system

Abstract

We provide the system. [Solution] A means of creating personalized choices for users based on a generative model, A means for interpreting natural language input from users and generating appropriate responses, A means of analyzing sales and inventory data to predict future demand and optimize inventory, A means of analyzing market trends and automatically generating personalized sales promotions, Means for processing quality control and tracking data from production to consumption, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the coffee industry, it is difficult to provide services based on different preferences and allergy information for each customer. Furthermore, it is not easy to quickly respond to inquiries in natural language from customers and provide a deep customer experience. Also, it is a challenge to improve the accuracy of demand forecasting based on sales data and reduce waste. In addition, a mechanism is required to automatically generate and execute effective promotions according to market trends. Moreover, improvement in quality control and traceability throughout the supply chain from production to consumption is also demanded.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for creating personalized choices for users based on a generative model, means for interpreting natural language input from users and generating appropriate responses, means for analyzing sales and inventory data to predict future demand and optimize inventory, means for analyzing market trends and automatically generating personalized sales promotions, and means for processing quality control and tracking data from production to consumption. This makes it possible to efficiently provide services that meet the diverse needs of customers and optimize the entire business process.

[0006] A "generative model" is an algorithm that uses mathematical and statistical approaches to generate new data or content based on patterns learned from existing data.

[0007] "User" refers to an individual or organization that uses this system to receive services or information.

[0008] "Natural language" refers to the language that humans use on a daily basis, and is a concept that includes means of communication such as speech and writing.

[0009] "Inventory data" refers to information that records the quantity and condition of products or goods when they are stored or sold.

[0010] "Demand forecasting" is the process of estimating future demand for a product or service by analyzing past data and current market trends.

[0011] "Promotion" refers to activities or campaigns aimed at increasing the sales of products or services.

[0012] "Quality control" refers to a series of activities aimed at monitoring and improving processes to ensure that products and services meet certain quality standards.

[0013] "Traceability" refers to a management method that aims to ensure quality and safety by making it possible to track the manufacturing process and history of a product. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The system for implementing the present invention operates on a network that includes a server, user terminals, and a platform for centrally managing data from users. Users input their preferences, allergy information, and other personal settings via their terminals, thereby forming a foundation for providing services tailored to the user.

[0036] The server receives the entered user data and uses an advanced generative model to create personalized menus. These menus are designed to suggest products that best suit the user's individual needs, taking into account their preferences and past purchase history.

[0037] Furthermore, when a user makes a request in natural language through their device, that request is sent to the server. The server utilizes a natural language processing engine to understand the content of the request and generate the optimal response. This response is then presented to the user on their device, allowing them to use the service intuitively and effectively.

[0038] The server also analyzes historical sales data and inventory information to predict future demand, enabling it to replenish and optimize inventory appropriately. This prevents inventory imbalances and reduces unnecessary losses.

[0039] In addition, the server analyzes market trends in real time and automatically generates promotional activities based on that analysis. These promotions are optimized to match users' purchasing trends, providing an effective marketing strategy.

[0040] Finally, the server manages the entire supply chain data from production to consumption, enhancing quality control and traceability. By maintaining the necessary quality standards, it can provide users with products that guarantee high reliability.

[0041] As a specific example, when a user orders coffee, they pre-set allergy information on a terminal, and the server generates and presents a menu that does not contain the specific allergens based on that information. In this way, the system of the present invention improves the user experience and provides coffee service efficiently and effectively.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user accesses the device and registers their preferences and allergy information. The device then captures this information and prepares to send it to the server.

[0045] Step 2:

[0046] The server receives user data sent from the terminal. The server uses a generative model to generate personalized menus for the user, taking into account the user's preferences and past purchase history.

[0047] Step 3:

[0048] The server sends the generated menu to the terminal. The terminal displays the received menu in its user interface, allowing the user to select an option.

[0049] Step 4:

[0050] The user selects an item from the menu and places an order. The terminal sends this information to the server, and the order processing is completed.

[0051] Step 5:

[0052] The user inputs questions or requests in natural language via the device. The device then prepares to send that input to the server.

[0053] Step 6:

[0054] The server uses a natural language processing engine to analyze the user's request and generate an appropriate response. The generated response is then sent back to the terminal.

[0055] Step 7:

[0056] The terminal presents the user with a response from the server. The user can then decide on their next action based on the information provided.

[0057] Step 8:

[0058] The server periodically collects and analyzes sales data and inventory information to forecast future demand. This information is used for efficient inventory management and is then provided to terminals.

[0059] Step 9:

[0060] The server analyzes market data, automatically creates customized promotional campaigns, and delivers information to target users through their devices.

[0061] Step 10:

[0062] The server ensures product reliability using quality control and traceability data. This information is provided to the terminal, giving users peace of mind.

[0063] (Example 1)

[0064] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0065] In modern information systems, optimizing service delivery to meet individual user preferences and needs, as well as efficiently managing inventory and analyzing market trends, is challenging. Furthermore, real-time processing is necessary to respond automatically and quickly to consumer demands. This demands improved user satisfaction and more efficient business operations.

[0066] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0067] In this invention, the server includes means for creating personalized choices for users based on a generation algorithm, means for analyzing sales and inventory data to predict future demand and optimize inventory, and means for processing quality control and tracking information from production to consumption. This enables the provision of customized services for each user, more efficient inventory management, and enhanced quality assurance.

[0068] A "generative algorithm" refers to a set of calculations used to automatically create personalized options based on a user's preferences and purchase history.

[0069] "Natural language input" refers to a method in which users intuitively provide information to a system using everyday language.

[0070] "Sales and inventory data" refers to information about when, where, and how many of a product were sold, as well as how much inventory is currently available.

[0071] "Market trends" refer to trends and changes in consumer purchasing patterns within a specific industry or field.

[0072] "Quality control" refers to activities aimed at ensuring that products and services meet specific standards and expectations.

[0073] "Tracking information" refers to data about the location and status of a product at each stage from production to consumption.

[0074] A "personalized menu" refers to a list of products and services that have been customized to take into account the preferences and requests of a specific user.

[0075] "Inventory optimization" refers to the process of maintaining an appropriate amount of inventory that is neither excessive nor insufficient in relation to demand.

[0076] "Integrating and analyzing in real time" refers to the process of instantly combining and analyzing data obtained from multiple sources.

[0077] In embodiments of this invention, the system operates around a server, a user terminal, and a platform that integrates and manages data.

[0078] When the server receives data sent from the user, it uses a generative AI model to create personalized choices and menus. This AI model is generated based on the user's preferences and past behavior history. The generated menus aim to provide different suggestions for each user, presenting products and services best suited to each individual's needs. The specific technologies used in this process include natural language processing engines and data analysis algorithms.

[0079] In addition, the server has the ability to continuously analyze sales and inventory data to predict future demand. This enables data-driven management to prevent inventory imbalances and optimize supply. The server also monitors market trends and automatically generates personalized sales promotion strategies based on consumer purchasing trends. These strategies are optimized by the system to support effective marketing activities.

[0080] On the device, users can input requests in natural language. For example, if a user inputs the request "What coffee do you recommend?", the server uses a generative AI model to generate an appropriate response and sends it back to the device. This allows users to interact with the system intuitively and efficiently.

[0081] As a concrete example, when a user orders coffee, they can set and save allergy information in advance. Based on this information, the server generates a menu that does not contain specific allergens and suggests it to the user, providing an environment where they can use the products with peace of mind. An example of a prompt message to the generating AI model is, "Based on the user's preferences and past purchase history, please suggest this week's recommended coffee menu."

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] Users input their personal preferences and allergy information via their device. Specifically, they open a dedicated application and enter data into an input form where they fill in their name, favorite foods, and allergy information. This data is collected by the device and sent to the server. The input data includes information about preferences and allergies.

[0085] Step 2:

[0086] The server receives data sent by the user and stores it in the database. Specifically, it decodes the received data in JSON format and updates the corresponding user profile in the database. This data is then prepared to be input into the generated AI model. The output is the updated user profile information.

[0087] Step 3:

[0088] The server uses a generative AI model to create personalized menus based on user preferences. The model is prompted with the recently updated user data, and the generative AI generates a menu that "matches the user's preferences." Specifically, it outputs a list of recommended menu items such as "latte, black coffee, and cafe mocha."

[0089] Step 4:

[0090] The generated personalized menu is sent from the server to the terminal. The terminal receives this menu information and displays it visually within the application. It is presented in a user-friendly format and offered to the user as a recommended menu. The output is a visual menu display that the user can select from.

[0091] Step 5:

[0092] When a user makes a natural language request through their device, that request is sent to the server. Specifically, the user enters a request such as "What are today's recommended dishes?" into a text input field within the app.

[0093] Step 6:

[0094] The server utilizes a natural language processing engine to analyze incoming requests and generate appropriate responses. The input includes natural language requests from the user. Through natural language processing, it understands the user's intent and generates a response such as "This week's recommendation is a latte," which it then outputs. Finally, the response is sent to the terminal, making it available for the user to review.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] There is a problem in providing product recommendations quickly and efficiently based on individual preferences and allergy information. Furthermore, there is a need for the automated generation of personalized sales strategies that instantly capture market trends.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes means for creating personalized choices for users based on a generative model, means for customizing product suggestions by utilizing preference and allergy information, and means for analyzing market trends and automatically generating personalized sales promotions. This enables the provision of products that meet the individual needs of users and the automatic generation of effective marketing strategies.

[0100] A "generative model" refers to an algorithm used to create personalized options and suggestions based on user data.

[0101] "Natural language input" refers to questions and requests made by users using everyday language, which serve as the basis for the system to interpret them.

[0102] "Inventory data" refers to information that shows the current inventory status of goods or products, and is used for future demand forecasting and optimization.

[0103] "Market trends" refer to a broad range of data, including consumer preferences, purchasing tendencies, and economic movements, and serve as the basis for planning sales promotion activities.

[0104] "Preference and allergy information" refers to individual data indicating products that users prefer and ingredients they should avoid, and is used to customize personalized recommendations.

[0105] "Quality control and tracking data" refers to data used to guarantee the quality of a product from the time it is manufactured until it reaches the consumer, and to manage its history.

[0106] The system for implementing this invention consists of a user terminal, a central server, and a platform for centrally managing data. Users input personal data, such as individual preferences and allergy information, using a terminal such as a smartphone. This information is immediately transmitted to the server and stored in a database.

[0107] On the server, a Python program runs, using Flask to process user requests. Natural language requests from users are parsed by the Hugging Face Transformers library. The results of this parsing are integrated with user preference data and past purchase data, and data processing is performed using the Pandas library.

[0108] The server further analyzes market trends and inventory information in real time using Apache® Kafka. This optimizes product recommendations and automatically generates promotional activities as needed.

[0109] For example, if a user sends a prompt message such as "I'd like recommendations for a dairy-free café au lait," the server analyzes past purchase data and the prompt message, selects products that meet the criteria, and sends the most suitable suggestion to the user's terminal. Through this series of processes, the system can provide personalized product suggestions to the user.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] Users access the application using their smartphones and enter their preferences and allergy information. This information is sent from the device to the server. The input here consists of the user's preferences and allergy information, while the output is user data recorded on the server. The server stores this information in a database.

[0113] Step 2:

[0114] The user enters a specific product request in natural language. For example, they might enter a prompt message like, "Please recommend a dairy-free café au lait," and send it from their device to the server. The input is the prompt message, and the output is the request sent to the server.

[0115] Step 3:

[0116] The server parses the received prompt text using the Hugging Face Transformers library. This parsing converts natural language into a machine-readable format and structures the data to clarify the user's request. The input is the prompt text, and the output is the parsing result. The server stores this as internal processing data.

[0117] Step 4:

[0118] The server program uses Pandas to integrate and process user preference data and past purchase history data based on the analysis results. The input consists of the analysis results and user data, and the output is a dataset for product recommendations. This dataset is used to identify products that match the user's criteria.

[0119] Step 5:

[0120] The server uses Apache Kafka to analyze market trends and inventory information in real time and create necessary promotions. The input is market and inventory data, and the output is the optimal promotion strategy. The server combines this with a proposed dataset.

[0121] Step 6:

[0122] The server uses a generative AI model to generate optimal product suggestions based on the processed data. The input is the dataset obtained in the previous steps, and the output is a customized product list for the user.

[0123] Step 7:

[0124] The terminal receives a customized product list from the server and displays it to the user. The user can then select products based on this list. The input is the product list sent from the server, and the output is the suggestions displayed on the terminal's screen.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] The system for implementing the present invention operates on a network including a server, a user terminal, and an emotion engine. Through the terminal, the user can input information about their preferences, allergies, and emotions. The input data is transmitted from the terminal to the server, forming the basis for providing personalized menu services.

[0127] The emotion engine recognizes the user's emotions from data such as natural language input, facial expressions, and voice. The server uses the emotion data analyzed by the emotion engine to provide choices that match the user's current emotional state. This process is designed to suggest products that the user will find most appealing using a generative model.

[0128] Specifically, the server analyzes emotional data received from the user and suggests relaxing products if the user is feeling stressed, or sweets or special seasonal items if the user is in a mood to have fun. This intelligent menu selection enables a more personalized customer experience.

[0129] Furthermore, when a user enters a question or request in natural language into their device, that data is sent to the server, which uses an emotion engine to analyze the emotion behind the request. The server then generates a response that matches the emotional state, enabling the user to communicate intuitively and effectively.

[0130] By analyzing market trends and inventory data in combination with sentiment information, the server automatically generates promotional campaigns and delivers content that resonates most with users' emotions. Furthermore, the server leverages quality control and traceability functions to ensure product reliability throughout the supply chain, providing peace of mind.

[0131] As an example of this system, if a user inputs a feeling such as "I'm tired today" through their terminal, the server uses an emotion engine to analyze that information and suggests things like a low-caffeine relaxing tea or a calming aroma to the user. In this way, the system of the present invention provides users with a more personal and satisfying experience.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user uses the device to input their preferences, allergy information, and current emotions using natural language or a selection of options. The device then prepares to send this information to the server.

[0135] Step 2:

[0136] The server receives information sent from the terminal. The server uses an emotion engine to analyze the input natural language or emotion data and identify the user's emotional state.

[0137] Step 3:

[0138] The server uses a generative model to generate an optimized product menu based on the user's emotional state and personal information. For example, if the user is identified as seeking relaxation, the server will prioritize selecting products with relaxing effects.

[0139] Step 4:

[0140] The server generates a personalized menu and sends it to the terminal. The terminal displays the received menu in its user interface, allowing the user to make a selection.

[0141] Step 5:

[0142] The user selects an item from the displayed menu and confirms the order. The terminal then sends this order information to the server.

[0143] Step 6:

[0144] The user enters questions or additional requests in natural language using their device. The device then sends this request data to the server.

[0145] Step 7:

[0146] The server then uses the emotion engine again to analyze the user's emotional state from their request and select an appropriate response. This response will be tailored to the user's emotions.

[0147] Step 8:

[0148] The server sends the parsed response to the terminal, which displays it in the user interface. The user then uses this information to decide on their next action.

[0149] Step 9:

[0150] The server integrates and analyzes accumulated emotional data, sales data, and market trends to automatically generate targeted promotional campaigns. This allows for optimal suggestions to users and improves customer satisfaction.

[0151] Step 10:

[0152] The server ensures quality control and traceability throughout all processes, maintaining the reliability of products and services. This provides users with peace of mind through their devices.

[0153] (Example 2)

[0154] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0155] In today's digital marketplace, there is a demand for personalized products or services that are tailored to users' preferences and emotions. However, traditional systems have struggled to adequately analyze user emotions and make accurate product recommendations and sales promotions based on them. Furthermore, there has been a lack of systems that enable quality control and reliable tracking to ensure user trust. As a result, there has been a challenge in adequately increasing user satisfaction.

[0156] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0157] In this invention, the server includes means for analyzing the user's emotional state based on a generative model and suggesting personalized products or services; means for analyzing market trends and inventory data and automatically generating sales promotions that correspond to the user's emotional state; and means for ensuring reliability using quality control and tracking data from production to consumption. This makes it possible not only to provide highly accurate product suggestions and appropriate sales promotions based on the user's emotions, but also to enhance the reliability of the product.

[0158] A "generative model" is an artificial intelligence algorithm used to suggest the most suitable products and services based on user information and circumstances.

[0159] "Emotional state" refers to data that indicates the user's mental and emotional condition, and is obtained from natural language, voice, facial expressions, etc.

[0160] "Proposing products or services" means presenting a selection of products or services chosen according to the user's preferences and feelings.

[0161] "Market trends" refer to information about current and future market changes, including trends in consumer preferences and demand.

[0162] "Sales promotion" refers to marketing activities conducted to expand the sales channels for a product and increase sales.

[0163] "Quality control" refers to management activities aimed at ensuring that products and services meet certain quality standards.

[0164] "Tracking data" refers to information used to record and track the process of a product from its production to its consumption.

[0165] The system for implementing this invention consists of a network comprising a server, a user terminal, and an emotion analysis engine. The terminal receives input from the user and can input preferences, allergy information, and even emotional information via natural language. Specifically, the terminal is equipped with a camera and microphone, capable of acquiring facial and voice data and transmitting it to the server.

[0166] Based on the received data, the server uses specific software called an emotion analysis engine to analyze the user's emotional state. This emotion analysis engine utilizes natural language processing technology and machine learning models to analyze the user's text, facial expressions, and voice to determine their emotions. The server then uses this analysis result to suggest the most suitable products and services to the user using a generative AI model. Specifically, the generative AI model suggests products with relaxing effects, sweets, and seasonal items.

[0167] Furthermore, the server analyzes market trends and inventory information in real time based on the user's emotional state and automatically generates promotional campaigns. In addition, product traceability and quality control functions guarantee product reliability and provide users with peace of mind.

[0168] As a concrete example, consider a scenario where a user inputs the emotion "I'm tired today" through their device. The server uses an emotion analysis engine to analyze this information and suggests a low-caffeine relaxing tea or a calming aroma to the user. An example of a prompt might be natural language input such as, "I'm feeling stressed today. I'm looking for something to help me relax. Do you have any recommendations?"

[0169] This makes it possible to provide users with a more personal and satisfying experience.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] Users input preferences, allergy information, and emotional information in natural language via the device. This input is done using the device's touchscreen, keyboard, camera, or microphone. The input data is collected by the device as text, image data, and audio data.

[0173] Step 2:

[0174] The device sends text, image, and audio data obtained from the user to the server. The data is encrypted and sent securely to the server via the internet. The server receives this data and stores it in a database.

[0175] Step 3:

[0176] The server analyzes the received data using an emotion analysis engine. Text data is analyzed using natural language processing techniques, facial expressions are recognized from image data, and emotions are analyzed from audio data using speech recognition. This process determines emotional states such as "stress" and "happiness."

[0177] Step 4:

[0178] Using the results of the emotion analysis engine, the server generates the optimal product or service using a generative AI model. If stress is detected, the server generates a list of products with relaxing effects. In this process, the AI ​​refers to a vast product database and makes suggestions that match the criteria.

[0179] Step 5:

[0180] The server creates actionable suggestions and sends them to the user's device as a notification. The device then displays the suggested content on the user's screen. For example, suggestions for relaxing tea or aromatherapy candles might be displayed as text and images.

[0181] Step 6:

[0182] The server simultaneously generates emotionally relevant sales promotion content based on market trends and inventory information, and presents it to the user as additional information. The automatic inclusion of promotional campaigns in the suggestions further stimulates the user's purchasing intent.

[0183] Through these steps, the system aims to provide users with a personalized experience and improve their satisfaction.

[0184] (Application Example 2)

[0185] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0186] Modern users have diverse preferences and emotional states, and there is a demand for personalized products and services tailored to these needs. However, conventional systems have struggled to provide real-time content recommendations based on emotions, and have failed to adequately enhance user satisfaction. Furthermore, there have been problems such as insufficient emotion analysis using visual and auditory data, and the inability to respond immediately.

[0187] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0188] In this invention, the server includes means for creating personalized choices for the user based on a generative model, means for analyzing the user's emotional data and recommending optimal content in real time, and means for coordinating with a device for acquiring visual and auditory information and performing emotional analysis. This enables real-time content recommendations tailored to the user's emotional state, thereby improving the personalized user experience.

[0189] A "generative model" is a mathematical or computer programmatic model used to generate personalized choices based on each user's preferences and emotional data.

[0190] "Personalized choices for users" refers to the provision of products and services that are customized based on the individual needs and emotional state of the user.

[0191] "Natural language input" refers to data in a format that is directly entered using the language that humans use on a daily basis.

[0192] "Real-time recommendations" is a process that instantly presents content and options based on the user's current state and emotions.

[0193] "Emotional data" refers to data related to a user's current psychological or emotional state, which is analyzed from information such as facial expressions and voice.

[0194] "Visual and auditory information" refers to data related to the user's visual and auditory aspects, such as facial expressions, voice, and words, which is used for emotion analysis.

[0195] "Content recommendation" is a process that suggests appropriate movies, music, and other multimedia based on the user's preferences and emotional state.

[0196] "Emotional analysis" is a technical method that analyzes collected visual and auditory data to identify the user's emotional state.

[0197] To realize this invention, the following configuration is essential. The server uses a generative model to provide personalized content recommendations based on emotional data and preference information acquired from the user's terminal. In this process, emotional data is collected from a terminal such as smart glasses, and voice input is received through the terminal's microphone. The hardware used includes smart glasses equipped with a high-resolution camera and a high-sensitivity microphone. This allows for the acquisition of the user's visual and auditory information in real time, which forms the basis for data analysis.

[0198] The server analyzes emotions from visual data using Microsoft® Azure® and Google® Cloud facial recognition APIs, while audio data is processed using the Google Speech-to-Text API. Based on the analyzed emotion data, a generative AI model using TENSORFLOW® operates to select the most suitable content. Furthermore, it uses Spotify and Netflix APIs to stream appropriate music and video content to the user.

[0199] As a concrete example of its use, consider a scenario where a user is wearing smart glasses in their daily life. In this state, if they voice-input, "I'm feeling a bit down today, so I'd like to change my mood," the system will analyze the user's emotional state based on their visual and auditory information and recommend energetic music or an enjoyable movie. It is possible to instantly provide appropriate content by taking into account the user's current emotional state and preferences.

[0200] Examples of prompt statements:

[0201] "Please list movies that users would recommend for when they want to relax."

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The device acquires the user's facial expressions and voice in real time. It collects visual and auditory data using a camera and microphone built into the smart glasses. Input consists of the user's facial image and voice data, which are sent to the server. Output is the transmission of raw data to the server.

[0205] Step 2:

[0206] The server performs sentiment analysis using the acquired visual data. The visual data is analyzed using the Microsoft Azure Face API, and the user's emotional state is output as numerical data. Image processing is performed during this process, and the output is an emotion score.

[0207] Step 3:

[0208] The server analyzes the audio data. It uses the Google Speech-to-Text API to convert speech to text and then analyzes the content using natural language processing. The input is audio data, and the output is text data. The server then processes the text content to identify the user's requests and emotions.

[0209] Step 4:

[0210] The server inputs sentiment data and natural language processing results into a generative AI model. The generative AI model (e.g., using TensorFlow) generates and outputs content best suited to the user's emotional state. This model creates a recommendation list of optimal music and video content based on the prompt text.

[0211] Step 5:

[0212] The server sends the generated content list to the device. It utilizes APIs from Spotify and Netflix to provide content links best suited to the user's mood. The input is a recommended list, and the output is a specific content link.

[0213] Step 6:

[0214] The user selects and views content suggested through their device. They access the content using a transmitted link to view it on their smart glasses. The output improves user satisfaction as content playback begins according to the user's selection.

[0215] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0216] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0217] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0218] [Second Embodiment]

[0219] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0220] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0221] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0222] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0223] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0224] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0225] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0226] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0227] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0228] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0229] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0230] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0231] The system for implementing the present invention operates on a network that includes a server, user terminals, and a platform for centrally managing data from users. Users input their preferences, allergy information, and other personal settings via their terminals, thereby forming a foundation for providing services tailored to the user.

[0232] The server receives the entered user data and uses an advanced generative model to create personalized menus. These menus are designed to suggest products that best suit the user's individual needs, taking into account their preferences and past purchase history.

[0233] Furthermore, when a user makes a request in natural language through their device, that request is sent to the server. The server utilizes a natural language processing engine to understand the content of the request and generate the optimal response. This response is then presented to the user on their device, allowing them to use the service intuitively and effectively.

[0234] The server also analyzes past sales data and inventory information to predict future demand, enabling it to replenish and optimize inventory appropriately. This prevents inventory imbalances and reduces unnecessary losses.

[0235] In addition, the server analyzes market trends in real time and automatically generates promotional activities based on that analysis. These promotions are optimized to match users' purchasing trends, providing an effective marketing strategy.

[0236] Finally, the server manages the entire supply chain data from production to consumption, enhancing quality control and traceability. By maintaining the necessary quality standards, it can provide users with products that guarantee high reliability.

[0237] As a specific example, when a user orders coffee, they pre-set allergy information on a terminal, and the server generates and presents a menu that does not contain the specific allergens based on that information. In this way, the system of the present invention improves the user experience and provides coffee service efficiently and effectively.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The user accesses the device and registers their preferences and allergy information. The device then captures this information and prepares to send it to the server.

[0241] Step 2:

[0242] The server receives user data sent from the terminal. The server uses a generative model to generate personalized menus for the user, taking into account the user's preferences and past purchase history.

[0243] Step 3:

[0244] The server sends the generated menu to the terminal. The terminal displays the received menu in its user interface, allowing the user to select an option.

[0245] Step 4:

[0246] The user selects an item from the menu and places an order. The terminal sends this information to the server, and the order processing is completed.

[0247] Step 5:

[0248] The user inputs questions or requests in natural language via the device. The device then prepares to send that input to the server.

[0249] Step 6:

[0250] The server uses a natural language processing engine to analyze the user's request and generate an appropriate response. The generated response is then sent back to the terminal.

[0251] Step 7:

[0252] The terminal presents the user with a response from the server. The user can then decide on their next action based on the information provided.

[0253] Step 8:

[0254] The server periodically collects and analyzes sales data and inventory information to forecast future demand. This information is used for efficient inventory management and is then provided to terminals.

[0255] Step 9:

[0256] The server analyzes market data, automatically creates customized promotional campaigns, and delivers information to target users through their devices.

[0257] Step 10:

[0258] The server ensures product reliability using quality control and traceability data. This information is provided to the terminal, giving users peace of mind.

[0259] (Example 1)

[0260] Next, we will describe Example 1. 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."

[0261] In modern information systems, optimizing service delivery to meet individual user preferences and needs, as well as efficiently managing inventory and analyzing market trends, is challenging. Furthermore, real-time processing is necessary to respond automatically and quickly to consumer demands. This demands improved user satisfaction and more efficient business operations.

[0262] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0263] In this invention, the server includes means for creating personalized choices for users based on a generation algorithm, means for analyzing sales and inventory data to predict future demand and optimize inventory, and means for processing quality control and tracking information from production to consumption. This enables the provision of customized services for each user, more efficient inventory management, and enhanced quality assurance.

[0264] A "generative algorithm" refers to a set of calculations used to automatically create personalized options based on a user's preferences and purchase history.

[0265] "Natural language input" refers to a method in which users intuitively provide information to a system using everyday language.

[0266] "Sales and inventory data" refers to information about when, where, and how many of a product were sold, as well as how much inventory is currently available.

[0267] "Market trends" refer to trends and changes in consumer purchasing patterns within a specific industry or field.

[0268] "Quality control" refers to activities aimed at ensuring that products and services meet specific standards and expectations.

[0269] "Tracking information" refers to data about the location and status of a product at each stage from production to consumption.

[0270] A "personalized menu" refers to a list of products and services that have been customized to take into account the preferences and requests of a specific user.

[0271] "Inventory optimization" refers to the process of maintaining an appropriate amount of inventory that is neither excessive nor insufficient in relation to demand.

[0272] "Integrating and analyzing in real time" refers to the process of instantly combining and analyzing data obtained from multiple sources.

[0273] In embodiments of this invention, the system operates around a server, a user terminal, and a platform that integrates and manages data.

[0274] When the server receives data sent from the user, it uses a generative AI model to create personalized choices and menus. This AI model is generated based on the user's preferences and past behavior history. The generated menus aim to provide different suggestions for each user, presenting products and services best suited to each individual's needs. The specific technologies used in this process include natural language processing engines and data analysis algorithms.

[0275] In addition, the server has the ability to continuously analyze sales and inventory data to predict future demand. This enables data-driven management to prevent inventory imbalances and optimize supply. The server also monitors market trends and automatically generates personalized sales promotion strategies based on consumer purchasing trends. These strategies are optimized by the system to support effective marketing activities.

[0276] On the device, users can input requests in natural language. For example, if a user inputs the request "What coffee do you recommend?", the server uses a generative AI model to generate an appropriate response and sends it back to the device. This allows users to interact with the system intuitively and efficiently.

[0277] As a concrete example, when a user orders coffee, they can set and save allergy information in advance. Based on this information, the server generates a menu that does not contain specific allergens and suggests it to the user, providing an environment where they can use the products with peace of mind. An example of a prompt message to the generating AI model is, "Based on the user's preferences and past purchase history, please suggest this week's recommended coffee menu."

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The user inputs personal preferences and allergy information via the terminal. Specifically, the user opens a dedicated application and enters data into an input form where they fill in their name, favorite foods, and allergy information. This data is collected by the terminal and sent to the server. The input data includes information related to preferences and allergies.

[0281] Step 2:

[0282] The server receives the data sent by the user and stores it in the database. Specifically, the received data is decoded in JSON format and the corresponding user profile in the database is updated. This data is then prepared to be input into the generative AI model. As output, updated user profile information is obtained.

[0283] Step 3:

[0284] The server uses the generative AI model to create a personalized menu based on the user's preferences. The previously updated user data is input into the model as a prompt, and the generative AI generates a "menu that suits the user's preferences". Specifically, it outputs a recommended menu list such as "latte, black coffee, caffe mocha".

[0285] Step 4:

[0286] The generated personalized menu is sent from the server to the terminal. The terminal receives this menu information and visually displays it on the application. It is presented in a form that is easy for the user to understand and provided to the user as a recommended menu. As output, a visual menu display in a state where the user can select is obtained.

[0287] Step 5:

[0288] When a user makes a natural language request through their device, that request is sent to the server. Specifically, the user enters a request such as "What are today's recommended dishes?" into a text input field within the app.

[0289] Step 6:

[0290] The server utilizes a natural language processing engine to analyze incoming requests and generate appropriate responses. The input includes natural language requests from the user. Through natural language processing, it understands the user's intent and generates a response such as "This week's recommendation is a latte," which it then outputs. Finally, the response is sent to the terminal, making it available for the user to review.

[0291] (Application Example 1)

[0292] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0293] There is a problem in providing product recommendations quickly and efficiently based on individual preferences and allergy information. Furthermore, there is a need for the automated generation of personalized sales strategies that instantly capture market trends.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes means for creating personalized choices for users based on a generative model, means for customizing product suggestions by utilizing preference and allergy information, and means for analyzing market trends and automatically generating personalized sales promotions. This enables the provision of products that meet the individual needs of users and the automatic generation of effective marketing strategies.

[0296] A "generative model" refers to an algorithm used to create personalized options and suggestions based on user data.

[0297] "Natural language input" refers to questions and requests made by users using everyday language, which serve as the basis for the system to interpret them.

[0298] "Inventory data" refers to information that shows the current inventory status of goods or products, and is used for future demand forecasting and optimization.

[0299] "Market trends" refer to a broad range of data, including consumer preferences, purchasing tendencies, and economic movements, and serve as the basis for planning sales promotion activities.

[0300] "Preference and allergy information" refers to individual data indicating products that users prefer and ingredients they should avoid, and is used to customize personalized recommendations.

[0301] "Quality control and tracking data" refers to data used to guarantee the quality of a product from the time it is manufactured until it reaches the consumer, and to manage its history.

[0302] The system for implementing this invention consists of a user terminal, a central server, and a platform for centrally managing data. Users input personal data, such as individual preferences and allergy information, using a terminal such as a smartphone. This information is immediately transmitted to the server and stored in a database.

[0303] On the server, a Python program runs, using Flask to process user requests. Natural language requests from users are parsed by the Hugging Face Transformers library. The results of this parsing are integrated with user preference data and past purchase data, and data processing is performed using the Pandas library.

[0304] The server further analyzes market trends and inventory information in real time using Apache Kafka. This optimizes product recommendations and automatically generates promotional activities as needed.

[0305] As a specific example, when a user sends a prompt sentence such as "I want a recommendation for a caffe latte without dairy products", the server analyzes based on past purchase data and the prompt sentence, selects products that meet the conditions, and sends an optimal recommendation to the user terminal. Through this series of processes, the system can provide personalized product recommendations to users.

[0306] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0307] Step 1:

[0308] The user uses a smartphone to access the application and enters their preferences and allergy information. The entered information is sent from the terminal to the server. The input here is the user's preferences and allergy information, and the output is the user data recorded on the server. The server saves this information in the database.

[0309] Step 2:

[0310] The user enters a specific product request in natural language. For example, enter a prompt sentence such as "I want a recommendation for a caffe latte without dairy products" and send it from the terminal to the server. The input is the prompt sentence, and the output is the request sent to the server.

[0311] Step 3:

[0312] The server parses the received prompt text using the Hugging Face Transformers library. This parsing converts natural language into a machine-readable format and structures the data to clarify the user's request. The input is the prompt text, and the output is the parsing result. The server stores this as internal processing data.

[0313] Step 4:

[0314] The server program uses Pandas to integrate and process user preference data and past purchase history data based on the analysis results. The input consists of the analysis results and user data, and the output is a dataset for product recommendations. This dataset is used to identify products that match the user's criteria.

[0315] Step 5:

[0316] The server uses Apache Kafka to analyze market trends and inventory information in real time and create necessary promotions. The input is market and inventory data, and the output is the optimal promotion strategy. The server combines this with a proposed dataset.

[0317] Step 6:

[0318] The server uses a generative AI model to generate optimal product suggestions based on the processed data. The input is the dataset obtained in the previous steps, and the output is a customized product list for the user.

[0319] Step 7:

[0320] The terminal receives a customized product list from the server and displays it to the user. The user can then select products based on this list. The input is the product list sent from the server, and the output is the suggestions displayed on the terminal's screen.

[0321] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0322] The system for implementing the present invention operates on a network including a server, a user terminal, and an emotion engine. Through the terminal, the user can input information about their preferences, allergies, and emotions. The input data is transmitted from the terminal to the server, forming the basis for providing personalized menu services.

[0323] The emotion engine recognizes the user's emotions from data such as natural language input, facial expressions, and voice. The server uses the emotion data analyzed by the emotion engine to provide choices that match the user's current emotional state. This process is designed to suggest products that the user will find most appealing using a generative model.

[0324] Specifically, the server analyzes emotional data received from the user and suggests relaxing products if the user is feeling stressed, or sweets or special seasonal items if the user is in a mood to have fun. This intelligent menu selection enables a more personalized customer experience.

[0325] Furthermore, when a user enters a question or request in natural language into their device, that data is sent to the server, which uses an emotion engine to analyze the emotion behind the request. The server then generates a response that matches the emotional state, enabling the user to communicate intuitively and effectively.

[0326] By analyzing market trends and inventory data in combination with sentiment information, the server automatically generates promotional campaigns and delivers content that resonates most with users' emotions. Furthermore, the server leverages quality control and traceability functions to ensure product reliability throughout the supply chain, providing peace of mind.

[0327] As an example of this system, if a user inputs a feeling such as "I'm tired today" through their terminal, the server uses an emotion engine to analyze that information and suggests things like a low-caffeine relaxing tea or a calming aroma to the user. In this way, the system of the present invention provides users with a more personal and satisfying experience.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] The user uses the device to input their preferences, allergy information, and current emotions using natural language or a selection of options. The device then prepares to send this information to the server.

[0331] Step 2:

[0332] The server receives information sent from the terminal. The server uses an emotion engine to analyze the input natural language or emotion data and identify the user's emotional state.

[0333] Step 3:

[0334] The server uses a generative model to generate an optimized product menu based on the user's emotional state and personal information. For example, if the user is identified as seeking relaxation, the server will prioritize selecting products with relaxing effects.

[0335] Step 4:

[0336] The server generates a personalized menu and sends it to the terminal. The terminal displays the received menu in its user interface, allowing the user to make a selection.

[0337] Step 5:

[0338] The user selects an item from the displayed menu and confirms the order. The terminal then sends this order information to the server.

[0339] Step 6:

[0340] The user enters questions or additional requests in natural language using their device. The device then sends this request data to the server.

[0341] Step 7:

[0342] The server then uses the emotion engine again to analyze the user's emotional state from their request and select an appropriate response. This response will be tailored to the user's emotions.

[0343] Step 8:

[0344] The server sends the parsed response to the terminal, which displays it in the user interface. The user then uses this information to decide on their next action.

[0345] Step 9:

[0346] The server integrates and analyzes accumulated emotional data, sales data, and market trends to automatically generate targeted promotional campaigns. This allows for optimal suggestions to users and improves customer satisfaction.

[0347] Step 10:

[0348] The server ensures quality control and traceability throughout all processes, maintaining the reliability of products and services. This provides users with peace of mind through their devices.

[0349] (Example 2)

[0350] Next, we will describe Example 2. 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".

[0351] In today's digital marketplace, there is a demand for personalized products or services that are tailored to users' preferences and emotions. However, traditional systems have struggled to adequately analyze user emotions and make accurate product recommendations and sales promotions based on them. Furthermore, there has been a lack of systems that enable quality control and reliable tracking to ensure user trust. As a result, there has been a challenge in adequately increasing user satisfaction.

[0352] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0353] In this invention, the server includes means for analyzing the user's emotional state based on a generative model and suggesting personalized products or services; means for analyzing market trends and inventory data and automatically generating sales promotions that correspond to the user's emotional state; and means for ensuring reliability using quality control and tracking data from production to consumption. This makes it possible not only to provide highly accurate product suggestions and appropriate sales promotions based on the user's emotions, but also to enhance the reliability of the product.

[0354] A "generative model" is an artificial intelligence algorithm used to suggest the most suitable products and services based on user information and circumstances.

[0355] "Emotional state" refers to data that indicates the user's mental and emotional condition, and is obtained from natural language, voice, facial expressions, etc.

[0356] "Proposing products or services" means presenting a selection of products or services chosen according to the user's preferences and feelings.

[0357] "Market trends" refer to information about current and future market changes, including trends in consumer preferences and demand.

[0358] "Sales promotion" refers to marketing activities conducted to expand the sales channels for a product and increase sales.

[0359] "Quality control" refers to management activities aimed at ensuring that products and services meet certain quality standards.

[0360] "Tracking data" refers to information used to record and track the process of a product from its production to its consumption.

[0361] The system for implementing this invention consists of a network comprising a server, a user terminal, and an emotion analysis engine. The terminal receives input from the user and can input preferences, allergy information, and even emotional information via natural language. Specifically, the terminal is equipped with a camera and microphone, capable of acquiring facial and voice data and transmitting it to the server.

[0362] Based on the received data, the server uses specific software called an emotion analysis engine to analyze the user's emotional state. This emotion analysis engine utilizes natural language processing technology and machine learning models to analyze the user's text, facial expressions, and voice to determine their emotions. The server then uses this analysis result to suggest the most suitable products and services to the user using a generative AI model. Specifically, the generative AI model suggests products with relaxing effects, sweets, and seasonal items.

[0363] Furthermore, the server analyzes market trends and inventory information in real time based on the user's emotional state and automatically generates promotional campaigns. In addition, product traceability and quality control functions guarantee product reliability and provide users with peace of mind.

[0364] As a concrete example, consider a scenario where a user inputs the emotion "I'm tired today" through their device. The server uses an emotion analysis engine to analyze this information and suggests a low-caffeine relaxing tea or a calming aroma to the user. An example of a prompt might be natural language input such as, "I'm feeling stressed today. I'm looking for something to help me relax. Do you have any recommendations?"

[0365] This makes it possible to provide users with a more personal and satisfying experience.

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] Users input preferences, allergy information, and emotional information in natural language via the device. This input is done using the device's touchscreen, keyboard, camera, or microphone. The input data is collected by the device as text, image data, and audio data.

[0369] Step 2:

[0370] The device sends text, image, and audio data obtained from the user to the server. The data is encrypted and sent securely to the server via the internet. The server receives this data and stores it in a database.

[0371] Step 3:

[0372] The server analyzes the received data using an emotion analysis engine. Text data is analyzed using natural language processing techniques, facial expressions are recognized from image data, and emotions are analyzed from audio data using speech recognition. This process determines emotional states such as "stress" and "happiness."

[0373] Step 4:

[0374] Using the results of the emotion analysis engine, the server generates the optimal product or service using a generative AI model. If stress is detected, the server generates a list of products with relaxing effects. In this process, the AI ​​refers to a vast product database and makes suggestions that match the criteria.

[0375] Step 5:

[0376] The server creates actionable suggestions and sends them to the user's device as a notification. The device then displays the suggested content on the user's screen. For example, suggestions for relaxing tea or aromatherapy candles might be displayed as text and images.

[0377] Step 6:

[0378] The server simultaneously generates emotionally relevant sales promotion content based on market trends and inventory information, and presents it to the user as additional information. The automatic inclusion of promotional campaigns in the suggestions further stimulates the user's purchasing intent.

[0379] Through these steps, the system aims to provide users with a personalized experience and improve their satisfaction.

[0380] (Application Example 2)

[0381] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0382] Modern users have diverse preferences and emotional states, and there is a demand for personalized products and services tailored to these needs. However, conventional systems have struggled to provide real-time content recommendations based on emotions, and have failed to adequately enhance user satisfaction. Furthermore, there have been problems such as insufficient emotion analysis using visual and auditory data, and the inability to respond immediately.

[0383] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0384] In this invention, the server includes means for creating personalized choices for the user based on a generative model, means for analyzing the user's emotional data and recommending optimal content in real time, and means for coordinating with a device for acquiring visual and auditory information and performing emotional analysis. This enables real-time content recommendations tailored to the user's emotional state, thereby improving the personalized user experience.

[0385] A "generative model" is a mathematical or computer programmatic model used to generate personalized choices based on each user's preferences and emotional data.

[0386] "Personalized choices for users" refers to the provision of products and services that are customized based on the individual needs and emotional state of the user.

[0387] "Natural language input" refers to data in a format that is directly entered using the language that humans use on a daily basis.

[0388] "Real-time recommendations" is a process that instantly presents content and options based on the user's current state and emotions.

[0389] "Emotional data" refers to data related to a user's current psychological or emotional state, which is analyzed from information such as facial expressions and voice.

[0390] "Visual and auditory information" refers to data related to the user's visual and auditory aspects, such as facial expressions, voice, and words, which is used for emotion analysis.

[0391] "Content recommendation" is a process that suggests appropriate movies, music, and other multimedia based on the user's preferences and emotional state.

[0392] "Emotional analysis" is a technical method that analyzes collected visual and auditory data to identify the user's emotional state.

[0393] To realize this invention, the following configuration is essential. The server uses a generative model to provide personalized content recommendations based on emotional data and preference information acquired from the user's terminal. In this process, emotional data is collected from a terminal such as smart glasses, and voice input is received through the terminal's microphone. The hardware used includes smart glasses equipped with a high-resolution camera and a high-sensitivity microphone. This allows for the acquisition of the user's visual and auditory information in real time, which forms the basis for data analysis.

[0394] The server analyzes emotions from visual data using Microsoft Azure and Google Cloud facial recognition APIs, while audio data is processed using the Google Speech-to-Text API. Based on the analyzed emotion data, a generative AI model using TensorFlow operates to select the most suitable content. Furthermore, it uses Spotify and Netflix APIs to stream appropriate music and video content to the user.

[0395] As a concrete example of its use, consider a scenario where a user is wearing smart glasses in their daily life. In this state, if they voice-input, "I'm feeling a bit down today, so I'd like to change my mood," the system will analyze the user's emotional state based on their visual and auditory information and recommend energetic music or an enjoyable movie. It is possible to instantly provide appropriate content by taking into account the user's current emotional state and preferences.

[0396] Examples of prompt statements:

[0397] "Please list movies that users would recommend for when they want to relax."

[0398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0399] Step 1:

[0400] The device acquires the user's facial expressions and voice in real time. It collects visual and auditory data using a camera and microphone built into the smart glasses. Input consists of the user's facial image and voice data, which are sent to the server. Output is the transmission of raw data to the server.

[0401] Step 2:

[0402] The server performs sentiment analysis using the acquired visual data. The visual data is analyzed using the Microsoft Azure Face API, and the user's emotional state is output as numerical data. Image processing is performed during this process, and the output is an emotion score.

[0403] Step 3:

[0404] The server analyzes the audio data. It uses the Google Speech-to-Text API to convert speech to text and then analyzes the content using natural language processing. The input is audio data, and the output is text data. The server then processes the text content to identify the user's requests and emotions.

[0405] Step 4:

[0406] The server inputs sentiment data and natural language processing results into a generative AI model. The generative AI model (e.g., using TensorFlow) generates and outputs content best suited to the user's emotional state. This model creates a recommendation list of optimal music and video content based on the prompt text.

[0407] Step 5:

[0408] The server sends the generated content list to the device. It utilizes APIs from Spotify and Netflix to provide content links best suited to the user's mood. The input is a recommended list, and the output is a specific content link.

[0409] Step 6:

[0410] The user selects and views content suggested through their device. They access the content using a transmitted link to view it on their smart glasses. The output improves user satisfaction as content playback begins according to the user's selection.

[0411] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0412] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0413] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0417] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0418] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0419] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0420] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0421] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0422] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0423] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0424] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0425] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0426] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0427] The system for implementing the present invention operates on a network that includes a server, user terminals, and a platform for centrally managing data from users. Users input their preferences, allergy information, and other personal settings via their terminals, thereby forming a foundation for providing services tailored to the user.

[0428] The server receives the entered user data and uses an advanced generative model to create personalized menus. These menus are designed to suggest products that best suit the user's individual needs, taking into account their preferences and past purchase history.

[0429] Furthermore, when a user makes a request in natural language through their device, that request is sent to the server. The server utilizes a natural language processing engine to understand the content of the request and generate the optimal response. This response is then presented to the user on their device, allowing them to use the service intuitively and effectively.

[0430] The server also analyzes past sales data and inventory information to predict future demand, enabling it to replenish and optimize inventory appropriately. This prevents inventory imbalances and reduces unnecessary losses.

[0431] In addition, the server analyzes market trends in real time and automatically generates promotional activities based on that analysis. These promotions are optimized to match users' purchasing trends, providing an effective marketing strategy.

[0432] Finally, the server manages the entire supply chain data from production to consumption, enhancing quality control and traceability. By maintaining the necessary quality standards, it can provide users with products that guarantee high reliability.

[0433] As a specific example, when a user orders coffee, they pre-set allergy information on a terminal, and the server generates and presents a menu that does not contain the specific allergens based on that information. In this way, the system of the present invention improves the user experience and provides coffee service efficiently and effectively.

[0434] The following describes the processing flow.

[0435] Step 1:

[0436] The user accesses the device and registers their preferences and allergy information. The device then captures this information and prepares to send it to the server.

[0437] Step 2:

[0438] The server receives user data sent from the terminal. The server uses a generative model to generate personalized menus for the user, taking into account the user's preferences and past purchase history.

[0439] Step 3:

[0440] The server sends the generated menu to the terminal. The terminal displays the received menu in its user interface, allowing the user to select an option.

[0441] Step 4:

[0442] The user selects an item from the menu and places an order. The terminal sends this information to the server, and the order processing is completed.

[0443] Step 5:

[0444] The user inputs questions or requests in natural language via the device. The device then prepares to send that input to the server.

[0445] Step 6:

[0446] The server uses a natural language processing engine to analyze the user's request and generate an appropriate response. The generated response is then sent back to the terminal.

[0447] Step 7:

[0448] The terminal presents the user with a response from the server. The user can then decide on their next action based on the information provided.

[0449] Step 8:

[0450] The server periodically collects and analyzes sales data and inventory information to forecast future demand. This information is used for efficient inventory management and is then provided to terminals.

[0451] Step 9:

[0452] The server analyzes market data, automatically creates customized promotional campaigns, and delivers information to target users through their devices.

[0453] Step 10:

[0454] The server ensures product reliability using quality control and traceability data. This information is provided to the terminal, giving users peace of mind.

[0455] (Example 1)

[0456] Next, we will describe Example 1. 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."

[0457] In modern information systems, optimizing service delivery to meet individual user preferences and needs, as well as efficiently managing inventory and analyzing market trends, is challenging. Furthermore, real-time processing is necessary to respond automatically and quickly to consumer demands. This demands improved user satisfaction and more efficient business operations.

[0458] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0459] In this invention, the server includes means for creating personalized choices for users based on a generation algorithm, means for analyzing sales and inventory data to predict future demand and optimize inventory, and means for processing quality control and tracking information from production to consumption. This enables the provision of customized services for each user, more efficient inventory management, and enhanced quality assurance.

[0460] A "generative algorithm" refers to a set of calculations used to automatically create personalized options based on a user's preferences and purchase history.

[0461] "Natural language input" refers to a method in which users intuitively provide information to a system using everyday language.

[0462] "Sales and inventory data" refers to information about when, where, and how many of a product were sold, as well as how much inventory is currently available.

[0463] "Market trends" refer to trends and changes in consumer purchasing patterns within a specific industry or field.

[0464] "Quality control" refers to activities aimed at ensuring that products and services meet specific standards and expectations.

[0465] "Tracking information" refers to data about the location and status of a product at each stage from production to consumption.

[0466] A "personalized menu" refers to a list of products and services that have been customized to take into account the preferences and requests of a specific user.

[0467] "Inventory optimization" refers to the process of maintaining an appropriate amount of inventory that is neither excessive nor insufficient in relation to demand.

[0468] "Integrating and analyzing in real time" refers to the process of instantly combining and analyzing data obtained from multiple sources.

[0469] In embodiments of this invention, the system operates around a server, a user terminal, and a platform that integrates and manages data.

[0470] When the server receives data sent from the user, it uses a generative AI model to create personalized choices and menus. This AI model is generated based on the user's preferences and past behavior history. The generated menus aim to provide different suggestions for each user, presenting products and services best suited to each individual's needs. The specific technologies used in this process include natural language processing engines and data analysis algorithms.

[0471] In addition, the server has the ability to continuously analyze sales and inventory data to predict future demand. This enables data-driven management to prevent inventory imbalances and optimize supply. The server also monitors market trends and automatically generates personalized sales promotion strategies based on consumer purchasing trends. These strategies are optimized by the system to support effective marketing activities.

[0472] On the device, users can input requests in natural language. For example, if a user inputs the request "What coffee do you recommend?", the server uses a generative AI model to generate an appropriate response and sends it back to the device. This allows users to interact with the system intuitively and efficiently.

[0473] As a concrete example, when a user orders coffee, they can set and save allergy information in advance. Based on this information, the server generates a menu that does not contain specific allergens and suggests it to the user, providing an environment where they can use the products with peace of mind. An example of a prompt message to the generating AI model is, "Based on the user's preferences and past purchase history, please suggest this week's recommended coffee menu."

[0474] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0475] Step 1:

[0476] Users input their personal preferences and allergy information via their device. Specifically, they open a dedicated application and enter data into an input form where they fill in their name, favorite foods, and allergy information. This data is collected by the device and sent to the server. The input data includes information about preferences and allergies.

[0477] Step 2:

[0478] The server receives data sent by the user and stores it in the database. Specifically, it decodes the received data in JSON format and updates the corresponding user profile in the database. This data is then prepared to be input into the generated AI model. The output is the updated user profile information.

[0479] Step 3:

[0480] The server uses a generative AI model to create personalized menus based on user preferences. The model is prompted with the recently updated user data, and the generative AI generates a menu that "matches the user's preferences." Specifically, it outputs a list of recommended menu items such as "latte, black coffee, and cafe mocha."

[0481] Step 4:

[0482] The generated personalized menu is sent from the server to the terminal. The terminal receives this menu information and displays it visually within the application. It is presented in a user-friendly format and offered to the user as a recommended menu. The output is a visual menu display that the user can select from.

[0483] Step 5:

[0484] When a user makes a natural language request through their device, that request is sent to the server. Specifically, the user enters a request such as "What are today's recommended dishes?" into a text input field within the app.

[0485] Step 6:

[0486] The server utilizes a natural language processing engine to analyze incoming requests and generate appropriate responses. The input includes natural language requests from the user. Through natural language processing, it understands the user's intent and generates a response such as "This week's recommendation is a latte," which it then outputs. Finally, the response is sent to the terminal, making it available for the user to review.

[0487] (Application Example 1)

[0488] Next, we will explain Application Example 1. In the following explanation, 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."

[0489] There is a problem in providing product recommendations quickly and efficiently based on individual preferences and allergy information. Furthermore, there is a need for the automated generation of personalized sales strategies that instantly capture market trends.

[0490] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0491] In this invention, the server includes means for creating personalized choices for users based on a generative model, means for customizing product suggestions by utilizing preference and allergy information, and means for analyzing market trends and automatically generating personalized sales promotions. This enables the provision of products that meet the individual needs of users and the automatic generation of effective marketing strategies.

[0492] A "generative model" refers to an algorithm used to create personalized options and suggestions based on user data.

[0493] "Natural language input" refers to questions and requests made by users using everyday language, which serve as the basis for the system to interpret them.

[0494] "Inventory data" refers to information that shows the current inventory status of goods or products, and is used for future demand forecasting and optimization.

[0495] "Market trends" refer to a broad range of data, including consumer preferences, purchasing tendencies, and economic movements, and serve as the basis for planning sales promotion activities.

[0496] "Preference and allergy information" refers to individual data indicating products that users prefer and ingredients they should avoid, and is used to customize personalized recommendations.

[0497] "Quality control and tracking data" refers to data used to guarantee the quality of a product from the time it is manufactured until it reaches the consumer, and to manage its history.

[0498] The system for implementing this invention consists of a user terminal, a central server, and a platform for centrally managing data. Users input personal data, such as individual preferences and allergy information, using a terminal such as a smartphone. This information is immediately transmitted to the server and stored in a database.

[0499] On the server, a Python program runs, using Flask to process user requests. Natural language requests from users are parsed by the Hugging Face Transformers library. The results of this parsing are integrated with user preference data and past purchase data, and data processing is performed using the Pandas library.

[0500] The server further analyzes market trends and inventory information in real time using Apache Kafka. This optimizes product recommendations and automatically generates promotional activities as needed.

[0501] For example, if a user sends a prompt message such as "I'd like recommendations for a dairy-free café au lait," the server analyzes past purchase data and the prompt message, selects products that meet the criteria, and sends the most suitable suggestion to the user's terminal. Through this series of processes, the system can provide personalized product suggestions to the user.

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] Users access the application using their smartphones and enter their preferences and allergy information. This information is sent from the device to the server. The input here consists of the user's preferences and allergy information, while the output is user data recorded on the server. The server stores this information in a database.

[0505] Step 2:

[0506] The user enters a specific product request in natural language. For example, they might enter a prompt message like, "Please recommend a dairy-free café au lait," and send it from their device to the server. The input is the prompt message, and the output is the request sent to the server.

[0507] Step 3:

[0508] The server parses the received prompt text using the Hugging Face Transformers library. This parsing converts natural language into a machine-readable format and structures the data to clarify the user's request. The input is the prompt text, and the output is the parsing result. The server stores this as internal processing data.

[0509] Step 4:

[0510] The server program uses Pandas to integrate and process user preference data and past purchase history data based on the analysis results. The input consists of the analysis results and user data, and the output is a dataset for product recommendations. This dataset is used to identify products that match the user's criteria.

[0511] Step 5:

[0512] The server uses Apache Kafka to analyze market trends and inventory information in real time and create necessary promotions. The input is market and inventory data, and the output is the optimal promotion strategy. The server combines this with a proposed dataset.

[0513] Step 6:

[0514] The server uses a generative AI model to generate optimal product suggestions based on the processed data. The input is the dataset obtained in the previous step, and the output is a customized product list for the user.

[0515] Step 7:

[0516] The terminal receives a customized product list from the server and displays it to the user. The user can then select products based on this list. The input is the product list sent from the server, and the output is the suggestions displayed on the terminal's screen.

[0517] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0518] The system for implementing the present invention operates on a network including a server, a user terminal, and an emotion engine. Through the terminal, the user can input information about their preferences, allergies, and emotions. The input data is transmitted from the terminal to the server, forming the basis for providing personalized menu services.

[0519] The emotion engine recognizes the user's emotions from data such as natural language input, facial expressions, and voice. The server uses the emotion data analyzed by the emotion engine to provide choices that match the user's current emotional state. This process is designed to suggest products that the user will find most appealing using a generative model.

[0520] Specifically, the server analyzes emotional data received from the user and suggests relaxing products if the user is feeling stressed, or sweets or special seasonal items if the user is in a mood to have fun. This intelligent menu selection enables a more personalized customer experience.

[0521] Furthermore, when a user enters a question or request in natural language into their device, that data is sent to the server, which uses an emotion engine to analyze the emotion behind the request. The server then generates a response that matches the emotional state, enabling the user to communicate intuitively and effectively.

[0522] By analyzing market trends and inventory data in combination with sentiment information, the server automatically generates promotional campaigns and delivers content that resonates most with users' emotions. Furthermore, the server leverages quality control and traceability functions to ensure product reliability throughout the supply chain, providing peace of mind.

[0523] As an example of this system, if a user inputs a feeling such as "I'm tired today" through their terminal, the server uses an emotion engine to analyze that information and suggests things like a low-caffeine relaxing tea or a calming aroma to the user. In this way, the system of the present invention provides users with a more personal and satisfying experience.

[0524] The following describes the processing flow.

[0525] Step 1:

[0526] The user uses the device to input their preferences, allergy information, and current emotions using natural language or a selection of options. The device then prepares to send this information to the server.

[0527] Step 2:

[0528] The server receives information sent from the terminal. The server uses an emotion engine to analyze the input natural language or emotion data and identify the user's emotional state.

[0529] Step 3:

[0530] The server uses a generative model to generate an optimized product menu based on the user's emotional state and personal information. For example, if the user is identified as seeking relaxation, the server will prioritize selecting products with relaxing effects.

[0531] Step 4:

[0532] The server generates a personalized menu and sends it to the terminal. The terminal displays the received menu in its user interface, allowing the user to make a selection.

[0533] Step 5:

[0534] The user selects an item from the displayed menu and confirms the order. The terminal then sends this order information to the server.

[0535] Step 6:

[0536] The user enters questions or additional requests in natural language using their device. The device then sends this request data to the server.

[0537] Step 7:

[0538] The server then uses the emotion engine again to analyze the user's emotional state from their request and select an appropriate response. This response will be tailored to the user's emotions.

[0539] Step 8:

[0540] The server sends the parsed response to the terminal, which displays it in the user interface. The user then uses this information to decide on their next action.

[0541] Step 9:

[0542] The server integrates and analyzes accumulated emotional data, sales data, and market trends to automatically generate targeted promotional campaigns. This allows for optimal suggestions to users and improves customer satisfaction.

[0543] Step 10:

[0544] The server ensures quality control and traceability throughout all processes, maintaining the reliability of products and services. This provides users with peace of mind through their terminals.

[0545] (Example 2)

[0546] Next, we will describe Example 2. 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."

[0547] In today's digital marketplace, there is a demand for personalized products or services that are tailored to users' preferences and emotions. However, traditional systems have struggled to adequately analyze user emotions and make accurate product recommendations and sales promotions based on them. Furthermore, there has been a lack of systems that enable quality control and reliable tracking to ensure user trust. As a result, there has been a challenge in adequately increasing user satisfaction.

[0548] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0549] In this invention, the server includes means for analyzing the user's emotional state based on a generative model and suggesting personalized products or services; means for analyzing market trends and inventory data and automatically generating sales promotions that correspond to the user's emotional state; and means for ensuring reliability using quality control and tracking data from production to consumption. This makes it possible not only to provide highly accurate product suggestions and appropriate sales promotions based on the user's emotions, but also to enhance the reliability of the product.

[0550] A "generative model" is an artificial intelligence algorithm used to suggest the most suitable products and services based on user information and circumstances.

[0551] "Emotional state" refers to data that indicates the user's mental and emotional condition, and is obtained from natural language, voice, facial expressions, etc.

[0552] "Proposing products or services" means presenting a selection of products or services chosen according to the user's preferences and feelings.

[0553] "Market trends" refer to information about current and future market changes, including trends in consumer preferences and demand.

[0554] "Sales promotion" refers to marketing activities conducted to expand the sales channels for a product and increase sales.

[0555] "Quality control" refers to management activities aimed at ensuring that products and services meet certain quality standards.

[0556] "Tracking data" refers to information used to record and track the process of a product from its production to its consumption.

[0557] The system for implementing this invention consists of a network comprising a server, a user terminal, and an emotion analysis engine. The terminal receives input from the user and can input preferences, allergy information, and even emotional information via natural language. Specifically, the terminal is equipped with a camera and microphone, capable of acquiring facial and voice data and transmitting it to the server.

[0558] Based on the received data, the server uses specific software called an emotion analysis engine to analyze the user's emotional state. This emotion analysis engine utilizes natural language processing technology and machine learning models to analyze the user's text, facial expressions, and voice to determine their emotions. The server then uses this analysis result to suggest the most suitable products and services to the user using a generative AI model. Specifically, the generative AI model suggests products with relaxing effects, sweets, and seasonal items.

[0559] Furthermore, the server analyzes market trends and inventory information in real time based on the user's emotional state and automatically generates promotional campaigns. In addition, product traceability and quality control functions guarantee product reliability and provide users with peace of mind.

[0560] As a concrete example, consider a scenario where a user inputs the emotion "I'm tired today" through their device. The server uses an emotion analysis engine to analyze this information and suggests a low-caffeine relaxing tea or a calming aroma to the user. An example of a prompt might be natural language input such as, "I'm feeling stressed today. I'm looking for something to help me relax. Do you have any recommendations?"

[0561] This makes it possible to provide users with a more personal and satisfying experience.

[0562] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0563] Step 1:

[0564] Users input preferences, allergy information, and emotional information in natural language via the device. This input is done using the device's touchscreen, keyboard, camera, or microphone. The input data is collected by the device as text, image data, and audio data.

[0565] Step 2:

[0566] The device sends text, image, and audio data obtained from the user to the server. The data is encrypted and sent securely to the server via the internet. The server receives this data and stores it in a database.

[0567] Step 3:

[0568] The server analyzes the received data using an emotion analysis engine. Text data is analyzed using natural language processing techniques, facial expressions are recognized from image data, and emotions are analyzed from audio data using speech recognition. This process determines emotional states such as "stress" and "happiness."

[0569] Step 4:

[0570] Using the results of the emotion analysis engine, the server generates the optimal product or service using a generative AI model. If stress is detected, the server generates a list of products with relaxing effects. In this process, the AI ​​refers to a vast product database and makes suggestions that match the criteria.

[0571] Step 5:

[0572] The server creates actionable suggestions and sends them to the user's device as a notification. The device then displays the suggested content on the user's screen. For example, suggestions for relaxing tea or aromatherapy candles might be displayed as text and images.

[0573] Step 6:

[0574] The server simultaneously generates emotionally relevant sales promotion content based on market trends and inventory information, and presents it to the user as additional information. The automatic inclusion of promotional campaigns in the suggestions further stimulates the user's purchasing intent.

[0575] Through these steps, the system aims to provide users with a personalized experience and improve their satisfaction.

[0576] (Application Example 2)

[0577] Next, we will explain application example 2. In the following explanation, 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."

[0578] Modern users have diverse preferences and emotional states, and there is a demand for personalized products and services tailored to these needs. However, conventional systems have struggled to provide real-time content recommendations based on emotions, and have failed to adequately enhance user satisfaction. Furthermore, there have been problems such as insufficient emotion analysis using visual and auditory data, and the inability to respond immediately.

[0579] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0580] In this invention, the server includes means for creating personalized choices for the user based on a generative model, means for analyzing the user's emotional data and recommending optimal content in real time, and means for coordinating with a device for acquiring visual and auditory information and performing emotional analysis. This enables real-time content recommendations tailored to the user's emotional state, thereby improving the personalized user experience.

[0581] A "generative model" is a mathematical or computer programmatic model used to generate personalized choices based on each user's preferences and emotional data.

[0582] "Personalized choices for users" refers to the provision of products and services that are customized based on the individual needs and emotional state of the user.

[0583] "Natural language input" refers to data in a format that is directly entered using the language that humans use on a daily basis.

[0584] "Real-time recommendations" is a process that instantly presents content and options based on the user's current state and emotions.

[0585] "Emotional data" refers to data related to a user's current psychological or emotional state, which is analyzed from information such as facial expressions and voice.

[0586] "Visual and auditory information" refers to data related to the user's visual and auditory aspects, such as facial expressions, voice, and words, which is used for emotion analysis.

[0587] "Content recommendation" is a process that suggests appropriate movies, music, and other multimedia based on the user's preferences and emotional state.

[0588] "Emotional analysis" is a technical method that analyzes collected visual and auditory data to identify the user's emotional state.

[0589] To realize this invention, the following configuration is essential. The server uses a generative model to provide personalized content recommendations based on emotional data and preference information acquired from the user's terminal. In this process, emotional data is collected from a terminal such as smart glasses, and voice input is received through the terminal's microphone. The hardware used includes smart glasses equipped with a high-resolution camera and a high-sensitivity microphone. This allows for the acquisition of the user's visual and auditory information in real time, which forms the basis for data analysis.

[0590] The server analyzes emotions from visual data using Microsoft Azure and Google Cloud facial recognition APIs, while audio data is processed using the Google Speech-to-Text API. Based on the analyzed emotion data, a generative AI model using TensorFlow operates to select the most suitable content. Furthermore, it uses Spotify and Netflix APIs to stream appropriate music and video content to the user.

[0591] As a concrete example of its use, consider a scenario where a user is wearing smart glasses in their daily life. In this state, if they voice-input, "I'm feeling a bit down today, so I'd like to change my mood," the system will analyze the user's emotional state based on their visual and auditory information and recommend energetic music or an enjoyable movie. It is possible to instantly provide appropriate content by taking into account the user's current emotional state and preferences.

[0592] Examples of prompt statements:

[0593] "Please list movies that users would recommend for when they want to relax."

[0594] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0595] Step 1:

[0596] The device acquires the user's facial expressions and voice in real time. It collects visual and auditory data using a camera and microphone built into the smart glasses. Input consists of the user's facial image and voice data, which are sent to the server. Output is the transmission of raw data to the server.

[0597] Step 2:

[0598] The server performs sentiment analysis using the acquired visual data. The visual data is analyzed using the Microsoft Azure Face API, and the user's emotional state is output as numerical data. Image processing is performed during this process, and the output is an emotion score.

[0599] Step 3:

[0600] The server analyzes the audio data. It uses the Google Speech-to-Text API to convert speech to text and then analyzes the content using natural language processing. The input is audio data, and the output is text data. The server then processes the text content to identify the user's requests and emotions.

[0601] Step 4:

[0602] The server inputs sentiment data and natural language processing results into a generative AI model. The generative AI model (e.g., using TensorFlow) generates and outputs content best suited to the user's emotional state. This model creates a recommendation list of optimal music and video content based on the prompt text.

[0603] Step 5:

[0604] The server sends the generated content list to the device. It utilizes APIs from Spotify and Netflix to provide content links best suited to the user's mood. The input is a recommended list, and the output is a specific content link.

[0605] Step 6:

[0606] The user selects and views content suggested through their device. They access the content using a transmitted link to view it on their smart glasses. The output improves user satisfaction as content playback begins according to the user's selection.

[0607] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0608] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0609] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0610] [Fourth Embodiment]

[0611] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0612] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0613] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0614] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0615] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0616] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0617] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0618] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0619] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0620] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0621] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0622] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0623] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0624] The system for implementing the present invention operates on a network that includes a server, user terminals, and a platform for centrally managing data from users. Users input their preferences, allergy information, and other personal settings via their terminals, thereby forming a foundation for providing services tailored to the user.

[0625] The server receives the entered user data and uses an advanced generative model to create personalized menus. These menus are designed to suggest products that best suit the user's individual needs, taking into account their preferences and past purchase history.

[0626] Furthermore, when a user makes a request in natural language through their device, that request is sent to the server. The server utilizes a natural language processing engine to understand the content of the request and generate the optimal response. This response is then presented to the user on their device, allowing them to use the service intuitively and effectively.

[0627] The server also analyzes past sales data and inventory information to predict future demand, enabling it to replenish and optimize inventory appropriately. This prevents inventory imbalances and reduces unnecessary losses.

[0628] In addition, the server analyzes market trends in real time and automatically generates promotional activities based on that analysis. These promotions are optimized to match users' purchasing trends, providing an effective marketing strategy.

[0629] Finally, the server manages the entire supply chain data from production to consumption, enhancing quality control and traceability. By maintaining the necessary quality standards, it can provide users with products that guarantee high reliability.

[0630] As a specific example, when a user orders coffee, they pre-set allergy information on a terminal, and the server generates and presents a menu that does not contain the specific allergens based on that information. In this way, the system of the present invention improves the user experience and provides coffee service efficiently and effectively.

[0631] The following describes the processing flow.

[0632] Step 1:

[0633] The user accesses the device and registers their preferences and allergy information. The device then captures this information and prepares to send it to the server.

[0634] Step 2:

[0635] The server receives user data sent from the terminal. The server uses a generative model to generate personalized menus for the user, taking into account the user's preferences and past purchase history.

[0636] Step 3:

[0637] The server sends the generated menu to the terminal. The terminal displays the received menu in its user interface, allowing the user to select an option.

[0638] Step 4:

[0639] The user selects an item from the menu and places an order. The terminal sends this information to the server, and the order processing is completed.

[0640] Step 5:

[0641] The user inputs questions or requests in natural language via the device. The device then prepares to send that input to the server.

[0642] Step 6:

[0643] The server uses a natural language processing engine to analyze the user's request and generate an appropriate response. The generated response is then sent back to the terminal.

[0644] Step 7:

[0645] The terminal presents the user with a response from the server. The user can then decide on their next action based on the information provided.

[0646] Step 8:

[0647] The server periodically collects and analyzes sales data and inventory information to forecast future demand. This information is used for efficient inventory management and is then provided to terminals.

[0648] Step 9:

[0649] The server analyzes market data, automatically creates customized promotional campaigns, and delivers information to target users through their devices.

[0650] Step 10:

[0651] The server ensures product reliability using quality control and traceability data. This information is provided to the terminal, giving users peace of mind.

[0652] (Example 1)

[0653] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0654] In modern information systems, optimizing service delivery to meet individual user preferences and needs, as well as efficiently managing inventory and analyzing market trends, is challenging. Furthermore, real-time processing is necessary to respond automatically and quickly to consumer demands. This demands improved user satisfaction and more efficient business operations.

[0655] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0656] In this invention, the server includes means for creating personalized choices for users based on a generation algorithm, means for analyzing sales and inventory data to predict future demand and optimize inventory, and means for processing quality control and tracking information from production to consumption. This enables the provision of customized services for each user, more efficient inventory management, and enhanced quality assurance.

[0657] A "generative algorithm" refers to a set of calculations used to automatically create personalized options based on a user's preferences and purchase history.

[0658] "Natural language input" refers to a method in which users intuitively provide information to a system using everyday language.

[0659] "Sales and inventory data" refers to information about when, where, and how many of a product were sold, as well as how much inventory is currently available.

[0660] "Market trends" refer to trends and changes in consumer purchasing patterns within a specific industry or field.

[0661] "Quality control" refers to activities aimed at ensuring that products and services meet specific standards and expectations.

[0662] "Tracking information" refers to data about the location and status of a product at each stage from production to consumption.

[0663] A "personalized menu" refers to a list of products and services that have been customized to take into account the preferences and requests of a specific user.

[0664] "Inventory optimization" refers to the process of maintaining an appropriate amount of inventory that is neither excessive nor insufficient in relation to demand.

[0665] "Integrating and analyzing in real time" refers to the process of instantly combining and analyzing data obtained from multiple sources.

[0666] In embodiments of this invention, the system operates around a server, a user terminal, and a platform that integrates and manages data.

[0667] When the server receives data sent from the user, it uses a generative AI model to create personalized choices and menus. This AI model is generated based on the user's preferences and past behavior history. The generated menus aim to provide different suggestions for each user, presenting products and services best suited to each individual's needs. The specific technologies used in this process include natural language processing engines and data analysis algorithms.

[0668] In addition, the server has the ability to continuously analyze sales and inventory data to predict future demand. This enables data-driven management to prevent inventory imbalances and optimize supply. The server also monitors market trends and automatically generates personalized sales promotion strategies based on consumer purchasing trends. These strategies are optimized by the system to support effective marketing activities.

[0669] On the device, users can input requests in natural language. For example, if a user inputs the request "What coffee do you recommend?", the server uses a generative AI model to generate an appropriate response and sends it back to the device. This allows users to interact with the system intuitively and efficiently.

[0670] As a concrete example, when a user orders coffee, they can set and save allergy information in advance. Based on this information, the server generates a menu that does not contain specific allergens and suggests it to the user, providing an environment where they can use the products with peace of mind. An example of a prompt message to the generating AI model is, "Based on the user's preferences and past purchase history, please suggest this week's recommended coffee menu."

[0671] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0672] Step 1:

[0673] Users input their personal preferences and allergy information via their device. Specifically, they open a dedicated application and enter data into an input form where they fill in their name, favorite foods, and allergy information. This data is collected by the device and sent to the server. The input data includes information about preferences and allergies.

[0674] Step 2:

[0675] The server receives data sent by the user and stores it in the database. Specifically, it decodes the received data in JSON format and updates the corresponding user profile in the database. This data is then prepared to be input into the generated AI model. The output is the updated user profile information.

[0676] Step 3:

[0677] The server uses a generative AI model to create personalized menus based on user preferences. The model is prompted with the recently updated user data, and the generative AI generates a menu that "matches the user's preferences." Specifically, it outputs a list of recommended menu items such as "latte, black coffee, and cafe mocha."

[0678] Step 4:

[0679] The generated personalized menu is sent from the server to the terminal. The terminal receives this menu information and displays it visually within the application. It is presented in a user-friendly format and offered to the user as a recommended menu. The output is a visual menu display that the user can select from.

[0680] Step 5:

[0681] When a user makes a natural language request through their device, that request is sent to the server. Specifically, the user enters a request such as "What are today's recommended dishes?" into a text input field within the app.

[0682] Step 6:

[0683] The server utilizes a natural language processing engine to analyze incoming requests and generate appropriate responses. The input includes natural language requests from the user. Through natural language processing, it understands the user's intent and generates a response such as "This week's recommendation is a latte," which it then outputs. Finally, the response is sent to the terminal, making it available for the user to review.

[0684] (Application Example 1)

[0685] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0686] There is a problem in providing product recommendations quickly and efficiently based on individual preferences and allergy information. Furthermore, there is a need for the automated generation of personalized sales strategies that instantly capture market trends.

[0687] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0688] In this invention, the server includes means for creating personalized choices for users based on a generative model, means for customizing product suggestions by utilizing preference and allergy information, and means for analyzing market trends and automatically generating personalized sales promotions. This enables the provision of products that meet the individual needs of users and the automatic generation of effective marketing strategies.

[0689] A "generative model" refers to an algorithm used to create personalized options and suggestions based on user data.

[0690] "Natural language input" refers to questions and requests made by users using everyday language, which serve as the basis for the system to interpret them.

[0691] "Inventory data" refers to information that shows the current inventory status of goods or products, and is used for future demand forecasting and optimization.

[0692] "Market trends" refer to a broad range of data, including consumer preferences, purchasing tendencies, and economic movements, and serve as the basis for planning sales promotion activities.

[0693] "Preference and allergy information" refers to individual data indicating products that users prefer and ingredients they should avoid, and is used to customize personalized recommendations.

[0694] "Quality control and tracking data" refers to data used to guarantee the quality of a product from the time it is manufactured until it reaches the consumer, and to manage its history.

[0695] The system for implementing this invention consists of a user terminal, a central server, and a platform for centrally managing data. Users input personal data, such as individual preferences and allergy information, using a terminal such as a smartphone. This information is immediately transmitted to the server and stored in a database.

[0696] On the server, a Python program runs, using Flask to process user requests. Natural language requests from users are parsed by the Hugging Face Transformers library. The results of this parsing are integrated with user preference data and past purchase data, and data processing is performed using the Pandas library.

[0697] The server further analyzes market trends and inventory information in real time using Apache Kafka. This optimizes product recommendations and automatically generates promotional activities as needed.

[0698] For example, if a user sends a prompt message such as "I'd like recommendations for a dairy-free café au lait," the server analyzes past purchase data and the prompt message, selects products that meet the criteria, and sends the most suitable suggestion to the user's terminal. Through this series of processes, the system can provide personalized product suggestions to the user.

[0699] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0700] Step 1:

[0701] Users access the application using their smartphones and enter their preferences and allergy information. This information is sent from the device to the server. The input here consists of the user's preferences and allergy information, while the output is user data recorded on the server. The server stores this information in a database.

[0702] Step 2:

[0703] The user enters a specific product request in natural language. For example, they might enter a prompt message like, "Please recommend a dairy-free café au lait," and send it from their device to the server. The input is the prompt message, and the output is the request sent to the server.

[0704] Step 3:

[0705] The server parses the received prompt text using the Hugging Face Transformers library. This parsing converts natural language into a machine-readable format and structures the data to clarify the user's request. The input is the prompt text, and the output is the parsing result. The server stores this as internal processing data.

[0706] Step 4:

[0707] The server program uses Pandas to integrate and process user preference data and past purchase history data based on the analysis results. The input consists of the analysis results and user data, and the output is a dataset for product recommendations. This dataset is used to identify products that match the user's criteria.

[0708] Step 5:

[0709] The server uses Apache Kafka to analyze market trends and inventory information in real time and create necessary promotions. The input is market and inventory data, and the output is the optimal promotion strategy. The server combines this with a proposed dataset.

[0710] Step 6:

[0711] The server uses a generative AI model to generate optimal product suggestions based on the processed data. The input is the dataset obtained in the previous step, and the output is a customized product list for the user.

[0712] Step 7:

[0713] The terminal receives a customized product list from the server and displays it to the user. The user can then select products based on this list. The input is the product list sent from the server, and the output is the suggestions displayed on the terminal's screen.

[0714] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0715] The system for implementing the present invention operates on a network including a server, a user terminal, and an emotion engine. Through the terminal, the user can input information about their preferences, allergies, and emotions. The input data is transmitted from the terminal to the server, forming the basis for providing personalized menu services.

[0716] The emotion engine recognizes the user's emotions from data such as natural language input, facial expressions, and voice. The server uses the emotion data analyzed by the emotion engine to provide choices that match the user's current emotional state. This process is designed to suggest products that the user will find most appealing using a generative model.

[0717] Specifically, the server analyzes emotional data received from the user and suggests relaxing products if the user is feeling stressed, or sweets or special seasonal items if the user is in a mood to have fun. This intelligent menu selection enables a more personalized customer experience.

[0718] Furthermore, when a user enters a question or request in natural language into their device, that data is sent to the server, which uses an emotion engine to analyze the emotion behind the request. The server then generates a response that matches the emotional state, enabling the user to communicate intuitively and effectively.

[0719] By analyzing market trends and inventory data in combination with sentiment information, the server automatically generates promotional campaigns and delivers content that resonates most with users' emotions. Furthermore, the server leverages quality control and traceability functions to ensure product reliability throughout the supply chain, providing peace of mind.

[0720] As an example of this system, if a user inputs a feeling such as "I'm tired today" through their terminal, the server uses an emotion engine to analyze that information and suggests things like a low-caffeine relaxing tea or a calming aroma to the user. In this way, the system of the present invention provides users with a more personal and satisfying experience.

[0721] The following describes the processing flow.

[0722] Step 1:

[0723] The user uses the device to input their preferences, allergy information, and current emotions using natural language or a selection of options. The device then prepares to send this information to the server.

[0724] Step 2:

[0725] The server receives information sent from the terminal. The server uses an emotion engine to analyze the input natural language or emotion data and identify the user's emotional state.

[0726] Step 3:

[0727] The server uses a generative model to generate an optimized product menu based on the user's emotional state and personal information. For example, if the user is identified as seeking relaxation, the server will prioritize selecting products with relaxing effects.

[0728] Step 4:

[0729] The server generates a personalized menu and sends it to the terminal. The terminal displays the received menu in its user interface, allowing the user to make a selection.

[0730] Step 5:

[0731] The user selects an item from the displayed menu and confirms the order. The terminal then sends this order information to the server.

[0732] Step 6:

[0733] The user enters questions or additional requests in natural language using their device. The device then sends this request data to the server.

[0734] Step 7:

[0735] The server then uses the emotion engine again to analyze the user's emotional state from their request and select an appropriate response. This response will be tailored to the user's emotions.

[0736] Step 8:

[0737] The server sends the parsed response to the terminal, which displays it in the user interface. The user then uses this information to decide on their next action.

[0738] Step 9:

[0739] The server integrates and analyzes accumulated emotional data, sales data, and market trends to automatically generate targeted promotional campaigns. This allows for optimal suggestions to users and improves customer satisfaction.

[0740] Step 10:

[0741] The server ensures quality control and traceability throughout all processes, maintaining the reliability of products and services. This provides users with peace of mind through their terminals.

[0742] (Example 2)

[0743] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0744] In today's digital marketplace, there is a demand for personalized products or services that are tailored to users' preferences and emotions. However, traditional systems have struggled to adequately analyze user emotions and make accurate product recommendations and sales promotions based on them. Furthermore, there has been a lack of systems that enable quality control and reliable tracking to ensure user trust. As a result, there has been a challenge in adequately increasing user satisfaction.

[0745] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0746] In this invention, the server includes means for analyzing the user's emotional state based on a generative model and suggesting personalized products or services; means for analyzing market trends and inventory data and automatically generating sales promotions that correspond to the user's emotional state; and means for ensuring reliability using quality control and tracking data from production to consumption. This makes it possible not only to provide highly accurate product suggestions and appropriate sales promotions based on the user's emotions, but also to enhance the reliability of the product.

[0747] A "generative model" is an artificial intelligence algorithm used to suggest the most suitable products and services based on user information and circumstances.

[0748] "Emotional state" refers to data that indicates the user's mental and emotional condition, and is obtained from natural language, voice, facial expressions, etc.

[0749] "Proposing products or services" means presenting a selection of products or services chosen according to the user's preferences and feelings.

[0750] "Market trends" refer to information about current and future market changes, including trends in consumer preferences and demand.

[0751] "Sales promotion" refers to marketing activities conducted to expand the sales channels for a product and increase sales.

[0752] "Quality control" refers to management activities aimed at ensuring that products and services meet certain quality standards.

[0753] "Tracking data" refers to information used to record and track the process of a product from its production to its consumption.

[0754] The system for implementing this invention consists of a network comprising a server, a user terminal, and an emotion analysis engine. The terminal receives input from the user and can input preferences, allergy information, and even emotional information via natural language. Specifically, the terminal is equipped with a camera and microphone, capable of acquiring facial and voice data and transmitting it to the server.

[0755] Based on the received data, the server uses specific software called an emotion analysis engine to analyze the user's emotional state. This emotion analysis engine utilizes natural language processing technology and machine learning models to analyze the user's text, facial expressions, and voice to determine their emotions. The server then uses this analysis result to suggest the most suitable products and services to the user using a generative AI model. Specifically, the generative AI model suggests products with relaxing effects, sweets, and seasonal items.

[0756] Furthermore, the server analyzes market trends and inventory information in real time based on the user's emotional state and automatically generates promotional campaigns. In addition, product traceability and quality control functions guarantee product reliability and provide users with peace of mind.

[0757] As a concrete example, consider a scenario where a user inputs the emotion "I'm tired today" through their device. The server uses an emotion analysis engine to analyze this information and suggests a low-caffeine relaxing tea or a calming aroma to the user. An example of a prompt might be natural language input such as, "I'm feeling stressed today. I'm looking for something to help me relax. Do you have any recommendations?"

[0758] This makes it possible to provide users with a more personal and satisfying experience.

[0759] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0760] Step 1:

[0761] Users input preferences, allergy information, and emotional information in natural language via the device. This input is done using the device's touchscreen, keyboard, camera, or microphone. The input data is collected by the device as text, image data, and audio data.

[0762] Step 2:

[0763] The device sends text, image, and audio data obtained from the user to the server. The data is encrypted and sent securely to the server via the internet. The server receives this data and stores it in a database.

[0764] Step 3:

[0765] The server analyzes the received data using an emotion analysis engine. Text data is analyzed using natural language processing techniques, facial expressions are recognized from image data, and emotions are analyzed from audio data using speech recognition. This process determines emotional states such as "stress" and "happiness."

[0766] Step 4:

[0767] Using the results of the emotion analysis engine, the server generates the optimal product or service using a generative AI model. If stress is detected, the server generates a list of products with relaxing effects. In this process, the AI ​​refers to a vast product database and makes suggestions that match the criteria.

[0768] Step 5:

[0769] The server creates actionable suggestions and sends them to the user's device as a notification. The device then displays the suggested content on the user's screen. For example, suggestions for relaxing tea or aromatherapy candles might be displayed as text and images.

[0770] Step 6:

[0771] The server simultaneously generates emotionally relevant sales promotion content based on market trends and inventory information, and presents it to the user as additional information. The automatic inclusion of promotional campaigns in the suggestions further stimulates the user's purchasing intent.

[0772] Through these steps, the system aims to provide users with a personalized experience and improve their satisfaction.

[0773] (Application Example 2)

[0774] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0775] Modern users have diverse preferences and emotional states, and there is a demand for personalized products and services tailored to these needs. However, conventional systems have struggled to provide real-time content recommendations based on emotions, and have failed to adequately enhance user satisfaction. Furthermore, there have been problems such as insufficient emotion analysis using visual and auditory data, and the inability to respond immediately.

[0776] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0777] In this invention, the server includes means for creating personalized choices for the user based on a generative model, means for analyzing the user's emotional data and recommending optimal content in real time, and means for coordinating with a device for acquiring visual and auditory information and performing emotional analysis. This enables real-time content recommendations tailored to the user's emotional state, thereby improving the personalized user experience.

[0778] A "generative model" is a mathematical or computer programmatic model used to generate personalized choices based on each user's preferences and emotional data.

[0779] "Personalized choices for users" refers to the provision of products and services that are customized based on the individual needs and emotional state of the user.

[0780] "Natural language input" refers to data in a format that is directly entered using the language that humans use on a daily basis.

[0781] "Real-time recommendations" is a process that instantly presents content and options based on the user's current state and emotions.

[0782] "Emotional data" refers to data related to a user's current psychological or emotional state, which is analyzed from information such as facial expressions and voice.

[0783] "Visual and auditory information" refers to data related to the user's visual and auditory aspects, such as facial expressions, voice, and words, which is used for emotion analysis.

[0784] "Content recommendation" is a process that suggests appropriate movies, music, and other multimedia based on the user's preferences and emotional state.

[0785] "Emotional analysis" is a technical method that analyzes collected visual and auditory data to identify the user's emotional state.

[0786] To realize this invention, the following configuration is essential. The server uses a generative model to provide personalized content recommendations based on emotional data and preference information acquired from the user's terminal. In this process, emotional data is collected from a terminal such as smart glasses, and voice input is received through the terminal's microphone. The hardware used includes smart glasses equipped with a high-resolution camera and a high-sensitivity microphone. This allows for the acquisition of the user's visual and auditory information in real time, which forms the basis for data analysis.

[0787] The server analyzes emotions from visual data using Microsoft Azure and Google Cloud facial recognition APIs, while audio data is processed using the Google Speech-to-Text API. Based on the analyzed emotion data, a generative AI model using TensorFlow operates to select the most suitable content. Furthermore, it uses Spotify and Netflix APIs to stream appropriate music and video content to the user.

[0788] As a concrete example of its use, consider a scenario where a user is wearing smart glasses in their daily life. In this state, if they voice-input, "I'm feeling a bit down today, so I'd like to change my mood," the system will analyze the user's emotional state based on their visual and auditory information and recommend energetic music or an enjoyable movie. It is possible to instantly provide appropriate content by taking into account the user's current emotional state and preferences.

[0789] Examples of prompt statements:

[0790] "Please list movies that users would recommend for when they want to relax."

[0791] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0792] Step 1:

[0793] The device acquires the user's facial expressions and voice in real time. It collects visual and auditory data using a camera and microphone built into the smart glasses. Input consists of the user's facial image and voice data, which are sent to the server. Output is the transmission of raw data to the server.

[0794] Step 2:

[0795] The server performs sentiment analysis using the acquired visual data. The visual data is analyzed using the Microsoft Azure Face API, and the user's emotional state is output as numerical data. Image processing is performed during this process, and the output is an emotion score.

[0796] Step 3:

[0797] The server analyzes the audio data. It uses the Google Speech-to-Text API to convert speech to text and then analyzes the content using natural language processing. The input is audio data, and the output is text data. The server then processes the text content to identify the user's requests and emotions.

[0798] Step 4:

[0799] The server inputs sentiment data and natural language processing results into a generative AI model. The generative AI model (e.g., using TensorFlow) generates and outputs content best suited to the user's emotional state. This model creates a recommendation list of optimal music and video content based on the prompt text.

[0800] Step 5:

[0801] The server sends the generated content list to the device. It utilizes APIs from Spotify and Netflix to provide content links best suited to the user's mood. The input is a recommended list, and the output is a specific content link.

[0802] Step 6:

[0803] The user selects and views content suggested through their device. They access the content using a transmitted link to view it on their smart glasses. The output improves user satisfaction as content playback begins according to the user's selection.

[0804] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0805] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0806] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0807] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0808] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0809] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0810] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0811] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0812] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0813] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0814] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0815] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0816] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0817] 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.

[0818] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0819] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0820] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0821] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0822] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0823] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0824] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0825] The following is further disclosed regarding the embodiments described above.

[0826] (Claim 1)

[0827] A means of creating personalized choices for users based on a generative model,

[0828] A means for interpreting natural language input from users and generating appropriate responses,

[0829] A means of analyzing sales and inventory data to predict future demand and optimize inventory,

[0830] A means of analyzing market trends and automatically generating personalized sales promotions,

[0831] Means for processing quality control and tracking data from production to consumption,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, which receives and processes data on user preferences and allergies.

[0835] (Claim 3)

[0836] The system according to claim 1, which integrates and analyzes information from multiple data sources in real time.

[0837] "Example 1"

[0838] (Claim 1)

[0839] A means for creating personalized choices for users based on a generation algorithm,

[0840] A means for interpreting natural language input from users and generating appropriate responses,

[0841] A means of analyzing sales and inventory data to predict future demand and optimize inventory,

[0842] A means of analyzing market trends and automatically generating personalized sales promotions,

[0843] Means for processing quality control and tracking information from production to consumption,

[0844] A means for receiving and processing user data input via a terminal,

[0845] A means of creating and presenting personalized menus based on user preferences using a generation algorithm,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, which receives and processes information regarding the user's preferences and allergies.

[0849] (Claim 3)

[0850] The system according to claim 1, which integrates and analyzes data from multiple sources in real time.

[0851] "Application Example 1"

[0852] (Claim 1)

[0853] A means of creating personalized choices for users based on a generative model,

[0854] A means for interpreting natural language input from users and generating appropriate responses,

[0855] A means of analyzing sales and inventory data to predict future demand and optimize inventory,

[0856] A means of analyzing market trends and automatically generating personalized sales promotions,

[0857] A means of customizing product suggestions by utilizing preference and allergy information,

[0858] Means for processing quality control and tracking data from production to consumption,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, which receives and processes data on user preferences and allergies.

[0862] (Claim 3)

[0863] The system according to claim 1, which integrates and analyzes information from multiple data sources in real time and generates customized product proposals.

[0864] "Example 2 of combining an emotion engine"

[0865] (Claim 1)

[0866] A means of analyzing a user's emotional state based on a generative model and proposing personalized products or services,

[0867] A means for interpreting input from users in the form of natural language, voice, or facial expression data, and generating an appropriate response,

[0868] A means of automatically generating sales promotions that respond to the emotional state of users by analyzing market trends and inventory data,

[0869] Means to guarantee reliability using quality control and tracking data from production to consumption,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, which receives and processes data relating to a user's preferences, allergies, and emotions.

[0873] (Claim 3)

[0874] The system according to claim 1, which integrates and analyzes sentiment information, sales information, and inventory information from multiple data sources in real time.

[0875] "Application example 2 when combining with an emotional engine"

[0876] (Claim 1)

[0877] A means of creating personalized choices for users based on a generative model,

[0878] A means for interpreting natural language input from users and generating appropriate responses,

[0879] A means of analyzing sales and inventory information to predict future demand and optimize inventory,

[0880] A means of analyzing market trends and automatically generating personalized sales promotions,

[0881] Means for processing quality control and tracking information from production to consumption,

[0882] A method for analyzing user sentiment data and recommending optimal content in real time,

[0883] A means for working in conjunction with a device that acquires visual and auditory information and performs emotion analysis,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, which receives and processes information regarding the user's preferences and allergies.

[0887] (Claim 3)

[0888] The system according to claim 1, which integrates and analyzes information from multiple data sources in real time. [Explanation of Symbols]

[0889] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of creating personalized choices for users based on a generative model, A means for interpreting natural language input from users and generating appropriate responses, A means of analyzing sales and inventory data to predict future demand and optimize inventory, A means of analyzing market trends and automatically generating personalized sales promotions, Means for processing quality control and tracking data from production to consumption, A system that includes this.

2. The system according to claim 1, which receives and processes data on user preferences and allergies.

3. The system according to claim 1, which integrates and analyzes information from multiple data sources in real time.

Images