] The device formats the user's request, including the personal data and emotional data collected, into JSON format.

[0227] The terminal sends the formatted data to the server.

[0228] Step 5: The server receives the data

[0229] The server receives the JSON data sent from the device.

[0230] The server analyzes the received data and identifies the necessary personal data and emotion data corresponding to the request content.

[0231] Step 6: The server retrieves additional data from the database

[0232] The server retrieves additional personal data from the database (e.g., recent viewing history and ratings).

[0233] Matching and integrating any additional data retrieved by the server.

[0234] Step 7: The server invokes the generative AI model

[0235] The server provides the integrated personal data and emotional data as variables to the generative AI model.

[0236] The server calls the API of the generative AI model and provides personal data and emotional data as arguments.

[0237] Step 8: The generative AI model generates the output

[0238] A generative AI model analyzes the provided data and generates an optimal list of movies to watch next based on the user's viewing history, ratings, and emotional state.

[0239] The recommendation list generated by the generative AI model is returned to the server in JSON format.

[0240] Step 9: The server receives the output of the generated AI.

[0241] The server receives the recommendation list returned by the generative AI model.

[0242] The server cleans up the received recommendation list and formats it as needed.

[0243] Step 10: Server sends output to terminal

[0244] The server sends the formatted recommendation list to the terminal.

[0245] Step 11: The terminal displays the output to the user

[0246] The terminal receives the recommendation list received from the server and visually displays it to the user.

[0247] The user selects the next movie to watch from the displayed list.

[0248] In this way, specific actions at each step allow users to receive individually optimized outputs. This system takes into account the user's emotions in particular, thereby realizing more personalized service provision.

[0249] Example 2

[0250] 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."

[0251] Conventional recommendation systems only provide recommendations based on the user's personal data, making it difficult to make optimal recommendations that take into account the user's current emotional state.In addition, the lack of appropriate data collection, analysis, and recommendations based on the user's emotional state limited the user experience.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0253] In this invention, the server includes means for receiving a request from a user, means for collecting personal data and emotional data of the user, means for transmitting the collected personal data and emotional data to the server, means for acquiring additional personal data from a database in the server, means for converting the acquired personal data and emotional data into prompt sentences and providing the prompt sentences to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, and means for displaying the recommendations on the user's terminal. This enables optimal recommendations that take into account both the user's personal data and current emotional state.

[0254] A "request" is a request or inquiry made by a user to the system.

[0255] "Personal data" refers to personal data such as a user's viewing history, ratings, and emotional state based on speech and facial expressions.

[0256] "Emotional data" refers to data that indicates the user's current emotional state, analyzed from voice, facial expressions, text input, and the like.

[0257] "Server" means a device or system that receives data sent from a user device, acquires and integrates additional data, and provides it to a generative AI model.

[0258] A "generative AI model" is an artificial intelligence model that generates optimal recommendation results based on input data.

[0259] A "prompt sentence" is an input sentence formatted to be provided to a generative AI model.

[0260] "Recommendations" refer to suggestions or recommendations generated by a generative AI model based on a user's personal and emotional data.

[0261] A "terminal" is a device that is directly operated by a user and that inputs requests, collects and transmits data, and displays recommendation results.

[0262] This invention relates to a system that utilizes personal data based on user requests and combines it with an emotion engine to provide optimal output using a generative AI model. This system collects and analyzes personal data and emotion data according to the user's specific needs and emotions, and provides this to a generative AI model to generate optimal suggestions and recommendations, which are then presented to the user.

[0263] Accepting requests from users

[0264] A user inputs a request, such as "Tell me what movie I should watch next," using an application installed on a device such as a smartphone or PC. The device receives the request and collects personal data such as the user's viewing history, ratings, and current emotional state.

[0265] Emotion recognition by emotion engine

[0266] The device analyzes the user's voice, facial expressions, text input, etc., and recognizes the user's current emotions using an emotion engine (e.g., a deep learning model). For example, the device collects facial expressions and speech content while the user is inputting a request through a camera or microphone and analyzes them in real time. The emotion engine generates user emotion data from this data and sends this emotion data to the server as personal data.

[0267] Collection and transmission of personal and emotional data

[0268] The device collects user operation logs, input data, and emotion data, formats them in JSON format, and sends them to the server. In this invention, the communication between the device and the server uses the HTTPS protocol to ensure security.

[0269] Data acquisition and analysis by the server

[0270] The server receives the data sent from the device. It then retrieves additional personal data from a database (such as past purchase history and viewing trends) and integrates this data. The server converts the integrated data into a prompt to be input into the generative AI model. Specifically, the prompt generated is, "Please recommend the next movie to watch based on the user's viewing history, ratings, and emotional data obtained from their speech and facial expressions."

[0271] Generative AI model generates output

[0272] The generative AI model receives the prompt and analyzes the user's personal and emotional data. For example, GPT-3 or other advanced natural language processing models are used as the generative AI model. The generative AI model generates an output that best suits the user's needs and emotions. For example, if a user requests, "What movie should I watch next?", the generative AI model will consider their viewing history, ratings, and emotional state to recommend an appropriate movie.

[0273] Sending and viewing recommendations

[0274] The server receives the recommendations generated by the generative AI model. The server then sends these recommendations to the user's device. The device displays the received recommendations to the user. Specifically, they are displayed as "movies to watch next" on the application interface. The user can view the displayed recommendations and choose the next movie to watch.

[0275] Specific examples

[0276] For example, if a user opens an application and requests, "What movie should I watch next?", the device receives this request and collects the user's viewing history, rating data, and emotional state analyzed from speech and facial expressions. These data are sent to the server in JSON format. The server then integrates additional personal data from the database and provides it to the generative AI model as a prompt (e.g., "Recommend the next movie to watch based on the user's viewing history, rating, and emotional data obtained from speech and facial expressions."). The generative AI model analyzes this data and generates a list of movies that the user might be interested in. The server then sends the generated list to the device, which then displays it to the user. In this way, the user can easily select their next viewing content that suits their preferences.

[0277] As described above, the present invention can significantly improve the user experience and a company's competitive advantage by effectively utilizing personal data and emotional data to generate individually optimized output.

[0278] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0279] Step 1:

[0280] A user opens the application and types in a request such as "What movie should I watch next?"

[0281] Input: User request: "What movie should I watch next?"

[0282] Output: The terminal captures the request

[0283] Specific operation: The user inputs a request through an input device such as a smartphone or PC, and the relevant application receives the request.

[0284] Step 2:

[0285] The device analyzes the user's voice, facial expressions, text input, etc., and generates emotional data using an emotion engine.

[0286] Input: User voice data, video data, and text input

[0287] Output: Emotion data

[0288] Specific operation: The device uses a microphone and camera to collect the user's voice and facial expressions, analyzes this data through an emotion engine (e.g., a deep learning model), and identifies the user's emotional state (e.g., joy, anger, sadness, etc.).

[0289] Step 3:

[0290] The device collects the user's viewing history and rating data, and sends it to the server in JSON format along with emotional data.

[0291] Input: User viewing history, rating data, and emotion data

[0292] Output: JSON data sent to the server

[0293] Specific operation: The device collects past viewing history, rating data, and newly generated emotion data, formats it into JSON format, and sends it to the server using the HTTPS protocol.

[0294] Step 4:

[0295] The server receives the data sent from the terminal and retrieves additional personal data from a database.

[0296] Input: JSON format data (viewing history, rating data, emotion data)

[0297] Output: A consolidated dataset

[0298] Specific operation: The server receives the JSON data sent from the device, queries the database for additional personal data to obtain the required data, and integrates this composite data.

[0299] Step 5:

[0300] The server converts the integrated data into prompt sentences and provides them to the generative AI model.

[0301] Input: Integrated dataset

[0302] Output: The prompt sentence that is fed into the generative AI model

[0303] Specific operation: Based on the integrated data, the server generates a prompt such as, "Please recommend the next movie to watch based on the user's viewing history, ratings, and emotional data obtained from speech and facial expressions."

[0304] Step 6:

[0305] A generative AI model generates optimal recommendations based on the prompt text.

[0306] Input: prompt statement

[0307] Output: Recommendation results

[0308] How it works: A generative AI model (e.g., GPT-3) analyzes the prompt and generates a list of movies to watch next based on the user's viewing history, ratings, and emotional state.

[0309] Step 7:

[0310] The server sends the recommendation results generated by the generative AI model to the terminal.

[0311] Input: Recommendation results

[0312] Output: Data sent to the terminal

[0313] Specific operation: The server receives the recommendation results from the generative AI model and sends them to the terminal using the HTTPS protocol.

[0314] Step 8:

[0315] The terminal displays the recommendation results to the user.

[0316] Input: Recommendation results

[0317] Output: Recommendation results displayed on the user's screen

[0318] Specific operation: The device displays the received recommendation results on the application UI, and the user can select the next movie to watch from the displayed recommendation list.

[0319] (Application example 2)

[0320] 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."

[0321] In conventional content distribution services, it has been difficult to make optimal recommendations based on a user's current emotional state simply by utilizing the user's personal data. This has led to problems such as users finding content that matches their emotions at any given time, resulting in a decrease in satisfaction with the service. The present invention aims to solve this problem by providing a content recommendation system that also takes into account the user's emotional state.

[0322] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0323] In this invention, the server includes means for receiving a request from a user, means for collecting personal data of the user, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for recognizing the user's emotions using voice analysis, facial expression analysis, and text analysis, and means for collecting the recognized emotional data as personal data and transmitting it to the server, thereby enabling optimal content to be recommended according to the user's emotional state.

[0324] "Means for receiving requests from users" refers to a function for receiving requests or questions entered by users.

[0325] "Means of collecting users' personal data" refers to the function of collecting data specific to individuals, such as users' viewing history, ratings, and location information.

[0326] "Means for transmitting collected personal data to a server" refers to the function of transferring collected personal data to a server via the Internet, etc.

[0327] "Means for obtaining additional personal data from the database" refers to the functionality by which the server retrieves further relevant data from the database.

[0328] "Means for providing acquired personal data to a generative AI model" refers to the function of providing collected and acquired data for input into a generative AI model.

[0329] "Means for receiving optimal recommendations generated by a generative AI model" refers to the function of receiving recommendations made by a generative AI model.

[0330] "Means for transmitting received recommendations to the user's device" refers to a function for the server to send the received recommendation results to the user's device.

[0331] "Means for displaying recommendations on the user's device" refers to a function for displaying recommended results on the user's device.

[0332] "Means for recognizing a user's emotions using voice analysis, facial expression analysis, and text analysis" refers to a function that analyzes a user's voice, facial expression, text input, etc. to grasp the user's emotional state.

[0333] "Means for collecting recognized emotion data as personal data and transmitting it to a server" refers to a function for compiling recognized emotion information as personal data and transferring it to a server.

[0334] The present invention provides a system for recommending optimal content using a generative AI model by utilizing personal data and emotional data of users in a content distribution service. Specific embodiments for carrying out the present invention will be described below.

[0335] First, a user uses a device such as a smartphone to request, "Tell me the next movie I should watch." The device receives this request and then collects the user's personal data and current emotional state. Personal data includes the user's viewing history, ratings, location information, etc. Emotional state is also obtained through voice analysis, facial expression analysis, and text analysis. Specifically, voice analysis uses voice recognition software (e.g., OpenAI's Whisper), facial expression analysis uses a facial recognition API (e.g., Microsoft Azure's Face API), and text analysis uses a natural language processing tool (e.g., OpenAI GPT-4).

[0336] The collected personal and emotional data is sent to a server, which retrieves additional personal data from a database (e.g., Amazon Web Services' RDS), integrates this data, and provides it to a generative AI model (e.g., OpenAI GPT-4). The generative AI model analyzes this integrated data and generates recommended content that best suits the user's needs and current emotions.

[0337] The generated recommended content is sent to the user's device via the server, and the device displays the recommended results. The user can then select the next movie to watch by looking at the recommended results. For example, if a user is looking for a relaxing movie, suitable movies will be recommended based on their past viewing history and current fatigue state.

[0338] As a concrete example, the prompt sentence is shown below.

[0339] User is looking for the next movie to watch. Based on past viewing history and current emotional state: tired. Recommend a relaxing movie.

[0340] In this way, by implementing the present invention, it becomes possible to recommend content with higher accuracy, taking into account the emotional state of the user, and an improvement in user satisfaction can be expected.

[0341] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0342] Step 1:

[0343] A user inputs a request using a device such as a smartphone. For example, the user inputs "Tell me the next movie I should watch." The input request is received by the device and stored for further processing.

[0344] Input: User request text

[0345] Output: Saved request

[0346] Specific behavior: A user opens the application, enters a request in text, and presses the send button.

[0347] Step 2:

[0348] The device collects your personal data, including your viewing history, ratings, and location information for the applications you use, and aggregates the collected data for further processing.

[0349] Input: User operation log, viewing history, ratings, location information

[0350] Output: Collected personal data

[0351] Specific operation: The device automatically retrieves viewing history and rating information from the application's database and obtains current location information from GPS.

[0352] Step 3:

[0353] The device recognizes the user's emotional state using voice analysis, facial expression analysis, and text analysis. Voice analysis uses voice recognition software, and facial expression analysis uses a facial recognition API. Emotional data is collected for further processing.

[0354] Input: User's voice data, facial expression data, text data

[0355] Output: Recognized emotion data

[0356] Specific operation: The device records the user's voice with a microphone, captures facial expressions with a camera, and processes them with analysis software.

[0357] Step 4:

[0358] The collected personal and emotional data is sent from the device to a server using a secure communication protocol.

[0359] Input: Collected personal and emotional data

[0360] Output: Data sent to the server

[0361] Specific operation: The device sends data to the specified endpoint using the HTTPS protocol.

[0362] Step 5:

[0363] The server retrieves additional personal data from the database, which is then merged with the data already received.

[0364] Input: Additional personal data stored on the server

[0365] Output: Consolidated personal data

[0366] Specific operation: The server retrieves the user's profile data and past behavior history from the database and merges them with the received data.

[0367] Step 6:

[0368] The server provides the integrated personal and emotional data to the generative AI model, which then analyzes the data and generates optimal recommendations.

[0369] Input: Integrated personal and emotional data

[0370] Output: Generated recommendation content

[0371] Specific operation: The server passes the integrated data as input to the generative AI model to generate a prompt sentence for content recommendation.

[0372] Step 7:

[0373] The server receives the optimal recommendations generated by the generative AI model and stores them for the next step.

[0374] Input: Recommended content by generative AI model

[0375] Output: Received recommendation results

[0376] Specific operation: The server receives and stores the results from the generative AI model.

[0377] Step 8:

[0378] The server then sends the received recommendation results to the user's device using a secure communication protocol.

[0379] Input: Received recommendation results

[0380] Output: Recommendation results sent to the user's device

[0381] Specific operation: The server sends the recommendation results to the user's terminal using the HTTPS protocol.

[0382] Step 9:

[0383] The user's device receives the recommendation results and displays them on the screen, allowing the user to review the results and select the next movie to watch.

[0384] Input: Recommendation results received from the server

[0385] Output: Recommendation results displayed on the device

[0386] Specific operation: The recommendation results received by the terminal are sent to the user interface and converted into an appropriate format for display.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] [Second embodiment]

[0391] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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."

[0403] This invention relates to a system that utilizes personal data based on user requests and uses generative AI to provide optimal output. This system collects personal data based on the user's specific needs, provides it to a generative AI model, and generates optimal suggestions and recommendations, which are then presented to the user.

[0404] Accepting requests from users

[0405] The user uses the application to input a request such as "Tell me the next movie I should watch." The device receives this request and collects personal data such as the user's viewing history and ratings.

[0406] Collection and transmission of personal data

[0407] The device collects the user's operation log and input data and sends it to the server. At this time, the collected personal data is properly formatted and provided in a format that the server can easily analyze.

[0408] Data acquisition and analysis by the server

[0409] The server receives the data sent from the device, retrieves additional personal data from the database, and integrates this data. The server then provides the integrated personal data to the generative AI model.

[0410] Generative AI model generates output

[0411] The generative AI model analyzes the user's personal data and generates output that best suits the user's needs. For example, if a user requests, "What movie should I watch next?", the generative AI model will take into account viewing history and ratings to recommend an appropriate movie.

[0412] Sending and viewing recommendations

[0413] The server receives the recommendations generated by the generative AI model. The server then sends the recommendations to the device. The device displays the received recommendations to the user. The user then selects the next movie to watch based on the displayed recommendations.

[0414] Specific examples

[0415] For example, consider the case where a user uses this system to request, "What book should I read next?" The device collects the user's reading history, past ratings and reviews, etc., and sends this to the server. The server retrieves additional information from the database and provides it to the generative AI model. The generative AI model analyzes this data and generates a list of books that the user might be interested in. The server sends the generated list to the device, which displays it to the user. In this way, the user can easily select their next reading preference.

[0416] With the above-mentioned configuration, the present invention can effectively utilize the user's personal data to generate individually optimized output, thereby significantly increasing a company's competitive advantage.

[0417] The processing flow will be explained below.

[0418] Step 1: User enters request

[0419] A user launches a movie recommendation app and types, "What movie should I watch next?"

[0420] Step 2: The terminal receives user input

[0421] The terminal receives the user's request.

[0422] The terminal collects personal data such as the user's past viewing history and ratings from the terminal's cache or database.

[0423] Step 3: The device sends the data to the server

[0424] The device formats the personal data collected and the user's request into JSON format.

[0425] The terminal sends the formatted data to the server.

[0426] Step 4: The server receives the data

[0427] The server receives the JSON data sent from the device.

[0428] The server analyzes the received data and identifies the required personal data corresponding to the request content.

[0429] Step 5: The server retrieves additional data from the database

[0430] The server retrieves additional personal data from the database (e.g., recent viewing history and ratings).

[0431] The server merges the additional data it retrieves with the existing data.

[0432] Step 6: The server invokes the generative AI model

[0433] The server provides the integrated personal data to the generative AI model.

[0434] The server calls the API of the generated AI model and provides personal data as an argument.

[0435] Step 7: The generative AI model generates the output

[0436] The generative AI model analyzes the provided data and generates an optimal list of movies to watch next based on the user's viewing history and ratings.

[0437] The recommendation list generated by the generative AI model is returned to the server in JSON format.

[0438] Step 8: The server receives the output of the generated AI.

[0439] The server receives the recommendation list returned by the generative AI model.

[0440] The server cleans up the received recommendation list and formats it as needed.

[0441] Step 9: Server sends output to terminal

[0442] The server sends the formatted recommendation list to the terminal.

[0443] Step 10: The terminal displays the output to the user

[0444] The terminal receives the recommendation list received from the server and visually displays it to the user.

[0445] The user selects the next movie to watch from the displayed list.

[0446] In this way, specific actions at each step allow the user to receive individually optimized output.

[0447] Example 1

[0448] 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."

[0449] Conventional recommendation systems have been unable to effectively utilize users' personal data, making it difficult to provide optimal recommendations tailored to user needs. Collecting and analyzing personal data also takes time and effort, reducing system efficiency. To address these issues, a system is needed that can quickly and efficiently collect and analyze personal data based on user requests and provide optimal output using a generative AI model.

[0450] 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.

[0451] In this invention, the server includes means for accepting requests from users, means for collecting personal data of users, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for the terminal to appropriately format the collected personal data, means for the server to integrate the data and input it into the generative AI model, and means for the generative AI model to analyze and generate output. This makes it possible to effectively utilize the user's personal data and quickly and efficiently provide individually optimized recommendation results.

[0452] "User request" refers to the wishes or requests that a user inputs into the system.

[0453] "Personal data" refers to data related to individual attributes and behavior, such as personal information about a user, behavioral history, and evaluation information.

[0454] "Terminal" is a general term for devices operated by users, including smartphones, tablets, and personal computers.

[0455] A "server" refers to a computer system that manages and processes data on a network, and is responsible for integrating and analyzing data from multiple terminals.

[0456] A "database" is a collection of data that is systematically organized and stored, and is used to store personal data and various other information for easy searching and retrieval.

[0457] "Generative AI models" refer to algorithms and trained data models that use artificial intelligence technology to analyze users' personal data and generate optimal outputs.

[0458] "Formatting" means the process of putting data into a particular form or structure to make it easier to analyze or communicate.

[0459] "Recommendations" refer to information and suggestions presented as a result of analysis by a generative AI model, and are provided in a form optimized to meet the user's needs.

[0460] "Output" refers to the results or proposals that a generative AI model ultimately generates after analysis, including various information and lists provided to users.

[0461] "Integration" refers to the process of bringing together data from different sources to make it consistent and improve the accuracy of analysis and recommendations.

[0462] This invention is a system that utilizes personal data based on user requests and uses a generative AI model to provide optimal output. The system aims to collect and analyze personal data that meets the user's needs and provide highly accurate recommendations to the user. The entire system is mainly composed of four main components: a terminal, a server, a database, and a generative AI model.

[0463] The user uses the device to input a request such as "Tell me what movie I should watch next." The device receives this request and collects personal data such as the user's past viewing history and ratings. This collected data is then appropriately formatted and sent to the server.

[0464] The server receives the data sent from the device and temporarily stores it in a buffer. Then, if additional data is needed, it retrieves additional personal data from the database and aggregates this data. This brings all relevant data into one unified dataset, ready to be fed to the generative AI model.

[0465] The generative AI model analyzes the user's personal data and generates an output that best suits the user's needs. This output is based on the data and algorithms that the generative AI model has learned. When a user requests, "Tell me what movie I should watch next," the generative AI model takes into account viewing history and ratings to generate a list of optimal movie recommendations.

[0466] The server receives the recommendations generated by the generative AI model and sends them to the device. The device then displays the recommendations to the user. The user can then select the next movie to watch by looking at the displayed recommendations. Through this process, the user receives the best recommendations based on their preferences and past behavioral history.

[0467] Specific examples

[0468] For example, consider the case where a user uses this system to request, "What book should I read next?" The device collects the user's reading history, past ratings, and reviews, and sends this to the server. The server retrieves additional reading data from the database, integrates it, and then provides it to the generative AI model. The generative AI model analyzes this data and generates a list of books that the user might be interested in. The server sends the generated list of books to the device, which displays it to the user. The user can then select the next book to read based on the displayed list.

[0469] Prompt Sentence Examples

[0470] Tell me what movie I should watch next

[0471] What books do you recommend?

[0472] Tell me where I should travel next

[0473] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0474] Step 1:

[0475] The user inputs a request. The user inputs a request using a device. Specifically, the user inputs a request such as "Tell me the next movie I should watch" through an application on a smartphone or tablet. This input is captured by the device. The input data is saved in text format as a prompt sentence.

[0476] Step 2:

[0477] The device collects personal data. The device retrieves user operation logs, viewing history, and rating data from an internal database or cache. This includes movies the user has previously viewed and their ratings. The collected data is formatted in an easy-to-parse format (e.g., JSON).

[0478] Step 3:

[0479] The device sends the collected personal data to the server. The device then sends the formatted personal data to the cloud server using a secure protocol such as HTTPS. The sent data includes the request prompt and the personal data.

[0480] Step 4:

[0481] The server receives the data sent from the device. The server temporarily stores the received data in a buffer and stores it in the appropriate data storage. The input data is personal data and a request prompt. This prepares the server for analysis and additional data acquisition.

[0482] Step 5:

[0483] The server retrieves additional personal data from the database. The server executes SQL queries to retrieve additional personal data related to the user from the database, including past browsing history, ratings, and related user rating data. The retrieved data is consolidated on the server.

[0484] Step 6:

[0485] The server provides the integrated data to the generative AI model. The server integrates the data acquired from the device with additional data from the database and provides it to the generative AI model (e.g., GPT-4). The input data is the integrated personal dataset. This allows the generative AI model to efficiently begin analysis.

[0486] Step 7:

[0487] The generative AI model generates recommendation results. The generative AI model analyzes the integrated personal data and generates output that best suits the user's needs. Specifically, it generates a list of movie recommendations based on viewing history and ratings. The output data is a list of recommended movies.

[0488] Step 8:

[0489] The server receives the recommendation results from the generative AI model. The server receives and stores the generated recommendation results in a data format such as JSON, which prepares the recommendation results for transmission to the device.

[0490] Step 9:

[0491] The server sends the recommendation results to the terminal. The server then sends the received recommendation results to the terminal using a secure protocol such as HTTPS. The input data is the recommendation result data, which is sent to the terminal as output.

[0492] Step 10:

[0493] The device displays the recommended results to the user. The device displays the recommended results received from the server to the user. Specifically, a list of recommended movies is displayed on the smartphone application screen. The user can refer to this list and select the next movie to watch.

[0494] (Application example 1)

[0495] 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."

[0496] Conventional content recommendation systems have not been able to fully utilize users' personal data, making it difficult to recommend optimal content to users. Furthermore, there is a lack of a means to effectively analyze users' past viewing history and rating data, generate prompts, and provide optimal recommendations based on those prompts. This often leaves users dissatisfied because they are unable to easily find content that matches their preferences.

[0497] 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.

[0498] In this invention, the server includes means for receiving a request from a user, means for collecting personal data of the user, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for providing prompt sentences generated based on the user's past viewing history and rating data to the generative AI model, and means for transmitting recommendation results generated from the prompt sentences to the server before displaying them to the user. This makes it possible to effectively utilize the user's personal data and provide individually optimized content to the user.

[0499] The "means for receiving requests from a user" is a function for receiving requests or questions input by a user through an application.

[0500] "Means for collecting user personal data" refers to a function that collects personal information such as the user's past behavioral history, ratings, and location information.

[0501] "Means for transmitting collected personal data to a server" refers to a function that transfers personal information collected from a user's terminal to a server via a network.

[0502] "Means for obtaining additional personal data from the database" refers to the function of retrieving necessary additional information from other related databases stored on the server.

[0503] "Means for providing acquired personal data to a generative AI model" refers to the function of handing over collected and acquired personal data to an AI model for analytical processing.

[0504] "Means for receiving optimal recommendations generated by a generative AI model" refers to a function for receiving recommendation results created by a generative AI model.

[0505] The "means for transmitting the received recommendation to the user's terminal" is a function for transferring the received recommendation results to the user's terminal.

[0506] The "means for displaying recommendations on the user's terminal" is a function for visually displaying the recommendation results on the user's terminal.

[0507] "Means for providing prompt sentences generated based on the user's past viewing history and rating data to a generative AI model" is a function for providing prompt sentences generated based on the user's past viewing history and rating data to an AI model.

[0508] The "means for sending the recommendation results generated from the prompt sentence to the server before displaying them to the user" is a function that returns the generated recommendation results to the server for confirmation or additional processing before displaying them to the user.

[0509] This invention relates to a system that utilizes personal data based on user requests and uses generative AI to provide optimal output. This system aims to recommend optimal content based on user viewing history and rating data, particularly for content distribution services.

[0510] Program Overview

[0511] This system mainly consists of the following process: First, the user inputs a request using a smartphone application. This request is for recommendations of movies, TV shows, etc. to watch next. The device receives this request, collects the user's past viewing history and rating data, and sends them to the server.

[0512] Hardware and software used

[0513] Hardware: Smartphone

[0514] Software: Python 3.x, Requests library, Flask (server side)

[0515] Processing flow

[0516] The server receives the user's personal data and retrieves additional personal data from the database. The collected and retrieved personal data is then provided to the generative AI model to generate prompt sentences. Based on the generated prompt sentences, the generative AI model recommends optimal content.

[0517] Prompt Sentence Examples

[0518] For example, if user "MovieFan123" requests "What movie should I watch next?", the following prompt will be generated:

[0519] "The user with user ID MovieFan123's viewing history includes The Matrix, Inception, and Interstellar, with ratings of 5, 4, and 5, respectively. Recommend the next best movie for this user."

[0520] Based on this, the generative AI model recommends a list of content (e.g., "Blade Runner 2049," "The Terminator," "Eternal Sunshine of the Spotless Mind") and sends it to the server, which then sends the recommendations to the user's device, which then displays them to the user.

[0521] Specific examples

[0522] As a concrete example, suppose a user requests an application, "What movie should I watch next?" The system generates a prompt based on the user's viewing history and rating data (e.g., "The Matrix" 5, "Inception" 4, "Interstellar" 5) and provides it to the generative AI model. Based on this data, the generative AI model recommends "Blade Runner 2049," "The Terminator," and "Eternal Sunshine of the Spotless Mind." The server sends the recommendation results to the user's smartphone, and the application displays them to the user. This allows the user to easily select the next movie to watch.

[0523] This process makes it possible to effectively utilize the user's personal data and provide individually optimized content.

[0524] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0525] Step 1:

[0526] A user types a request into a smartphone application, sending a request such as "Tell me what movie I should watch next."

[0527] Input: User request

[0528] Output: Request string

[0529] Specific operation: The user uses the app interface to enter a request and presses the send button.

[0530] Step 2:

[0531] The device collects and stores the user's viewing history and rating data.

[0532] Input: User viewing history and rating data

[0533] Output: Formatted personal data

[0534] What it does: The app retrieves the user's past viewing history and rating data from a local database or cloud service and formats it into a usable format.

[0535] Step 3:

[0536] The terminal transmits the collected personal data to the server.

[0537] Input: Formatted personal data

[0538] Output: Data request sent to the server

[0539] Specific operation: The device sends the collected data to the specified API endpoint using an HTTP request, etc.

[0540] Step 4:

[0541] The server retrieves the additional personal data from the database.

[0542] Input: Personal data submitted

[0543] Output: Consolidated personal data

[0544] Specific operation: Based on the data received by the server, related additional data is retrieved from the database using a query and integrated.

[0545] Step 5:

[0546] The server provides the integrated personal data to the generative AI model to generate prompt sentences.

[0547] Input: Integrated personal data

[0548] Output: Generated prompt statement

[0549] How it works: The server analyzes the integrated data and generates effective prompts for the generative AI model. The prompts are created in text format based on past viewing history and rating data.

[0550] Step 6:

[0551] A generative AI model generates optimal recommendations based on the prompt.

[0552] Input: prompt statement

[0553] Output: A list of recommendations

[0554] How it works: The generative AI model analyzes the prompt and uses algorithms and learned data to generate optimal recommendations.

[0555] Step 7:

[0556] The server sends the recommendation results received from the generative AI model to the user's device.

[0557] Input: List of recommended results

[0558] Output: Recommendation results sent to the user's device

[0559] Specific operation: The server sends the recommendation results to the user's device using a secure communication method.

[0560] Step 8:

[0561] The terminal displays the recommendation results to the user.

[0562] Input: List of recommended results

[0563] Output: Displayed recommendation results

[0564] Specific operation: The user's device receives the recommendation results and displays them on the screen. Specifically, the titles and ratings of the recommended movies are displayed in an easy-to-read format.

[0565] This allows users to easily find content that suits their preferences and select what to watch next.

[0566] 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.

[0567] This invention relates to a system that utilizes personal data based on user requests and combines it with an emotion engine to provide optimal output using generative AI. This system collects and analyzes personal data and emotion data according to the user's specific needs and emotions, and provides this to a generative AI model to generate optimal suggestions and recommendations, which are then presented to the user.

[0568] Accepting requests from users

[0569] The user uses the application to input a request such as "Tell me the next movie I should watch." The device receives this request and collects personal data such as the user's past viewing history, ratings, and current emotional state.

[0570] Emotion recognition by emotion engine

[0571] The device analyzes the user's voice, facial expressions, text input, etc., and uses an emotion engine to recognize the user's current emotion. The recognized emotion data is sent to the server as personal data.

[0572] Collection and transmission of personal and emotional data

[0573] The device collects the user's operation log, input data, and emotional data, and sends it to the server, where it is properly formatted and provided in a format that the server can easily analyze.

[0574] Data acquisition and analysis by the server

[0575] The server receives the data sent from the device, retrieves additional personal data from a database, and integrates this data. The server then provides the integrated data to the generative AI model.

[0576] Generative AI model generates output

[0577] The generative AI model analyzes the user's personal and emotional data to generate an output that best suits the user's needs and emotions. For example, if a user requests, "Tell me the next movie I should watch," the generative AI model will consider their viewing history, ratings, and emotional state to recommend an appropriate movie.

[0578] Sending and viewing recommendations

[0579] The server receives the recommendations generated by the generative AI model. The server then sends the recommendations to the device. The device displays the received recommendations to the user. The user then selects the next movie to watch based on the displayed recommendations.

[0580] Specific examples

[0581] For example, consider the case where a user uses this system to request, "Tell me the next movie I should watch." The device collects the user's viewing history, ratings, and emotional state analyzed from speech and facial expressions, and sends this to the server. The server retrieves additional information from the database and provides it to the generative AI model. The generative AI model analyzes this data and generates a list of movies that the user might be interested in. The server sends the generated list to the device, which displays it to the user. In this way, the user can easily select the next viewing content that suits their preferences.

[0582] With the above configuration, the present invention can effectively utilize personal data and emotional data to generate individually optimized output, thereby significantly increasing a company's competitive advantage.

[0583] The processing flow will be explained below.

[0584] Step 1: User enters request

[0585] A user launches a movie recommendation app and types, "What movie should I watch next?"

[0586] Step 2: The terminal receives user input

[0587] The terminal receives the user's request.

[0588] The device collects personal data such as the user's past viewing history and ratings from the device's cache or local database.

[0589] Step 3: The device uses the emotion engine to recognize emotions.

[0590] The device analyzes the user's voice, facial expressions, and text input, and uses an emotion engine to recognize their current emotional state.

[0591] The recognized emotion data is recorded as personal data.

[0592] Step 4: The device sends the data to the server

[0593] The device formats the user's request, including the personal data and emotional data collected, into JSON format.

[0594] The terminal sends the formatted data to the server.

[0595] Step 5: The server receives the data

[0596] The server receives the JSON data sent from the device.

[0597] The server analyzes the received data and identifies the necessary personal data and emotion data corresponding to the request content.

[0598] Step 6: The server retrieves additional data from the database

[0599] The server retrieves additional personal data from the database (e.g., recent viewing history and ratings).

[0600] Matching and integrating any additional data retrieved by the server.

[0601] Step 7: The server invokes the generative AI model

[0602] The server provides the integrated personal data and emotional data as variables to the generative AI model.

[0603] The server calls the API of the generative AI model and provides personal data and emotional data as arguments.

[0604] Step 8: The generative AI model generates the output

[0605] A generative AI model analyzes the provided data and generates an optimal list of movies to watch next based on the user's viewing history, ratings, and emotional state.

[0606] The recommendation list generated by the generative AI model is returned to the server in JSON format.

[0607] Step 9: The server receives the output of the generated AI.

[0608] The server receives the recommendation list returned by the generative AI model.

[0609] The server cleans up the received recommendation list and formats it as needed.

[0610] Step 10: Server sends output to terminal

[0611] The server sends the formatted recommendation list to the terminal.

[0612] Step 11: The terminal displays the output to the user

[0613] The terminal receives the recommendation list received from the server and visually displays it to the user.

[0614] The user selects the next movie to watch from the displayed list.

[0615] In this way, specific actions at each step allow users to receive individually optimized outputs. This system takes into account the user's emotions in particular, thereby realizing more personalized service provision.

[0616] Example 2

[0617] 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."

[0618] Conventional recommendation systems only provide recommendations based on the user's personal data, making it difficult to make optimal recommendations that take into account the user's current emotional state.In addition, the lack of appropriate data collection, analysis, and recommendations based on the user's emotional state limited the user experience.

[0619] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0620] In this invention, the server includes means for receiving a request from a user, means for collecting personal data and emotional data of the user, means for transmitting the collected personal data and emotional data to the server, means for acquiring additional personal data from a database in the server, means for converting the acquired personal data and emotional data into prompt sentences and providing the prompt sentences to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, and means for displaying the recommendations on the user's terminal. This enables optimal recommendations that take into account both the user's personal data and current emotional state.

[0621] A "request" is a request or inquiry made by a user to the system.

[0622] "Personal data" refers to personal data such as a user's viewing history, ratings, and emotional state based on speech and facial expressions.

[0623] "Emotional data" refers to data that indicates the user's current emotional state, analyzed from voice, facial expressions, text input, and the like.

[0624] "Server" means a device or system that receives data sent from a user device, acquires and integrates additional data, and provides it to a generative AI model.

[0625] A "generative AI model" is an artificial intelligence model that generates optimal recommendation results based on input data.

[0626] A "prompt sentence" is an input sentence formatted to be provided to a generative AI model.

[0627] "Recommendations" refer to suggestions or recommendations generated by a generative AI model based on a user's personal and emotional data.

[0628] A "terminal" is a device that is directly operated by a user and that inputs requests, collects and transmits data, and displays recommendation results.

[0629] This invention relates to a system that utilizes personal data based on user requests and combines it with an emotion engine to provide optimal output using a generative AI model. This system collects and analyzes personal data and emotion data according to the user's specific needs and emotions, and provides this to a generative AI model to generate optimal suggestions and recommendations, which are then presented to the user.

[0630] Accepting requests from users

[0631] A user inputs a request, such as "Tell me what movie I should watch next," using an application installed on a device such as a smartphone or PC. The device receives the request and collects personal data such as the user's viewing history, ratings, and current emotional state.

[0632] Emotion recognition by emotion engine

[0633] The device analyzes the user's voice, facial expressions, text input, etc., and recognizes the user's current emotions using an emotion engine (e.g., a deep learning model). For example, the device collects facial expressions and speech content while the user is inputting a request through a camera or microphone and analyzes them in real time. The emotion engine generates user emotion data from this data and sends this emotion data to the server as personal data.

[0634] Collection and transmission of personal and emotional data

[0635] The device collects user operation logs, input data, and emotion data, formats them in JSON format, and sends them to the server. In this invention, the communication between the device and the server uses the HTTPS protocol to ensure security.

[0636] Data acquisition and analysis by the server

[0637] The server receives the data sent from the device. It then retrieves additional personal data from a database (such as past purchase history and viewing trends) and integrates this data. The server converts the integrated data into a prompt to be input into the generative AI model. Specifically, the prompt generated is, "Please recommend the next movie to watch based on the user's viewing history, ratings, and emotional data obtained from their speech and facial expressions."

[0638] Generative AI model generates output

[0639] The generative AI model receives the prompt and analyzes the user's personal and emotional data. For example, GPT-3 or other advanced natural language processing models are used as the generative AI model. The generative AI model generates an output that best suits the user's needs and emotions. For example, if a user requests, "What movie should I watch next?", the generative AI model will consider their viewing history, ratings, and emotional state to recommend an appropriate movie.

[0640] Sending and viewing recommendations

[0641] The server receives the recommendations generated by the generative AI model. The server then sends these recommendations to the user's device. The device displays the received recommendations to the user. Specifically, they are displayed as "movies to watch next" on the application interface. The user can view the displayed recommendations and choose the next movie to watch.

[0642] Specific examples

[0643] For example, if a user opens an application and requests, "What movie should I watch next?", the device receives this request and collects the user's viewing history, rating data, and emotional state analyzed from speech and facial expressions. These data are sent to the server in JSON format. The server then integrates additional personal data from the database and provides it to the generative AI model as a prompt (e.g., "Recommend the next movie to watch based on the user's viewing history, rating, and emotional data obtained from speech and facial expressions."). The generative AI model analyzes this data and generates a list of movies that the user might be interested in. The server then sends the generated list to the device, which then displays it to the user. In this way, the user can easily select their next viewing content that suits their preferences.

[0644] As described above, the present invention can significantly improve the user experience and a company's competitive advantage by effectively utilizing personal data and emotional data to generate individually optimized output.

[0645] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0646] Step 1:

[0647] A user opens the application and types in a request such as "What movie should I watch next?"

[0648] Input: User request: "What movie should I watch next?"

[0649] Output: The terminal captures the request

[0650] Specific operation: The user inputs a request through an input device such as a smartphone or PC, and the relevant application receives the request.

[0651] Step 2:

[0652] The device analyzes the user's voice, facial expressions, text input, etc., and generates emotional data using an emotion engine.

[0653] Input: User voice data, video data, and text input

[0654] Output: Emotion data

[0655] Specific operation: The device uses a microphone and camera to collect the user's voice and facial expressions, analyzes this data through an emotion engine (e.g., a deep learning model), and identifies the user's emotional state (e.g., joy, anger, sadness, etc.).

[0656] Step 3:

[0657] The device collects the user's viewing history and rating data, and sends it to the server in JSON format along with emotional data.

[0658] Input: User viewing history, rating data, and emotion data

[0659] Output: JSON data sent to the server

[0660] Specific operation: The device collects past viewing history, rating data, and newly generated emotion data, formats it into JSON format, and sends it to the server using the HTTPS protocol.

[0661] Step 4:

[0662] The server receives the data sent from the terminal and retrieves additional personal data from a database.

[0663] Input: JSON format data (viewing history, rating data, emotion data)

[0664] Output: A consolidated dataset

[0665] Specific operation: The server receives the JSON data sent from the device, queries the database for additional personal data to obtain the required data, and integrates this composite data.

[0666] Step 5:

[0667] The server converts the integrated data into prompt sentences and provides them to the generative AI model.

[0668] Input: Integrated dataset

[0669] Output: The prompt sentence that is fed into the generative AI model

[0670] Specific operation: Based on the integrated data, the server generates a prompt such as, "Please recommend the next movie to watch based on the user's viewing history, ratings, and emotional data obtained from speech and facial expressions."

[0671] Step 6:

[0672] A generative AI model generates optimal recommendations based on the prompt text.

[0673] Input: prompt statement

[0674] Output: Recommendation results

[0675] How it works: A generative AI model (e.g., GPT-3) analyzes the prompt and generates a list of movies to watch next based on the user's viewing history, ratings, and emotional state.

[0676] Step 7:

[0677] The server sends the recommendation results generated by the generative AI model to the terminal.

[0678] Input: Recommendation results

[0679] Output: Data sent to the terminal

[0680] Specific operation: The server receives the recommendation results from the generative AI model and sends them to the terminal using the HTTPS protocol.

[0681] Step 8:

[0682] The terminal displays the recommendation results to the user.

[0683] Input: Recommendation results

[0684] Output: Recommendation results displayed on the user's screen

[0685] Specific operation: The device displays the received recommendation results on the application UI, and the user can select the next movie to watch from the displayed recommendation list.

[0686] (Application example 2)

[0687] 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."

[0688] In conventional content distribution services, it has been difficult to make optimal recommendations based on a user's current emotional state simply by utilizing the user's personal data. This has led to problems such as users finding content that matches their emotions at any given time, resulting in a decrease in satisfaction with the service. The present invention aims to solve this problem by providing a content recommendation system that also takes into account the user's emotional state.

[0689] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0690] In this invention, the server includes means for receiving a request from a user, means for collecting personal data of the user, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for recognizing the user's emotions using voice analysis, facial expression analysis, and text analysis, and means for collecting the recognized emotional data as personal data and transmitting it to the server, thereby enabling optimal content to be recommended according to the user's emotional state.

[0691] "Means for receiving requests from users" refers to a function for receiving requests or questions entered by users.

[0692] "Means of collecting users' personal data" refers to the function of collecting data specific to individuals, such as users' viewing history, ratings, and location information.

[0693] "Means for transmitting collected personal data to a server" refers to the function of transferring collected personal data to a server via the Internet, etc.

[0694] "Means for obtaining additional personal data from the database" refers to the functionality by which the server retrieves further relevant data from the database.

[0695] "Means for providing acquired personal data to a generative AI model" refers to the function of providing collected and acquired data for input into a generative AI model.

[0696] "Means for receiving optimal recommendations generated by a generative AI model" refers to the function of receiving recommendations made by a generative AI model.

[0697] "Means for transmitting received recommendations to the user's device" refers to a function for the server to send the received recommendation results to the user's device.

[0698] "Means for displaying recommendations on the user's device" refers to a function for displaying recommended results on the user's device.

[0699] "Means for recognizing a user's emotions using voice analysis, facial expression analysis, and text analysis" refers to a function that analyzes a user's voice, facial expression, text input, etc. to grasp the user's emotional state.

[0700] "Means for collecting recognized emotion data as personal data and transmitting it to a server" refers to a function for compiling recognized emotion information as personal data and transferring it to a server.

[0701] The present invention provides a system for recommending optimal content using a generative AI model by utilizing personal data and emotional data of users in a content distribution service. Specific embodiments for carrying out the present invention will be described below.

[0702] First, a user uses a device such as a smartphone to request, "Tell me the next movie I should watch." The device receives this request and then collects the user's personal data and current emotional state. Personal data includes the user's viewing history, ratings, location information, etc. Emotional state is also obtained through voice analysis, facial expression analysis, and text analysis. Specifically, voice analysis uses voice recognition software (e.g., OpenAI's Whisper), facial expression analysis uses a facial recognition API (e.g., Microsoft Azure's Face API), and text analysis uses a natural language processing tool (e.g., OpenAI GPT-4).

[0703] The collected personal and emotional data is sent to a server, which retrieves additional personal data from a database (e.g., Amazon Web Services' RDS), integrates this data, and provides it to a generative AI model (e.g., OpenAI GPT-4). The generative AI model analyzes this integrated data and generates recommended content that best suits the user's needs and current emotions.

[0704] The generated recommended content is sent to the user's device via the server, and the device displays the recommended results. The user can then select the next movie to watch by looking at the recommended results. For example, if a user is looking for a relaxing movie, suitable movies will be recommended based on their past viewing history and current fatigue state.

[0705] As a concrete example, the prompt sentence is shown below.

[0706] User is looking for the next movie to watch. Based on past viewing history and current emotional state: tired. Recommend a relaxing movie.

[0707] In this way, by implementing the present invention, it becomes possible to recommend content with higher accuracy, taking into account the emotional state of the user, and an improvement in user satisfaction can be expected.

[0708] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0709] Step 1:

[0710] A user inputs a request using a device such as a smartphone. For example, the user inputs "Tell me the next movie I should watch." The input request is received by the device and stored for further processing.

[0711] Input: User request text

[0712] Output: Saved request

[0713] Specific behavior: A user opens the application, enters a request in text, and presses the send button.

[0714] Step 2:

[0715] The device collects your personal data, including your viewing history, ratings, and location information for the applications you use, and aggregates the collected data for further processing.

[0716] Input: User operation log, viewing history, ratings, location information

[0717] Output: Collected personal data

[0718] Specific operation: The device automatically retrieves viewing history and rating information from the application's database and obtains current location information from GPS.

[0719] Step 3:

[0720] The device recognizes the user's emotional state using voice analysis, facial expression analysis, and text analysis. Voice analysis uses voice recognition software, and facial expression analysis uses a facial recognition API. Emotional data is collected for further processing.

[0721] Input: User's voice data, facial expression data, text data

[0722] Output: Recognized emotion data

[0723] Specific operation: The device records the user's voice with a microphone, captures facial expressions with a camera, and processes them with analysis software.

[0724] Step 4:

[0725] The collected personal and emotional data is sent from the device to a server using a secure communication protocol.

[0726] Input: Collected personal and emotional data

[0727] Output: Data sent to the server

[0728] Specific operation: The device sends data to the specified endpoint using the HTTPS protocol.

[0729] Step 5:

[0730] The server retrieves additional personal data from the database, which is then merged with the data already received.

[0731] Input: Additional personal data stored on the server

[0732] Output: Consolidated personal data

[0733] Specific operation: The server retrieves the user's profile data and past behavior history from the database and merges them with the received data.

[0734] Step 6:

[0735] The server provides the integrated personal and emotional data to the generative AI model, which then analyzes the data and generates optimal recommendations.

[0736] Input: Integrated personal and emotional data

[0737] Output: Generated recommendation content

[0738] Specific operation: The server passes the integrated data as input to the generative AI model to generate a prompt sentence for content recommendation.

[0739] Step 7:

[0740] The server receives the optimal recommendations generated by the generative AI model and stores them for the next step.

[0741] Input: Recommended content by generative AI model

[0742] Output: Received recommendation results

[0743] Specific operation: The server receives and stores the results from the generative AI model.

[0744] Step 8:

[0745] The server then sends the received recommendation results to the user's device using a secure communication protocol.

[0746] Input: Received recommendation results

[0747] Output: Recommendation results sent to the user's device

[0748] Specific operation: The server sends the recommendation results to the user's terminal using the HTTPS protocol.

[0749] Step 9:

[0750] The user's device receives the recommendation results and displays them on the screen, allowing the user to review the results and select the next movie to watch.

[0751] Input: Recommendation results received from the server

[0752] Output: Recommendation results displayed on the device

[0753] Specific operation: The recommendation results received by the terminal are sent to the user interface and converted into an appropriate format for display.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] [Third embodiment]

[0758] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0759] 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.

[0760] 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).

[0761] 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.

[0762] 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.

[0763] 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).

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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."

[0770] This invention relates to a system that utilizes personal data based on user requests and uses generative AI to provide optimal output. This system collects personal data based on the user's specific needs, provides it to a generative AI model, and generates optimal suggestions and recommendations, which are then presented to the user.

[0771] Accepting requests from users

[0772] The user uses the application to input a request such as "Tell me the next movie I should watch." The device receives this request and collects personal data such as the user's viewing history and ratings.

[0773] Collection and transmission of personal data

[0774] The device collects the user's operation log and input data and sends it to the server. At this time, the collected personal data is properly formatted and provided in a format that the server can easily analyze.

[0775] Data acquisition and analysis by the server

[0776] The server receives the data sent from the device, retrieves additional personal data from the database, and integrates this data. The server then provides the integrated personal data to the generative AI model.

[0777] Generative AI model generates output

[0778] The generative AI model analyzes the user's personal data and generates output that best suits the user's needs. For example, if a user requests, "What movie should I watch next?", the generative AI model will take into account viewing history and ratings to recommend an appropriate movie.

[0779] Sending and viewing recommendations

[0780] The server receives the recommendations generated by the generative AI model. The server then sends the recommendations to the device. The device displays the received recommendations to the user. The user then selects the next movie to watch based on the displayed recommendations.

[0781] Specific examples

[0782] For example, consider the case where a user uses this system to request, "What book should I read next?" The device collects the user's reading history, past ratings and reviews, etc., and sends this to the server. The server retrieves additional information from the database and provides it to the generative AI model. The generative AI model analyzes this data and generates a list of books that the user might be interested in. The server sends the generated list to the device, which displays it to the user. In this way, the user can easily select their next reading preference.

[0783] With the above-mentioned configuration, the present invention can effectively utilize the user's personal data to generate individually optimized output, thereby significantly increasing a company's competitive advantage.

[0784] The processing flow will be explained below.

[0785] Step 1: User enters request

[0786] A user launches a movie recommendation app and types, "What movie should I watch next?"

[0787] Step 2: The terminal receives user input

[0788] The terminal receives the user's request.

[0789] The terminal collects personal data such as the user's past viewing history and ratings from the terminal's cache or database.

[0790] Step 3: The device sends the data to the server

[0791] The device formats the personal data collected and the user's request into JSON format.

[0792] The terminal sends the formatted data to the server.

[0793] Step 4: The server receives the data

[0794] The server receives the JSON data sent from the device.

[0795] The server analyzes the received data and identifies the required personal data corresponding to the request content.

[0796] Step 5: The server retrieves additional data from the database

[0797] The server retrieves additional personal data from the database (e.g., recent viewing history and ratings).

[0798] The server merges the additional data it retrieves with the existing data.

[0799] Step 6: The server invokes the generative AI model

[0800] The server provides the integrated personal data to the generative AI model.

[0801] The server calls the API of the generated AI model and provides personal data as an argument.

[0802] Step 7: The generative AI model generates the output

[0803] The generative AI model analyzes the provided data and generates an optimal list of movies to watch next based on the user's viewing history and ratings.

[0804] The recommendation list generated by the generative AI model is returned to the server in JSON format.

[0805] Step 8: The server receives the output of the generated AI.

[0806] The server receives the recommendation list returned by the generative AI model.

[0807] The server cleans up the received recommendation list and formats it as needed.

[0808] Step 9: Server sends output to terminal

[0809] The server sends the formatted recommendation list to the terminal.

[0810] Step 10: The terminal displays the output to the user

[0811] The terminal receives the recommendation list received from the server and visually displays it to the user.

[0812] The user selects the next movie to watch from the displayed list.

[0813] In this way, specific actions at each step allow the user to receive individually optimized output.

[0814] Example 1

[0815] 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."

[0816] Conventional recommendation systems have been unable to effectively utilize users' personal data, making it difficult to provide optimal recommendations tailored to user needs. Collecting and analyzing personal data also takes time and effort, reducing system efficiency. To address these issues, a system is needed that can quickly and efficiently collect and analyze personal data based on user requests and provide optimal output using a generative AI model.

[0817] 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.

[0818] In this invention, the server includes means for accepting requests from users, means for collecting personal data of users, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for the terminal to appropriately format the collected personal data, means for the server to integrate the data and input it into the generative AI model, and means for the generative AI model to analyze and generate output. This makes it possible to effectively utilize the user's personal data and quickly and efficiently provide individually optimized recommendation results.

[0819] "User request" refers to the wishes or requests that a user inputs into the system.

[0820] "Personal data" refers to data related to individual attributes and behavior, such as personal information about a user, behavioral history, and evaluation information.

[0821] "Terminal" is a general term for devices operated by users, including smartphones, tablets, and personal computers.

[0822] A "server" refers to a computer system that manages and processes data on a network, and is responsible for integrating and analyzing data from multiple terminals.

[0823] A "database" is a collection of data that is systematically organized and stored, and is used to store personal data and various other information for easy searching and retrieval.

[0824] "Generative AI models" refer to algorithms and trained data models that use artificial intelligence technology to analyze users' personal data and generate optimal outputs.

[0825] "Formatting" means the process of putting data into a particular form or structure to make it easier to analyze or communicate.

[0826] "Recommendations" refer to information and suggestions presented as a result of analysis by a generative AI model, and are provided in a form optimized to meet the user's needs.

[0827] "Output" refers to the results or proposals that a generative AI model ultimately generates after analysis, including various information and lists provided to users.

[0828] "Integration" refers to the process of bringing together data from different sources to make it consistent and improve the accuracy of analysis and recommendations.

[0829] This invention is a system that utilizes personal data based on user requests and uses a generative AI model to provide optimal output. The system aims to collect and analyze personal data that meets the user's needs and provide highly accurate recommendations to the user. The entire system is mainly composed of four main components: a terminal, a server, a database, and a generative AI model.

[0830] The user uses the device to input a request such as "Tell me what movie I should watch next." The device receives this request and collects personal data such as the user's past viewing history and ratings. This collected data is then appropriately formatted and sent to the server.

[0831] The server receives the data sent from the device and temporarily stores it in a buffer. Then, if additional data is needed, it retrieves additional personal data from the database and aggregates this data. This brings all relevant data into one unified dataset, ready to be fed to the generative AI model.

[0832] The generative AI model analyzes the user's personal data and generates an output that best suits the user's needs. This output is based on the data and algorithms that the generative AI model has learned. When a user requests, "Tell me what movie I should watch next," the generative AI model takes into account viewing history and ratings to generate a list of optimal movie recommendations.

[0833] The server receives the recommendations generated by the generative AI model and sends them to the device. The device then displays the recommendations to the user. The user can then select the next movie to watch by looking at the displayed recommendations. Through this process, the user receives the best recommendations based on their preferences and past behavioral history.

[0834] Specific examples

[0835] For example, consider the case where a user uses this system to request, "What book should I read next?" The device collects the user's reading history, past ratings, and reviews, and sends this to the server. The server retrieves additional reading data from the database, integrates it, and then provides it to the generative AI model. The generative AI model analyzes this data and generates a list of books that the user might be interested in. The server sends the generated list of books to the device, which displays it to the user. The user can then select the next book to read based on the displayed list.

[0836] Prompt Sentence Examples

[0837] Tell me what movie I should watch next

[0838] What books do you recommend?

[0839] Tell me where I should travel next

[0840] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0841] Step 1:

[0842] The user inputs a request. The user inputs a request using a device. Specifically, the user inputs a request such as "Tell me the next movie I should watch" through an application on a smartphone or tablet. This input is captured by the device. The input data is saved in text format as a prompt sentence.

[0843] Step 2:

[0844] The device collects personal data. The device retrieves user operation logs, viewing history, and rating data from an internal database or cache. This includes movies the user has previously viewed and their ratings. The collected data is formatted in an easy-to-parse format (e.g., JSON).

[0845] Step 3:

[0846] The device sends the collected personal data to the server. The device then sends the formatted personal data to the cloud server using a secure protocol such as HTTPS. The sent data includes the request prompt and the personal data.

[0847] Step 4:

[0848] The server receives the data sent from the device. The server temporarily stores the received data in a buffer and stores it in the appropriate data storage. The input data is personal data and a request prompt. This prepares the server for analysis and additional data acquisition.

[0849] Step 5:

[0850] The server retrieves additional personal data from the database. The server executes SQL queries to retrieve additional personal data related to the user from the database, including past browsing history, ratings, and related user rating data. The retrieved data is consolidated on the server.

[0851] Step 6:

[0852] The server provides the integrated data to the generative AI model. The server integrates the data acquired from the device with additional data from the database and provides it to the generative AI model (e.g., GPT-4). The input data is the integrated personal dataset. This allows the generative AI model to efficiently begin analysis.

[0853] Step 7:

[0854] The generative AI model generates recommendation results. The generative AI model analyzes the integrated personal data and generates output that best suits the user's needs. Specifically, it generates a list of movie recommendations based on viewing history and ratings. The output data is a list of recommended movies.

[0855] Step 8:

[0856] The server receives the recommendation results from the generative AI model. The server receives and stores the generated recommendation results in a data format such as JSON, which prepares the recommendation results for transmission to the device.

[0857] Step 9:

[0858] The server sends the recommendation results to the terminal. The server then sends the received recommendation results to the terminal using a secure protocol such as HTTPS. The input data is the recommendation result data, which is sent to the terminal as output.

[0859] Step 10:

[0860] The device displays the recommended results to the user. The device displays the recommended results received from the server to the user. Specifically, a list of recommended movies is displayed on the smartphone application screen. The user can refer to this list and select the next movie to watch.

[0861] (Application example 1)

[0862] 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."

[0863] Conventional content recommendation systems have not been able to fully utilize users' personal data, making it difficult to recommend optimal content to users. Furthermore, there is a lack of a means to effectively analyze users' past viewing history and rating data, generate prompts, and provide optimal recommendations based on those prompts. This often leaves users dissatisfied because they are unable to easily find content that matches their preferences.

[0864] 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.

[0865] In this invention, the server includes means for receiving a request from a user, means for collecting personal data of the user, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for providing prompt sentences generated based on the user's past viewing history and rating data to the generative AI model, and means for transmitting recommendation results generated from the prompt sentences to the server before displaying them to the user. This makes it possible to effectively utilize the user's personal data and provide individually optimized content to the user.

[0866] The "means for receiving requests from a user" is a function for receiving requests or questions input by a user through an application.

[0867] "Means for collecting user personal data" refers to a function that collects personal information such as the user's past behavioral history, ratings, and location information.

[0868] "Means for transmitting collected personal data to a server" refers to a function that transfers personal information collected from a user's terminal to a server via a network.

[0869] "Means for obtaining additional personal data from the database" refers to the function of retrieving necessary additional information from other related databases stored on the server.

[0870] "Means for providing acquired personal data to a generative AI model" refers to the function of handing over collected and acquired personal data to an AI model for analytical processing.

[0871] "Means for receiving optimal recommendations generated by a generative AI model" refers to a function for receiving recommendation results created by a generative AI model.

[0872] The "means for transmitting the received recommendation to the user's terminal" is a function for transferring the received recommendation results to the user's terminal.

[0873] The "means for displaying recommendations on the user's terminal" is a function for visually displaying the recommendation results on the user's terminal.

[0874] "Means for providing prompt sentences generated based on the user's past viewing history and rating data to a generative AI model" is a function for providing prompt sentences generated based on the user's past viewing history and rating data to an AI model.

[0875] The "means for sending the recommendation results generated from the prompt sentence to the server before displaying them to the user" is a function that returns the generated recommendation results to the server for confirmation or additional processing before displaying them to the user.

[0876] This invention relates to a system that utilizes personal data based on user requests and uses generative AI to provide optimal output. This system aims to recommend optimal content based on user viewing history and rating data, particularly for content distribution services.

[0877] Program Overview

[0878] This system mainly consists of the following process: First, the user inputs a request using a smartphone application. This request is for recommendations of movies, TV shows, etc. to watch next. The device receives this request, collects the user's past viewing history and rating data, and sends them to the server.

[0879] Hardware and software used

[0880] Hardware: Smartphone

[0881] Software: Python 3.x, Requests library, Flask (server side)

[0882] Processing flow

[0883] The server receives the user's personal data and retrieves additional personal data from the database. The collected and retrieved personal data is then provided to the generative AI model to generate prompt sentences. Based on the generated prompt sentences, the generative AI model recommends optimal content.

[0884] Prompt Sentence Examples

[0885] For example, if user "MovieFan123" requests "What movie should I watch next?", the following prompt will be generated:

[0886] "The user with user ID MovieFan123's viewing history includes The Matrix, Inception, and Interstellar, with ratings of 5, 4, and 5, respectively. Recommend the next best movie for this user."

[0887] Based on this, the generative AI model recommends a list of content (e.g., "Blade Runner 2049," "The Terminator," "Eternal Sunshine of the Spotless Mind") and sends it to the server, which then sends the recommendations to the user's device, which then displays them to the user.

[0888] Specific examples

[0889] As a concrete example, suppose a user requests an application, "What movie should I watch next?" The system generates a prompt based on the user's viewing history and rating data (e.g., "The Matrix" 5, "Inception" 4, "Interstellar" 5) and provides it to the generative AI model. Based on this data, the generative AI model recommends "Blade Runner 2049," "The Terminator," and "Eternal Sunshine of the Spotless Mind." The server sends the recommendation results to the user's smartphone, and the application displays them to the user. This allows the user to easily select the next movie to watch.

[0890] This process makes it possible to effectively utilize the user's personal data and provide individually optimized content.

[0891] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0892] Step 1:

[0893] A user types a request into a smartphone application, sending a request such as "Tell me what movie I should watch next."

[0894] Input: User request

[0895] Output: Request string

[0896] Specific operation: The user uses the app interface to enter a request and presses the send button.

[0897] Step 2:

[0898] The device collects and stores the user's viewing history and rating data.

[0899] Input: User viewing history and rating data

[0900] Output: Formatted personal data

[0901] What it does: The app retrieves the user's past viewing history and rating data from a local database or cloud service and formats it into a usable format.

[0902] Step 3:

[0903] The terminal transmits the collected personal data to the server.

[0904] Input: Formatted personal data

[0905] Output: Data request sent to the server

[0906] Specific operation: The device sends the collected data to the specified API endpoint using an HTTP request, etc.

[0907] Step 4:

[0908] The server retrieves the additional personal data from the database.

[0909] Input: Personal data submitted

[0910] Output: Consolidated personal data

[0911] Specific operation: Based on the data received by the server, related additional data is retrieved from the database using a query and integrated.

[0912] Step 5:

[0913] The server provides the integrated personal data to the generative AI model to generate prompt sentences.

[0914] Input: Integrated personal data

[0915] Output: Generated prompt statement

[0916] How it works: The server analyzes the integrated data and generates effective prompts for the generative AI model. The prompts are created in text format based on past viewing history and rating data.

[0917] Step 6:

[0918] A generative AI model generates optimal recommendations based on the prompt.

[0919] Input: prompt statement

[0920] Output: A list of recommendations

[0921] How it works: The generative AI model analyzes the prompt and uses algorithms and learned data to generate optimal recommendations.

[0922] Step 7:

[0923] The server sends the recommendation results received from the generative AI model to the user's device.

[0924] Input: List of recommended results

[0925] Output: Recommendation results sent to the user's device

[0926] Specific operation: The server sends the recommendation results to the user's device using a secure communication method.

[0927] Step 8:

[0928] The terminal displays the recommendation results to the user.

[0929] Input: List of recommended results

[0930] Output: Displayed recommendation results

[0931] Specific operation: The user's device receives the recommendation results and displays them on the screen. Specifically, the titles and ratings of the recommended movies are displayed in an easy-to-read format.

[0932] This allows users to easily find content that suits their preferences and select what to watch next.

[0933] 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.

[0934] This invention relates to a system that utilizes personal data based on user requests and combines it with an emotion engine to provide optimal output using generative AI. This system collects and analyzes personal data and emotion data according to the user's specific needs and emotions, and provides this to a generative AI model to generate optimal suggestions and recommendations, which are then presented to the user.

[0935] Accepting requests from users

[0936] The user uses the application to input a request such as "Tell me the next movie I should watch." The device receives this request and collects personal data such as the user's past viewing history, ratings, and current emotional state.

[0937] Emotion recognition by emotion engine

[0938] The device analyzes the user's voice, facial expressions, text input, etc., and uses an emotion engine to recognize the user's current emotion. The recognized emotion data is sent to the server as personal data.

[0939] Collection and transmission of personal and emotional data

[0940] The device collects the user's operation log, input data, and emotional data, and sends it to the server, where it is properly formatted and provided in a format that the server can easily analyze.

[0941] Data acquisition and analysis by the server

[0942] The server receives the data sent from the device, retrieves additional personal data from a database, and integrates this data. The server then provides the integrated data to the generative AI model.

[0943] Generative AI model generates output

[0944] The generative AI model analyzes the user's personal and emotional data to generate an output that best suits the user's needs and emotions. For example, if a user requests, "Tell me the next movie I should watch," the generative AI model will consider their viewing history, ratings, and emotional state to recommend an appropriate movie.

[0945] Sending and viewing recommendations

[0946] The server receives the recommendations generated by the generative AI model. The server then sends the recommendations to the device. The device displays the received recommendations to the user. The user then selects the next movie to watch based on the displayed recommendations.

[0947] Specific examples

[0948] For example, consider the case where a user uses this system to request, "Tell me the next movie I should watch." The device collects the user's viewing history, ratings, and emotional state analyzed from speech and facial expressions, and sends this to the server. The server retrieves additional information from the database and provides it to the generative AI model. The generative AI model analyzes this data and generates a list of movies that the user might be interested in. The server sends the generated list to the device, which displays it to the user. In this way, the user can easily select the next viewing content that suits their preferences.

[0949] With the above configuration, the present invention can effectively utilize personal data and emotional data to generate individually optimized output, thereby significantly increasing a company's competitive advantage.

[0950] The processing flow will be explained below.

[0951] Step 1: User enters request

[0952] A user launches a movie recommendation app and types, "What movie should I watch next?"

[0953] Step 2: The terminal receives user input

[0954] The terminal receives the user's request.

[0955] The device collects personal data such as the user's past viewing history and ratings from the device's cache or local database.

[0956] Step 3: The device uses the emotion engine to recognize emotions.

[0957] The device analyzes the user's voice, facial expressions, and text input, and uses an emotion engine to recognize their current emotional state.

[0958] The recognized emotion data is recorded as personal data.

[0959] Step 4: The device sends the data to the server

[0960] The device formats the user's request, including the personal data and emotional data collected, into JSON format.

[0961] The terminal sends the formatted data to the server.

[0962] Step 5: The server receives the data

[0963] The server receives the JSON data sent from the device.

[0964] The server analyzes the received data and identifies the necessary personal data and emotion data corresponding to the request content.

[0965] Step 6: The server retrieves additional data from the database

[0966] The server retrieves additional personal data from the database (e.g., recent viewing history and ratings).

[0967] Matching and integrating any additional data retrieved by the server.

[0968] Step 7: The server invokes the generative AI model

[0969] The server provides the integrated personal data and emotional data as variables to the generative AI model.

[0970] The server calls the API of the generative AI model and provides personal data and emotional data as arguments.

[0971] Step 8: The generative AI model generates the output

[0972] A generative AI model analyzes the provided data and generates an optimal list of movies to watch next based on the user's viewing history, ratings, and emotional state.

[0973] The recommendation list generated by the generative AI model is returned to the server in JSON format.

[0974] Step 9: The server receives the output of the generated AI.

[0975] The server receives the recommendation list returned by the generative AI model.

[0976] The server cleans up the received recommendation list and formats it as needed.

[0977] Step 10: Server sends output to terminal

[0978] The server sends the formatted recommendation list to the terminal.

[0979] Step 11: The terminal displays the output to the user

[0980] The terminal receives the recommendation list received from the server and visually displays it to the user.

[0981] The user selects the next movie to watch from the displayed list.

[0982] In this way, specific actions at each step allow users to receive individually optimized outputs. This system takes into account the user's emotions in particular, thereby realizing more personalized service provision.

[0983] Example 2

[0984] 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."

[0985] Conventional recommendation systems only provide recommendations based on the user's personal data, making it difficult to make optimal recommendations that take into account the user's current emotional state.In addition, the lack of appropriate data collection, analysis, and recommendations based on the user's emotional state limited the user experience.

[0986] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0987] In this invention, the server includes means for receiving a request from a user, means for collecting personal data and emotional data of the user, means for transmitting the collected personal data and emotional data to the server, means for acquiring additional personal data from a database in the server, means for converting the acquired personal data and emotional data into prompt sentences and providing the prompt sentences to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, and means for displaying the recommendations on the user's terminal. This enables optimal recommendations that take into account both the user's personal data and current emotional state.

[0988] A "request" is a request or inquiry made by a user to the system.

[0989] "Personal data" refers to personal data such as a user's viewing history, ratings, and emotional state based on speech and facial expressions.

[0990] "Emotional data" refers to data that indicates the user's current emotional state, analyzed from voice, facial expressions, text input, and the like.

[0991] "Server" means a device or system that receives data sent from a user device, acquires and integrates additional data, and provides it to a generative AI model.

[0992] A "generative AI model" is an artificial intelligence model that generates optimal recommendation results based on input data.

[0993] A "prompt sentence" is an input sentence formatted to be provided to a generative AI model.

[0994] "Recommendations" refer to suggestions or recommendations generated by a generative AI model based on a user's personal and emotional data.

[0995] A "terminal" is a device that is directly operated by a user and that inputs requests, collects and transmits data, and displays recommendation results.

[0996] This invention relates to a system that utilizes personal data based on user requests and combines it with an emotion engine to provide optimal output using a generative AI model. This system collects and analyzes personal data and emotion data according to the user's specific needs and emotions, and provides this to a generative AI model to generate optimal suggestions and recommendations, which are then presented to the user.

[0997] Accepting requests from users

[0998] A user inputs a request, such as "Tell me what movie I should watch next," using an application installed on a device such as a smartphone or PC. The device receives the request and collects personal data such as the user's viewing history, ratings, and current emotional state.

[0999] Emotion recognition by emotion engine

[1000] The device analyzes the user's voice, facial expressions, text input, etc., and recognizes the user's current emotions using an emotion engine (e.g., a deep learning model). For example, the device collects facial expressions and speech content while the user is inputting a request through a camera or microphone and analyzes them in real time. The emotion engine generates user emotion data from this data and sends this emotion data to the server as personal data.

[1001] Collection and transmission of personal and emotional data

[1002] The device collects user operation logs, input data, and emotion data, formats them in JSON format, and sends them to the server. In this invention, the communication between the device and the server uses the HTTPS protocol to ensure security.

[1003] Data acquisition and analysis by the server

[1004] The server receives the data sent from the device. It then retrieves additional personal data from a database (such as past purchase history and viewing trends) and integrates this data. The server converts the integrated data into a prompt to be input into the generative AI model. Specifically, the prompt generated is, "Please recommend the next movie to watch based on the user's viewing history, ratings, and emotional data obtained from their speech and facial expressions."

[1005] Generative AI model generates output

[1006] The generative AI model receives the prompt and analyzes the user's personal and emotional data. For example, GPT-3 or other advanced natural language processing models are used as the generative AI model. The generative AI model generates an output that best suits the user's needs and emotions. For example, if a user requests, "What movie should I watch next?", the generative AI model will consider their viewing history, ratings, and emotional state to recommend an appropriate movie.

[1007] Sending and viewing recommendations

[1008] The server receives the recommendations generated by the generative AI model. The server then sends these recommendations to the user's device. The device displays the received recommendations to the user. Specifically, they are displayed as "movies to watch next" on the application interface. The user can view the displayed recommendations and choose the next movie to watch.

[1009] Specific examples

[1010] For example, if a user opens an application and requests, "What movie should I watch next?", the device receives this request and collects the user's viewing history, rating data, and emotional state analyzed from speech and facial expressions. These data are sent to the server in JSON format. The server then integrates additional personal data from the database and provides it to the generative AI model as a prompt (e.g., "Recommend the next movie to watch based on the user's viewing history, rating, and emotional data obtained from speech and facial expressions."). The generative AI model analyzes this data and generates a list of movies that the user might be interested in. The server then sends the generated list to the device, which then displays it to the user. In this way, the user can easily select their next viewing content that suits their preferences.

[1011] As described above, the present invention can significantly improve the user experience and a company's competitive advantage by effectively utilizing personal data and emotional data to generate individually optimized output.

[1012] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1013] Step 1:

[1014] A user opens the application and types in a request such as "What movie should I watch next?"

[1015] Input: User request: "What movie should I watch next?"

[1016] Output: The terminal captures the request

[1017] Specific operation: The user inputs a request through an input device such as a smartphone or PC, and the relevant application receives the request.

[1018] Step 2:

[1019] The device analyzes the user's voice, facial expressions, text input, etc., and generates emotional data using an emotion engine.

[1020] Input: User voice data, video data, and text input

[1021] Output: Emotion data

[1022] Specific operation: The device uses a microphone and camera to collect the user's voice and facial expressions, analyzes this data through an emotion engine (e.g., a deep learning model), and identifies the user's emotional state (e.g., joy, anger, sadness, etc.).

[1023] Step 3:

[1024] The device collects the user's viewing history and rating data, and sends it to the server in JSON format along with emotional data.

[1025] Input: User viewing history, rating data, and emotion data

[1026] Output: JSON data sent to the server

[1027] Specific operation: The device collects past viewing history, rating data, and newly generated emotion data, formats it into JSON format, and sends it to the server using the HTTPS protocol.

[1028] Step 4:

[1029] The server receives the data sent from the terminal and retrieves additional personal data from a database.

[1030] Input: JSON format data (viewing history, rating data, emotion data)

[1031] Output: A consolidated dataset

[1032] Specific operation: The server receives the JSON data sent from the device, queries the database for additional personal data to obtain the required data, and integrates this composite data.

[1033] Step 5:

[1034] The server converts the integrated data into prompt sentences and provides them to the generative AI model.

[1035] Input: Integrated dataset

[1036] Output: The prompt sentence that is fed into the generative AI model

[1037] Specific operation: Based on the integrated data, the server generates a prompt such as, "Please recommend the next movie to watch based on the user's viewing history, ratings, and emotional data obtained from speech and facial expressions."

[1038] Step 6:

[1039] A generative AI model generates optimal recommendations based on the prompt text.

[1040] Input: prompt statement

[1041] Output: Recommendation results

[1042] How it works: A generative AI model (e.g., GPT-3) analyzes the prompt and generates a list of movies to watch next based on the user's viewing history, ratings, and emotional state.

[1043] Step 7:

[1044] The server sends the recommendation results generated by the generative AI model to the terminal.

[1045] Input: Recommendation results

[1046] Output: Data sent to the terminal

[1047] Specific operation: The server receives the recommendation results from the generative AI model and sends them to the terminal using the HTTPS protocol.

[1048] Step 8:

[1049] The terminal displays the recommendation results to the user.

[1050] Input: Recommendation results

[1051] Output: Recommendation results displayed on the user's screen

[1052] Specific operation: The device displays the received recommendation results on the application UI, and the user can select the next movie to watch from the displayed recommendation list.

[1053] (Application example 2)

[1054] 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."

[1055] In conventional content distribution services, it has been difficult to make optimal recommendations based on a user's current emotional state simply by utilizing the user's personal data. This has led to problems such as users finding content that matches their emotions at any given time, resulting in a decrease in satisfaction with the service. The present invention aims to solve this problem by providing a content recommendation system that also takes into account the user's emotional state.

[1056] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1057] In this invention, the server includes means for receiving a request from a user, means for collecting personal data of the user, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for recognizing the user's emotions using voice analysis, facial expression analysis, and text analysis, and means for collecting the recognized emotional data as personal data and transmitting it to the server, thereby enabling optimal content to be recommended according to the user's emotional state.

[1058] "Means for receiving requests from users" refers to a function for receiving requests or questions entered by users.

[1059] "Means of collecting users' personal data" refers to the function of collecting data specific to individuals, such as users' viewing history, ratings, and location information.

[1060] "Means for transmitting collected personal data to a server" refers to the function of transferring collected personal data to a server via the Internet, etc.

[1061] "Means for obtaining additional personal data from the database" refers to the functionality by which the server retrieves further relevant data from the database.

[1062] "Means for providing acquired personal data to a generative AI model" refers to the function of providing collected and acquired data for input into a generative AI model.

[1063] "Means for receiving optimal recommendations generated by a generative AI model" refers to the function of receiving recommendations made by a generative AI model.

[1064] "Means for transmitting received recommendations to the user's device" refers to a function for the server to send the received recommendation results to the user's device.

[1065] "Means for displaying recommendations on the user's device" refers to a function for displaying recommended results on the user's device.

[1066] "Means for recognizing a user's emotions using voice analysis, facial expression analysis, and text analysis" refers to a function that analyzes a user's voice, facial expression, text input, etc. to grasp the user's emotional state.

[1067] "Means for collecting recognized emotion data as personal data and transmitting it to a server" refers to a function for compiling recognized emotion information as personal data and transferring it to a server.

[1068] The present invention provides a system for recommending optimal content using a generative AI model by utilizing personal data and emotional data of users in a content distribution service. Specific embodiments for carrying out the present invention will be described below.

[1069] First, a user uses a device such as a smartphone to request, "Tell me the next movie I should watch." The device receives this request and then collects the user's personal data and current emotional state. Personal data includes the user's viewing history, ratings, location information, etc. Emotional state is also obtained through voice analysis, facial expression analysis, and text analysis. Specifically, voice analysis uses voice recognition software (e.g., OpenAI's Whisper), facial expression analysis uses a facial recognition API (e.g., Microsoft Azure's Face API), and text analysis uses a natural language processing tool (e.g., OpenAI GPT-4).

[1070] The collected personal and emotional data is sent to a server, which retrieves additional personal data from a database (e.g., Amazon Web Services' RDS), integrates this data, and provides it to a generative AI model (e.g., OpenAI GPT-4). The generative AI model analyzes this integrated data and generates recommended content that best suits the user's needs and current emotions.

[1071] The generated recommended content is sent to the user's device via the server, and the device displays the recommended results. The user can then select the next movie to watch by looking at the recommended results. For example, if a user is looking for a relaxing movie, suitable movies will be recommended based on their past viewing history and current fatigue state.

[1072] As a concrete example, the prompt sentence is shown below.

[1073] User is looking for the next movie to watch. Based on past viewing history and current emotional state: tired. Recommend a relaxing movie.

[1074] In this way, by implementing the present invention, it becomes possible to recommend content with higher accuracy, taking into account the emotional state of the user, and an improvement in user satisfaction can be expected.

[1075] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1076] Step 1:

[1077] A user inputs a request using a device such as a smartphone. For example, the user inputs "Tell me the next movie I should watch." The input request is received by the device and stored for further processing.

[1078] Input: User request text

[1079] Output: Saved request

[1080] Specific behavior: A user opens the application, enters a request in text, and presses the send button.

[1081] Step 2:

[1082] The device collects your personal data, including your viewing history, ratings, and location information for the applications you use, and aggregates the collected data for further processing.

[1083] Input: User operation log, viewing history, ratings, location information

[1084] Output: Collected personal data

[1085] Specific operation: The device automatically retrieves viewing history and rating information from the application's database and obtains current location information from GPS.

[1086] Step 3:

[1087] The device recognizes the user's emotional state using voice analysis, facial expression analysis, and text analysis. Voice analysis uses voice recognition software, and facial expression analysis uses a facial recognition API. Emotional data is collected for further processing.

[1088] Input: User's voice data, facial expression data, text data

[1089] Output: Recognized emotion data

[1090] Specific operation: The device records the user's voice with a microphone, captures facial expressions with a camera, and processes them with analysis software.

[1091] Step 4:

[1092] The collected personal and emotional data is sent from the device to a server using a secure communication protocol.

[1093] Input: Collected personal and emotional data

[1094] Output: Data sent to the server

[1095] Specific operation: The device sends data to the specified endpoint using the HTTPS protocol.

[1096] Step 5:

[1097] The server retrieves additional personal data from the database, which is then merged with the data already received.

[1098] Input: Additional personal data stored on the server

[1099] Output: Consolidated personal data

[1100] Specific operation: The server retrieves the user's profile data and past behavior history from the database and merges them with the received data.

[1101] Step 6:

[1102] The server provides the integrated personal and emotional data to the generative AI model, which then analyzes the data and generates optimal recommendations.

[1103] Input: Integrated personal and emotional data

[1104] Output: Generated recommendation content

[1105] Specific operation: The server passes the integrated data as input to the generative AI model to generate a prompt sentence for content recommendation.

[1106] Step 7:

[1107] The server receives the optimal recommendations generated by the generative AI model and stores them for the next step.

[1108] Input: Recommended content by generative AI model

[1109] Output: Received recommendation results

[1110] Specific operation: The server receives and stores the results from the generative AI model.

[1111] Step 8:

[1112] The server then sends the received recommendation results to the user's device using a secure communication protocol.

[1113] Input: Received recommendation results

[1114] Output: Recommendation results sent to the user's device

[1115] Specific operation: The server sends the recommendation results to the user's terminal using the HTTPS protocol.

[1116] Step 9:

[1117] The user's device receives the recommendation results and displays them on the screen, allowing the user to review the results and select the next movie to watch.

[1118] Input: Recommendation results received from the server

[1119] Output: Recommendation results displayed on the device

[1120] Specific operation: The recommendation results received by the terminal are sent to the user interface and converted into an appropriate format for display.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] [Fourth embodiment]

[1125] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1126] 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.

[1127] 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).

[1128] 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.

[1129] 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.

[1130] 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).

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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."

[1138] This invention relates to a system that utilizes personal data based on user requests and uses generative AI to provide optimal output. This system collects personal data based on the user's specific needs, provides it to a generative AI model, and generates optimal suggestions and recommendations, which are then presented to the user.

[1139] Accepting requests from users

[1140] The user uses the application to input a request such as "Tell me the next movie I should watch." The device receives this request and collects personal data such as the user's viewing history and ratings.

[1141] Collection and transmission of personal data

[1142] The device collects the user's operation log and input data and sends it to the server. At this time, the collected personal data is properly formatted and provided in a format that the server can easily analyze.

[1143] Data acquisition and analysis by the server

[1144] The server receives the data sent from the device, retrieves additional personal data from the database, and integrates this data. The server then provides the integrated personal data to the generative AI model.

[1145] Generative AI model generates output

[1146] The generative AI model analyzes the user's personal data and generates output that best suits the user's needs. For example, if a user requests, "What movie should I watch next?", the generative AI model will take into account viewing history and ratings to recommend an appropriate movie.

[1147] Sending and viewing recommendations

[1148] The server receives the recommendations generated by the generative AI model. The server then sends the recommendations to the device. The device displays the received recommendations to the user. The user then selects the next movie to watch based on the displayed recommendations.

[1149] Specific examples

[1150] For example, consider the case where a user uses this system to request, "What book should I read next?" The device collects the user's reading history, past ratings and reviews, etc., and sends this to the server. The server retrieves additional information from the database and provides it to the generative AI model. The generative AI model analyzes this data and generates a list of books that the user might be interested in. The server sends the generated list to the device, which displays it to the user. In this way, the user can easily select their next reading preference.

[1151] With the above-mentioned configuration, the present invention can effectively utilize the user's personal data to generate individually optimized output, thereby significantly increasing a company's competitive advantage.

[1152] The processing flow will be explained below.

[1153] Step 1: User enters request

[1154] A user launches a movie recommendation app and types, "What movie should I watch next?"

[1155] Step 2: The terminal receives user input

[1156] The terminal receives the user's request.

[1157] The terminal collects personal data such as the user's past viewing history and ratings from the terminal's cache or database.

[1158] Step 3: The device sends the data to the server

[1159] The device formats the personal data collected and the user's request into JSON format.

[1160] The terminal sends the formatted data to the server.

[1161] Step 4: The server receives the data

[1162] The server receives the JSON data sent from the device.

[1163] The server analyzes the received data and identifies the required personal data corresponding to the request content.

[1164] Step 5: The server retrieves additional data from the database

[1165] The server retrieves additional personal data from the database (e.g., recent viewing history and ratings).

[1166] The server merges the additional data it retrieves with the existing data.

[1167] Step 6: The server invokes the generative AI model

[1168] The server provides the integrated personal data to the generative AI model.

[1169] The server calls the API of the generated AI model and provides personal data as an argument.

[1170] Step 7: The generative AI model generates the output

[1171] The generative AI model analyzes the provided data and generates an optimal list of movies to watch next based on the user's viewing history and ratings.

[1172] The recommendation list generated by the generative AI model is returned to the server in JSON format.

[1173] Step 8: The server receives the output of the generated AI.

[1174] The server receives the recommendation list returned by the generative AI model.

[1175] The server cleans up the received recommendation list and formats it as needed.

[1176] Step 9: Server sends output to terminal

[1177] The server sends the formatted recommendation list to the terminal.

[1178] Step 10: The terminal displays the output to the user

[1179] The terminal receives the recommendation list received from the server and visually displays it to the user.

[1180] The user selects the next movie to watch from the displayed list.

[1181] In this way, specific actions at each step allow the user to receive individually optimized output.

[1182] Example 1

[1183] 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."

[1184] Conventional recommendation systems have been unable to effectively utilize users' personal data, making it difficult to provide optimal recommendations tailored to user needs. Collecting and analyzing personal data also takes time and effort, reducing system efficiency. To address these issues, a system is needed that can quickly and efficiently collect and analyze personal data based on user requests and provide optimal output using a generative AI model.

[1185] 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.

[1186] In this invention, the server includes means for accepting requests from users, means for collecting personal data of users, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for the terminal to appropriately format the collected personal data, means for the server to integrate the data and input it into the generative AI model, and means for the generative AI model to analyze and generate output. This makes it possible to effectively utilize the user's personal data and quickly and efficiently provide individually optimized recommendation results.

[1187] "User request" refers to the wishes or requests that a user inputs into the system.

[1188] "Personal data" refers to data related to individual attributes and behavior, such as personal information about a user, behavioral history, and evaluation information.

[1189] "Terminal" is a general term for devices operated by users, including smartphones, tablets, and personal computers.

[1190] A "server" refers to a computer system that manages and processes data on a network, and is responsible for integrating and analyzing data from multiple terminals.

[1191] A "database" is a collection of data that is systematically organized and stored, and is used to store personal data and various other information for easy searching and retrieval.

[1192] "Generative AI models" refer to algorithms and trained data models that use artificial intelligence technology to analyze users' personal data and generate optimal outputs.

[1193] "Formatting" means the process of putting data into a particular form or structure to make it easier to analyze or communicate.

[1194] "Recommendations" refer to information and suggestions presented as a result of analysis by a generative AI model, and are provided in a form optimized to meet the user's needs.

[1195] "Output" refers to the results or proposals that a generative AI model ultimately generates after analysis, including various information and lists provided to users.

[1196] "Integration" refers to the process of bringing together data from different sources to make it consistent and improve the accuracy of analysis and recommendations.

[1197] This invention is a system that utilizes personal data based on user requests and uses a generative AI model to provide optimal output. The system aims to collect and analyze personal data that meets the user's needs and provide highly accurate recommendations to the user. The entire system is mainly composed of four main components: a terminal, a server, a database, and a generative AI model.

[1198] The user uses the device to input a request such as "Tell me what movie I should watch next." The device receives this request and collects personal data such as the user's past viewing history and ratings. This collected data is then appropriately formatted and sent to the server.

[1199] The server receives the data sent from the device and temporarily stores it in a buffer. Then, if additional data is needed, it retrieves additional personal data from the database and aggregates this data. This brings all relevant data into one unified dataset, ready to be fed to the generative AI model.

[1200] The generative AI model analyzes the user's personal data and generates an output that best suits the user's needs. This output is based on the data and algorithms that the generative AI model has learned. When a user requests, "Tell me what movie I should watch next," the generative AI model takes into account viewing history and ratings to generate a list of optimal movie recommendations.

[1201] The server receives the recommendations generated by the generative AI model and sends them to the device. The device then displays the recommendations to the user. The user can then select the next movie to watch by looking at the displayed recommendations. Through this process, the user receives the best recommendations based on their preferences and past behavioral history.

[1202] Specific examples

[1203] For example, consider the case where a user uses this system to request, "What book should I read next?" The device collects the user's reading history, past ratings, and reviews, and sends this to the server. The server retrieves additional reading data from the database, integrates it, and then provides it to the generative AI model. The generative AI model analyzes this data and generates a list of books that the user might be interested in. The server sends the generated list of books to the device, which displays it to the user. The user can then select the next book to read based on the displayed list.

[1204] Prompt Sentence Examples

[1205] Tell me what movie I should watch next

[1206] What books do you recommend?

[1207] Tell me where I should travel next

[1208] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1209] Step 1:

[1210] The user inputs a request. The user inputs a request using a device. Specifically, the user inputs a request such as "Tell me the next movie I should watch" through an application on a smartphone or tablet. This input is captured by the device. The input data is saved in text format as a prompt sentence.

[1211] Step 2:

[1212] The device collects personal data. The device retrieves user operation logs, viewing history, and rating data from an internal database or cache. This includes movies the user has previously viewed and their ratings. The collected data is formatted in an easy-to-parse format (e.g., JSON).

[1213] Step 3:

[1214] The device sends the collected personal data to the server. The device then sends the formatted personal data to the cloud server using a secure protocol such as HTTPS. The sent data includes the request prompt and the personal data.

[1215] Step 4:

[1216] The server receives the data sent from the device. The server temporarily stores the received data in a buffer and stores it in the appropriate data storage. The input data is personal data and a request prompt. This prepares the server for analysis and additional data acquisition.

[1217] Step 5:

[1218] The server retrieves additional personal data from the database. The server executes SQL queries to retrieve additional personal data related to the user from the database, including past browsing history, ratings, and related user rating data. The retrieved data is consolidated on the server.

[1219] Step 6:

[1220] The server provides the integrated data to the generative AI model. The server integrates the data acquired from the device with additional data from the database and provides it to the generative AI model (e.g., GPT-4). The input data is the integrated personal dataset. This allows the generative AI model to efficiently begin analysis.

[1221] Step 7:

[1222] The generative AI model generates recommendation results. The generative AI model analyzes the integrated personal data and generates output that best suits the user's needs. Specifically, it generates a list of movie recommendations based on viewing history and ratings. The output data is a list of recommended movies.

[1223] Step 8:

[1224] The server receives the recommendation results from the generative AI model. The server receives and stores the generated recommendation results in a data format such as JSON, which prepares the recommendation results for transmission to the device.

[1225] Step 9:

[1226] The server sends the recommendation results to the terminal. The server then sends the received recommendation results to the terminal using a secure protocol such as HTTPS. The input data is the recommendation result data, which is sent to the terminal as output.

[1227] Step 10:

[1228] The device displays the recommended results to the user. The device displays the recommended results received from the server to the user. Specifically, a list of recommended movies is displayed on the smartphone application screen. The user can refer to this list and select the next movie to watch.

[1229] (Application example 1)

[1230] 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."

[1231] Conventional content recommendation systems have not been able to fully utilize users' personal data, making it difficult to recommend optimal content to users. Furthermore, there is a lack of a means to effectively analyze users' past viewing history and rating data, generate prompts, and provide optimal recommendations based on those prompts. This often leaves users dissatisfied because they are unable to easily find content that matches their preferences.

[1232] 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.

[1233] In this invention, the server includes means for receiving a request from a user, means for collecting personal data of the user, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for providing prompt sentences generated based on the user's past viewing history and rating data to the generative AI model, and means for transmitting recommendation results generated from the prompt sentences to the server before displaying them to the user. This makes it possible to effectively utilize the user's personal data and provide individually optimized content to the user.

[1234] The "means for receiving requests from a user" is a function for receiving requests or questions input by a user through an application.

[1235] "Means for collecting user personal data" refers to a function that collects personal information such as the user's past behavioral history, ratings, and location information.

[1236] "Means for transmitting collected personal data to a server" refers to a function that transfers personal information collected from a user's terminal to a server via a network.

[1237] "Means for obtaining additional personal data from the database" refers to the function of retrieving necessary additional information from other related databases stored on the server.

[1238] "Means for providing acquired personal data to a generative AI model" refers to the function of handing over collected and acquired personal data to an AI model for analytical processing.

[1239] "Means for receiving optimal recommendations generated by a generative AI model" refers to a function for receiving recommendation results created by a generative AI model.

[1240] The "means for transmitting the received recommendation to the user's terminal" is a function for transferring the received recommendation results to the user's terminal.

[1241] The "means for displaying recommendations on the user's terminal" is a function for visually displaying the recommendation results on the user's terminal.

[1242] "Means for providing prompt sentences generated based on the user's past viewing history and rating data to a generative AI model" is a function for providing prompt sentences generated based on the user's past viewing history and rating data to an AI model.

[1243] The "means for sending the recommendation results generated from the prompt sentence to the server before displaying them to the user" is a function that returns the generated recommendation results to the server for confirmation or additional processing before displaying them to the user.

[1244] This invention relates to a system that utilizes personal data based on user requests and uses generative AI to provide optimal output. This system aims to recommend optimal content based on user viewing history and rating data, particularly for content distribution services.

[1245] Program Overview

[1246] This system mainly consists of the following process: First, the user inputs a request using a smartphone application. This request is for recommendations of movies, TV shows, etc. to watch next. The device receives this request, collects the user's past viewing history and rating data, and sends them to the server.

[1247] Hardware and software used

[1248] Hardware: Smartphone

[1249] Software: Python 3.x, Requests library, Flask (server side)

[1250] Processing flow

[1251] The server receives the user's personal data and retrieves additional personal data from the database. The collected and retrieved personal data is then provided to the generative AI model to generate prompt sentences. Based on the generated prompt sentences, the generative AI model recommends optimal content.

[1252] Prompt Sentence Examples

[1253] For example, if user "MovieFan123" requests "What movie should I watch next?", the following prompt will be generated:

[1254] "The user with user ID MovieFan123's viewing history includes The Matrix, Inception, and Interstellar, with ratings of 5, 4, and 5, respectively. Recommend the next best movie for this user."

[1255] Based on this, the generative AI model recommends a list of content (e.g., "Blade Runner 2049," "The Terminator," "Eternal Sunshine of the Spotless Mind") and sends it to the server, which then sends the recommendations to the user's device, which then displays them to the user.

[1256] Specific examples

[1257] As a concrete example, suppose a user requests an application, "What movie should I watch next?" The system generates a prompt based on the user's viewing history and rating data (e.g., "The Matrix" 5, "Inception" 4, "Interstellar" 5) and provides it to the generative AI model. Based on this data, the generative AI model recommends "Blade Runner 2049," "The Terminator," and "Eternal Sunshine of the Spotless Mind." The server sends the recommendation results to the user's smartphone, and the application displays them to the user. This allows the user to easily select the next movie to watch.

[1258] This process makes it possible to effectively utilize the user's personal data and provide individually optimized content.

[1259] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1260] Step 1:

[1261] A user types a request into a smartphone application, sending a request such as "Tell me what movie I should watch next."

[1262] Input: User request

[1263] Output: Request string

[1264] Specific operation: The user uses the app interface to enter a request and presses the send button.

[1265] Step 2:

[1266] The device collects and stores the user's viewing history and rating data.

[1267] Input: User viewing history and rating data

[1268] Output: Formatted personal data

[1269] What it does: The app retrieves the user's past viewing history and rating data from a local database or cloud service and formats it into a usable format.

[1270] Step 3:

[1271] The terminal transmits the collected personal data to the server.

[1272] Input: Formatted personal data

[1273] Output: Data request sent to the server

[1274] Specific operation: The device sends the collected data to the specified API endpoint using an HTTP request, etc.

[1275] Step 4:

[1276] The server retrieves the additional personal data from the database.

[1277] Input: Personal data submitted

[1278] Output: Consolidated personal data

[1279] Specific operation: Based on the data received by the server, related additional data is retrieved from the database using a query and integrated.

[1280] Step 5:

[1281] The server provides the integrated personal data to the generative AI model to generate prompt sentences.

[1282] Input: Integrated personal data

[1283] Output: Generated prompt statement

[1284] How it works: The server analyzes the integrated data and generates effective prompts for the generative AI model. The prompts are created in text format based on past viewing history and rating data.

[1285] Step 6:

[1286] A generative AI model generates optimal recommendations based on the prompt.

[1287] Input: prompt statement

[1288] Output: A list of recommendations

[1289] How it works: The generative AI model analyzes the prompt and uses algorithms and learned data to generate optimal recommendations.

[1290] Step 7:

[1291] The server sends the recommendation results received from the generative AI model to the user's device.

[1292] Input: List of recommended results

[1293] Output: Recommendation results sent to the user's device

[1294] Specific operation: The server sends the recommendation results to the user's device using a secure communication method.

[1295] Step 8:

[1296] The terminal displays the recommendation results to the user.

[1297] Input: List of recommended results

[1298] Output: Displayed recommendation results

[1299] Specific operation: The user's device receives the recommendation results and displays them on the screen. Specifically, the titles and ratings of the recommended movies are displayed in an easy-to-read format.

[1300] This allows users to easily find content that suits their preferences and select what to watch next.

[1301] 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.

[1302] This invention relates to a system that utilizes personal data based on user requests and combines it with an emotion engine to provide optimal output using generative AI. This system collects and analyzes personal data and emotion data according to the user's specific needs and emotions, and provides this to a generative AI model to generate optimal suggestions and recommendations, which are then presented to the user.

[1303] Accepting requests from users

[1304] The user uses the application to input a request such as "Tell me the next movie I should watch." The device receives this request and collects personal data such as the user's past viewing history, ratings, and current emotional state.

[1305] Emotion recognition by emotion engine

[1306] The device analyzes the user's voice, facial expressions, text input, etc., and uses an emotion engine to recognize the user's current emotion. The recognized emotion data is sent to the server as personal data.

[1307] Collection and transmission of personal and emotional data

[1308] The device collects the user's operation log, input data, and emotional data, and sends it to the server, where it is properly formatted and provided in a format that the server can easily analyze.

[1309] Data acquisition and analysis by the server

[1310] The server receives the data sent from the device, retrieves additional personal data from a database, and integrates this data. The server then provides the integrated data to the generative AI model.

[1311] Generative AI model generates output

[1312] The generative AI model analyzes the user's personal and emotional data to generate an output that best suits the user's needs and emotions. For example, if a user requests, "Tell me the next movie I should watch," the generative AI model will consider their viewing history, ratings, and emotional state to recommend an appropriate movie.

[1313] Sending and viewing recommendations

[1314] The server receives the recommendations generated by the generative AI model. The server then sends the recommendations to the device. The device displays the received recommendations to the user. The user then selects the next movie to watch based on the displayed recommendations.

[1315] Specific examples

[1316] For example, consider the case where a user uses this system to request, "Tell me the next movie I should watch." The device collects the user's viewing history, ratings, and emotional state analyzed from speech and facial expressions, and sends this to the server. The server retrieves additional information from the database and provides it to the generative AI model. The generative AI model analyzes this data and generates a list of movies that the user might be interested in. The server sends the generated list to the device, which displays it to the user. In this way, the user can easily select the next viewing content that suits their preferences.

[1317] With the above configuration, the present invention can effectively utilize personal data and emotional data to generate individually optimized output, thereby significantly increasing a company's competitive advantage.

[1318] The processing flow will be explained below.

[1319] Step 1: User enters request

[1320] A user launches a movie recommendation app and types, "What movie should I watch next?"

[1321] Step 2: The terminal receives user input

[1322] The terminal receives the user's request.

[1323] The device collects personal data such as the user's past viewing history and ratings from the device's cache or local database.

[1324] Step 3: The device uses the emotion engine to recognize emotions.

[1325] The device analyzes the user's voice, facial expressions, and text input, and uses an emotion engine to recognize their current emotional state.

[1326] The recognized emotion data is recorded as personal data.

[1327] Step 4: The device sends the data to the server

[1328] The device formats the user's request, including the personal data and emotional data collected, into JSON format.

[1329] The terminal sends the formatted data to the server.

[1330] Step 5: The server receives the data

[1331] The server receives the JSON data sent from the device.

[1332] The server analyzes the received data and identifies the necessary personal data and emotion data corresponding to the request content.

[1333] Step 6: The server retrieves additional data from the database

[1334] The server retrieves additional personal data from the database (e.g., recent viewing history and ratings).

[1335] Matching and integrating any additional data retrieved by the server.

[1336] Step 7: The server invokes the generative AI model

[1337] The server provides the integrated personal data and emotional data as variables to the generative AI model.

[1338] The server calls the API of the generative AI model and provides personal data and emotional data as arguments.

[1339] Step 8: The generative AI model generates the output

[1340] A generative AI model analyzes the provided data and generates an optimal list of movies to watch next based on the user's viewing history, ratings, and emotional state.

[1341] The recommendation list generated by the generative AI model is returned to the server in JSON format.

[1342] Step 9: The server receives the output of the generated AI.

[1343] The server receives the recommendation list returned by the generative AI model.

[1344] The server cleans up the received recommendation list and formats it as needed.

[1345] Step 10: Server sends output to terminal

[1346] The server sends the formatted recommendation list to the terminal.

[1347] Step 11: The terminal displays the output to the user

[1348] The terminal receives the recommendation list received from the server and visually displays it to the user.

[1349] The user selects the next movie to watch from the displayed list.

[1350] In this way, specific actions at each step allow users to receive individually optimized outputs. This system takes into account the user's emotions in particular, thereby realizing more personalized service provision.

[1351] Example 2

[1352] 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."

[1353] Conventional recommendation systems only provide recommendations based on the user's personal data, making it difficult to make optimal recommendations that take into account the user's current emotional state.In addition, the lack of appropriate data collection, analysis, and recommendations based on the user's emotional state limited the user experience.

[1354] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1355] In this invention, the server includes means for receiving a request from a user, means for collecting personal data and emotional data of the user, means for transmitting the collected personal data and emotional data to the server, means for acquiring additional personal data from a database in the server, means for converting the acquired personal data and emotional data into prompt sentences and providing the prompt sentences to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, and means for displaying the recommendations on the user's terminal. This enables optimal recommendations that take into account both the user's personal data and current emotional state.

[1356] A "request" is a request or inquiry made by a user to the system.

[1357] "Personal data" refers to personal data such as a user's viewing history, ratings, and emotional state based on speech and facial expressions.

[1358] "Emotional data" refers to data that indicates the user's current emotional state, analyzed from voice, facial expressions, text input, and the like.

[1359] "Server" means a device or system that receives data sent from a user device, acquires and integrates additional data, and provides it to a generative AI model.

[1360] A "generative AI model" is an artificial intelligence model that generates optimal recommendation results based on input data.

[1361] A "prompt sentence" is an input sentence formatted to be provided to a generative AI model.

[1362] "Recommendations" refer to suggestions or recommendations generated by a generative AI model based on a user's personal and emotional data.

[1363] A "terminal" is a device that is directly operated by a user and that inputs requests, collects and transmits data, and displays recommendation results.

[1364] This invention relates to a system that utilizes personal data based on user requests and combines it with an emotion engine to provide optimal output using a generative AI model. This system collects and analyzes personal data and emotion data according to the user's specific needs and emotions, and provides this to a generative AI model to generate optimal suggestions and recommendations, which are then presented to the user.

[1365] Accepting requests from users

[1366] A user inputs a request, such as "Tell me what movie I should watch next," using an application installed on a device such as a smartphone or PC. The device receives the request and collects personal data such as the user's viewing history, ratings, and current emotional state.

[1367] Emotion recognition by emotion engine

[1368] The device analyzes the user's voice, facial expressions, text input, etc., and recognizes the user's current emotions using an emotion engine (e.g., a deep learning model). For example, the device collects facial expressions and speech content while the user is inputting a request through a camera or microphone and analyzes them in real time. The emotion engine generates user emotion data from this data and sends this emotion data to the server as personal data.

[1369] Collection and transmission of personal and emotional data

[1370] The device collects user operation logs, input data, and emotion data, formats them in JSON format, and sends them to the server. In this invention, the communication between the device and the server uses the HTTPS protocol to ensure security.

[1371] Data acquisition and analysis by the server

[1372] The server receives the data sent from the device. It then retrieves additional personal data from a database (such as past purchase history and viewing trends) and integrates this data. The server converts the integrated data into a prompt to be input into the generative AI model. Specifically, the prompt generated is, "Please recommend the next movie to watch based on the user's viewing history, ratings, and emotional data obtained from their speech and facial expressions."

[1373] Generative AI model generates output

[1374] The generative AI model receives the prompt and analyzes the user's personal and emotional data. For example, GPT-3 or other advanced natural language processing models are used as the generative AI model. The generative AI model generates an output that best suits the user's needs and emotions. For example, if a user requests, "What movie should I watch next?", the generative AI model will consider their viewing history, ratings, and emotional state to recommend an appropriate movie.

[1375] Sending and viewing recommendations

[1376] The server receives the recommendations generated by the generative AI model. The server then sends these recommendations to the user's device. The device displays the received recommendations to the user. Specifically, they are displayed as "movies to watch next" on the application interface. The user can view the displayed recommendations and choose the next movie to watch.

[1377] Specific examples

[1378] For example, if a user opens an application and requests, "What movie should I watch next?", the device receives this request and collects the user's viewing history, rating data, and emotional state analyzed from speech and facial expressions. These data are sent to the server in JSON format. The server then integrates additional personal data from the database and provides it to the generative AI model as a prompt (e.g., "Recommend the next movie to watch based on the user's viewing history, rating, and emotional data obtained from speech and facial expressions."). The generative AI model analyzes this data and generates a list of movies that the user might be interested in. The server then sends the generated list to the device, which then displays it to the user. In this way, the user can easily select their next viewing content that suits their preferences.

[1379] As described above, the present invention can significantly improve the user experience and a company's competitive advantage by effectively utilizing personal data and emotional data to generate individually optimized output.

[1380] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1381] Step 1:

[1382] A user opens the application and types in a request such as "What movie should I watch next?"

[1383] Input: User request: "What movie should I watch next?"

[1384] Output: The terminal captures the request

[1385] Specific operation: The user inputs a request through an input device such as a smartphone or PC, and the relevant application receives the request.

[1386] Step 2:

[1387] The device analyzes the user's voice, facial expressions, text input, etc., and generates emotional data using an emotion engine.

[1388] Input: User voice data, video data, and text input

[1389] Output: Emotion data

[1390] Specific operation: The device uses a microphone and camera to collect the user's voice and facial expressions, analyzes this data through an emotion engine (e.g., a deep learning model), and identifies the user's emotional state (e.g., joy, anger, sadness, etc.).

[1391] Step 3:

[1392] The device collects the user's viewing history and rating data, and sends it to the server in JSON format along with emotional data.

[1393] Input: User viewing history, rating data, and emotion data

[1394] Output: JSON data sent to the server

[1395] Specific operation: The device collects past viewing history, rating data, and newly generated emotion data, formats it into JSON format, and sends it to the server using the HTTPS protocol.

[1396] Step 4:

[1397] The server receives the data sent from the terminal and retrieves additional personal data from a database.

[1398] Input: JSON format data (viewing history, rating data, emotion data)

[1399] Output: A consolidated dataset

[1400] Specific operation: The server receives the JSON data sent from the device, queries the database for additional personal data to obtain the required data, and integrates this composite data.

[1401] Step 5:

[1402] The server converts the integrated data into prompt sentences and provides them to the generative AI model.

[1403] Input: Integrated dataset

[1404] Output: The prompt sentence that is fed into the generative AI model

[1405] Specific operation: Based on the integrated data, the server generates a prompt such as, "Please recommend the next movie to watch based on the user's viewing history, ratings, and emotional data obtained from speech and facial expressions."

[1406] Step 6:

[1407] A generative AI model generates optimal recommendations based on the prompt text.

[1408] Input: prompt statement

[1409] Output: Recommendation results

[1410] How it works: A generative AI model (e.g., GPT-3) analyzes the prompt and generates a list of movies to watch next based on the user's viewing history, ratings, and emotional state.

[1411] Step 7:

[1412] The server sends the recommendation results generated by the generative AI model to the terminal.

[1413] Input: Recommendation results

[1414] Output: Data sent to the terminal

[1415] Specific operation: The server receives the recommendation results from the generative AI model and sends them to the terminal using the HTTPS protocol.

[1416] Step 8:

[1417] The terminal displays the recommendation results to the user.

[1418] Input: Recommendation results

[1419] Output: Recommendation results displayed on the user's screen

[1420] Specific operation: The device displays the received recommendation results on the application UI, and the user can select the next movie to watch from the displayed recommendation list.

[1421] (Application example 2)

[1422] 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."

[1423] In conventional content distribution services, it has been difficult to make optimal recommendations based on a user's current emotional state simply by utilizing the user's personal data. This has led to problems such as users finding content that matches their emotions at any given time, resulting in a decrease in satisfaction with the service. The present invention aims to solve this problem by providing a content recommendation system that also takes into account the user's emotional state.

[1424] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1425] In this invention, the server includes means for receiving a request from a user, means for collecting personal data of the user, means for transmitting the collected personal data to the server, means for acquiring additional personal data from a database, means for providing the acquired personal data to the generative AI model, means for receiving optimal recommendations generated by the generative AI model, means for transmitting the received recommendations to the user's terminal, means for displaying the recommendations on the user's terminal, means for recognizing the user's emotions using voice analysis, facial expression analysis, and text analysis, and means for collecting the recognized emotional data as personal data and transmitting it to the server, thereby enabling optimal content to be recommended according to the user's emotional state.

[1426] "Means for receiving requests from users" refers to a function for receiving requests or questions entered by users.

[1427] "Means of collecting users' personal data" refers to the function of collecting data specific to individuals, such as users' viewing history, ratings, and location information.

[1428] "Means for transmitting collected personal data to a server" refers to the function of transferring collected personal data to a server via the Internet, etc.

[1429] "Means for obtaining additional personal data from the database" refers to the functionality by which the server retrieves further relevant data from the database.

[1430] "Means for providing acquired personal data to a generative AI model" refers to the function of providing collected and acquired data for input into a generative AI model.

[1431] "Means for receiving optimal recommendations generated by a generative AI model" refers to the function of receiving recommendations made by a generative AI model.

[1432] "Means for transmitting received recommendations to the user's device" refers to a function for the server to send the received recommendation results to the user's device.

[1433] "Means for displaying recommendations on the user's device" refers to a function for displaying recommended results on the user's device.

[1434] "Means for recognizing a user's emotions using voice analysis, facial expression analysis, and text analysis" refers to a function that analyzes a user's voice, facial expression, text input, etc. to grasp the user's emotional state.

[1435] "Means for collecting recognized emotion data as personal data and transmitting it to a server" refers to a function for compiling recognized emotion information as personal data and transferring it to a server.

[1436] The present invention provides a system for recommending optimal content using a generative AI model by utilizing personal data and emotional data of users in a content distribution service. Specific embodiments for carrying out the present invention will be described below.

[1437] First, a user uses a device such as a smartphone to request, "Tell me the next movie I should watch." The device receives this request and then collects the user's personal data and current emotional state. Personal data includes the user's viewing history, ratings, location information, etc. Emotional state is also obtained through voice analysis, facial expression analysis, and text analysis. Specifically, voice analysis uses voice recognition software (e.g., OpenAI's Whisper), facial expression analysis uses a facial recognition API (e.g., Microsoft Azure's Face API), and text analysis uses a natural language processing tool (e.g., OpenAI GPT-4).

[1438] The collected personal and emotional data is sent to a server, which retrieves additional personal data from a database (e.g., Amazon Web Services' RDS), integrates this data, and provides it to a generative AI model (e.g., OpenAI GPT-4). The generative AI model analyzes this integrated data and generates recommended content that best suits the user's needs and current emotions.

[1439] The generated recommended content is sent to the user's device via the server, and the device displays the recommended results. The user can then select the next movie to watch by looking at the recommended results. For example, if a user is looking for a relaxing movie, suitable movies will be recommended based on their past viewing history and current fatigue state.

[1440] As a concrete example, the prompt sentence is shown below.

[1441] User is looking for the next movie to watch. Based on past viewing history and current emotional state: tired. Recommend a relaxing movie.

[1442] In this way, by implementing the present invention, it becomes possible to recommend content with higher accuracy, taking into account the emotional state of the user, and an improvement in user satisfaction can be expected.

[1443] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1444] Step 1:

[1445] A user inputs a request using a device such as a smartphone. For example, the user inputs "Tell me the next movie I should watch." The input request is received by the device and stored for further processing.

[1446] Input: User request text

[1447] Output: Saved request

[1448] Specific behavior: A user opens the application, enters a request in text, and presses the send button.

[1449] Step 2:

[1450] The device collects your personal data, including your viewing history, ratings, and location information for the applications you use, and aggregates the collected data for further processing.

[1451] Input: User operation log, viewing history, ratings, location information

[1452] Output: Collected personal data

[1453] Specific operation: The device automatically retrieves viewing history and rating information from the application's database and obtains current location information from GPS.

[1454] Step 3:

[1455] The device recognizes the user's emotional state using voice analysis, facial expression analysis, and text analysis. Voice analysis uses voice recognition software, and facial expression analysis uses a facial recognition API. Emotional data is collected for further processing.

[1456] Input: User's voice data, facial expression data, text data

[1457] Output: Recognized emotion data

[1458] Specific operation: The device records the user's voice with a microphone, captures facial expressions with a camera, and processes them with analysis software.

[1459] Step 4:

[1460] The collected personal and emotional data is sent from the device to a server using a secure communication protocol.

[1461] Input: Collected personal and emotional data

[1462] Output: Data sent to the server

[1463] Specific operation: The device sends data to the specified endpoint using the HTTPS protocol.

[1464] Step 5:

[1465] The server retrieves additional personal data from the database, which is then merged with the data already received.

[1466] Input: Additional personal data stored on the server

[1467] Output: Consolidated personal data

[1468] Specific operation: The server retrieves the user's profile data and past behavior history from the database and merges them with the received data.

[1469] Step 6:

[1470] The server provides the integrated personal and emotional data to the generative AI model, which then analyzes the data and generates optimal recommendations.

[1471] Input: Integrated personal and emotional data

[1472] Output: Generated recommendation content

[1473] Specific operation: The server passes the integrated data as input to the generative AI model to generate a prompt sentence for content recommendation.

[1474] Step 7:

[1475] The server receives the optimal recommendations generated by the generative AI model and stores them for the next step.

[1476] Input: Recommended content by generative AI model

[1477] Output: Received recommendation results

[1478] Specific operation: The server receives and stores the results from the generative AI model.

[1479] Step 8:

[1480] The server then sends the received recommendation results to the user's device using a secure communication protocol.

[1481] Input: Received recommendation results

[1482] Output: Recommendation results sent to the user's device

[1483] Specific operation: The server sends the recommendation results to the user's terminal using the HTTPS protocol.

[1484] Step 9:

[1485] The user's device receives the recommendation results and displays them on the screen, allowing the user to review the results and select the next movie to watch.

[1486] Input: Recommendation results received from the server

[1487] Output: Recommendation results displayed on the device

[1488] Specific operation: The recommendation results received by the terminal are sent to the user interface and converted into an appropriate format for display.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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).

[1496] 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.

[1497] 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."

[1498] 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.

[1499] 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).

[1500] 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.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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.

[1510] The following is further disclosed regarding the above embodiment.

[1511] (Claim 1)

[1512] a means for receiving a request from a user;

[1513] means for collecting personal data of users;

[1514] means for transmitting the collected personal data to a server;

[1515] a means for obtaining additional personal data from the database;

[1516] A means for providing the acquired personal data to the generative AI model;

[1517] a means for receiving the optimal recommendations generated by the generative AI model;

[1518] means for transmitting the received recommendations to a user's terminal;

[1519] means for displaying the recommendation on the user's device;

[1520] A system including:

[1521] (Claim 2)

[1522] 2. The system of claim 1, wherein the personal data includes a user's browsing history, ratings, and location information.

[1523] (Claim 3)

[1524] The system of claim 1, wherein the generative AI model generates a recommendation list of movies, books, products, etc. based on the user's personal data.

[1525] "Example 1"

[1526] (Claim 1)

[1527] means for accepting requests from users;

[1528] means for collecting personal data of users;

[1529] means for transmitting the collected personal data to a server;

[1530] a means for obtaining additional personal data from the database;

[1531] A means for providing the acquired personal data to the generative AI model;

[1532] a means for receiving the optimal recommendations generated by the generative AI model;

[1533] means for transmitting the received recommendations to a user's terminal;

[1534] means for displaying the recommendation on the user's device;

[1535] a means for properly formatting the personal data collected by the device;

[1536] A means for the server to integrate the data and input it into the generative AI model;

[1537] A means by which the generative AI model performs analysis and generates output;

[1538] A system including:

[1539] (Claim 2)

[1540] 10. The system of claim 1, wherein the personal data includes a user's browsing history, ratings, and geographic information.

[1541] (Claim 3)

[1542] The system of claim 1, wherein the generative AI model generates a recommendation list of content, books, products, etc. based on the user's personal data.

[1543] "Application Example 1"

[1544] (Claim 1)

[1545] a means for receiving a request from a user;

[1546] means for collecting personal data of users;

[1547] means for transmitting the collected personal data to a server;

[1548] a means for obtaining additional personal data from the database;

[1549] A means for providing the acquired personal data to the generative AI model;

[1550] a means for receiving the optimal recommendations generated by the generative AI model;

[1551] means for transmitting the received recommendations to a user's terminal;

[1552] means for displaying the recommendation on the user's device;

[1553] A means for providing prompt sentences generated based on the user's past viewing history and evaluation data to the generative AI model;

[1554] means for transmitting the recommendation results generated from the prompt sentence to a server before displaying them to the user;

[1555] A system including:

[1556] (Claim 2)

[1557] 2. The system of claim 1, wherein the personal data includes a user's browsing history, ratings, location information, and operation logs.

[1558] (Claim 3)

[1559] 2. The system of claim 1, wherein the generative AI model generates a list of media content recommendations based on the user's personal data.

[1560] "Example 2: Combining Emotion Engines"

[1561] (Claim 1)

[1562] a means for receiving a request from a user;

[1563] means for collecting personal data and emotional data of a user;

[1564] means for transmitting the collected personal data and emotion data to a server;

[1565] means at the server for obtaining additional personal data from a database;

[1566] A means for converting the acquired personal data and emotional data into a prompt sentence and providing it to a generative AI model;

[1567] a means for receiving the optimal recommendations generated by the generative AI model;

[1568] means for transmitting the received recommendations to a user's terminal;

[1569] means for displaying the recommendation on the user's device;

[1570] A system including:

[1571] (Claim 2)

[1572] 10. The system of claim 1, wherein the personal data includes the user's viewing history, ratings, and emotional state based on speech and facial expressions.

[1573] (Claim 3)

[1574] 2. The system of claim 1, wherein the generative AI model generates a recommendation list including movies to watch next based on the user's personal data and emotional data.

[1575] "Application example 2 when combining emotion engines"

[1576] (Claim 1)

[1577] a means for receiving a request from a user;

[1578] means for collecting personal data of users;

[1579] means for transmitting the collected personal data to a server;

[1580] a means for obtaining additional personal data from the database;

[1581] A means for providing the acquired personal data to the generative AI model;

[1582] a means for receiving the optimal recommendations generated by the generative AI model;

[1583] means for transmitting the received recommendations to a user's terminal;

[1584] means for displaying the recommendation on the user's device;

[1585] A means for recognizing a user's emotions using voice analysis, facial expression analysis, and text analysis;

[1586] means for collecting the recognized emotion data as personal data and transmitting the collected data to a server;

[1587] A system including:

[1588] (Claim 2)

[1589] 10. The system of claim 1, wherein the personal data includes a user's browsing history, ratings, location information, and emotional state.

[1590] (Claim 3)

[1591] 2. The system of claim 1, wherein the generative AI model generates a recommendation list of movies, books, products, etc. based on the user's personal data and emotional state. [Explanation of symbols]

[1592] 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. a means for receiving a request from a user; means for collecting personal data of users; means for transmitting the collected personal data to a server; a means for obtaining additional personal data from the database; A means for providing the acquired personal data to the generative AI model; a means for receiving the optimal recommendations generated by the generative AI model; means for transmitting the received recommendations to a user's terminal; means for displaying the recommendation on the user's device; A system including:

2. 10. The system of claim 1, wherein the personal data includes a user's browsing history, ratings, and location information.

3. The system of claim 1, wherein the generative AI model generates a recommendation list of movies, books, products, etc. based on the user's personal data.

Images