System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving a prompt from a user; means for identifying a category and a brand from the prompt; means for generating content that includes the category and brand; means for providing the generated content to the user; means for collecting user feedback; and means for analyzing the feedback to improve generation performance.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] Conventional generative AI systems have difficulty inserting ads that naturally relate to content that users are interested in. They also lack a mechanism to ensure that users perceive ads positively and increase their effectiveness. Furthermore, they lack a mechanism for collecting user feedback and continuously improving the performance of generative AI. The present invention aims to solve these problems and maximize advertising effectiveness while improving the user experience. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving prompts from a user, a means for identifying categories and brands from the prompts, a means for generating content including the categories and brands, a means for providing the generated content to the user, a means for collecting user feedback, and a means for analyzing the feedback and improving generation performance. This allows the generation AI to naturally insert advertisements based on the user's interests and further improve the accuracy of content generation based on user feedback. The system also includes a means for inserting advertisements based on the identified categories and brands and a means for using a natural language processing algorithm to identify categories and brands from the prompts, thereby improving the accuracy and effectiveness of the entire system.

[0006] A "prompt" refers to a question or instruction that a user inputs to a system.

[0007] "Category" refers to the type of subject or theme extracted from the prompt.

[0008] A "brand" refers to a specific company, product, or service name that is related to a category.

[0009] "Content" refers to the entire text and information created by generative AI.

[0010] "User feedback" refers to the actions and reactions that users take in response to content provided by the system.

[0011] "Generative AI" refers to artificial intelligence algorithms or systems used to generate content from user prompts.

[0012] "Natural language processing algorithm" refers to a computer algorithm used to analyze and understand human language.

[0013] "Analysis" refers to the process of examining, understanding, and making sense of the data and feedback collected.

[0014] "Content generation accuracy" refers to the ability of the generative AI to create appropriate and relevant content for a given prompt.

[0015] "Advertising effectiveness" refers to the extent to which an advertisement included in the generated content has an impact on a user and its ability to encourage action. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system that receives prompts from a user, identifies relevant categories and brands, and generates content that includes them, and is embodied in the following manner.

[0038] Program processing

[0039] The system operates through the following steps: Based on prompts from the user, a natural language processing algorithm is used to identify relevant categories and brands, and the generation AI generates content based on this information. The generated content is provided to the user, and user feedback is collected. This feedback is analyzed and used to improve the accuracy of the generation AI.

[0040] Specific examples

[0041] 1. User types, "Recommendations for pet toys."

[0042] The user enters the prompt into the input field and clicks the submit button.

[0043] 2. The device sends this prompt to the server.

[0044] A prompt is sent over the Internet to a server, which confirms receipt.

[0045] 3. The server receives the prompt.

[0046] Receive and log prompts.

[0047] 4. The server passes the prompt to a natural language processing (NLP) algorithm to identify the category and brand.

[0048] Example: Parse the prompt "What are your pet toy recommendations?" to identify the categories "Pets" and "Toys" and the brands "Pet Shops" and "Popular Brands."

[0049] 5. The server passes the extracted category and brand information to the generation AI.

[0050] Example: Input the categories "Pets" and "Toys" and the brands "Pet Shop" and "Popular Brands" into the generation AI.

[0051] 6. The generation AI on the server generates content based on category and brand information.

[0052] Example: A generation AI generates the following sentence:

[0053] Our recommended pet toys include the latest collections from pet stores, which are durable and safe, supporting your pet's health. Popular brands of interactive toys are also perfect for making playtime fun with your pet.

[0054] 7. The server sends the generated content to the device.

[0055] Example: Deliver the generated text to the user's device.

[0056] 8. The device receives the content and displays it to the user.

[0057] Example: Displaying text generated on a web page or within an app to the user.

[0058] 9. The user views the content and takes an action, such as clicking.

[0059] Example: User clicks on the "Pet Shop" link.

[0060] 10. The device records the user's actions and sends feedback to the server.

[0061] Example: Sending details of clicked links and actions to the server as logs.

[0062] 11. The server receives the feedback and analyzes the data to improve the performance of the generative AI.

[0063] Example: Analyze data such as click-through rate and time to complete reading and use it to generate new content.

[0064] One of the features of this invention is that it can provide a positive experience to users by naturally inserting advertisements according to their interests. In addition, by improving the accuracy of the generation AI based on user feedback, the effectiveness of the entire system can be continuously improved.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The user types a question or request into the input field, which becomes the prompt.

[0068] Step 2:

[0069] The device sends the prompt to the server, which then transmits it over the Internet.

[0070] Step 3:

[0071] The server receives the prompt. At this stage, it logs the receipt of the prompt.

[0072] Step 4:

[0073] The server passes the prompt to a natural language processing (NLP) algorithm, which parses the prompt and extracts key keywords and categories.

[0074] Step 5:

[0075] The server identifies relevant brands based on the extracted keywords and categories, searching an internal database.

[0076] Step 6:

[0077] The server passes the identified category and brand information to the generation AI, which then generates content based on this input data.

[0078] Step 7:

[0079] The server-based AI generates text content based on category and brand information, and advertisements are inserted into this content in a natural way.

[0080] Step 8:

[0081] The server then transmits the generated content to the terminal, which is also transmitted via the Internet.

[0082] Step 9:

[0083] The device receives the content and displays it to the user, such as on a web page or within an application.

[0084] Step 10:

[0085] The user views the content and takes actions such as clicking links and scrolling.

[0086] Step 11:

[0087] The device records user actions, collecting information such as which links are clicked and where the user scrolls.

[0088] Step 12:

[0089] The device sends the recorded feedback to a server, and the feedback data is transmitted over the Internet.

[0090] Step 13:

[0091] The server receives the feedback and performs data analysis, which is used to improve the performance of the generative AI.

[0092] Step 14:

[0093] The server feeds back the analysis results to the generation AI and uses them to generate new content, thereby continuously improving the accuracy and effectiveness of the entire system.

[0094] Example 1

[0095] 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."

[0096] Conventional content generation systems lack the accuracy and efficiency to quickly and accurately respond to user needs. In particular, they lack the ability to identify categories and brands based on user prompts and generate content accordingly. Furthermore, they lack a feedback system to continuously improve the quality of generated content, limiting the improvement of the user experience. Furthermore, they also have limited means to naturally insert advertisements that match the user's interests.

[0097] 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.

[0098] In this invention, the server includes a means for receiving prompts from a user, a means for passing the prompts to a natural language processing algorithm and extracting related information, a means for identifying a category and a brand, a means for generating content including the category and the brand, a means for providing the generated content to the user, a means for collecting user feedback, a means for analyzing the feedback and improving generation performance, a means for transmitting the generated content to the user's device, and a means for recording user actions and transmitting the recorded actions to the server as feedback. This enables highly accurate content generation based on user prompts and allows the performance of the generation AI model to be continuously improved based on the feedback. Furthermore, advertisements that match the user's interests can be inserted naturally, improving the user experience.

[0099] A "user" is an individual or organization that uses a system or application.

[0100] A "prompt" is specific text information such as a question or request that a user enters.

[0101] A "category" is a classification of general themes or topics extracted from the prompt.

[0102] A "brand" is an identifier such as a trademark or company name associated with a particular category.

[0103] "Content" refers to text and information generated based on category and brand information.

[0104] A "server" is a computer system that provides data processing and storage over a network.

[0105] A "terminal" is a device that a user uses to communicate with a server, such as a PC or smartphone.

[0106] A "natural language processing algorithm" is a computational method for analyzing text data and understanding the meaning and structure of natural language.

[0107] "Generative AI" is an artificial intelligence model that generates new content based on specified input data.

[0108] "Feedback" refers to data collected based on user actions and reactions.

[0109] "Performance" refers to the effectiveness or efficiency of a system or algorithm.

[0110] The present invention is a system that receives prompts from users, identifies relevant categories and brands, and generates and provides content that includes them. The operation of this system mainly involves a server, a user's device, and a generative AI model.

[0111] Hardware and software used

[0112] Server: The server is the main component that receives, analyzes, processes, stores, and transmits data. The server must have a powerful CPU, sufficient memory, and disk space; for example, it can be an EC2 instance from Amazon Web Services (AWS).

[0113] User device: The device on which the user enters prompts and receives content. Devices include PCs, smartphones, tablets, etc.

[0114] Software: A natural language processing algorithm is used to analyze the prompts, and OpenAI's GPT-3 is used as the generative AI model. This enables advanced text generation. Python's SpaCy and NLTK can be used as analysis libraries.

[0115] Specific examples of processing

[0116] Specific prompt examples

[0117] The user types, "What are your pet toy recommendations?" This prompt is provided as content through the following processing steps:

[0118] SUMMARY STEPS

[0119] 1. Receiving the prompt: The prompt entered by the user is sent from the device to the server, along with metadata such as the user ID and a timestamp.

[0120] 2. Parse the prompt: The server passes the prompt to a natural language processing algorithm to identify the category and brand. For example, the prompt "What are your pet toy recommendations?" identifies the categories "Pets" and "Toys" and the brands "Pet Shop" and "Popular Brands."

[0121] 3. Content generation: Based on the identified category and brand information, generative AI creates content. Specifically, the following content is generated:

[0122] For example: "Our recommended pet toys include the latest collections from pet stores. These durable, safe toys support your pet's health. We also offer interactive toys from popular brands, perfect for making playtime fun with your pet."

[0123] 4. Content Delivery: The generated content is sent from the server to the user's device, where it is displayed in the appropriate format.

[0124] 5. Feedback collection: Users browse content and take actions such as clicks. These actions are recorded by the device and sent to the server.

[0125] 6. Feedback Analysis: The server analyzes the collected feedback and uses it to improve the performance of the generation AI, which will improve the accuracy of content generation next time.

[0126] The present invention can continuously improve the accuracy of the AI ​​generation based on user feedback. Furthermore, it can improve the user experience by inserting advertisements naturally. In this way, the system can respond to user needs quickly and accurately.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Program processing steps

[0129] Step 1:

[0130] The user enters the prompt.

[0131] What happens: A user enters a question or request into a field in a web browser or mobile app and clicks the submit button.

[0132] Input: User prompt (e.g., "What are your pet toy recommendations?")

[0133] Output: Signals that a prompt is sent to the user's terminal.

[0134] Step 2:

[0135] The terminal sends a prompt to the server.

[0136] What happens: After the user clicks the submit button, the user's device sends the prompt they entered to the server as an HTTPS request, along with metadata such as the user ID and a timestamp.

[0137] Input: User prompts and metadata

[0138] Output: HTTP request sent to the server

[0139] Step 3:

[0140] The server receives the prompt.

[0141] What it does: The server analyzes the received request and records the prompt content in a log, along with other information such as the time of receipt and the source IP address.

[0142] Input: HTTP request sent from the terminal

[0143] Output: Logged prompts and metadata

[0144] Step 4:

[0145] The server passes the prompt to a natural language processing (NLP) algorithm.

[0146] What happens: The server passes the prompt to an NLP module to identify relevant categories and brands, parsing it using, for example, Python's SpaCy or NLTK.

[0147] Input: Prompt (e.g., "What are your pet toy recommendations?")

[0148] Output: Identified categories (e.g., "pets" or "toys") and brands (e.g., "pet shops" or "popular brands")

[0149] Step 5:

[0150] The server passes category and brand information to the generation AI.

[0151] Specific operation: The server passes the identified category and brand information to the generative AI. For example, using OpenAI's GPT-3 as the generative AI model, it sends a request to the API endpoint containing the necessary parameters.

[0152] Input: Identified category and brand information

[0153] Output: Parameters input to the generation AI

[0154] Step 6:

[0155] The generation AI on the server generates the content.

[0156] Specific operation: The AI ​​generates content based on the received category and brand information. For example, it might generate a sentence like, "Recommended pet toys include the latest collection of toys from pet shops. Durability and safety are guaranteed, supporting your pet's health. Popular brands of interactive toys are also perfect for making playtime with your pet more enjoyable."

[0157] Input: Category and brand information

[0158] Output: Generated content

[0159] Step 7:

[0160] The server transmits the generated content to the terminal.

[0161] Specific operation: The server sends the generated content to the user's device as an HTTP response. The content is organized in HTML or JSON format and sent in a format appropriate for the user's environment.

[0162] Input: Generated content

[0163] Output: The HTTP response sent to the user's device

[0164] Step 8:

[0165] The terminal displays the content to the user.

[0166] What it does: The user's device analyzes the received content and displays it in the web page or app interface. For example, a web browser might insert generated text into specific elements on the page and apply styling to make it more user-friendly.

[0167] Input: Content received from the server

[0168] Output: The content displayed to the user

[0169] Step 9:

[0170] Users view content and take action.

[0171] Specific behavior: The user reads the displayed content. If they find it interesting, they take an action such as clicking a link. For example, they click the "Pet Shop" link to go to the product page.

[0172] Input: Displayed content

[0173] Output: User action (e.g., link click)

[0174] Step 10:

[0175] The device records the user's actions and sends feedback to the server.

[0176] What it does: When a user action occurs, the device records the event and sends feedback to the server as an HTTP request, including the link clicked and a timestamp.

[0177] Input: User action data

[0178] Output: Feedback sent to the server

[0179] Step 11:

[0180] The server receives and analyzes the feedback.

[0181] How it works: The server logs the received feedback data and passes it to an analysis program. The analysis results are used to train the generative AI model, helping to improve the accuracy of future content generation.

[0182] Input: Feedback data sent from the device

[0183] Output: Parsed feedback and model training data

[0184] These steps enable the system to generate highly accurate content based on prompts from the user and use feedback to improve performance.

[0185] (Application example 1)

[0186] 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."

[0187] In recent years, the diversification of information and rapid changes in user needs have led to a demand for providing appropriate information to individual users. However, conventional systems have been unable to efficiently provide personalized content based on users' interests and preferences. In particular, they lack mechanisms for generating content in real time in response to user prompts and for improving the accuracy of generated content by incorporating user feedback. This not only degrades the user experience, but also poses challenges for companies, limiting their marketing effectiveness.

[0188] 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.

[0189] In this invention, the server includes means for receiving instructions from a user, means for identifying a category and a brand from the instructions, means for generating information using a generative AI model based on the specified category and brand, means for displaying the generated information on a mobile device or a web application, means for collecting user responses, and means for analyzing the responses and improving generation performance. This makes it possible to provide personalized content in real time based on user prompts and improve the accuracy of the generative AI by reflecting user feedback.

[0190] "User instructions" refers to text or voice input by a user requesting specific information.

[0191] A "category" refers to a subject or area of ​​interest identified based on a user's instructions.

[0192] "Brand" refers to the source and recognized name of a particular product or service.

[0193] "Information" refers to all content generated by a generative AI model and provided to users.

[0194] "Generative AI Model" refers to an artificial intelligence algorithm that generates content based on a specified category and brand.

[0195] "Mobile Device or Web Application" refers to the computing device or software used to display generated information to a user.

[0196] "User response" refers to the actions and feedback that users take in response to the generated information, such as "likes," "shares," and "clicks."

[0197] "Generative performance" refers to the efficiency and quality of how accurately a generative AI model can generate content that meets user needs.

[0198] This invention is a system that appropriately generates and provides specific information when a user acquires that information through a mobile device or web application.

[0199] First, a user inputs a "prompt sentence" in a specific format into a mobile device or web application, expressing their desire to obtain specific information. For example, "Tell me the latest technology news." This prompt sentence is sent to the system's server, which then receives it.

[0200] The server then parses the prompt and uses natural language processing algorithms to identify relevant categories and brands within the prompt, such as categories like "technology" or "news," or the brand "famous technology websites."

[0201] Based on this identified category and brand information, the server uses a generative AI model, such as OpenAI's "gpt-3.5-turbo," to generate information tailored to the user's interests. When this model generates information, it tailors it to the context of the specified category or brand.

[0202] The generated information is then sent back to the mobile terminal or web application and displayed to the user. It is important that the generated information meets the user's requirements.

[0203] When a user views this information and takes an action, such as "liking," "sharing," or "clicking," their reaction is fed back to the system. This feedback information is sent to the server, which analyzes it and uses it to improve the performance of the generative AI model. At this time, the generative AI model is adjusted based on user feedback, enabling it to generate information with greater accuracy.

[0204] To further improve the system, the server needs to periodically train the model and evaluate its performance based on collected user response data. This will enable the continuous provision of high-quality generated information tailored to user needs. It's a fine line. This is an important feature of this system.

[0205] In this way, users can obtain highly accurate information tailored to their interests and needs in real time. To implement this system, an internet-enabled mobile device or web application and a high-performance server are required. Specifically, a server with sufficient computing power to run natural language processing algorithms and API access to the generative AI model "gpt-3.5-turbo" are required.

[0206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0207] Step 1:

[0208] On a mobile device or web application, a user enters a prompt to obtain specific information and clicks a submit button.

[0209] Input: The prompt text entered by the user (e.g., "What's the latest technology news?").

[0210] Output: The prompt text is sent to the server.

[0211] Step 2:

[0212] The terminal transmits the prompt text from the user to the server via the Internet.

[0213] Input: The user's prompt.

[0214] Output: The prompt is transmitted to the server via the Internet.

[0215] Step 3:

[0216] The server receives the prompt and logs it.

[0217] Input: The prompt text received over the Internet.

[0218] Output: The prompt statement logged.

[0219] Step 4:

[0220] The server passes the prompt sentence to a natural language processing (NLP) algorithm to identify relevant categories and brands.

[0221] Input: The user's prompt.

[0222] Data processing: NLP algorithms analyze the prompt and extract key keywords (category and brand) from the text.

[0223] Output: Identified categories and brands (e.g., "Technology," "News," and "Famous Technology Websites").

[0224] Step 5:

[0225] The server passes the identified category and brand information to a generative AI model to generate content.

[0226] Input: Identified category and brand.

[0227] Data calculation: A generative AI model (e.g., "gpt-3.5-turbo") generates appropriate content based on the specified category and brand.

[0228] Output: The generated content (e.g., an article about the latest technology news).

[0229] Step 6:

[0230] The server transmits the generated content to the user's terminal.

[0231] Input: Generated content.

[0232] Output: The generated content that is sent to the user's device.

[0233] Step 7:

[0234] The terminal receives the generated content and displays it to the user.

[0235] Input: Generated content sent from the server.

[0236] Output: The generated content that is displayed on the device screen.

[0237] Step 8:

[0238] Users view the provided content and take actions such as "like," "share," or "click."

[0239] Input: The content displayed on the device.

[0240] Output: User action (e.g. "like", "share", "click").

[0241] Step 9:

[0242] The terminal records the user's actions and sends them as feedback to the server.

[0243] Input: User action.

[0244] Output: Feedback data sent to the server.

[0245] Step 10:

[0246] The server analyzes the received feedback and uses it to improve the performance of the generative AI model.

[0247] Input: User feedback data.

[0248] Data processing: Analyze feedback data, evaluate the performance of generative AI models, and retrain the models as needed.

[0249] Output: An improved generative AI model.

[0250] 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.

[0251] The present invention is characterized in that the system receives prompts from a user, identifies related categories and brands, and generates content including them, and further recognizes the user's emotions using an emotion engine and reflects them in the content generation. Specific embodiments are described below.

[0252] Program processing

[0253] The system identifies relevant categories and brands based on user prompts and uses an emotion engine to analyze the user's emotions at the time of the prompt. The generative AI then generates content based on the category, brand, and user emotion information. The generated content is provided to the user, and user feedback is collected. This feedback is analyzed and used to improve the accuracy of the generative AI.

[0254] Specific examples

[0255] 1. A user types, "Tell me how to relax and relieve stress."

[0256] The user enters the prompt into the input field and clicks the submit button.

[0257] 2. The device sends this prompt to the server.

[0258] The prompt is sent over the Internet to a server, which confirms receipt.

[0259] 3. The server receives the prompt.

[0260] Receive and log prompts.

[0261] 4. The server passes the prompt to a natural language processing (NLP) algorithm to identify the category and brand.

[0262] Example: Parse the prompt "What relaxation techniques can I use to relieve stress?" to identify the categories "relaxation" and "stress" and the brands "wellness center" and "relaxation products."

[0263] 5. The server has the emotion engine analyze the prompt and identify the user's emotion.

[0264] Example: The emotion engine identifies "stress" as the emotion from the user's prompt.

[0265] 6. The server passes the identified category, brand, and user sentiment information to the generation AI.

[0266] Example: The categories "relaxation" and "stress relief," the brands "wellness center" and "relaxation goods," and the user emotion "stress" are input into the generation AI.

[0267] 7. Generative AI in the server creates text content based on category, brand, and user sentiment information. Advertisements are inserted into this content in a natural way.

[0268] Example: A generation AI generates the following sentence:

[0269] We recommend yoga classes at wellness centers as a relaxation method to relieve stress. Popular aroma diffusers are also effective as relaxation tools. By utilizing these, you can ease the stress of everyday life.

[0270] 8. The server sends the generated content to the device.

[0271] Example: Deliver the generated text to the user's device.

[0272] 9. The device receives the content and displays it to the user.

[0273] Example: Displaying text generated on a web page or within an app to the user.

[0274] 10. The user views the content and takes action, such as clicking a link or scrolling.

[0275] 11. The device records the user's actions and sends feedback to the server.

[0276] Example: Sending details of clicked links and actions to the server as logs.

[0277] 12. The server receives the feedback and performs data analysis, which helps improve the performance of the generative AI.

[0278] This embodiment enables the generation of personalized content that takes into account the emotional state of the user, thereby achieving higher user satisfaction. Furthermore, by reflecting the analysis results of the emotion engine in the content generation, the user experience can be further improved.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] The user types a question or request into the input field, which becomes the prompt.

[0282] Step 2:

[0283] The device sends the prompt to the server, which then transmits it over the Internet.

[0284] Step 3:

[0285] The server receives the prompt. At this stage, it logs the receipt of the prompt.

[0286] Step 4:

[0287] The server passes the prompt to a natural language processing (NLP) algorithm, which parses the prompt and extracts key keywords and categories.

[0288] Step 5:

[0289] The server identifies relevant brands based on the extracted keywords and categories, searching an internal database.

[0290] Step 6:

[0291] The server passes the prompt to the emotion engine, which analyzes the user's emotion from the words and phrases in the prompt.

[0292] Step 7:

[0293] The server receives the analysis results of the emotion engine and identifies the user's emotion. For example, it recognizes that the user is in a stressful state based on the keyword "stress" in the prompt.

[0294] Step 8:

[0295] The server passes the identified category, brand, and user sentiment information to the generation AI, which then generates content based on this input data.

[0296] Step 9:

[0297] The server-based generative AI creates text content based on category, brand, and user sentiment information, and advertisements are inserted into this content in a natural way.

[0298] Step 10:

[0299] The server then transmits the generated content to the terminal, which is also transmitted via the Internet.

[0300] Step 11:

[0301] The device receives the content and displays it to the user, such as on a web page or within an application.

[0302] Step 12:

[0303] The user views the content and takes actions such as clicking links and scrolling.

[0304] Step 13:

[0305] The device records user actions, collecting information such as which links are clicked and where the user scrolls.

[0306] Step 14:

[0307] The device sends the recorded feedback to a server, and the feedback data is transmitted over the Internet.

[0308] Step 15:

[0309] The server receives the feedback and performs data analysis, which is used to improve the performance of the generative AI.

[0310] Step 16:

[0311] The server feeds back the analysis results to the generation AI and uses them to generate new content, thereby continuously improving the accuracy and effectiveness of the entire system.

[0312] Example 2

[0313] 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."

[0314] Conventional content generation systems have difficulty generating personalized content that takes user emotions into account, making it difficult to improve user satisfaction. Furthermore, there was a lack of a mechanism to effectively collect and analyze user feedback on the generated content, limiting improvements to content quality.

[0315] 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.

[0316] In this invention, the server includes means for receiving a prompt from a user, means for identifying a category and a brand from the prompt, means for analyzing emotions from the prompt, means for generating content based on the category, brand, and emotion information, means for providing the generated content to the user, means for collecting user feedback, and means for analyzing the feedback and improving content generation performance. This enables the generation of personalized content that corresponds to the user's emotional state, thereby improving user satisfaction. Furthermore, by analyzing the feedback and reflecting it in the next generation, the quality of the generated content can be continuously improved.

[0317] A "prompt" is a question or request that a user enters into a system.

[0318] "Category" refers to a classification that indicates an area related to a particular theme or topic.

[0319] "Brand" refers to the name or identification used to identify a particular product or service.

[0320] "Emotion" refers to the psychological state of the user when entering the prompt.

[0321] "Content" refers to a collection of information, text, images, videos, etc., provided to users.

[0322] "Feedback" refers to information that indicates the user's reaction and behavior to the generated content.

[0323] "Natural language processing algorithms" refer to computer programs that analyze user prompts and identify relevant categories, brands, and sentiments.

[0324] "Generative AI" refers to artificial intelligence technology that generates new content based on input data.

[0325] "Database" refers to a data management system for storing prompts, generated content, feedback information, etc.

[0326] "Server" refers to a central computer system that manages the entire system and processes requests from users.

[0327] The present invention is a system that receives prompts from users, identifies relevant categories and brands, and generates content based on them. Furthermore, the system aims to increase user satisfaction by using an emotion engine to recognize the user's emotions and reflecting that emotion information in the content generation.

[0328] The system includes the following major components:

[0329] 1. User Interface

[0330] 2. Server

[0331] 3. Natural Language Processing Algorithms

[0332] 4. Emotion Engine

[0333] 5. Generation AI

[0334] 6. Database

[0335] 1. User Interface

[0336] A user accesses the system using a terminal connected to the Internet (e.g., a PC, a smartphone, a tablet, etc.). The user interface has an input field where the user can enter a prompt.

[0337] 2. Server

[0338] The server is the central processing unit of the system, receiving prompts from users and performing various analyses and generation. The server is also connected to a database that manages prompts, generated content, and feedback information.

[0339] 3. Natural Language Processing Algorithms

[0340] The server then passes the received prompts to a natural language processing algorithm to identify categories and brands, which analyzes the text data and extracts meaning and relationships.

[0341] 4. Emotion Engine

[0342] The server analyzes the user's emotion in the prompt using an emotion engine, which works in conjunction with natural language processing to analyze emotion keywords and context in the sentence to identify the user's mental state.

[0343] 5. Generation AI

[0344] Generative AI generates content based on identified categories, brands, and user sentiment information. This generative AI is a model that uses deep learning to create natural-looking text.

[0345] 6. Database

[0346] The database is connected to the server and is a system that stores and manages prompts, generated content, and user feedback data, allowing the feedback data to be analyzed and used to improve the generative AI.

[0347] As a specific example, when a user types "Tell me some relaxation techniques to relieve stress" and clicks the send button, the device sends this prompt to the server. The server receives the prompt and passes it to a natural language processing algorithm for analysis, identifying the categories "relaxation" and "stress relief" and the brands "wellness center" and "relaxation products." At the same time, the emotion engine analyzes the user's emotions and identifies "stress." Based on the identified information, the generation AI generates text content introducing relaxation techniques related to "yoga classes at wellness centers" and "aromatherapy diffusers." The server then sends this content to the device and displays it to the user. The system is continuously improved as users view the generated content and provide feedback.

[0348] This invention enables the generation of personalized content that takes into account the user's emotional state, improving the user experience. Furthermore, by utilizing user feedback to improve the accuracy of the generation AI, further quality improvements can be expected.

[0349] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0350] Step 1:

[0351] The user enters and submits the prompt.

[0352] Input: A user-written prompt in natural language (e.g., "Tell me some relaxation techniques to relieve stress")

[0353] Output: Send button press signal to terminal

[0354] Specific operation: The user enters a prompt into the input field of the terminal and clicks the send button, which sends the prompt to the server via the terminal's send function.

[0355] Step 2:

[0356] The terminal sends a prompt to the server.

[0357] Input: Prompt from user

[0358] Output: The prompt reaches the server

[0359] What it does: The device sends the prompt over the internet to a server, encrypting the data using a security protocol such as SSL.

[0360] Step 3:

[0361] The server receives the prompt and logs it.

[0362] Input: Prompt sent from the terminal

[0363] Output: Prompt log entry

[0364] Specific operation: The server receives the prompt and records its contents in a log file. The log includes the time of receipt and the prompt contents.

[0365] Step 4:

[0366] The server passes the prompt to a natural language processing (NLP) algorithm to parse it and identify the category and brand.

[0367] Input: Prompt (e.g., "What relaxation techniques can I use to relieve stress?")

[0368] Output: Identified categories and brands (e.g., categories "relaxation" and "stress relief" and brands "wellness center" and "relaxation products")

[0369] What happens: The server feeds the prompt into an NLP algorithm for semantic analysis, which identifies relevant categories and brands.

[0370] Step 5:

[0371] The server analyzes the prompt with an emotion engine to identify the user's emotion.

[0372] Input: prompt

[0373] Output: Identified user emotion (e.g. "stressed")

[0374] Specific operation: The server uses the emotion engine to analyze the emotion keywords and contextual information in the prompt to identify the user's emotional state.

[0375] Step 6:

[0376] The server passes the identified category, brand, and user sentiment information to the generation AI.

[0377] Input: Category, brand, and sentiment information

[0378] Output: Input data to the generative AI

[0379] Specific operation: The server formats the identified information to be input into the generative AI model and sends it to the generative AI.

[0380] Step 7:

[0381] Generative AI generates text content based on category, brand, and user sentiment information.

[0382] Input: Category, brand, and emotion information (e.g., category "relaxation" and "stress relief", brand "wellness center" and "relaxation goods", emotion "stress")

[0383] Output: Generated text content (e.g., "I recommend yoga classes at the wellness center as a relaxing way to relieve stress.")

[0384] How it works: Generative AI generates text content in a natural way based on input data, with relevant ads naturally inserted.

[0385] Step 8:

[0386] The server transmits the generated content to the terminal.

[0387] Input: Generated text content

[0388] Output: Content sent to the device

[0389] Specific operation: The server formats the generated content appropriately and sends the data to the device.

[0390] Step 9:

[0391] The terminal receives the content and displays it to the user.

[0392] Input: Content sent from the server

[0393] Output: Content displayed on the user's screen

[0394] Specific operation: The device analyzes the data it receives and displays it on the web page or app user interface.

[0395] Step 10:

[0396] The user views the content and takes actions such as clicking links and scrolling.

[0397] Input: Displayed content

[0398] Output: User action data (e.g., link click, scroll)

[0399] Specific Action: The user browses the generated content and takes an action such as clicking on a link that interests them.

[0400] Step 11:

[0401] The device records the user's actions and sends feedback to the server.

[0402] Input: User action data

[0403] Output: Feedback data sent to the server

[0404] Specific operation: The device logs user behavior data (e.g., click history, viewing time) and sends it to the server.

[0405] Step 12:

[0406] The server receives the feedback and performs data analysis, which is used to improve the performance of the generation AI.

[0407] Input: Feedback data

[0408] Output: Analysis results and improved generative AI

[0409] What it does: The server analyzes the feedback data and uses the results to modify the AI ​​generation algorithm, which is reflected in the next content generation and improves its accuracy.

[0410] (Application example 2)

[0411] 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."

[0412] The problem to be solved by the present invention is to provide more personalized content in response to user input, and to improve the user experience by recommending related products and services taking into account the user's emotions.

[0413] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a prompt from a user, means for identifying a category and a brand from the prompt, means for analyzing the user's emotions from the prompt, means for generating content based on the category, brand, and user emotions, means for providing the generated content to the user, means for collecting user feedback, and means for analyzing the feedback and improving generation performance. This makes it possible to provide personalized content that takes the user's emotional state into consideration and recommend optimal products and services.

[0414] A "means for receiving prompts from a user" is a device or program for receiving commands, such as text or voice, entered by a user.

[0415] "Category and brand identification means" refers to technology that includes natural language processing algorithms for identifying relevant product categories and brands from the received prompts.

[0416] The "means for analyzing user emotions" is an emotion engine or analysis algorithm for analyzing the user's current emotional state from the user's prompts.

[0417] The "content generation means" is a generative AI model for creating information such as text and images based on identified categories, brands, and user sentiment.

[0418] The "means for providing to the user" refers to an interface or communication means for displaying or transmitting the generated content to the user.

[0419] A "means for collecting user feedback" is a tool or system for recording reactions and actions taken by users in response to generated content.

[0420] "Means for analyzing feedback and improving generative performance" refers to data analysis techniques that analyze collected feedback and improve the accuracy and efficiency of generative AI models.

[0421] A "product recommendation means" is a system for selecting and recommending appropriate products and services based on identified categories, brands, and user sentiment.

[0422] This invention is a system that generates personalized content by identifying appropriate categories and brands based on prompts from users and analyzing user sentiment. The system can be accessed from devices such as smartphones, tablets, and PCs, and the entire process is performed by a server via the Internet.

[0423] First, a user inputs a prompt (for example, "Tell me about a product you like to use when you're tired") using a terminal. This prompt is sent to a server via the Internet.

[0424] The server then runs the prompt through a natural language processing algorithm (e.g., the TextBlob library) to identify categories and brands. For example, the prompt "Tell me what products you like to use when you're tired" might identify categories like "relaxation products" and "wellness products."

[0425] An emotion engine is then used to analyze the user's emotion (e.g., "fatigue"). This emotion information is passed to a generative AI model, which generates personalized content based on the identified category and brand. The generated content includes recommended products and services. For example, based on the emotion "fatigue," products such as "aroma diffusers" and "massage pillows" are recommended.

[0426] The server sends the generated content to the terminal, where the user can view the content. The terminal also records the actions the user takes while viewing the content (for example, clicking links or scrolling), and sends the records back to the server.

[0427] Finally, the server analyzes the collected feedback to improve the performance of the generative AI model, which will enable more accurate content generation in the future.

[0428] For example, if a user inputs the prompt "I've been feeling stressed lately, please tell me about some products that will help me relax," the emotion engine will determine the emotion "stress," and the generative AI model will generate content that recommends products such as "aroma diffusers" and "relaxation cushions." This content will be displayed on the user's device, improving the user experience.

[0429] As described above, the present invention generates personalized content by taking into consideration not only the category and brand but also the user's emotions, thereby enabling more effective product and service recommendations.

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] The user uses the terminal to enter and send a prompt.

[0433] Input: Prompt sentence (e.g., "Tell me what products you like to use when you're tired.")

[0434] Output: The prompt is sent to the server.

[0435] Step 2:

[0436] The server passes the received prompts to a natural language processing algorithm to identify the category and brand.

[0437] Input: The prompt text sent by the user

[0438] Data processing: Parsing prompts using natural language processing algorithms (e.g., TextBlob library)

[0439] Output: Identified category (e.g., "Relaxation Products") and brand (e.g., "Wellness Products")

[0440] Step 3:

[0441] The server uses an emotion engine to analyze the user's emotion from the prompt sentence.

[0442] Input: The prompt text sent by the user

[0443] Data Computation: Identify emotional states (e.g., "fatigue") from prompts using an emotion engine

[0444] Output: User's emotional state (e.g., "fatigue")

[0445] Step 4:

[0446] The server generates content using a generative AI model based on identified categories, brands, and user sentiment.

[0447] Input: Category (e.g., "Relaxation Products"), Brand (e.g., "Wellness Products"), User Sentiment (e.g., "Fatigue")

[0448] Data computation: Generative AI models are used to generate content based on category, brand, and user sentiment (e.g., recommendations for "aroma diffusers" or "massage pillows").

[0449] Output: Generated content (e.g., "When you're tired, we recommend using an aroma diffuser!")

[0450] Step 5:

[0451] The server transmits the generated content to the terminal.

[0452] Input: Generated content

[0453] Output: Content is sent to the device

[0454] Step 6:

[0455] The user views the content on the device.

[0456] Input: Content sent from the server

[0457] Output: The content is displayed on the device screen.

[0458] Step 7:

[0459] The terminal records the user's feedback and sends it to the server.

[0460] Input: User actions (e.g., clicking a link, scrolling)

[0461] Data processing: Recording user actions and compiling them as feedback data

[0462] Output: Feedback data is sent to the server

[0463] Step 8:

[0464] The server analyzes the received feedback data and improves the performance of the generative AI model.

[0465] Input: Feedback data

[0466] Data computation: Analyzing feedback data using analytical algorithms to identify areas for improvement in the generative AI model

[0467] Output: Update and improve the accuracy of the generative AI model

[0468] Through the above steps, the system can generate personalized content according to the user's emotional state and improve the user experience.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] [Second embodiment]

[0473] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0474] 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.

[0475] 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).

[0476] 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.

[0477] 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.

[0478] 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).

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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.

[0483] 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.

[0484] 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."

[0485] The present invention is a system that receives prompts from a user, identifies relevant categories and brands, and generates content that includes them, and is embodied in the following manner.

[0486] Program processing

[0487] The system operates through the following steps: Based on prompts from the user, a natural language processing algorithm is used to identify relevant categories and brands, and the generation AI generates content based on this information. The generated content is provided to the user, and user feedback is collected. This feedback is analyzed and used to improve the accuracy of the generation AI.

[0488] Specific examples

[0489] 1. User types, "Recommendations for pet toys."

[0490] The user enters the prompt into the input field and clicks the submit button.

[0491] 2. The device sends this prompt to the server.

[0492] A prompt is sent over the Internet to a server, which confirms receipt.

[0493] 3. The server receives the prompt.

[0494] Receive and log prompts.

[0495] 4. The server passes the prompt to a natural language processing (NLP) algorithm to identify the category and brand.

[0496] Example: Parse the prompt "What are your pet toy recommendations?" to identify the categories "Pets" and "Toys" and the brands "Pet Shops" and "Popular Brands."

[0497] 5. The server passes the extracted category and brand information to the generation AI.

[0498] Example: Input the categories "Pets" and "Toys" and the brands "Pet Shop" and "Popular Brands" into the generation AI.

[0499] 6. The generation AI on the server generates content based on category and brand information.

[0500] Example: A generation AI generates the following sentence:

[0501] Our recommended pet toys include the latest collections from pet stores, which are durable and safe, supporting your pet's health. Popular brands of interactive toys are also perfect for making playtime fun with your pet.

[0502] 7. The server sends the generated content to the device.

[0503] Example: Deliver the generated text to the user's device.

[0504] 8. The device receives the content and displays it to the user.

[0505] Example: Displaying text generated on a web page or within an app to the user.

[0506] 9. The user views the content and takes an action, such as clicking.

[0507] Example: User clicks on the "Pet Shop" link.

[0508] 10. The device records the user's actions and sends feedback to the server.

[0509] Example: Sending details of clicked links and actions to the server as logs.

[0510] 11. The server receives the feedback and analyzes the data to improve the performance of the generative AI.

[0511] Example: Analyze data such as click-through rate and time to complete reading and use it to generate new content.

[0512] One of the features of this invention is that it can provide a positive experience to users by naturally inserting advertisements according to their interests. In addition, by improving the accuracy of the generation AI based on user feedback, the effectiveness of the entire system can be continuously improved.

[0513] The processing flow will be explained below.

[0514] Step 1:

[0515] The user types a question or request into the input field, which becomes the prompt.

[0516] Step 2:

[0517] The device sends the prompt to the server, which then transmits it over the Internet.

[0518] Step 3:

[0519] The server receives the prompt. At this stage, it logs the receipt of the prompt.

[0520] Step 4:

[0521] The server passes the prompt to a natural language processing (NLP) algorithm, which parses the prompt and extracts key keywords and categories.

[0522] Step 5:

[0523] The server identifies relevant brands based on the extracted keywords and categories, searching an internal database.

[0524] Step 6:

[0525] The server passes the identified category and brand information to the generation AI, which then generates content based on this input data.

[0526] Step 7:

[0527] The server-based AI generates text content based on category and brand information, and advertisements are inserted into this content in a natural way.

[0528] Step 8:

[0529] The server then transmits the generated content to the terminal, which is also transmitted via the Internet.

[0530] Step 9:

[0531] The device receives the content and displays it to the user, such as on a web page or within an application.

[0532] Step 10:

[0533] The user views the content and takes actions such as clicking links and scrolling.

[0534] Step 11:

[0535] The device records user actions, collecting information such as which links are clicked and where the user scrolls.

[0536] Step 12:

[0537] The device sends the recorded feedback to a server, and the feedback data is transmitted over the Internet.

[0538] Step 13:

[0539] The server receives the feedback and performs data analysis, which is used to improve the performance of the generative AI.

[0540] Step 14:

[0541] The server feeds back the analysis results to the generation AI and uses them to generate new content, thereby continuously improving the accuracy and effectiveness of the entire system.

[0542] Example 1

[0543] 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."

[0544] Conventional content generation systems lack the accuracy and efficiency to quickly and accurately respond to user needs. In particular, they lack the ability to identify categories and brands based on user prompts and generate content accordingly. Furthermore, they lack a feedback system to continuously improve the quality of generated content, limiting the improvement of the user experience. Furthermore, they also have limited means to naturally insert advertisements that match the user's interests.

[0545] 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.

[0546] In this invention, the server includes a means for receiving prompts from a user, a means for passing the prompts to a natural language processing algorithm and extracting related information, a means for identifying a category and a brand, a means for generating content including the category and the brand, a means for providing the generated content to the user, a means for collecting user feedback, a means for analyzing the feedback and improving generation performance, a means for transmitting the generated content to the user's device, and a means for recording user actions and transmitting the recorded actions to the server as feedback. This enables highly accurate content generation based on user prompts and allows the performance of the generation AI model to be continuously improved based on the feedback. Furthermore, advertisements that match the user's interests can be inserted naturally, improving the user experience.

[0547] A "user" is an individual or organization that uses a system or application.

[0548] A "prompt" is specific text information such as a question or request that a user enters.

[0549] A "category" is a classification of general themes or topics extracted from the prompt.

[0550] A "brand" is an identifier such as a trademark or company name associated with a particular category.

[0551] "Content" refers to text and information generated based on category and brand information.

[0552] A "server" is a computer system that provides data processing and storage over a network.

[0553] A "terminal" is a device that a user uses to communicate with a server, such as a PC or smartphone.

[0554] A "natural language processing algorithm" is a computational method for analyzing text data and understanding the meaning and structure of natural language.

[0555] "Generative AI" is an artificial intelligence model that generates new content based on specified input data.

[0556] "Feedback" refers to data collected based on user actions and reactions.

[0557] "Performance" refers to the effectiveness or efficiency of a system or algorithm.

[0558] The present invention is a system that receives prompts from users, identifies relevant categories and brands, and generates and provides content that includes them. The operation of this system mainly involves a server, a user's device, and a generative AI model.

[0559] Hardware and software used

[0560] Server: The server is the main component that receives, analyzes, processes, stores, and transmits data. The server must have a powerful CPU, sufficient memory, and disk space; for example, it can be an EC2 instance from Amazon Web Services (AWS).

[0561] User device: The device on which the user enters prompts and receives content. Devices include PCs, smartphones, tablets, etc.

[0562] Software: A natural language processing algorithm is used to analyze the prompts, and OpenAI's GPT-3 is used as the generative AI model. This enables advanced text generation. Python's SpaCy and NLTK can be used as analysis libraries.

[0563] Specific examples of processing

[0564] Specific prompt examples

[0565] The user types, "What are your pet toy recommendations?" This prompt is provided as content through the following processing steps:

[0566] SUMMARY STEPS

[0567] 1. Receiving the prompt: The prompt entered by the user is sent from the device to the server, along with metadata such as the user ID and a timestamp.

[0568] 2. Parse the prompt: The server passes the prompt to a natural language processing algorithm to identify the category and brand. For example, the prompt "What are your pet toy recommendations?" identifies the categories "Pets" and "Toys" and the brands "Pet Shop" and "Popular Brands."

[0569] 3. Content generation: Based on the identified category and brand information, generative AI creates content. Specifically, the following content is generated:

[0570] For example: "Our recommended pet toys include the latest collections from pet stores. These durable, safe toys support your pet's health. We also offer interactive toys from popular brands, perfect for making playtime fun with your pet."

[0571] 4. Content Delivery: The generated content is sent from the server to the user's device, where it is displayed in the appropriate format.

[0572] 5. Feedback collection: Users browse content and take actions such as clicks. These actions are recorded by the device and sent to the server.

[0573] 6. Feedback Analysis: The server analyzes the collected feedback and uses it to improve the performance of the generation AI, which will improve the accuracy of content generation next time.

[0574] The present invention can continuously improve the accuracy of the AI ​​generation based on user feedback. Furthermore, it can improve the user experience by inserting advertisements naturally. In this way, the system can respond to user needs quickly and accurately.

[0575] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0576] Program processing steps

[0577] Step 1:

[0578] The user enters the prompt.

[0579] What happens: A user enters a question or request into a field in a web browser or mobile app and clicks the submit button.

[0580] Input: User prompt (e.g., "What are your pet toy recommendations?")

[0581] Output: Signals that a prompt is sent to the user's terminal.

[0582] Step 2:

[0583] The terminal sends a prompt to the server.

[0584] What happens: After the user clicks the submit button, the user's device sends the prompt they entered to the server as an HTTPS request, along with metadata such as the user ID and a timestamp.

[0585] Input: User prompts and metadata

[0586] Output: HTTP request sent to the server

[0587] Step 3:

[0588] The server receives the prompt.

[0589] What it does: The server analyzes the received request and records the prompt content in a log, along with other information such as the time of receipt and the source IP address.

[0590] Input: HTTP request sent from the terminal

[0591] Output: Logged prompts and metadata

[0592] Step 4:

[0593] The server passes the prompt to a natural language processing (NLP) algorithm.

[0594] What happens: The server passes the prompt to an NLP module to identify relevant categories and brands, parsing it using, for example, Python's SpaCy or NLTK.

[0595] Input: Prompt (e.g., "What are your pet toy recommendations?")

[0596] Output: Identified categories (e.g., "pets" or "toys") and brands (e.g., "pet shops" or "popular brands")

[0597] Step 5:

[0598] The server passes category and brand information to the generation AI.

[0599] Specific operation: The server passes the identified category and brand information to the generative AI. For example, using OpenAI's GPT-3 as the generative AI model, it sends a request to the API endpoint containing the necessary parameters.

[0600] Input: Identified category and brand information

[0601] Output: Parameters input to the generation AI

[0602] Step 6:

[0603] The generation AI on the server generates the content.

[0604] Specific operation: The AI ​​generates content based on the received category and brand information. For example, it might generate a sentence like, "Recommended pet toys include the latest collection of toys from pet shops. Durability and safety are guaranteed, supporting your pet's health. Popular brands of interactive toys are also perfect for making playtime with your pet more enjoyable."

[0605] Input: Category and brand information

[0606] Output: Generated content

[0607] Step 7:

[0608] The server transmits the generated content to the terminal.

[0609] Specific operation: The server sends the generated content to the user's device as an HTTP response. The content is organized in HTML or JSON format and sent in a format appropriate for the user's environment.

[0610] Input: Generated content

[0611] Output: The HTTP response sent to the user's device

[0612] Step 8:

[0613] The terminal displays the content to the user.

[0614] What it does: The user's device analyzes the received content and displays it in the web page or app interface. For example, a web browser might insert generated text into specific elements on the page and apply styling to make it more user-friendly.

[0615] Input: Content received from the server

[0616] Output: The content displayed to the user

[0617] Step 9:

[0618] Users view content and take action.

[0619] Specific behavior: The user reads the displayed content. If they find it interesting, they take an action such as clicking a link. For example, they click the "Pet Shop" link to go to the product page.

[0620] Input: Displayed content

[0621] Output: User action (e.g., link click)

[0622] Step 10:

[0623] The device records the user's actions and sends feedback to the server.

[0624] What it does: When a user action occurs, the device records the event and sends feedback to the server as an HTTP request, including the link clicked and a timestamp.

[0625] Input: User action data

[0626] Output: Feedback sent to the server

[0627] Step 11:

[0628] The server receives and analyzes the feedback.

[0629] How it works: The server logs the received feedback data and passes it to an analysis program. The analysis results are used to train the generative AI model, helping to improve the accuracy of future content generation.

[0630] Input: Feedback data sent from the device

[0631] Output: Parsed feedback and model training data

[0632] These steps enable the system to generate highly accurate content based on prompts from the user and use feedback to improve performance.

[0633] (Application example 1)

[0634] 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."

[0635] In recent years, the diversification of information and rapid changes in user needs have led to a demand for providing appropriate information to individual users. However, conventional systems have been unable to efficiently provide personalized content based on users' interests and preferences. In particular, they lack mechanisms for generating content in real time in response to user prompts and for improving the accuracy of generated content by incorporating user feedback. This not only degrades the user experience, but also poses challenges for companies, limiting their marketing effectiveness.

[0636] 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.

[0637] In this invention, the server includes means for receiving instructions from a user, means for identifying a category and a brand from the instructions, means for generating information using a generative AI model based on the specified category and brand, means for displaying the generated information on a mobile device or a web application, means for collecting user responses, and means for analyzing the responses and improving generation performance. This makes it possible to provide personalized content in real time based on user prompts and improve the accuracy of the generative AI by reflecting user feedback.

[0638] "User instructions" refers to text or voice input by a user requesting specific information.

[0639] A "category" refers to a subject or area of ​​interest identified based on a user's instructions.

[0640] "Brand" refers to the source and recognized name of a particular product or service.

[0641] "Information" refers to all content generated by a generative AI model and provided to users.

[0642] "Generative AI Model" refers to an artificial intelligence algorithm that generates content based on a specified category and brand.

[0643] "Mobile Device or Web Application" refers to the computing device or software used to display generated information to a user.

[0644] "User response" refers to the actions and feedback that users take in response to the generated information, such as "likes," "shares," and "clicks."

[0645] "Generative performance" refers to the efficiency and quality of how accurately a generative AI model can generate content that meets user needs.

[0646] This invention is a system that appropriately generates and provides specific information when a user acquires that information through a mobile device or web application.

[0647] First, a user inputs a "prompt sentence" in a specific format into a mobile device or web application, expressing their desire to obtain specific information. For example, "Tell me the latest technology news." This prompt sentence is sent to the system's server, which then receives it.

[0648] The server then parses the prompt and uses natural language processing algorithms to identify relevant categories and brands within the prompt, such as categories like "technology" or "news," or the brand "famous technology websites."

[0649] Based on this identified category and brand information, the server uses a generative AI model, such as OpenAI's "gpt-3.5-turbo," to generate information tailored to the user's interests. When this model generates information, it tailors it to the context of the specified category or brand.

[0650] The generated information is then sent back to the mobile terminal or web application and displayed to the user. It is important that the generated information meets the user's requirements.

[0651] When a user views this information and takes an action, such as "liking," "sharing," or "clicking," their reaction is fed back to the system. This feedback information is sent to the server, which analyzes it and uses it to improve the performance of the generative AI model. At this time, the generative AI model is adjusted based on user feedback, enabling it to generate information with greater accuracy.

[0652] To further improve the system, the server needs to periodically train the model and evaluate its performance based on collected user response data. This will enable the continuous provision of high-quality generated information tailored to user needs. It's a fine line. This is an important feature of this system.

[0653] In this way, users can obtain highly accurate information tailored to their interests and needs in real time. To implement this system, an internet-enabled mobile device or web application and a high-performance server are required. Specifically, a server with sufficient computing power to run natural language processing algorithms and API access to the generative AI model "gpt-3.5-turbo" are required.

[0654] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0655] Step 1:

[0656] On a mobile device or web application, a user enters a prompt to obtain specific information and clicks a submit button.

[0657] Input: The prompt text entered by the user (e.g., "What's the latest technology news?").

[0658] Output: The prompt text is sent to the server.

[0659] Step 2:

[0660] The terminal transmits the prompt text from the user to the server via the Internet.

[0661] Input: The user's prompt.

[0662] Output: The prompt is transmitted to the server via the Internet.

[0663] Step 3:

[0664] The server receives the prompt and logs it.

[0665] Input: The prompt text received over the Internet.

[0666] Output: The prompt statement logged.

[0667] Step 4:

[0668] The server passes the prompt sentence to a natural language processing (NLP) algorithm to identify relevant categories and brands.

[0669] Input: The user's prompt.

[0670] Data processing: NLP algorithms analyze the prompt and extract key keywords (category and brand) from the text.

[0671] Output: Identified categories and brands (e.g., "Technology," "News," and "Famous Technology Websites").

[0672] Step 5:

[0673] The server passes the identified category and brand information to a generative AI model to generate content.

[0674] Input: Identified category and brand.

[0675] Data calculation: A generative AI model (e.g., "gpt-3.5-turbo") generates appropriate content based on the specified category and brand.

[0676] Output: The generated content (e.g., an article about the latest technology news).

[0677] Step 6:

[0678] The server transmits the generated content to the user's terminal.

[0679] Input: Generated content.

[0680] Output: The generated content that is sent to the user's device.

[0681] Step 7:

[0682] The terminal receives the generated content and displays it to the user.

[0683] Input: Generated content sent from the server.

[0684] Output: The generated content that is displayed on the device screen.

[0685] Step 8:

[0686] Users view the provided content and take actions such as "like," "share," or "click."

[0687] Input: The content displayed on the device.

[0688] Output: User action (e.g. "like", "share", "click").

[0689] Step 9:

[0690] The terminal records the user's actions and sends them as feedback to the server.

[0691] Input: User action.

[0692] Output: Feedback data sent to the server.

[0693] Step 10:

[0694] The server analyzes the received feedback and uses it to improve the performance of the generative AI model.

[0695] Input: User feedback data.

[0696] Data processing: Analyze feedback data, evaluate the performance of generative AI models, and retrain the models as needed.

[0697] Output: An improved generative AI model.

[0698] 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.

[0699] The present invention is characterized in that the system receives prompts from a user, identifies related categories and brands, and generates content including them, and further recognizes the user's emotions using an emotion engine and reflects them in the content generation. Specific embodiments are described below.

[0700] Program processing

[0701] The system identifies relevant categories and brands based on user prompts and uses an emotion engine to analyze the user's emotions at the time of the prompt. The generative AI then generates content based on the category, brand, and user emotion information. The generated content is provided to the user, and user feedback is collected. This feedback is analyzed and used to improve the accuracy of the generative AI.

[0702] Specific examples

[0703] 1. A user types, "Tell me how to relax and relieve stress."

[0704] The user enters the prompt into the input field and clicks the submit button.

[0705] 2. The device sends this prompt to the server.

[0706] The prompt is sent over the Internet to a server, which confirms receipt.

[0707] 3. The server receives the prompt.

[0708] Receive and log prompts.

[0709] 4. The server passes the prompt to a natural language processing (NLP) algorithm to identify the category and brand.

[0710] Example: Parse the prompt "What relaxation techniques can I use to relieve stress?" to identify the categories "relaxation" and "stress" and the brands "wellness center" and "relaxation products."

[0711] 5. The server has the emotion engine analyze the prompt and identify the user's emotion.

[0712] Example: The emotion engine identifies "stress" as the emotion from the user's prompt.

[0713] 6. The server passes the identified category, brand, and user sentiment information to the generation AI.

[0714] Example: The categories "relaxation" and "stress relief," the brands "wellness center" and "relaxation goods," and the user emotion "stress" are input into the generation AI.

[0715] 7. Generative AI in the server creates text content based on category, brand, and user sentiment information. Advertisements are inserted into this content in a natural way.

[0716] Example: A generation AI generates the following sentence:

[0717] We recommend yoga classes at wellness centers as a relaxation method to relieve stress. Popular aroma diffusers are also effective as relaxation tools. By utilizing these, you can ease the stress of everyday life.

[0718] 8. The server sends the generated content to the device.

[0719] Example: Deliver the generated text to the user's device.

[0720] 9. The device receives the content and displays it to the user.

[0721] Example: Displaying text generated on a web page or within an app to the user.

[0722] 10. The user views the content and takes action, such as clicking a link or scrolling.

[0723] 11. The device records the user's actions and sends feedback to the server.

[0724] Example: Sending details of clicked links and actions to the server as logs.

[0725] 12. The server receives the feedback and performs data analysis, which helps improve the performance of the generative AI.

[0726] This embodiment enables the generation of personalized content that takes into account the emotional state of the user, thereby achieving higher user satisfaction. Furthermore, by reflecting the analysis results of the emotion engine in the content generation, the user experience can be further improved.

[0727] The processing flow will be explained below.

[0728] Step 1:

[0729] The user types a question or request into the input field, which becomes the prompt.

[0730] Step 2:

[0731] The device sends the prompt to the server, which then transmits it over the Internet.

[0732] Step 3:

[0733] The server receives the prompt. At this stage, it logs the receipt of the prompt.

[0734] Step 4:

[0735] The server passes the prompt to a natural language processing (NLP) algorithm, which parses the prompt and extracts key keywords and categories.

[0736] Step 5:

[0737] The server identifies relevant brands based on the extracted keywords and categories, searching an internal database.

[0738] Step 6:

[0739] The server passes the prompt to the emotion engine, which analyzes the user's emotion from the words and phrases in the prompt.

[0740] Step 7:

[0741] The server receives the analysis results of the emotion engine and identifies the user's emotion. For example, it recognizes that the user is in a stressful state based on the keyword "stress" in the prompt.

[0742] Step 8:

[0743] The server passes the identified category, brand, and user sentiment information to the generation AI, which then generates content based on this input data.

[0744] Step 9:

[0745] The server-based generative AI creates text content based on category, brand, and user sentiment information, and advertisements are inserted into this content in a natural way.

[0746] Step 10:

[0747] The server then transmits the generated content to the terminal, which is also transmitted via the Internet.

[0748] Step 11:

[0749] The device receives the content and displays it to the user, such as on a web page or within an application.

[0750] Step 12:

[0751] The user views the content and takes actions such as clicking links and scrolling.

[0752] Step 13:

[0753] The device records user actions, collecting information such as which links are clicked and where the user scrolls.

[0754] Step 14:

[0755] The device sends the recorded feedback to a server, and the feedback data is transmitted over the Internet.

[0756] Step 15:

[0757] The server receives the feedback and performs data analysis, which is used to improve the performance of the generative AI.

[0758] Step 16:

[0759] The server feeds back the analysis results to the generation AI and uses them to generate new content, thereby continuously improving the accuracy and effectiveness of the entire system.

[0760] Example 2

[0761] 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."

[0762] Conventional content generation systems have difficulty generating personalized content that takes user emotions into account, making it difficult to improve user satisfaction. Furthermore, there was a lack of a mechanism to effectively collect and analyze user feedback on the generated content, limiting improvements to content quality.

[0763] 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.

[0764] In this invention, the server includes means for receiving a prompt from a user, means for identifying a category and a brand from the prompt, means for analyzing emotions from the prompt, means for generating content based on the category, brand, and emotion information, means for providing the generated content to the user, means for collecting user feedback, and means for analyzing the feedback and improving content generation performance. This enables the generation of personalized content that corresponds to the user's emotional state, thereby improving user satisfaction. Furthermore, by analyzing the feedback and reflecting it in the next generation, the quality of the generated content can be continuously improved.

[0765] A "prompt" is a question or request that a user enters into a system.

[0766] "Category" refers to a classification that indicates an area related to a particular theme or topic.

[0767] "Brand" refers to the name or identification used to identify a particular product or service.

[0768] "Emotion" refers to the psychological state of the user when entering the prompt.

[0769] "Content" refers to a collection of information, text, images, videos, etc., provided to users.

[0770] "Feedback" refers to information that indicates the user's reaction and behavior to the generated content.

[0771] "Natural language processing algorithms" refer to computer programs that analyze user prompts and identify relevant categories, brands, and sentiments.

[0772] "Generative AI" refers to artificial intelligence technology that generates new content based on input data.

[0773] "Database" refers to a data management system for storing prompts, generated content, feedback information, etc.

[0774] "Server" refers to a central computer system that manages the entire system and processes requests from users.

[0775] The present invention is a system that receives prompts from users, identifies relevant categories and brands, and generates content based on them. Furthermore, the system aims to increase user satisfaction by using an emotion engine to recognize the user's emotions and reflecting that emotion information in the content generation.

[0776] The system includes the following major components:

[0777] 1. User Interface

[0778] 2. Server

[0779] 3. Natural Language Processing Algorithms

[0780] 4. Emotion Engine

[0781] 5. Generation AI

[0782] 6. Database

[0783] 1. User Interface

[0784] A user accesses the system using a terminal connected to the Internet (e.g., a PC, a smartphone, a tablet, etc.). The user interface has an input field where the user can enter a prompt.

[0785] 2. Server

[0786] The server is the central processing unit of the system, receiving prompts from users and performing various analyses and generation. The server is also connected to a database that manages prompts, generated content, and feedback information.

[0787] 3. Natural Language Processing Algorithms

[0788] The server then passes the received prompts to a natural language processing algorithm to identify categories and brands, which analyzes the text data and extracts meaning and relationships.

[0789] 4. Emotion Engine

[0790] The server analyzes the user's emotion in the prompt using an emotion engine, which works in conjunction with natural language processing to analyze emotion keywords and context in the sentence to identify the user's mental state.

[0791] 5. Generation AI

[0792] Generative AI generates content based on identified categories, brands, and user sentiment information. This generative AI is a model that uses deep learning to create natural-looking text.

[0793] 6. Database

[0794] The database is connected to the server and is a system that stores and manages prompts, generated content, and user feedback data, allowing the feedback data to be analyzed and used to improve the generative AI.

[0795] As a specific example, when a user types "Tell me some relaxation techniques to relieve stress" and clicks the send button, the device sends this prompt to the server. The server receives the prompt and passes it to a natural language processing algorithm for analysis, identifying the categories "relaxation" and "stress relief" and the brands "wellness center" and "relaxation products." At the same time, the emotion engine analyzes the user's emotions and identifies "stress." Based on the identified information, the generation AI generates text content introducing relaxation techniques related to "yoga classes at wellness centers" and "aromatherapy diffusers." The server then sends this content to the device and displays it to the user. The system is continuously improved as users view the generated content and provide feedback.

[0796] This invention enables the generation of personalized content that takes into account the user's emotional state, improving the user experience. Furthermore, by utilizing user feedback to improve the accuracy of the generation AI, further quality improvements can be expected.

[0797] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0798] Step 1:

[0799] The user enters and submits the prompt.

[0800] Input: A user-written prompt in natural language (e.g., "Tell me some relaxation techniques to relieve stress")

[0801] Output: Send button press signal to terminal

[0802] Specific operation: The user enters a prompt into the input field of the terminal and clicks the send button, which sends the prompt to the server via the terminal's send function.

[0803] Step 2:

[0804] The terminal sends a prompt to the server.

[0805] Input: Prompt from user

[0806] Output: The prompt reaches the server

[0807] What it does: The device sends the prompt over the internet to a server, encrypting the data using a security protocol such as SSL.

[0808] Step 3:

[0809] The server receives the prompt and logs it.

[0810] Input: Prompt sent from the terminal

[0811] Output: Prompt log entry

[0812] Specific operation: The server receives the prompt and records its contents in a log file. The log includes the time of receipt and the prompt contents.

[0813] Step 4:

[0814] The server passes the prompt to a natural language processing (NLP) algorithm to parse it and identify the category and brand.

[0815] Input: Prompt (e.g., "What relaxation techniques can I use to relieve stress?")

[0816] Output: Identified categories and brands (e.g., categories "relaxation" and "stress relief" and brands "wellness center" and "relaxation products")

[0817] What happens: The server feeds the prompt into an NLP algorithm for semantic analysis, which identifies relevant categories and brands.

[0818] Step 5:

[0819] The server analyzes the prompt with an emotion engine to identify the user's emotion.

[0820] Input: prompt

[0821] Output: Identified user emotion (e.g. "stressed")

[0822] Specific operation: The server uses the emotion engine to analyze the emotion keywords and contextual information in the prompt to identify the user's emotional state.

[0823] Step 6:

[0824] The server passes the identified category, brand, and user sentiment information to the generation AI.

[0825] Input: Category, brand, and sentiment information

[0826] Output: Input data to the generative AI

[0827] Specific operation: The server formats the identified information to be input into the generative AI model and sends it to the generative AI.

[0828] Step 7:

[0829] Generative AI generates text content based on category, brand, and user sentiment information.

[0830] Input: Category, brand, and emotion information (e.g., category "relaxation" and "stress relief", brand "wellness center" and "relaxation goods", emotion "stress")

[0831] Output: Generated text content (e.g., "I recommend yoga classes at the wellness center as a relaxing way to relieve stress.")

[0832] How it works: Generative AI generates text content in a natural way based on input data, with relevant ads naturally inserted.

[0833] Step 8:

[0834] The server transmits the generated content to the terminal.

[0835] Input: Generated text content

[0836] Output: Content sent to the device

[0837] Specific operation: The server formats the generated content appropriately and sends the data to the device.

[0838] Step 9:

[0839] The terminal receives the content and displays it to the user.

[0840] Input: Content sent from the server

[0841] Output: Content displayed on the user's screen

[0842] Specific operation: The device analyzes the data it receives and displays it on the web page or app user interface.

[0843] Step 10:

[0844] The user views the content and takes actions such as clicking links and scrolling.

[0845] Input: Displayed content

[0846] Output: User action data (e.g., link click, scroll)

[0847] Specific Action: The user browses the generated content and takes an action such as clicking on a link that interests them.

[0848] Step 11:

[0849] The device records the user's actions and sends feedback to the server.

[0850] Input: User action data

[0851] Output: Feedback data sent to the server

[0852] Specific operation: The device logs user behavior data (e.g., click history, viewing time) and sends it to the server.

[0853] Step 12:

[0854] The server receives the feedback and performs data analysis, which is used to improve the performance of the generation AI.

[0855] Input: Feedback data

[0856] Output: Analysis results and improved generative AI

[0857] What it does: The server analyzes the feedback data and uses the results to modify the AI ​​generation algorithm, which is reflected in the next content generation and improves its accuracy.

[0858] (Application example 2)

[0859] 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."

[0860] The problem to be solved by the present invention is to provide more personalized content in response to user input, and to improve the user experience by recommending related products and services taking into account the user's emotions.

[0861] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a prompt from a user, means for identifying a category and a brand from the prompt, means for analyzing the user's emotions from the prompt, means for generating content based on the category, brand, and user emotions, means for providing the generated content to the user, means for collecting user feedback, and means for analyzing the feedback and improving generation performance. This makes it possible to provide personalized content that takes the user's emotional state into consideration and recommend optimal products and services.

[0862] A "means for receiving prompts from a user" is a device or program for receiving commands, such as text or voice, entered by a user.

[0863] "Category and brand identification means" refers to technology that includes natural language processing algorithms for identifying relevant product categories and brands from the received prompts.

[0864] The "means for analyzing user emotions" is an emotion engine or analysis algorithm for analyzing the user's current emotional state from the user's prompts.

[0865] The "content generation means" is a generative AI model for creating information such as text and images based on identified categories, brands, and user sentiment.

[0866] The "means for providing to the user" refers to an interface or communication means for displaying or transmitting the generated content to the user.

[0867] A "means for collecting user feedback" is a tool or system for recording reactions and actions taken by users in response to generated content.

[0868] "Means for analyzing feedback and improving generative performance" refers to data analysis techniques that analyze collected feedback and improve the accuracy and efficiency of generative AI models.

[0869] A "product recommendation means" is a system for selecting and recommending appropriate products and services based on identified categories, brands, and user sentiment.

[0870] This invention is a system that generates personalized content by identifying appropriate categories and brands based on prompts from users and analyzing user sentiment. The system can be accessed from devices such as smartphones, tablets, and PCs, and the entire process is performed by a server via the Internet.

[0871] First, a user inputs a prompt (for example, "Tell me about a product you like to use when you're tired") using a terminal. This prompt is sent to a server via the Internet.

[0872] The server then runs the prompt through a natural language processing algorithm (e.g., the TextBlob library) to identify categories and brands. For example, the prompt "Tell me what products you like to use when you're tired" might identify categories like "relaxation products" and "wellness products."

[0873] An emotion engine is then used to analyze the user's emotion (e.g., "fatigue"). This emotion information is passed to a generative AI model, which generates personalized content based on the identified category and brand. The generated content includes recommended products and services. For example, based on the emotion "fatigue," products such as "aroma diffusers" and "massage pillows" are recommended.

[0874] The server sends the generated content to the terminal, where the user can view the content. The terminal also records the actions the user takes while viewing the content (for example, clicking links or scrolling), and sends the records back to the server.

[0875] Finally, the server analyzes the collected feedback to improve the performance of the generative AI model, which will enable more accurate content generation in the future.

[0876] For example, if a user inputs the prompt "I've been feeling stressed lately, please tell me about some products that will help me relax," the emotion engine will determine the emotion "stress," and the generative AI model will generate content that recommends products such as "aroma diffusers" and "relaxation cushions." This content will be displayed on the user's device, improving the user experience.

[0877] As described above, the present invention generates personalized content by taking into consideration not only the category and brand but also the user's emotions, thereby enabling more effective product and service recommendations.

[0878] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0879] Step 1:

[0880] The user uses the terminal to enter and send a prompt.

[0881] Input: Prompt sentence (e.g., "Tell me what products you like to use when you're tired.")

[0882] Output: The prompt is sent to the server.

[0883] Step 2:

[0884] The server passes the received prompts to a natural language processing algorithm to identify the category and brand.

[0885] Input: The prompt text sent by the user

[0886] Data processing: Parsing prompts using natural language processing algorithms (e.g., TextBlob library)

[0887] Output: Identified category (e.g., "Relaxation Products") and brand (e.g., "Wellness Products")

[0888] Step 3:

[0889] The server uses an emotion engine to analyze the user's emotion from the prompt sentence.

[0890] Input: The prompt text sent by the user

[0891] Data Computation: Identify emotional states (e.g., "fatigue") from prompts using an emotion engine

[0892] Output: User's emotional state (e.g., "fatigue")

[0893] Step 4:

[0894] The server generates content using a generative AI model based on identified categories, brands, and user sentiment.

[0895] Input: Category (e.g., "Relaxation Products"), Brand (e.g., "Wellness Products"), User Sentiment (e.g., "Fatigue")

[0896] Data computation: Generative AI models are used to generate content based on category, brand, and user sentiment (e.g., recommendations for "aroma diffusers" or "massage pillows").

[0897] Output: Generated content (e.g., "When you're tired, we recommend using an aroma diffuser!")

[0898] Step 5:

[0899] The server transmits the generated content to the terminal.

[0900] Input: Generated content

[0901] Output: Content is sent to the device

[0902] Step 6:

[0903] The user views the content on the device.

[0904] Input: Content sent from the server

[0905] Output: The content is displayed on the device screen.

[0906] Step 7:

[0907] The terminal records the user's feedback and sends it to the server.

[0908] Input: User actions (e.g., clicking a link, scrolling)

[0909] Data processing: Recording user actions and compiling them as feedback data

[0910] Output: Feedback data is sent to the server

[0911] Step 8:

[0912] The server analyzes the received feedback data and improves the performance of the generative AI model.

[0913] Input: Feedback data

[0914] Data computation: Analyzing feedback data using analytical algorithms to identify areas for improvement in the generative AI model

[0915] Output: Update and improve the accuracy of the generative AI model

[0916] Through the above steps, the system can generate personalized content according to the user's emotional state and improve the user experience.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] [Third embodiment]

[0921] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0922] 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.

[0923] 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).

[0924] 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.

[0925] 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.

[0926] 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).

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] 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."

[0933] The present invention is a system that receives prompts from a user, identifies relevant categories and brands, and generates content that includes them, and is embodied in the following manner.

[0934] Program processing

[0935] The system operates through the following steps: Based on prompts from the user, a natural language processing algorithm is used to identify relevant categories and brands, and the generation AI generates content based on this information. The generated content is provided to the user, and user feedback is collected. This feedback is analyzed and used to improve the accuracy of the generation AI.

[0936] Specific examples

[0937] 1. User types, "Recommendations for pet toys."

[0938] The user enters the prompt into the input field and clicks the submit button.

[0939] 2. The device sends this prompt to the server.

[0940] A prompt is sent over the Internet to a server, which confirms receipt.

[0941] 3. The server receives the prompt.

[0942] Receive and log prompts.

[0943] 4. The server passes the prompt to a natural language processing (NLP) algorithm to identify the category and brand.

[0944] Example: Parse the prompt "What are your pet toy recommendations?" to identify the categories "Pets" and "Toys" and the brands "Pet Shops" and "Popular Brands."

[0945] 5. The server passes the extracted category and brand information to the generation AI.

[0946] Example: Input the categories "Pets" and "Toys" and the brands "Pet Shop" and "Popular Brands" into the generation AI.

[0947] 6. The generation AI on the server generates content based on category and brand information.

[0948] Example: A generation AI generates the following sentence:

[0949] Our recommended pet toys include the latest collections from pet stores, which are durable and safe, supporting your pet's health. Popular brands of interactive toys are also perfect for making playtime fun with your pet.

[0950] 7. The server sends the generated content to the device.

[0951] Example: Deliver the generated text to the user's device.

[0952] 8. The device receives the content and displays it to the user.

[0953] Example: Displaying text generated on a web page or within an app to the user.

[0954] 9. The user views the content and takes an action, such as clicking.

[0955] Example: User clicks on the "Pet Shop" link.

[0956] 10. The device records the user's actions and sends feedback to the server.

[0957] Example: Sending details of clicked links and actions to the server as logs.

[0958] 11. The server receives the feedback and analyzes the data to improve the performance of the generative AI.

[0959] Example: Analyze data such as click-through rate and time to complete reading and use it to generate new content.

[0960] One of the features of this invention is that it can provide a positive experience to users by naturally inserting advertisements according to their interests. In addition, by improving the accuracy of the generation AI based on user feedback, the effectiveness of the entire system can be continuously improved.

[0961] The processing flow will be explained below.

[0962] Step 1:

[0963] The user types a question or request into the input field, which becomes the prompt.

[0964] Step 2:

[0965] The device sends the prompt to the server, which then transmits it over the Internet.

[0966] Step 3:

[0967] The server receives the prompt. At this stage, it logs the receipt of the prompt.

[0968] Step 4:

[0969] The server passes the prompt to a natural language processing (NLP) algorithm, which parses the prompt and extracts key keywords and categories.

[0970] Step 5:

[0971] The server identifies relevant brands based on the extracted keywords and categories, searching an internal database.

[0972] Step 6:

[0973] The server passes the identified category and brand information to the generation AI, which then generates content based on this input data.

[0974] Step 7:

[0975] The server-based AI generates text content based on category and brand information, and advertisements are inserted into this content in a natural way.

[0976] Step 8:

[0977] The server then transmits the generated content to the terminal, which is also transmitted via the Internet.

[0978] Step 9:

[0979] The device receives the content and displays it to the user, such as on a web page or within an application.

[0980] Step 10:

[0981] The user views the content and takes actions such as clicking links and scrolling.

[0982] Step 11:

[0983] The device records user actions, collecting information such as which links are clicked and where the user scrolls.

[0984] Step 12:

[0985] The device sends the recorded feedback to a server, and the feedback data is transmitted over the Internet.

[0986] Step 13:

[0987] The server receives the feedback and performs data analysis, which is used to improve the performance of the generative AI.

[0988] Step 14:

[0989] The server feeds back the analysis results to the generation AI and uses them to generate new content, thereby continuously improving the accuracy and effectiveness of the entire system.

[0990] Example 1

[0991] 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."

[0992] Conventional content generation systems lack the accuracy and efficiency to quickly and accurately respond to user needs. In particular, they lack the ability to identify categories and brands based on user prompts and generate content accordingly. Furthermore, they lack a feedback system to continuously improve the quality of generated content, limiting the improvement of the user experience. Furthermore, they also have limited means to naturally insert advertisements that match the user's interests.

[0993] 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.

[0994] In this invention, the server includes a means for receiving prompts from a user, a means for passing the prompts to a natural language processing algorithm and extracting related information, a means for identifying a category and a brand, a means for generating content including the category and the brand, a means for providing the generated content to the user, a means for collecting user feedback, a means for analyzing the feedback and improving generation performance, a means for transmitting the generated content to the user's device, and a means for recording user actions and transmitting the recorded actions to the server as feedback. This enables highly accurate content generation based on user prompts and allows the performance of the generation AI model to be continuously improved based on the feedback. Furthermore, advertisements that match the user's interests can be inserted naturally, improving the user experience.

[0995] A "user" is an individual or organization that uses a system or application.

[0996] A "prompt" is specific text information such as a question or request that a user enters.

[0997] A "category" is a classification of general themes or topics extracted from the prompt.

[0998] A "brand" is an identifier such as a trademark or company name associated with a particular category.

[0999] "Content" refers to text and information generated based on category and brand information.

[1000] A "server" is a computer system that provides data processing and storage over a network.

[1001] A "terminal" is a device that a user uses to communicate with a server, such as a PC or smartphone.

[1002] A "natural language processing algorithm" is a computational method for analyzing text data and understanding the meaning and structure of natural language.

[1003] "Generative AI" is an artificial intelligence model that generates new content based on specified input data.

[1004] "Feedback" refers to data collected based on user actions and reactions.

[1005] "Performance" refers to the effectiveness or efficiency of a system or algorithm.

[1006] The present invention is a system that receives prompts from users, identifies relevant categories and brands, and generates and provides content that includes them. The operation of this system mainly involves a server, a user's device, and a generative AI model.

[1007] Hardware and software used

[1008] Server: The server is the main component that receives, analyzes, processes, stores, and transmits data. The server must have a powerful CPU, sufficient memory, and disk space; for example, it can be an EC2 instance from Amazon Web Services (AWS).

[1009] User device: The device on which the user enters prompts and receives content. Devices include PCs, smartphones, tablets, etc.

[1010] Software: A natural language processing algorithm is used to analyze the prompts, and OpenAI's GPT-3 is used as the generative AI model. This enables advanced text generation. Python's SpaCy and NLTK can be used as analysis libraries.

[1011] Specific examples of processing

[1012] Specific prompt examples

[1013] The user types, "What are your pet toy recommendations?" This prompt is provided as content through the following processing steps:

[1014] SUMMARY STEPS

[1015] 1. Receiving the prompt: The prompt entered by the user is sent from the device to the server, along with metadata such as the user ID and a timestamp.

[1016] 2. Parse the prompt: The server passes the prompt to a natural language processing algorithm to identify the category and brand. For example, the prompt "What are your pet toy recommendations?" identifies the categories "Pets" and "Toys" and the brands "Pet Shop" and "Popular Brands."

[1017] 3. Content generation: Based on the identified category and brand information, generative AI creates content. Specifically, the following content is generated:

[1018] For example: "Our recommended pet toys include the latest collections from pet stores. These durable, safe toys support your pet's health. We also offer interactive toys from popular brands, perfect for making playtime fun with your pet."

[1019] 4. Content Delivery: The generated content is sent from the server to the user's device, where it is displayed in the appropriate format.

[1020] 5. Feedback collection: Users browse content and take actions such as clicks. These actions are recorded by the device and sent to the server.

[1021] 6. Feedback Analysis: The server analyzes the collected feedback and uses it to improve the performance of the generation AI, which will improve the accuracy of content generation next time.

[1022] The present invention can continuously improve the accuracy of the AI ​​generation based on user feedback. Furthermore, it can improve the user experience by inserting advertisements naturally. In this way, the system can respond to user needs quickly and accurately.

[1023] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1024] Program processing steps

[1025] Step 1:

[1026] The user enters the prompt.

[1027] What happens: A user enters a question or request into a field in a web browser or mobile app and clicks the submit button.

[1028] Input: User prompt (e.g., "What are your pet toy recommendations?")

[1029] Output: Signals that a prompt is sent to the user's terminal.

[1030] Step 2:

[1031] The terminal sends a prompt to the server.

[1032] What happens: After the user clicks the submit button, the user's device sends the prompt they entered to the server as an HTTPS request, along with metadata such as the user ID and a timestamp.

[1033] Input: User prompts and metadata

[1034] Output: HTTP request sent to the server

[1035] Step 3:

[1036] The server receives the prompt.

[1037] What it does: The server analyzes the received request and records the prompt content in a log, along with other information such as the time of receipt and the source IP address.

[1038] Input: HTTP request sent from the terminal

[1039] Output: Logged prompts and metadata

[1040] Step 4:

[1041] The server passes the prompt to a natural language processing (NLP) algorithm.

[1042] What happens: The server passes the prompt to an NLP module to identify relevant categories and brands, parsing it using, for example, Python's SpaCy or NLTK.

[1043] Input: Prompt (e.g., "What are your pet toy recommendations?")

[1044] Output: Identified categories (e.g., "pets" or "toys") and brands (e.g., "pet shops" or "popular brands")

[1045] Step 5:

[1046] The server passes category and brand information to the generation AI.

[1047] Specific operation: The server passes the identified category and brand information to the generative AI. For example, using OpenAI's GPT-3 as the generative AI model, it sends a request to the API endpoint containing the necessary parameters.

[1048] Input: Identified category and brand information

[1049] Output: Parameters input to the generation AI

[1050] Step 6:

[1051] The generation AI on the server generates the content.

[1052] Specific operation: The AI ​​generates content based on the received category and brand information. For example, it might generate a sentence like, "Recommended pet toys include the latest collection of toys from pet shops. Durability and safety are guaranteed, supporting your pet's health. Popular brands of interactive toys are also perfect for making playtime with your pet more enjoyable."

[1053] Input: Category and brand information

[1054] Output: Generated content

[1055] Step 7:

[1056] The server transmits the generated content to the terminal.

[1057] Specific operation: The server sends the generated content to the user's device as an HTTP response. The content is organized in HTML or JSON format and sent in a format appropriate for the user's environment.

[1058] Input: Generated content

[1059] Output: The HTTP response sent to the user's device

[1060] Step 8:

[1061] The terminal displays the content to the user.

[1062] What it does: The user's device analyzes the received content and displays it in the web page or app interface. For example, a web browser might insert generated text into specific elements on the page and apply styling to make it more user-friendly.

[1063] Input: Content received from the server

[1064] Output: The content displayed to the user

[1065] Step 9:

[1066] Users view content and take action.

[1067] Specific behavior: The user reads the displayed content. If they find it interesting, they take an action such as clicking a link. For example, they click the "Pet Shop" link to go to the product page.

[1068] Input: Displayed content

[1069] Output: User action (e.g., link click)

[1070] Step 10:

[1071] The device records the user's actions and sends feedback to the server.

[1072] What it does: When a user action occurs, the device records the event and sends feedback to the server as an HTTP request, including the link clicked and a timestamp.

[1073] Input: User action data

[1074] Output: Feedback sent to the server

[1075] Step 11:

[1076] The server receives and analyzes the feedback.

[1077] How it works: The server logs the received feedback data and passes it to an analysis program. The analysis results are used to train the generative AI model, helping to improve the accuracy of future content generation.

[1078] Input: Feedback data sent from the device

[1079] Output: Parsed feedback and model training data

[1080] Through these steps, the system is able to generate highly accurate content based on prompts from the user and use feedback to improve performance.

[1081] (Application example 1)

[1082] 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."

[1083] In recent years, the diversification of information and rapid changes in user needs have led to a demand for providing appropriate information to individual users. However, conventional systems have been unable to efficiently provide personalized content based on users' interests and preferences. In particular, they lack mechanisms for generating content in real time in response to user prompts and for improving the accuracy of generated content by incorporating user feedback. This not only degrades the user experience, but also poses challenges for companies, limiting their marketing effectiveness.

[1084] 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.

[1085] In this invention, the server includes means for receiving instructions from a user, means for identifying a category and a brand from the instructions, means for generating information using a generative AI model based on the specified category and brand, means for displaying the generated information on a mobile device or a web application, means for collecting user responses, and means for analyzing the responses and improving generation performance. This makes it possible to provide personalized content in real time based on user prompts and improve the accuracy of the generative AI by reflecting user feedback.

[1086] "User instructions" refers to text or voice input by a user requesting specific information.

[1087] A "category" refers to a subject or area of ​​interest identified based on a user's instructions.

[1088] "Brand" refers to the source and recognized name of a particular product or service.

[1089] "Information" refers to all content generated by a generative AI model and provided to users.

[1090] "Generative AI Model" refers to an artificial intelligence algorithm that generates content based on a specified category and brand.

[1091] "Mobile Device or Web Application" refers to the computing device or software used to display generated information to a user.

[1092] "User response" refers to the actions and feedback that users take in response to the generated information, such as "likes," "shares," and "clicks."

[1093] "Generative performance" refers to the efficiency and quality of how accurately a generative AI model can generate content that meets user needs.

[1094] This invention is a system that appropriately generates and provides specific information when a user acquires that information through a mobile device or web application.

[1095] First, a user inputs a "prompt sentence" in a specific format into a mobile device or web application, expressing their desire to obtain specific information. For example, "Tell me the latest technology news." This prompt sentence is sent to the system's server, which then receives it.

[1096] The server then parses the prompt and uses natural language processing algorithms to identify relevant categories and brands within the prompt, such as categories like "technology" or "news," or the brand "famous technology websites."

[1097] Based on this identified category and brand information, the server uses a generative AI model, such as OpenAI's "gpt-3.5-turbo," to generate information tailored to the user's interests. When this model generates information, it tailors it to the context of the specified category or brand.

[1098] The generated information is then sent back to the mobile terminal or web application and displayed to the user. It is important that the generated information meets the user's requirements.

[1099] When a user views this information and takes an action, such as "liking," "sharing," or "clicking," their reaction is fed back to the system. This feedback information is sent to the server, which analyzes it and uses it to improve the performance of the generative AI model. At this time, the generative AI model is adjusted based on user feedback, enabling it to generate information with greater accuracy.

[1100] To further improve the system, the server needs to periodically train the model and evaluate its performance based on collected user response data. This will enable the continuous provision of high-quality generated information tailored to user needs. It's a fine line. This is an important feature of this system.

[1101] In this way, users can obtain highly accurate information tailored to their interests and needs in real time. To implement this system, an internet-enabled mobile device or web application and a high-performance server are required. Specifically, a server with sufficient computing power to run natural language processing algorithms and API access to the generative AI model "gpt-3.5-turbo" are required.

[1102] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1103] Step 1:

[1104] On a mobile device or web application, a user enters a prompt sentence to obtain specific information and clicks a submit button.

[1105] Input: The prompt text entered by the user (e.g., "What's the latest technology news?").

[1106] Output: The prompt text is sent to the server.

[1107] Step 2:

[1108] The terminal transmits the prompt text from the user to the server via the Internet.

[1109] Input: The user's prompt.

[1110] Output: The prompt is transmitted to the server via the Internet.

[1111] Step 3:

[1112] The server receives the prompt and logs it.

[1113] Input: The prompt text received over the Internet.

[1114] Output: The prompt statement logged.

[1115] Step 4:

[1116] The server passes the prompt sentence to a natural language processing (NLP) algorithm to identify relevant categories and brands.

[1117] Input: The user's prompt.

[1118] Data processing: NLP algorithms analyze the prompt and extract important keywords (categories and brands) from the text.

[1119] Output: Identified categories and brands (e.g., "Technology," "News," and "Famous Technology Websites").

[1120] Step 5:

[1121] The server passes the identified category and brand information to a generative AI model to generate content.

[1122] Input: Identified category and brand.

[1123] Data calculation: A generative AI model (e.g., "gpt-3.5-turbo") generates appropriate content based on the specified category and brand.

[1124] Output: The generated content (e.g., an article about the latest technology news).

[1125] Step 6:

[1126] The server transmits the generated content to the user's terminal.

[1127] Input: Generated content.

[1128] Output: The generated content that is sent to the user's device.

[1129] Step 7:

[1130] The terminal receives the generated content and displays it to the user.

[1131] Input: Generated content sent from the server.

[1132] Output: The generated content that is displayed on the device screen.

[1133] Step 8:

[1134] Users view the provided content and take actions such as "like," "share," or "click."

[1135] Input: The content displayed on the device.

[1136] Output: User action (e.g. "like", "share", "click").

[1137] Step 9:

[1138] The terminal records the user's actions and sends them as feedback to the server.

[1139] Input: User action.

[1140] Output: Feedback data sent to the server.

[1141] Step 10:

[1142] The server analyzes the received feedback and uses it to improve the performance of the generative AI model.

[1143] Input: User feedback data.

[1144] Data processing: Analyze feedback data, evaluate the performance of generative AI models, and retrain the models as needed.

[1145] Output: An improved generative AI model.

[1146] 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.

[1147] The present invention is characterized in that the system receives prompts from a user, identifies related categories and brands, and generates content including them, and further recognizes the user's emotions using an emotion engine and reflects them in the content generation. Specific embodiments are described below.

[1148] Program processing

[1149] The system identifies relevant categories and brands based on user prompts and uses an emotion engine to analyze the user's emotions at the time of the prompt. The generative AI then generates content based on the category, brand, and user emotion information. The generated content is provided to the user, and user feedback is collected. This feedback is analyzed and used to improve the accuracy of the generative AI.

[1150] Specific examples

[1151] 1. A user types, "Tell me how to relax and relieve stress."

[1152] The user enters the prompt into the input field and clicks the submit button.

[1153] 2. The device sends this prompt to the server.

[1154] The prompt is sent over the Internet to a server, which confirms receipt.

[1155] 3. The server receives the prompt.

[1156] Receive and log prompts.

[1157] 4. The server passes the prompt to a natural language processing (NLP) algorithm to identify the category and brand.

[1158] Example: Parse the prompt "What relaxation techniques can I use to relieve stress?" to identify the categories "relaxation" and "stress" and the brands "wellness center" and "relaxation products."

[1159] 5. The server has the emotion engine analyze the prompt and identify the user's emotion.

[1160] Example: The emotion engine identifies "stress" as the emotion from the user's prompt.

[1161] 6. The server passes the identified category, brand, and user sentiment information to the generation AI.

[1162] Example: The categories "relaxation" and "stress relief," the brands "wellness center" and "relaxation goods," and the user emotion "stress" are input into the generation AI.

[1163] 7. Generative AI in the server creates text content based on category, brand, and user sentiment information. Advertisements are inserted into this content in a natural way.

[1164] Example: A generation AI generates the following sentence:

[1165] We recommend yoga classes at wellness centers as a relaxation method to relieve stress. Popular aroma diffusers are also effective as relaxation tools. By utilizing these, you can ease the stress of everyday life.

[1166] 8. The server sends the generated content to the device.

[1167] Example: Deliver the generated text to the user's device.

[1168] 9. The device receives the content and displays it to the user.

[1169] Example: Displaying text generated on a web page or within an app to the user.

[1170] 10. The user views the content and takes action, such as clicking a link or scrolling.

[1171] 11. The device records the user's actions and sends feedback to the server.

[1172] Example: Sending details of clicked links and actions to the server as logs.

[1173] 12. The server receives the feedback and performs data analysis, which helps improve the performance of the generative AI.

[1174] This embodiment enables the generation of personalized content that takes into account the emotional state of the user, thereby achieving higher user satisfaction. Furthermore, by reflecting the analysis results of the emotion engine in the content generation, the user experience can be further improved.

[1175] The processing flow will be explained below.

[1176] Step 1:

[1177] The user types a question or request into the input field, which becomes the prompt.

[1178] Step 2:

[1179] The device sends the prompt to the server, which then transmits it over the Internet.

[1180] Step 3:

[1181] The server receives the prompt. At this stage, it logs the receipt of the prompt.

[1182] Step 4:

[1183] The server passes the prompt to a natural language processing (NLP) algorithm, which parses the prompt and extracts key keywords and categories.

[1184] Step 5:

[1185] The server identifies relevant brands based on the extracted keywords and categories, searching an internal database.

[1186] Step 6:

[1187] The server passes the prompt to the emotion engine, which analyzes the user's emotion from the words and phrases in the prompt.

[1188] Step 7:

[1189] The server receives the analysis results of the emotion engine and identifies the user's emotion. For example, it recognizes that the user is in a stressful state based on the keyword "stress" in the prompt.

[1190] Step 8:

[1191] The server passes the identified category, brand, and user sentiment information to the generation AI, which then generates content based on this input data.

[1192] Step 9:

[1193] The server-based generative AI creates text content based on category, brand, and user sentiment information, and advertisements are inserted into this content in a natural way.

[1194] Step 10:

[1195] The server then transmits the generated content to the terminal, which is also transmitted via the Internet.

[1196] Step 11:

[1197] The device receives the content and displays it to the user, such as on a web page or within an application.

[1198] Step 12:

[1199] The user views the content and takes actions such as clicking links and scrolling.

[1200] Step 13:

[1201] The device records user actions, collecting information such as which links are clicked and where the user scrolls.

[1202] Step 14:

[1203] The device sends the recorded feedback to a server, and the feedback data is transmitted over the Internet.

[1204] Step 15:

[1205] The server receives the feedback and performs data analysis, which is used to improve the performance of the generative AI.

[1206] Step 16:

[1207] The server feeds back the analysis results to the generation AI and uses them to generate new content, thereby continuously improving the accuracy and effectiveness of the entire system.

[1208] Example 2

[1209] 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."

[1210] Conventional content generation systems have difficulty generating personalized content that takes user emotions into account, making it difficult to improve user satisfaction. Furthermore, the lack of a mechanism for effectively collecting and analyzing user feedback on generated content has limited the improvement of content quality.

[1211] 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.

[1212] In this invention, the server includes means for receiving a prompt from a user, means for identifying a category and a brand from the prompt, means for analyzing emotions from the prompt, means for generating content based on the category, brand, and emotion information, means for providing the generated content to the user, means for collecting user feedback, and means for analyzing the feedback and improving content generation performance. This enables the generation of personalized content that corresponds to the user's emotional state, thereby improving user satisfaction. Furthermore, by analyzing the feedback and reflecting it in the next generation, the quality of the generated content can be continuously improved.

[1213] A "prompt" is a question or request that a user enters into a system.

[1214] "Category" refers to a classification that indicates an area related to a particular theme or topic.

[1215] "Brand" refers to the name or identification used to identify a particular product or service.

[1216] "Emotion" refers to the psychological state of the user when entering the prompt.

[1217] "Content" refers to a collection of information, text, images, videos, etc., provided to users.

[1218] "Feedback" refers to information that indicates the user's reaction and behavior to the generated content.

[1219] "Natural language processing algorithms" refer to computer programs that analyze user prompts and identify relevant categories, brands, and sentiments.

[1220] "Generative AI" refers to artificial intelligence technology that generates new content based on input data.

[1221] "Database" refers to a data management system for storing prompts, generated content, feedback information, etc.

[1222] "Server" refers to a central computer system that manages the entire system and processes requests from users.

[1223] The present invention is a system that receives prompts from users, identifies related categories and brands, and generates content based on them. Furthermore, the system aims to increase user satisfaction by using an emotion engine to recognize the user's emotions and reflecting that emotion information in the content generation.

[1224] The system includes the following major components:

[1225] 1. User Interface

[1226] 2. Server

[1227] 3. Natural Language Processing Algorithms

[1228] 4. Emotion Engine

[1229] 5. Generation AI

[1230] 6. Database

[1231] 1. User Interface

[1232] A user accesses the system using a terminal connected to the Internet (e.g., a PC, a smartphone, a tablet, etc.). The user interface has an input field where the user can enter a prompt.

[1233] 2. Server

[1234] The server is the central processing unit of the system, receiving prompts from users and performing various analyses and generation. The server is also connected to a database that manages prompts, generated content, and feedback information.

[1235] 3. Natural Language Processing Algorithms

[1236] The server then passes the received prompts to a natural language processing algorithm to identify categories and brands, which analyzes the text data and extracts meaning and relationships.

[1237] 4. Emotion Engine

[1238] The server analyzes the user's emotion in the prompt using an emotion engine, which works in conjunction with natural language processing to analyze emotion keywords and context in the sentence to identify the user's mental state.

[1239] 5. Generation AI

[1240] Generative AI generates content based on identified categories, brands, and user sentiment information. This generative AI is a model that uses deep learning to create natural-looking text.

[1241] 6. Database

[1242] The database is connected to the server and is a system that stores and manages prompts, generated content, and user feedback data, allowing the feedback data to be analyzed and used to improve the generative AI.

[1243] As a specific example, when a user types "Tell me some relaxation techniques to relieve stress" and clicks the send button, the device sends this prompt to the server. The server receives the prompt and passes it to a natural language processing algorithm for analysis, identifying the categories "relaxation" and "stress relief" and the brands "wellness center" and "relaxation products." At the same time, the emotion engine analyzes the user's emotions and identifies "stress." Based on the identified information, the generation AI generates text content introducing relaxation techniques related to "yoga classes at wellness centers" and "aromatherapy diffusers." The server then sends this content to the device and displays it to the user. The system is continuously improved as users view the generated content and provide feedback.

[1244] This invention enables the generation of personalized content that takes into account the user's emotional state, improving the user experience. Furthermore, by utilizing user feedback to improve the accuracy of the generation AI, further quality improvements can be expected.

[1245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] The user enters and submits the prompt.

[1248] Input: A user-written prompt in natural language (e.g., "Tell me some relaxation techniques to relieve stress")

[1249] Output: Send button press signal to terminal

[1250] Specific operation: The user enters a prompt into the input field of the terminal and clicks the send button, which sends the prompt to the server via the terminal's send function.

[1251] Step 2:

[1252] The terminal sends a prompt to the server.

[1253] Input: Prompt from user

[1254] Output: The prompt reaches the server

[1255] What it does: The device sends the prompt over the internet to a server, encrypting the data using a security protocol such as SSL.

[1256] Step 3:

[1257] The server receives the prompt and logs it.

[1258] Input: Prompt sent from the terminal

[1259] Output: Prompt log entry

[1260] Specific operation: The server receives the prompt and records its contents in a log file. The log includes the time of receipt and the prompt contents.

[1261] Step 4:

[1262] The server passes the prompt to a natural language processing (NLP) algorithm to parse it and identify the category and brand.

[1263] Input: Prompt (e.g., "What relaxation techniques can I use to relieve stress?")

[1264] Output: Identified categories and brands (e.g., categories "relaxation" and "stress relief" and brands "wellness center" and "relaxation products")

[1265] What happens: The server feeds the prompt into an NLP algorithm for semantic analysis, which identifies relevant categories and brands.

[1266] Step 5:

[1267] The server analyzes the prompt with an emotion engine to identify the user's emotion.

[1268] Input: prompt

[1269] Output: Identified user emotion (e.g. "stressed")

[1270] Specific operation: The server uses the emotion engine to analyze the emotion keywords and contextual information in the prompt to identify the user's emotional state.

[1271] Step 6:

[1272] The server passes the identified category, brand, and user sentiment information to the generation AI.

[1273] Input: Category, brand, and sentiment information

[1274] Output: Input data to the generative AI

[1275] Specific operation: The server formats the identified information to be input into the generative AI model and sends it to the generative AI.

[1276] Step 7:

[1277] Generative AI generates text content based on category, brand, and user sentiment information.

[1278] Input: Category, brand, and emotion information (e.g., category "relaxation" and "stress relief", brand "wellness center" and "relaxation goods", emotion "stress")

[1279] Output: Generated text content (e.g., "I recommend yoga classes at the wellness center as a relaxing way to relieve stress.")

[1280] How it works: Generative AI generates text content in a natural way based on input data, with relevant ads naturally inserted.

[1281] Step 8:

[1282] The server transmits the generated content to the terminal.

[1283] Input: Generated text content

[1284] Output: Content sent to the device

[1285] Specific operation: The server formats the generated content appropriately and sends the data to the device.

[1286] Step 9:

[1287] The terminal receives the content and displays it to the user.

[1288] Input: Content sent from the server

[1289] Output: Content displayed on the user's screen

[1290] Specific operation: The device analyzes the data it receives and displays it on the web page or app user interface.

[1291] Step 10:

[1292] The user views the content and takes actions such as clicking links and scrolling.

[1293] Input: Displayed content

[1294] Output: User action data (e.g., link click, scroll)

[1295] Specific Action: The user browses the generated content and takes an action such as clicking on a link that interests them.

[1296] Step 11:

[1297] The device records the user's actions and sends feedback to the server.

[1298] Input: User action data

[1299] Output: Feedback data sent to the server

[1300] Specific operation: The device logs user behavior data (e.g., click history, viewing time) and sends it to the server.

[1301] Step 12:

[1302] The server receives the feedback and performs data analysis, which is used to improve the performance of the generation AI.

[1303] Input: Feedback data

[1304] Output: Analysis results and improved generative AI

[1305] What it does: The server analyzes the feedback data and uses the results to modify the AI ​​generation algorithm, which is reflected in the next content generation and improves its accuracy.

[1306] (Application example 2)

[1307] 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."

[1308] The problem to be solved by the present invention is to provide more personalized content in response to user input, and to improve the user experience by recommending related products and services taking into account the user's emotions.

[1309] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a prompt from a user, means for identifying a category and a brand from the prompt, means for analyzing the user's emotions from the prompt, means for generating content based on the category, brand, and user emotions, means for providing the generated content to the user, means for collecting user feedback, and means for analyzing the feedback and improving generation performance. This makes it possible to provide personalized content that takes the user's emotional state into consideration and recommend optimal products and services.

[1310] A "means for receiving prompts from a user" is a device or program for receiving commands, such as text or voice, entered by a user.

[1311] "Category and brand identification means" refers to technology that includes natural language processing algorithms for identifying relevant product categories and brands from the received prompts.

[1312] The "means for analyzing user emotions" is an emotion engine or analysis algorithm for analyzing the user's current emotional state from the user's prompts.

[1313] The "content generation means" is a generative AI model for creating information such as text and images based on identified categories, brands, and user sentiment.

[1314] The "means for providing to the user" refers to an interface or communication means for displaying or transmitting the generated content to the user.

[1315] A "means for collecting user feedback" is a tool or system for recording reactions and actions taken by users in response to generated content.

[1316] "Means for analyzing feedback and improving generative performance" refers to data analysis techniques that analyze collected feedback and improve the accuracy and efficiency of generative AI models.

[1317] A "product recommendation means" is a system for selecting and recommending appropriate products and services based on identified categories, brands, and user sentiment.

[1318] This invention is a system that generates personalized content by identifying appropriate categories and brands based on prompts from users and analyzing user sentiment. The system can be accessed from devices such as smartphones, tablets, and PCs, and the entire process is performed by a server via the Internet.

[1319] First, a user inputs a prompt (for example, "Tell me about a product you like to use when you're tired") using a terminal. This prompt is sent to a server via the Internet.

[1320] The server then runs the prompt through a natural language processing algorithm (e.g., the TextBlob library) to identify categories and brands. For example, the prompt "Tell me what products you like to use when you're tired" might identify categories like "relaxation products" and "wellness products."

[1321] An emotion engine is then used to analyze the user's emotion (e.g., "fatigue"). This emotion information is passed to a generative AI model, which generates personalized content based on the identified category and brand. The generated content includes recommended products and services. For example, based on the emotion "fatigue," products such as "aroma diffusers" and "massage pillows" are recommended.

[1322] The server sends the generated content to the terminal, where the user can view the content. The terminal also records the actions the user takes while viewing the content (for example, clicking links or scrolling), and sends the records back to the server.

[1323] Finally, the server analyzes the collected feedback to improve the performance of the generative AI model, which will enable more accurate content generation in the future.

[1324] For example, if a user inputs the prompt "I've been feeling stressed lately, please tell me about some products that will help me relax," the emotion engine will determine the emotion "stress," and the generative AI model will generate content that recommends products such as "aroma diffusers" and "relaxation cushions." This content will be displayed on the user's device, improving the user experience.

[1325] As described above, the present invention generates personalized content by taking into consideration not only the category and brand but also the user's emotions, thereby enabling more effective product and service recommendations.

[1326] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1327] Step 1:

[1328] The user uses the terminal to enter and send a prompt.

[1329] Input: Prompt sentence (e.g., "Tell me what products you like to use when you're tired.")

[1330] Output: The prompt is sent to the server.

[1331] Step 2:

[1332] The server passes the received prompts to a natural language processing algorithm to identify the category and brand.

[1333] Input: The prompt text sent by the user

[1334] Data processing: Parsing prompts using natural language processing algorithms (e.g., TextBlob library)

[1335] Output: Identified category (e.g., "Relaxation Products") and brand (e.g., "Wellness Products")

[1336] Step 3:

[1337] The server uses an emotion engine to analyze the user's emotion from the prompt sentence.

[1338] Input: The prompt text sent by the user

[1339] Data Computation: Identify emotional states (e.g., "fatigue") from prompts using an emotion engine

[1340] Output: User's emotional state (e.g., "fatigue")

[1341] Step 4:

[1342] The server generates content using a generative AI model based on identified categories, brands, and user sentiment.

[1343] Input: Category (e.g., "Relaxation Products"), Brand (e.g., "Wellness Products"), User Sentiment (e.g., "Fatigue")

[1344] Data computation: Generative AI models are used to generate content based on category, brand, and user sentiment (e.g., recommendations for "aroma diffusers" or "massage pillows").

[1345] Output: Generated content (e.g., "When you're tired, we recommend using an aroma diffuser!")

[1346] Step 5:

[1347] The server transmits the generated content to the terminal.

[1348] Input: Generated content

[1349] Output: Content is sent to the device

[1350] Step 6:

[1351] The user views the content on the device.

[1352] Input: Content sent from the server

[1353] Output: The content is displayed on the device screen.

[1354] Step 7:

[1355] The terminal records the user's feedback and sends it to the server.

[1356] Input: User actions (e.g., clicking a link, scrolling)

[1357] Data processing: Recording user actions and compiling them as feedback data

[1358] Output: Feedback data is sent to the server

[1359] Step 8:

[1360] The server analyzes the received feedback data and improves the performance of the generative AI model.

[1361] Input: Feedback data

[1362] Data computation: Analyzing feedback data using analytical algorithms to identify areas for improvement in the generative AI model

[1363] Output: Update and improve the accuracy of the generative AI model

[1364] Through the above steps, the system can generate personalized content according to the user's emotional state and improve the user experience.

[1365] 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.

[1366] 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.

[1367] 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.

[1368] [Fourth embodiment]

[1369] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1370] 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.

[1371] 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).

[1372] 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.

[1373] 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.

[1374] 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).

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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.

[1379] 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.

[1380] 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.

[1381] 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."

[1382] The present invention is a system that receives prompts from a user, identifies relevant categories and brands, and generates content that includes them, and is embodied in the following manner.

[1383] Program processing

[1384] The system operates through the following steps: Based on prompts from the user, a natural language processing algorithm is used to identify relevant categories and brands, and the generation AI generates content based on this information. The generated content is provided to the user, and user feedback is collected. This feedback is analyzed and used to improve the accuracy of the generation AI.

[1385] Specific examples

[1386] 1. User types, "Recommendations for pet toys."

[1387] The user enters the prompt into the input field and clicks the submit button.

[1388] 2. The device sends this prompt to the server.

[1389] A prompt is sent over the Internet to a server, which confirms receipt.

[1390] 3. The server receives the prompt.

[1391] Receive and log prompts.

[1392] 4. The server passes the prompt to a natural language processing (NLP) algorithm to identify the category and brand.

[1393] Example: Parse the prompt "What are your pet toy recommendations?" to identify the categories "Pets" and "Toys" and the brands "Pet Shops" and "Popular Brands."

[1394] 5. The server passes the extracted category and brand information to the generation AI.

[1395] Example: Input the categories "Pets" and "Toys" and the brands "Pet Shop" and "Popular Brands" into the generation AI.

[1396] 6. The generation AI on the server generates content based on category and brand information.

[1397] Example: A generation AI generates the following sentence:

[1398] Our recommended pet toys include the latest collections from pet stores, which are durable and safe, supporting your pet's health. Popular brands of interactive toys are also perfect for making playtime fun with your pet.

[1399] 7. The server sends the generated content to the device.

[1400] Example: Deliver the generated text to the user's device.

[1401] 8. The device receives the content and displays it to the user.

[1402] Example: Displaying text generated on a web page or within an app to the user.

[1403] 9. The user views the content and takes an action, such as clicking.

[1404] Example: User clicks on the "Pet Shop" link.

[1405] 10. The device records the user's actions and sends feedback to the server.

[1406] Example: Sending details of clicked links and actions to the server as logs.

[1407] 11. The server receives the feedback and analyzes the data to improve the performance of the generative AI.

[1408] Example: Analyze data such as click-through rate and time to complete reading and use it to generate new content.

[1409] One of the features of this invention is that it can provide a positive experience to users by naturally inserting advertisements according to their interests. In addition, by improving the accuracy of the generation AI based on user feedback, the effectiveness of the entire system can be continuously improved.

[1410] The processing flow will be explained below.

[1411] Step 1:

[1412] The user types a question or request into the input field, which becomes the prompt.

[1413] Step 2:

[1414] The device sends the prompt to the server, which then transmits it over the Internet.

[1415] Step 3:

[1416] The server receives the prompt. At this stage, it logs the receipt of the prompt.

[1417] Step 4:

[1418] The server passes the prompt to a natural language processing (NLP) algorithm, which parses the prompt and extracts key keywords and categories.

[1419] Step 5:

[1420] The server identifies relevant brands based on the extracted keywords and categories, searching an internal database.

[1421] Step 6:

[1422] The server passes the identified category and brand information to the generation AI, which then generates content based on this input data.

[1423] Step 7:

[1424] The server-based AI generates text content based on category and brand information, and advertisements are inserted into this content in a natural way.

[1425] Step 8:

[1426] The server then transmits the generated content to the terminal, which is also transmitted via the Internet.

[1427] Step 9:

[1428] The device receives the content and displays it to the user, such as on a web page or within an application.

[1429] Step 10:

[1430] The user views the content and takes actions such as clicking links and scrolling.

[1431] Step 11:

[1432] The device records user actions, collecting information such as which links are clicked and where the user scrolls.

[1433] Step 12:

[1434] The device sends the recorded feedback to a server, and the feedback data is transmitted over the Internet.

[1435] Step 13:

[1436] The server receives the feedback and performs data analysis, which is used to improve the performance of the generative AI.

[1437] Step 14:

[1438] The server feeds back the analysis results to the generation AI and uses them to generate new content, thereby continuously improving the accuracy and effectiveness of the entire system.

[1439] Example 1

[1440] 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."

[1441] Conventional content generation systems lack the accuracy and efficiency to quickly and accurately respond to user needs. In particular, they lack the ability to identify categories and brands based on user prompts and generate content accordingly. Furthermore, they lack a feedback system to continuously improve the quality of generated content, limiting the improvement of the user experience. Furthermore, they also have limited means to naturally insert advertisements that match the user's interests.

[1442] 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.

[1443] In this invention, the server includes a means for receiving prompts from a user, a means for passing the prompts to a natural language processing algorithm and extracting related information, a means for identifying a category and a brand, a means for generating content including the category and the brand, a means for providing the generated content to the user, a means for collecting user feedback, a means for analyzing the feedback and improving generation performance, a means for transmitting the generated content to the user's device, and a means for recording user actions and transmitting the recorded actions to the server as feedback. This enables highly accurate content generation based on user prompts and allows the performance of the generation AI model to be continuously improved based on the feedback. Furthermore, advertisements that match the user's interests can be inserted naturally, improving the user experience.

[1444] A "user" is an individual or organization that uses a system or application.

[1445] A "prompt" is specific text information such as a question or request that a user enters.

[1446] A "category" is a classification of general themes or topics extracted from the prompt.

[1447] A "brand" is an identifier such as a trademark or company name associated with a particular category.

[1448] "Content" refers to text and information generated based on category and brand information.

[1449] A "server" is a computer system that provides data processing and storage over a network.

[1450] A "terminal" is a device that a user uses to communicate with a server, such as a PC or smartphone.

[1451] A "natural language processing algorithm" is a computational method for analyzing text data and understanding the meaning and structure of natural language.

[1452] "Generative AI" is an artificial intelligence model that generates new content based on specified input data.

[1453] "Feedback" refers to data collected based on user actions and reactions.

[1454] "Performance" refers to the effectiveness or efficiency of a system or algorithm.

[1455] The present invention is a system that receives prompts from users, identifies relevant categories and brands, and generates and provides content that includes them. The operation of this system mainly involves a server, a user's device, and a generative AI model.

[1456] Hardware and software used

[1457] Server: The server is the main component that receives, analyzes, processes, stores, and transmits data. The server must have a powerful CPU, sufficient memory, and disk space; for example, it can be an EC2 instance from Amazon Web Services (AWS).

[1458] User device: The device on which the user enters prompts and receives content. Devices include PCs, smartphones, tablets, etc.

[1459] Software: A natural language processing algorithm is used to analyze the prompts, and OpenAI's GPT-3 is used as the generative AI model. This enables advanced text generation. Python's SpaCy and NLTK can be used as analysis libraries.

[1460] Specific examples of processing

[1461] Specific prompt examples

[1462] The user types, "What are your pet toy recommendations?" This prompt is provided as content through the following processing steps:

[1463] SUMMARY STEPS

[1464] 1. Receiving the prompt: The prompt entered by the user is sent from the device to the server, along with metadata such as the user ID and a timestamp.

[1465] 2. Parse the prompt: The server passes the prompt to a natural language processing algorithm to identify the category and brand. For example, the prompt "What are your pet toy recommendations?" identifies the categories "Pets" and "Toys" and the brands "Pet Shop" and "Popular Brands."

[1466] 3. Content generation: Based on the identified category and brand information, generative AI creates content. Specifically, the following content is generated:

[1467] For example: "Our recommended pet toys include the latest collections from pet stores. These durable, safe toys support your pet's health. We also offer interactive toys from popular brands, perfect for making playtime fun with your pet."

[1468] 4. Content Delivery: The generated content is sent from the server to the user's device, where it is displayed in the appropriate format.

[1469] 5. Feedback collection: Users browse content and take actions such as clicks. These actions are recorded by the device and sent to the server.

[1470] 6. Feedback Analysis: The server analyzes the collected feedback and uses it to improve the performance of the generation AI, which will improve the accuracy of content generation next time.

[1471] The present invention can continuously improve the accuracy of the AI ​​generation based on user feedback. Furthermore, it can improve the user experience by inserting advertisements naturally. In this way, the system can respond to user needs quickly and accurately.

[1472] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1473] Program processing steps

[1474] Step 1:

[1475] The user enters the prompt.

[1476] What happens: A user enters a question or request into a field in a web browser or mobile app and clicks the submit button.

[1477] Input: User prompt (e.g., "What are your pet toy recommendations?")

[1478] Output: Signals that a prompt is sent to the user's terminal.

[1479] Step 2:

[1480] The terminal sends a prompt to the server.

[1481] What happens: After the user clicks the submit button, the user's device sends the prompt they entered to the server as an HTTPS request, along with metadata such as the user ID and a timestamp.

[1482] Input: User prompts and metadata

[1483] Output: HTTP request sent to the server

[1484] Step 3:

[1485] The server receives the prompt.

[1486] What it does: The server analyzes the received request and records the prompt content in a log, along with other information such as the time of receipt and the source IP address.

[1487] Input: HTTP request sent from the terminal

[1488] Output: Logged prompts and metadata

[1489] Step 4:

[1490] The server passes the prompt to a natural language processing (NLP) algorithm.

[1491] What happens: The server passes the prompt to an NLP module to identify relevant categories and brands, parsing it using, for example, Python's SpaCy or NLTK.

[1492] Input: Prompt (e.g., "What are your pet toy recommendations?")

[1493] Output: Identified categories (e.g., "pets" or "toys") and brands (e.g., "pet shops" or "popular brands")

[1494] Step 5:

[1495] The server passes category and brand information to the generation AI.

[1496] Specific operation: The server passes the identified category and brand information to the generative AI. For example, using OpenAI's GPT-3 as the generative AI model, it sends a request to the API endpoint containing the necessary parameters.

[1497] Input: Identified category and brand information

[1498] Output: Parameters input to the generation AI

[1499] Step 6:

[1500] The generation AI on the server generates the content.

[1501] Specific operation: The AI ​​generates content based on the received category and brand information. For example, it might generate a sentence like, "Recommended pet toys include the latest collection of toys from pet shops. Durability and safety are guaranteed, supporting your pet's health. Popular brands of interactive toys are also perfect for making playtime with your pet more enjoyable."

[1502] Input: Category and brand information

[1503] Output: Generated content

[1504] Step 7:

[1505] The server transmits the generated content to the terminal.

[1506] Specific operation: The server sends the generated content to the user's device as an HTTP response. The content is organized in HTML or JSON format and sent in a format appropriate for the user's environment.

[1507] Input: Generated content

[1508] Output: The HTTP response sent to the user's device

[1509] Step 8:

[1510] The terminal displays the content to the user.

[1511] What it does: The user's device analyzes the received content and displays it in the web page or app interface. For example, a web browser might insert generated text into specific elements on the page and apply styling to make it more user-friendly.

[1512] Input: Content received from the server

[1513] Output: The content displayed to the user

[1514] Step 9:

[1515] Users view content and take action.

[1516] Specific behavior: The user reads the displayed content. If they find it interesting, they take an action such as clicking a link. For example, they click the "Pet Shop" link to go to the product page.

[1517] Input: Displayed content

[1518] Output: User action (e.g., link click)

[1519] Step 10:

[1520] The device records the user's actions and sends feedback to the server.

[1521] What it does: When a user action occurs, the device records the event and sends feedback to the server as an HTTP request, including the link clicked and a timestamp.

[1522] Input: User action data

[1523] Output: Feedback sent to the server

[1524] Step 11:

[1525] The server receives and analyzes the feedback.

[1526] How it works: The server logs the received feedback data and passes it to an analysis program. The analysis results are used to train the generative AI model, helping to improve the accuracy of future content generation.

[1527] Input: Feedback data sent from the device

[1528] Output: Parsed feedback and model training data

[1529] Through these steps, the system is able to generate highly accurate content based on prompts from the user and use feedback to improve performance.

[1530] (Application example 1)

[1531] 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."

[1532] In recent years, the diversification of information and rapid changes in user needs have led to a demand for providing appropriate information to individual users. However, conventional systems have been unable to efficiently provide personalized content based on users' interests and preferences. In particular, they lack mechanisms for generating content in real time in response to user prompts and for improving the accuracy of generated content by incorporating user feedback. This not only degrades the user experience, but also poses challenges for companies, limiting their marketing effectiveness.

[1533] 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.

[1534] In this invention, the server includes means for receiving instructions from a user, means for identifying a category and a brand from the instructions, means for generating information using a generative AI model based on the specified category and brand, means for displaying the generated information on a mobile device or a web application, means for collecting user responses, and means for analyzing the responses and improving generation performance. This makes it possible to provide personalized content in real time based on user prompts and improve the accuracy of the generative AI by reflecting user feedback.

[1535] "User instructions" refers to text or voice input by a user requesting specific information.

[1536] A "category" refers to a subject or area of ​​interest identified based on a user's instructions.

[1537] "Brand" refers to the source and recognized name of a particular product or service.

[1538] "Information" refers to all content generated by a generative AI model and provided to users.

[1539] "Generative AI Model" refers to an artificial intelligence algorithm that generates content based on a specified category and brand.

[1540] "Mobile Device or Web Application" refers to the computing device or software used to display generated information to a user.

[1541] "User response" refers to the actions and feedback that users take in response to the generated information, such as "likes," "shares," and "clicks."

[1542] "Generative performance" refers to the efficiency and quality of how accurately a generative AI model can generate content that meets user needs.

[1543] This invention is a system that appropriately generates and provides specific information when a user acquires that information through a mobile device or web application.

[1544] First, a user inputs a "prompt sentence" in a specific format into a mobile device or web application, expressing their desire to obtain specific information. For example, "Tell me the latest technology news." This prompt sentence is sent to the system's server, which then receives it.

[1545] The server then parses the prompt and uses natural language processing algorithms to identify relevant categories and brands within the prompt, such as categories like "technology" or "news," or the brand "famous technology websites."

[1546] Based on this identified category and brand information, the server uses a generative AI model, such as OpenAI's "gpt-3.5-turbo," to generate information tailored to the user's interests. When this model generates information, it tailors it to the context of the specified category or brand.

[1547] The generated information is then sent back to the mobile terminal or web application and displayed to the user. It is important that the generated information meets the user's requirements.

[1548] When a user views this information and takes an action, such as "liking," "sharing," or "clicking," their reaction is fed back to the system. This feedback information is sent to the server, which analyzes it and uses it to improve the performance of the generative AI model. At this time, the generative AI model is adjusted based on user feedback, enabling it to generate information with greater accuracy.

[1549] To further improve the system, the server needs to periodically train the model and evaluate its performance based on collected user response data. This will enable the continuous provision of high-quality generated information tailored to user needs. It's a fine line. This is an important feature of this system.

[1550] In this way, users can obtain highly accurate information tailored to their interests and needs in real time. To implement this system, an internet-enabled mobile device or web application and a high-performance server are required. Specifically, a server with sufficient computing power to run natural language processing algorithms and API access to the generative AI model "gpt-3.5-turbo" are required.

[1551] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1552] Step 1:

[1553] On a mobile device or web application, a user enters a prompt sentence to obtain specific information and clicks a submit button.

[1554] Input: The prompt text entered by the user (e.g., "What's the latest technology news?").

[1555] Output: The prompt text is sent to the server.

[1556] Step 2:

[1557] The terminal transmits the prompt text from the user to the server via the Internet.

[1558] Input: The user's prompt.

[1559] Output: The prompt is transmitted to the server via the Internet.

[1560] Step 3:

[1561] The server receives the prompt and logs it.

[1562] Input: The prompt text received over the Internet.

[1563] Output: The prompt statement logged.

[1564] Step 4:

[1565] The server passes the prompt sentence to a natural language processing (NLP) algorithm to identify relevant categories and brands.

[1566] Input: The user's prompt.

[1567] Data processing: NLP algorithms analyze the prompt and extract important keywords (categories and brands) from the text.

[1568] Output: Identified categories and brands (e.g., "Technology," "News," and "Famous Technology Websites").

[1569] Step 5:

[1570] The server passes the identified category and brand information to a generative AI model to generate content.

[1571] Input: Identified category and brand.

[1572] Data calculation: A generative AI model (e.g., "gpt-3.5-turbo") generates appropriate content based on the specified category and brand.

[1573] Output: The generated content (e.g., an article about the latest technology news).

[1574] Step 6:

[1575] The server transmits the generated content to the user's terminal.

[1576] Input: Generated content.

[1577] Output: The generated content that is sent to the user's device.

[1578] Step 7:

[1579] The terminal receives the generated content and displays it to the user.

[1580] Input: Generated content sent from the server.

[1581] Output: The generated content that is displayed on the device screen.

[1582] Step 8:

[1583] Users view the provided content and take actions such as "like," "share," or "click."

[1584] Input: The content displayed on the device.

[1585] Output: User action (e.g. "like", "share", "click").

[1586] Step 9:

[1587] The terminal records the user's actions and sends them as feedback to the server.

[1588] Input: User action.

[1589] Output: Feedback data sent to the server.

[1590] Step 10:

[1591] The server analyzes the received feedback and uses it to improve the performance of the generative AI model.

[1592] Input: User feedback data.

[1593] Data processing: Analyze feedback data, evaluate the performance of generative AI models, and retrain the models as needed.

[1594] Output: An improved generative AI model.

[1595] 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.

[1596] The present invention is characterized in that the system receives prompts from a user, identifies related categories and brands, and generates content including them, and further recognizes the user's emotions using an emotion engine and reflects them in the content generation. Specific embodiments are described below.

[1597] Program processing

[1598] The system identifies relevant categories and brands based on user prompts and uses an emotion engine to analyze the user's emotions at the time of the prompt. The generative AI then generates content based on the category, brand, and user emotion information. The generated content is provided to the user, and user feedback is collected. This feedback is analyzed and used to improve the accuracy of the generative AI.

[1599] Specific examples

[1600] 1. A user types, "Tell me how to relax and relieve stress."

[1601] The user enters the prompt into the input field and clicks the submit button.

[1602] 2. The device sends this prompt to the server.

[1603] The prompt is sent over the Internet to a server, which confirms receipt.

[1604] 3. The server receives the prompt.

[1605] Receive and log prompts.

[1606] 4. The server passes the prompt to a natural language processing (NLP) algorithm to identify the category and brand.

[1607] Example: Parse the prompt "What relaxation techniques can I use to relieve stress?" to identify the categories "relaxation" and "stress" and the brands "wellness center" and "relaxation products."

[1608] 5. The server has the emotion engine analyze the prompt and identify the user's emotion.

[1609] Example: The emotion engine identifies "stress" as the emotion from the user's prompt.

[1610] 6. The server passes the identified category, brand, and user sentiment information to the generation AI.

[1611] Example: The categories "relaxation" and "stress relief," the brands "wellness center" and "relaxation goods," and the user emotion "stress" are input into the generation AI.

[1612] 7. Generative AI in the server creates text content based on category, brand, and user sentiment information. Advertisements are inserted into this content in a natural way.

[1613] Example: A generation AI generates the following sentence:

[1614] We recommend yoga classes at wellness centers as a relaxation method to relieve stress. Popular aroma diffusers are also effective as relaxation tools. By utilizing these, you can ease the stress of everyday life.

[1615] 8. The server sends the generated content to the device.

[1616] Example: Deliver the generated text to the user's device.

[1617] 9. The device receives the content and displays it to the user.

[1618] Example: Displaying text generated on a web page or within an app to the user.

[1619] 10. The user views the content and takes action, such as clicking a link or scrolling.

[1620] 11. The device records the user's actions and sends feedback to the server.

[1621] Example: Sending details of clicked links and actions to the server as logs.

[1622] 12. The server receives the feedback and performs data analysis, which helps improve the performance of the generative AI.

[1623] This embodiment enables the generation of personalized content that takes into account the emotional state of the user, thereby achieving higher user satisfaction. Furthermore, by reflecting the analysis results of the emotion engine in the content generation, the user experience can be further improved.

[1624] The processing flow will be explained below.

[1625] Step 1:

[1626] The user types a question or request into the input field, which becomes the prompt.

[1627] Step 2:

[1628] The device sends the prompt to the server, which then transmits it over the Internet.

[1629] Step 3:

[1630] The server receives the prompt. At this stage, it logs the receipt of the prompt.

[1631] Step 4:

[1632] The server passes the prompt to a natural language processing (NLP) algorithm, which parses the prompt and extracts key keywords and categories.

[1633] Step 5:

[1634] The server identifies relevant brands based on the extracted keywords and categories, searching an internal database.

[1635] Step 6:

[1636] The server passes the prompt to the emotion engine, which analyzes the user's emotion from the words and phrases in the prompt.

[1637] Step 7:

[1638] The server receives the analysis results of the emotion engine and identifies the user's emotion. For example, it recognizes that the user is in a stressful state based on the keyword "stress" in the prompt.

[1639] Step 8:

[1640] The server passes the identified category, brand, and user sentiment information to the generation AI, which then generates content based on this input data.

[1641] Step 9:

[1642] The server-based generative AI creates text content based on category, brand, and user sentiment information, and advertisements are inserted into this content in a natural way.

[1643] Step 10:

[1644] The server then transmits the generated content to the terminal, which is also transmitted via the Internet.

[1645] Step 11:

[1646] The device receives the content and displays it to the user, such as on a web page or within an application.

[1647] Step 12:

[1648] The user views the content and takes actions such as clicking links and scrolling.

[1649] Step 13:

[1650] The device records user actions, collecting information such as which links are clicked and where the user scrolls.

[1651] Step 14:

[1652] The device sends the recorded feedback to a server, and the feedback data is transmitted over the Internet.

[1653] Step 15:

[1654] The server receives the feedback and performs data analysis, which is used to improve the performance of the generative AI.

[1655] Step 16:

[1656] The server feeds back the analysis results to the generation AI and uses them to generate new content, thereby continuously improving the accuracy and effectiveness of the entire system.

[1657] Example 2

[1658] 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."

[1659] Conventional content generation systems have difficulty generating personalized content that takes user emotions into account, making it difficult to improve user satisfaction. Furthermore, the lack of a mechanism for effectively collecting and analyzing user feedback on generated content has limited the improvement of content quality.

[1660] 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.

[1661] In this invention, the server includes means for receiving a prompt from a user, means for identifying a category and a brand from the prompt, means for analyzing emotions from the prompt, means for generating content based on the category, brand, and emotion information, means for providing the generated content to the user, means for collecting user feedback, and means for analyzing the feedback and improving content generation performance. This enables the generation of personalized content that corresponds to the user's emotional state, thereby improving user satisfaction. Furthermore, by analyzing the feedback and reflecting it in the next generation, the quality of the generated content can be continuously improved.

[1662] A "prompt" is a question or request that a user enters into a system.

[1663] "Category" refers to a classification that indicates an area related to a particular theme or topic.

[1664] "Brand" refers to the name or identification used to identify a particular product or service.

[1665] "Emotion" refers to the psychological state of the user when entering the prompt.

[1666] "Content" refers to a collection of information, text, images, videos, etc., provided to users.

[1667] "Feedback" refers to information that indicates the user's reaction and behavior to the generated content.

[1668] "Natural language processing algorithms" refer to computer programs that analyze user prompts and identify relevant categories, brands, and sentiments.

[1669] "Generative AI" refers to artificial intelligence technology that generates new content based on input data.

[1670] "Database" refers to a data management system for storing prompts, generated content, feedback information, etc.

[1671] "Server" refers to a central computer system that manages the entire system and processes requests from users.

[1672] The present invention is a system that receives prompts from users, identifies related categories and brands, and generates content based on them. Furthermore, the system aims to increase user satisfaction by using an emotion engine to recognize the user's emotions and reflecting that emotion information in the content generation.

[1673] The system includes the following major components:

[1674] 1. User Interface

[1675] 2. Server

[1676] 3. Natural Language Processing Algorithms

[1677] 4. Emotion Engine

[1678] 5. Generation AI

[1679] 6. Database

[1680] 1. User Interface

[1681] A user accesses the system using a terminal connected to the Internet (e.g., a PC, a smartphone, a tablet, etc.). The user interface has an input field where the user can enter a prompt.

[1682] 2. Server

[1683] The server is the central processing unit of the system, receiving prompts from users and performing various analyses and generation. The server is also connected to a database that manages prompts, generated content, and feedback information.

[1684] 3. Natural Language Processing Algorithms

[1685] The server then passes the received prompts to a natural language processing algorithm to identify categories and brands, which analyzes the text data and extracts meaning and relationships.

[1686] 4. Emotion Engine

[1687] The server analyzes the user's emotion in the prompt using an emotion engine, which works in conjunction with natural language processing to analyze emotion keywords and context in the sentence to identify the user's mental state.

[1688] 5. Generation AI

[1689] Generative AI generates content based on identified categories, brands, and user sentiment information. This generative AI is a model that uses deep learning to create natural-looking text.

[1690] 6. Database

[1691] The database is connected to the server and is a system that stores and manages prompts, generated content, and user feedback data, allowing the feedback data to be analyzed and used to improve the generative AI.

[1692] As a specific example, when a user types "Tell me some relaxation techniques to relieve stress" and clicks the send button, the device sends this prompt to the server. The server receives the prompt and passes it to a natural language processing algorithm for analysis, identifying the categories "relaxation" and "stress relief" and the brands "wellness center" and "relaxation products." At the same time, the emotion engine analyzes the user's emotions and identifies "stress." Based on the identified information, the generation AI generates text content introducing relaxation techniques related to "yoga classes at wellness centers" and "aromatherapy diffusers." The server then sends this content to the device and displays it to the user. The system is continuously improved as users view the generated content and provide feedback.

[1693] This invention enables the generation of personalized content that takes into account the user's emotional state, improving the user experience. Furthermore, by utilizing user feedback to improve the accuracy of the generation AI, further quality improvements can be expected.

[1694] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1695] Step 1:

[1696] The user enters and submits the prompt.

[1697] Input: A user-written prompt in natural language (e.g., "Tell me some relaxation techniques to relieve stress")

[1698] Output: Send button press signal to terminal

[1699] Specific operation: The user enters a prompt into the input field of the terminal and clicks the send button, which sends the prompt to the server via the terminal's send function.

[1700] Step 2:

[1701] The terminal sends a prompt to the server.

[1702] Input: Prompt from user

[1703] Output: The prompt reaches the server

[1704] What it does: The device sends the prompt over the internet to a server, encrypting the data using a security protocol such as SSL.

[1705] Step 3:

[1706] The server receives the prompt and logs it.

[1707] Input: Prompt sent from the terminal

[1708] Output: Prompt log entry

[1709] Specific operation: The server receives the prompt and records its contents in a log file. The log includes the time of receipt and the prompt contents.

[1710] Step 4:

[1711] The server passes the prompt to a natural language processing (NLP) algorithm to parse it and identify the category and brand.

[1712] Input: Prompt (e.g., "What relaxation techniques can I use to relieve stress?")

[1713] Output: Identified categories and brands (e.g., categories "relaxation" and "stress relief" and brands "wellness center" and "relaxation products")

[1714] What happens: The server feeds the prompt into an NLP algorithm for semantic analysis, which identifies relevant categories and brands.

[1715] Step 5:

[1716] The server analyzes the prompt with an emotion engine to identify the user's emotion.

[1717] Input: prompt

[1718] Output: Identified user emotion (e.g. "stressed")

[1719] Specific operation: The server uses the emotion engine to analyze the emotion keywords and contextual information in the prompt to identify the user's emotional state.

[1720] Step 6:

[1721] The server passes the identified category, brand, and user sentiment information to the generation AI.

[1722] Input: Category, brand, and sentiment information

[1723] Output: Input data to the generative AI

[1724] Specific operation: The server formats the identified information to be input into the generative AI model and sends it to the generative AI.

[1725] Step 7:

[1726] Generative AI generates text content based on category, brand, and user sentiment information.

[1727] Input: Category, brand, and emotion information (e.g., category "relaxation" and "stress relief", brand "wellness center" and "relaxation goods", emotion "stress")

[1728] Output: Generated text content (e.g., "I recommend yoga classes at the wellness center as a relaxing way to relieve stress.")

[1729] How it works: Generative AI generates text content in a natural way based on input data, with relevant ads naturally inserted.

[1730] Step 8:

[1731] The server transmits the generated content to the terminal.

[1732] Input: Generated text content

[1733] Output: Content sent to the device

[1734] Specific operation: The server formats the generated content appropriately and sends the data to the device.

[1735] Step 9:

[1736] The terminal receives the content and displays it to the user.

[1737] Input: Content sent from the server

[1738] Output: Content displayed on the user's screen

[1739] Specific operation: The device analyzes the data it receives and displays it on the web page or app user interface.

[1740] Step 10:

[1741] The user views the content and takes actions such as clicking links and scrolling.

[1742] Input: Displayed content

[1743] Output: User action data (e.g., link click, scroll)

[1744] Specific Action: The user browses the generated content and takes an action such as clicking on a link that interests them.

[1745] Step 11:

[1746] The device records the user's actions and sends feedback to the server.

[1747] Input: User action data

[1748] Output: Feedback data sent to the server

[1749] Specific operation: The device logs user behavior data (e.g., click history, viewing time) and sends it to the server.

[1750] Step 12:

[1751] The server receives the feedback and performs data analysis, which is used to improve the performance of the generation AI.

[1752] Input: Feedback data

[1753] Output: Analysis results and improved generative AI

[1754] What it does: The server analyzes the feedback data and uses the results to modify the AI ​​algorithm, which is then reflected in the next content generation, improving its accuracy.

[1755] (Application example 2)

[1756] 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."

[1757] The problem to be solved by the present invention is to provide more personalized content in response to user input, and to improve the user experience by recommending related products and services taking into account the user's emotions.

[1758] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a prompt from a user, means for identifying a category and a brand from the prompt, means for analyzing the user's emotions from the prompt, means for generating content based on the category, brand, and user emotions, means for providing the generated content to the user, means for collecting user feedback, and means for analyzing the feedback and improving generation performance. This makes it possible to provide personalized content that takes the user's emotional state into consideration and recommend optimal products and services.

[1759] A "means for receiving prompts from a user" is a device or program for receiving commands, such as text or voice, entered by a user.

[1760] The "category and brand identification means" is a technology that includes natural language processing algorithms for identifying relevant product categories and brands from the received prompts.

[1761] The "means for analyzing user emotions" is an emotion engine or analysis algorithm for analyzing the user's current emotional state from the user's prompts.

[1762] The "content generation means" is a generative AI model for creating information such as text and images based on identified categories, brands, and user sentiment.

[1763] The "means for providing to the user" refers to an interface or communication means for displaying or transmitting the generated content to the user.

[1764] A "means for collecting user feedback" is a tool or system for recording reactions and actions taken by users in response to generated content.

[1765] "Means for analyzing feedback and improving generative performance" refers to data analysis techniques that analyze collected feedback and improve the accuracy and efficiency of generative AI models.

[1766] A "product recommendation means" is a system for selecting and recommending appropriate products and services based on identified categories, brands, and user sentiment.

[1767] This invention is a system that generates personalized content by identifying appropriate categories and brands based on prompts from users and analyzing user sentiment. The system can be accessed from devices such as smartphones, tablets, and PCs, and the entire process is performed by a server via the Internet.

[1768] First, a user inputs a prompt (for example, "Tell me about a product you like to use when you're tired") using a terminal. This prompt is sent to a server via the Internet.

[1769] The server then runs the prompt through a natural language processing algorithm (e.g., the TextBlob library) to identify categories and brands. For example, the prompt "Tell me what products you like to use when you're tired" might identify categories like "relaxation products" and "wellness products."

[1770] An emotion engine is then used to analyze the user's emotion (e.g., "fatigue"). This emotion information is passed to a generative AI model, which generates personalized content based on the identified category and brand. The generated content includes recommended products and services. For example, based on the emotion "fatigue," products such as "aroma diffusers" and "massage pillows" are recommended.

[1771] The server sends the generated content to the terminal, where the user can view the content. The terminal also records the actions the user takes while viewing the content (for example, clicking links or scrolling), and sends the records back to the server.

[1772] Finally, the server analyzes the collected feedback to improve the performance of the generative AI model, which will enable more accurate content generation in the future.

[1773] For example, if a user inputs the prompt "I've been feeling stressed lately, please tell me about some products that will help me relax," the emotion engine will determine the emotion "stress," and the generative AI model will generate content that recommends products such as "aroma diffusers" and "relaxation cushions." This content will be displayed on the user's device, improving the user experience.

[1774] As described above, the present invention generates personalized content by taking into consideration not only the category and brand but also the user's emotions, thereby enabling more effective product and service recommendations.

[1775] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1776] Step 1:

[1777] The user uses the terminal to enter and send a prompt.

[1778] Input: Prompt sentence (e.g., "Tell me what products you like to use when you're tired.")

[1779] Output: The prompt is sent to the server.

[1780] Step 2:

[1781] The server passes the received prompts to a natural language processing algorithm to identify the category and brand.

[1782] Input: The prompt text sent by the user

[1783] Data processing: Parse prompts using natural language processing algorithms (e.g., TextBlob library)

[1784] Output: Identified category (e.g., "Relaxation Products") and brand (e.g., "Wellness Products")

[1785] Step 3:

[1786] The server uses an emotion engine to analyze the user's emotion from the prompt sentence.

[1787] Input: The prompt text sent by the user

[1788] Data Computation: Identify emotional states (e.g., "fatigue") from prompts using an emotion engine

[1789] Output: User's emotional state (e.g., "fatigue")

[1790] Step 4:

[1791] The server generates content using a generative AI model based on identified categories, brands, and user sentiment.

[1792] Input: Category (e.g., "Relaxation Products"), Brand (e.g., "Wellness Products"), User Sentiment (e.g., "Fatigue")

[1793] Data computation: Generative AI models are used to generate content based on category, brand, and user sentiment (e.g., recommendations for "aroma diffusers" or "massage pillows").

[1794] Output: Generated content (e.g., "When you're feeling tired, we recommend using an aroma diffuser!")

[1795] Step 5:

[1796] The server transmits the generated content to the terminal.

[1797] Input: Generated content

[1798] Output: Content is sent to the device

[1799] Step 6:

[1800] The user views the content on the device.

[1801] Input: Content sent from the server

[1802] Output: Content is displayed on the device screen

[1803] Step 7:

[1804] The terminal records the user's feedback and sends it to the server.

[1805] Input: User actions (e.g., clicking a link, scrolling)

[1806] Data processing: Recording user actions and compiling them as feedback data

[1807] Output: Feedback data is sent to the server

[1808] Step 8:

[1809] The server analyzes the received feedback data and improves the performance of the generative AI model.

[1810] Input: Feedback data

[1811] Data computation: Analyzing feedback data using analytical algorithms to identify areas for improvement in the generative AI model

[1812] Output: Update and improve the accuracy of the generative AI model

[1813] Through the above steps, the system can generate personalized content according to the user's emotional state and improve the user experience.

[1814] 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.

[1815] 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.

[1816] 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.

[1817] 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.

[1818] 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.

[1819] 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.

[1820] 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).

[1821] 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.

[1822] 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."

[1823] 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.

[1824] 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).

[1825] 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.

[1826] 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.

[1827] 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.

[1828] 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.

[1829] 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.

[1830] 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.

[1831] 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.

[1832] 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.

[1833] 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.

[1834] 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.

[1835] The following is further disclosed regarding the above embodiment.

[1836] (Claim 1)

[1837] means for receiving a prompt from a user;

[1838] means for identifying a category and brand from said prompt;

[1839] means for generating content including the category and brand;

[1840] means for providing the generated content to a user;

[1841] a means for collecting user feedback;

[1842] means for analyzing said feedback and improving generation performance;

[1843] A system including:

[1844] (Claim 2)

[1845] 10. The system of claim 1, further comprising means for inserting advertisements based on the identified category and brand.

[1846] (Claim 3)

[1847] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to identify a category and a brand from the prompt.

[1848] "Example 1"

[1849] (Claim 1)

[1850] means for receiving a prompt from a user;

[1851] means for identifying a category and brand from said prompt;

[1852] means for generating content including the category and brand;

[1853] means for providing the generated content to a user;

[1854] a means for collecting user feedback;

[1855] means for analyzing said feedback and improving generation performance;

[1856] means for passing the prompt to a natural language processing algorithm to extract relevant information;

[1857] means for transmitting the generated content to a user terminal;

[1858] means for recording the user's actions and sending them as feedback to a server;

[1859] A system including:

[1860] (Claim 2)

[1861] 10. The system of claim 1, further comprising means for inserting advertisements based on the identified category and brand.

[1862] (Claim 3)

[1863] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to identify a category and a brand from the prompt.

[1864] "Application Example 1"

[1865] (Claim 1)

[1866] means for receiving instructions from a user;

[1867] means for identifying a category and brand from said instructions;

[1868] means for generating information including the category and brand;

[1869] means for providing the generated information to a user;

[1870] a means for collecting user responses;

[1871] a means for analyzing the reaction and improving the performance of the product;

[1872] a means for generating information based on a specified category and brand using a generative AI model;

[1873] means for displaying the generated information on a mobile terminal or a web application;

[1874] A system including:

[1875] (Claim 2)

[1876] 10. The system of claim 1, further comprising means for inserting advertisements based on the identified category and brand.

[1877] (Claim 3)

[1878] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to identify a category and a brand from the instruction.

[1879] "Example 2: Combining Emotion Engines"

[1880] (Claim 1)

[1881] means for receiving a prompt from a user;

[1882] means for identifying a category and brand from said prompt;

[1883] means for analyzing emotion from the prompt;

[1884] means for generating content based on the category, brand and emotion information;

[1885] means for providing the generated content to a user;

[1886] a means for collecting user feedback;

[1887] means for analyzing said feedback and improving generation performance;

[1888] A system including:

[1889] (Claim 2)

[1890] 10. The system of claim 1, further comprising means for inserting advertisements based on the identified category and brand.

[1891] (Claim 3)

[1892] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to identify a category, a brand, and a sentiment from the prompt.

[1893] "Application example 2 when combining emotion engines"

[1894] (Claim 1)

[1895] means for receiving a prompt from a user;

[1896] means for identifying a category and brand from said prompt;

[1897] means for analyzing a user's emotion from the prompt;

[1898] means for generating content based on the category, brand and user sentiment;

[1899] means for providing the generated content to a user;

[1900] a means for collecting user feedback;

[1901] means for analyzing said feedback and improving generation performance;

[1902] A system including:

[1903] (Claim 2)

[1904] 10. The system of claim 1, further comprising means for recommending products based on the identified category, brand, and user sentiment.

[1905] (Claim 3)

[1906] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to identify a category and a brand from the prompt. [Explanation of symbols]

[1907] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a prompt from a user; means for identifying a category and brand from said prompt; means for generating content including the category and brand; means for providing the generated content to a user; a means for collecting user feedback; means for analyzing said feedback and improving generation performance; A system including:

2. 10. The system of claim 1, further comprising means for inserting advertisements based on the identified category and brand.

3. The system of claim 1 , further comprising means for using a natural language processing algorithm to identify a category and a brand from the prompt.

Images