system

Abstract

Provide a system. 【Solution means】 Means for receiving preference information from a user, Means for searching a database for cocktail recipes based on the received preference information, Means for analyzing the search results using a generation model and generating an optimal cocktail recipe, Means for creating visual data and methods for the generated cocktail recipe, Means for generating a name for the cocktail, Means for providing the generated cocktail recipe, visual data, and name to the user, Means for receiving feedback from the user and updating the generation model, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a bartender quickly proposes an original cocktail according to the diverse demands of customers, it is difficult to make an optimal selection from a huge number of recipes, and there is also a problem that the time and labor required to propose a creative cocktail are large.

Means for Solving the Problems

[0005] This invention provides a system for generating optimal cocktail recipes based on user preference information. The system includes means for receiving preference information from the user and means for searching a database for cocktail recipes based on that information. Furthermore, it includes means for analyzing the search results using a generation model to generate the optimal cocktail recipe, and means for generating visual data and methods for that cocktail recipe. In addition, it includes means for generating and providing cocktail names to the user, and means for receiving user feedback and updating the generation model to ensure continuous improvement.

[0006] A "user" is an individual or group that uses the system to request cocktail suggestions.

[0007] "Preference information" refers to information related to the user's preferences and requests, such as the taste and theme of the cocktail, and the type of alcohol.

[0008] A "cocktail recipe" is a detailed description of the ingredients and steps required to create a specific cocktail.

[0009] A "database" is a collection of information that stores various cocktail recipes, ingredient information, and past customer feedback.

[0010] A "generative model" is a machine learning algorithm used to analyze data and suggest new data or solutions based on the input conditions.

[0011] "Visual data" refers to image data generated to visually represent the appearance of a cocktail.

[0012] "Method" refers to the specific steps and techniques involved in creating a cocktail, including the steps of how to make it.

[0013] A "name" is a unique name created to identify and characterize a particular cocktail.

[0014] "Feedback" refers to the evaluations and opinions that users give regarding the suggested cocktails, and this information is used to improve the system. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [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]It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] 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.

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

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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), etc.

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

[0020] In the following embodiments, a numbered 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.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is implemented as a platform that enables cocktail suggestions tailored to the user's preferences throughout the entire system. The details of its form, including program processing and specific examples, are described below.

[0037] The user first uses a terminal to input their specific cocktail preferences. These preferences cover a wide range of details, including the flavor profile, the type of alcohol and ingredients they want to use, and the theme of the cocktail. The terminal sends this information to the server, which then receives the user's request.

[0038] The server searches a database based on the information it receives and collects the relevant cocktail recipes. This database includes past cocktail recipes, ingredient information, and even customer feedback. The server then uses a generative model to analyze the search results and generate the cocktail recipe that best matches the user's preferences.

[0039] The generated recipe consists of visual data and instructions. The server generates image data representing the appearance of the cocktail and provides a video demonstrating how to make it. Furthermore, it generates a unique cocktail name and transmits all of this information to the terminal.

[0040] The terminal presents the received information to the user and completes the cocktail suggestion. When the user provides feedback on the suggestion, the terminal sends that information back to the server. The server uses this feedback to update the generative model and further improve the accuracy of future suggestions.

[0041] For example, if a user requests a "vibrantly-looking cocktail with tropical flavors," the server will create a cocktail called "Tropical Sunset," primarily flavored with mango and coconut, and featuring a blue and orange gradient. The name, recipe, and a video demonstrating the creation process are provided to the user, allowing interested users to enjoy this cocktail.

[0042] Thus, the present invention realizes a cocktail suggestion system that continuously learns and evolves based on information tailored to the user's preferences.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] Users use a terminal to input their cocktail preferences. This includes taste preferences, desired ingredients, and event themes. This helps to specify the user's desired conditions.

[0046] Step 2:

[0047] The terminal transmits the entered preference information to the server. The transmitted data is used as basic information for cocktail suggestions.

[0048] Step 3:

[0049] Based on the received preference information, the server searches its internal cocktail database for relevant recipes. The database contains past recipes, ingredient information, and customer feedback.

[0050] Step 4:

[0051] The server launches a generative model and analyzes the retrieved data. The generative model creates candidate cocktail recipes that best suit the user's preferences and selects the best one from the generated recipes.

[0052] Step 5:

[0053] The server generates visual data (image format) based on the optimal cocktail recipe. This visually represents the appearance of the cocktail, and the preparation steps are created in video format.

[0054] Step 6:

[0055] The server generates a unique name suitable for the cocktail. The generated name reflects the cocktail's characteristics and enhances the overall quality of the suggestion.

[0056] Step 7:

[0057] The server sends the generated cocktail recipe, visual data, name, and video to the terminal.

[0058] Step 8:

[0059] The terminal presents the user with the provided information and suggests cocktails. The user can review these suggestions and, if interested, try making a cocktail based on the recipe.

[0060] Step 9:

[0061] Users enter feedback about the suggested cocktail into the terminal. This feedback may include evaluations of taste and appearance, as well as suggestions for improvement.

[0062] Step 10:

[0063] The device sends the feedback received from the user to the server.

[0064] Step 11:

[0065] The server analyzes the feedback and fine-tunes the generative model. This process improves the accuracy of the system's suggestions, which can be used to improve future cocktail recommendations.

[0066] (Example 1)

[0067] 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."

[0068] Conventional cocktail suggestion systems have difficulty suggesting the optimal cocktail based on the user's preferences, and the recipes and visual information provided often fail to meet user expectations. In particular, there is a need to provide suggestions that reflect individual user preferences while being visual and dynamic.

[0069] 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.

[0070] In this invention, the server includes means for receiving preference information from a user, means for searching for cocktail recipes from an information set based on the received preference information, means for analyzing the search results using a generative model and generating an optimal cocktail recipe that suits the user's preferences, means for generating image data based on the generated cocktail recipe, means for generating a name to identify the cocktail, means for providing the user with the generated cocktail recipe, image data, and name, and means for receiving feedback from the user and updating the generative model to improve its accuracy. This makes it possible to visually and dynamically provide optimal cocktail suggestions that match the user's preferences.

[0071] A "user" is the entity that operates the cocktail suggestion system and provides individual preference information.

[0072] "Preference information" refers to data that shows the individual preferences and requests of users regarding taste and themes.

[0073] An "information collection" is a database containing past cocktail recipes, information on ingredients, and customer feedback.

[0074] A "generative model" is an algorithm that analyzes and optimizes input data to output the optimal cocktail recipe tailored to the user's preferences.

[0075] "Image data" refers to a visual representation created based on the generated cocktail recipe.

[0076] The "name" is a unique designation given to identify the cocktail that is created.

[0077] "Opinions" refer to feedback information from users, including their thoughts and suggestions for improvement regarding the suggested cocktails.

[0078] "Updating to improve accuracy" is a process of incorporating user feedback into the generative model to improve the quality of future suggestions.

[0079] This invention comprises a technology for generating an optimal cocktail based on the user's preferences in a cocktail suggestion system. In embodiments of this invention, the system primarily operates around three elements: a server, a terminal, and a user.

[0080] The user uses a terminal to input information about their desired cocktail, i.e., their preferences. This input includes the flavor profile, the type of alcohol and ingredients they want to use, and the theme of the cocktail. This information is sent to the server via the terminal.

[0081] The server searches a database based on the received preference information. This database contains past cocktail recipes, ingredient information, and customer feedback. The server processes this information and uses a generative AI model to generate a cocktail recipe that best matches the user's preferences. The generative AI model is built using Python and machine learning libraries, and it specifically reflects the user's requests through prompt messages.

[0082] As a concrete example, consider a prompt message in which the user enters "a cocktail with tropical flavors and a vibrant appearance." Based on this information, the server searches the database and uses a generative AI model to generate a cocktail called "Tropical Sunset," which primarily features mango and coconut flavors.

[0083] The generated recipes are visualized as images, and the cocktail-making process is provided in video format. This allows the device to present cocktail suggestions to the user in a visually easy-to-understand manner. The user can then refer to this while enjoying the preparation and presentation of the cocktail.

[0084] Ultimately, the user inputs feedback on the suggestions into the device, and the device sends that data back to the server. The server uses this feedback to update the generative model, which improves the accuracy of future suggestions. In this way, the system can continuously learn and evolve.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The user uses a terminal to input cocktail preference information. Specifically, they input information such as the flavor profile, desired ingredients and alcohol, and theme as text through the terminal's interface. The entered data is converted to JSON format and sent to the server as an API request.

[0088] Step 2:

[0089] The server starts a database search based on the preference information received from the terminal. At this time, the server parses the input JSON data and generates an SQL query. The database contains past cocktail recipes, ingredients used, and feedback information, and the server extracts relevant cocktail recipes as a list from this information. The output is a list of the relevant recipes.

[0090] Step 3:

[0091] The server uses a generative AI model to analyze the already acquired recipe list. This process generates further prompts for the selected recipes and inputs them into the AI ​​model. The model selects the recipe that best matches the user's preferences and outputs it as newly generated data. The output includes information on the optimal cocktail recipe.

[0092] Step 4:

[0093] The server creates visual data using an image generation tool based on the generated cocktail recipe. The program takes the specified recipe information as input, goes through a process to generate an image of the cocktail, and outputs the image data. It also uses video editing software to generate a video explaining the cocktail mixing procedure and outputs it in a viewable format.

[0094] Step 5:

[0095] The server sends the cocktail recipe content, images, videos, and generated name to the device. The device displays the received data on its screen for the user to review. Here, the UI layout is used to present the data in an organized manner, allowing the user to intuitively grasp the overall picture of the cocktail.

[0096] Step 6:

[0097] Users input feedback on the suggested cocktail via a device. Specifically, they fill out a dedicated feedback form indicating their satisfaction level and areas for improvement, and send that data back to the server. The device collects the received feedback and sends it to the server in JSON format.

[0098] Step 7:

[0099] The server analyzes the feedback and incorporates the data into the learning algorithm of the AI ​​model that generates the data. This improves the accuracy of cocktail recommendations in subsequent attempts. The updated model will be able to respond more precisely to the user's preferences. The output is the state of the updated model.

[0100] (Application Example 1)

[0101] 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."

[0102] There is a need to efficiently propose personalized beverage preparation procedures based on user preferences and provide appropriate visual information, enabling cooks to prepare beverages quickly and accurately. To effectively utilize this system in real-world settings (e.g., physical stores), technology is required to provide information in a visually verifiable format using visual display devices.

[0103] 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.

[0104] In this invention, the server includes means for receiving preference information from the user, means for searching a database for beverage preparation procedures based on the received preference information, means for analyzing the search results using a generative model to generate the optimal beverage preparation procedure, and means for visualizing the information using a visual display device on a terminal. This enables personalized beverage suggestions that meet the user's needs.

[0105] A "user" is an individual or organization that uses this system to receive beverage recommendations.

[0106] "Preference information" refers to information indicating the user's preferences and requests regarding beverages.

[0107] "Beverage preparation instructions" refer to the ingredients and detailed steps required to prepare a specified beverage.

[0108] A "database" is a source of information that stores data such as past beverage preparation procedures, ingredient information, and user feedback.

[0109] A "generative model" is an algorithm or system that analyzes input information and makes optimal suggestions.

[0110] "Visual information" refers to data used to visually represent the appearance of a beverage, and may include images and video formats.

[0111] A "visual display device" is a device that displays information so that it can be visually confirmed, and includes devices such as eyeglasses-type displays and monitors.

[0112] A "terminal" is a device used by users to input information or receive suggestions from a system.

[0113] "Feedback" refers to evaluations and opinions that users provide regarding system suggestions, and these are used to improve the system.

[0114] The system that realizes this application utilizes a multi-layered data processing and generative AI model. First, the user inputs preference information using a terminal. This information concerns preferred flavors, ingredients used, and the visual theme of the cocktail. The input information is sent to a server, which searches a database based on this data. The database stores preparation procedures, ingredient information, and past feedback for various beverages.

[0115] The server utilizes a generative AI model to analyze search results and generate the most suitable beverage preparation instructions for the user's preferences. The generated instructions are comprised of visual information and instructional videos. The visual information, for example, represents the colors and arrangement of the cocktail in image format. The instructional videos are videos that visualize the creation process at each step.

[0116] Next, the generated information is sent to a terminal and presented to the user via a visual display device. In some cases, smart glasses or other display terminals can be used to allow the cook to check the beverage preparation method in real time. This supports the quick and accurate preparation of beverages. Furthermore, when the user provides feedback on the provided suggestions, the server uses this feedback to improve the generation model, thereby increasing accuracy in subsequent attempts.

[0117] For example, if a user inputs a request to "create a refreshing, tangy beverage," the server generates a recipe including lime and mint, and provides visual information of a beverage with a green tone. After the user confirms the visual information and image on their terminal, they can prepare the beverage accordingly.

[0118] An example of a prompt message is one that asks the user for information such as, "Please tell us what ingredients you will be using and when you would like to drink it."

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The user uses a terminal to input preference information. This input includes preferred flavors, desired ingredients, and visual themes. The terminal converts the input information into data packets and sends them to the server. It is important that the input data is structured as text and converted into a format that the server can access.

[0122] Step 2:

[0123] The server searches the database based on preference information received from the terminal. The database used contains past beverage preparation procedures, ingredient lists, and past user feedback information. The server uses the received preference information as a query to retrieve relevant information from the database. The output consists of several possible preparation procedure candidates.

[0124] Step 3:

[0125] The server utilizes a generative AI model to analyze database search results. The input consists of candidate cooking procedures retrieved from the database. The generative AI model compares preference information with the search results to generate the optimal beverage cooking procedure. The output is a single cooking procedure that best matches the user's preferences. The generative model's automatic learning and optimization are crucial elements of this process.

[0126] Step 4:

[0127] The server creates visual information and procedural videos based on the generated cooking instructions. The input is the generated cooking instructions, and the output is the corresponding visual information (images) and procedural videos (videos). This allows the user to visually confirm the process, and the visualized information is sent to the terminal.

[0128] Step 5:

[0129] The terminal displays visual information and procedural videos received from the server on a visual display device. Smart glasses or display terminals are used here, allowing users to receive visual information in real time. Instructions are then provided to the user for creating the beverage based on the information.

[0130] Step 6:

[0131] The user creates a beverage based on a suggestion and inputs feedback on the result into a terminal. The terminal converts this feedback information into a data format and sends it to the server. The feedback serves as important improvement data for the system and is used to improve the accuracy of future suggestions.

[0132] 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.

[0133] This invention combines a cocktail suggestion system with an emotion engine, utilizing the user's emotional information to provide more personalized cocktail suggestions. The system uses the emotion engine to identify the user's emotional state and then suggests cocktails based on that information.

[0134] The user uses a device to input emotional information in addition to their usual preference information, through facial recognition and voice analysis. This emotional information represents the user's current emotional state, such as joy, sadness, or surprise. The device then transmits the preference and emotional information to the server.

[0135] The server uses the received information to analyze emotional information with its emotion engine. Based on the analysis results, it not only searches for relevant recipes from the cocktail database but also uses a generative model to generate a cocktail recipe that is best suited to the user's emotions.

[0136] The generated cocktail recipe is embodied in the form of visual data and video. The server generates the most suitable name for the cocktail and sends all the information to the terminal. The terminal presents this to the user, completing the cocktail suggestion process.

[0137] The device also receives feedback from users and sends it to the server along with sentiment information. The server updates the generative model based on the feedback, improving the accuracy of the suggestions.

[0138] For example, if a user requests a "relaxing cocktail" and the emotion engine detects "calmness," the server will create a relaxing cocktail called "Midnight Calm," which contains lavender and chamomile. The generated recipe, name, and preparation steps are then provided to the user.

[0139] Thus, by implementing the embodiments of the present invention, it becomes possible to propose more individually optimized cocktails tailored to the user's condition.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] Users use a device to input information about their cocktail preferences and emotions. Emotional information is collected via camera and microphone as data reflecting their current emotional state.

[0143] Step 2:

[0144] The terminal transmits user preference and emotional information to the server. This information serves as foundational data for further personalizing cocktail recommendations.

[0145] Step 3:

[0146] The server analyzes the received information and uses an emotion engine to analyze the user's emotional information in detail. It categorizes the information into specific emotional categories (e.g., stress, happiness, surprise) to understand the user's state.

[0147] Step 4:

[0148] The server integrates emotional and preference information and searches a cocktail database based on that information. It collects cocktail recipes that match the emotions and preferences.

[0149] Step 5:

[0150] The server uses a generative model to further analyze the search results and generate the optimal cocktail recipe for the user. This process takes into account factors such as flavor harmony, ingredient selection, and seasonality.

[0151] Step 6:

[0152] The server generates visual data (images) for the generated cocktail recipe and also prepares the creation procedure in video format.

[0153] Step 7:

[0154] The server generates a unique name that reflects the characteristics of the cocktail and sends it to the terminal along with the recipe, visual data, and video.

[0155] Step 8:

[0156] The terminal displays the received information to the user and suggests cocktails. The user can review the provided recipes and try making them.

[0157] Step 9:

[0158] The user enters feedback about the suggested cocktail into the device. This feedback includes an evaluation of how well the provided cocktail matched their emotional state.

[0159] Step 10:

[0160] The device sends user feedback, along with emotional information, to the server.

[0161] Step 11:

[0162] The server takes feedback into account and updates its sentiment engine and generative model. This update adjusts future suggestions to be more accurate.

[0163] (Example 2)

[0164] 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".

[0165] Conventional cocktail suggestion systems make suggestions based solely on user preference information, making it difficult to provide personalized suggestions that take into account the emotional state of individual users. This can lead to decreased user satisfaction. Therefore, there is a need for new technologies that enable suggestions that consider the emotional state of the user.

[0166] 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.

[0167] In this invention, the server includes means for acquiring preference information and emotional information from the user, means for analyzing the user's emotional state based on the acquired preference information and emotional information, and means for retrieving cocktail recipes from data storage based on the analysis results. This makes it possible to suggest the optimal cocktail recipe that reflects the user's current emotional state.

[0168] A "user" refers to an individual who uses the system to provide their preference and emotional information and receive cocktail suggestions.

[0169] "Preference information" refers to information about the tastes and types of drinks that users prefer.

[0170] "Emotional information" refers to data that indicates the user's current emotional state, and is acquired through facial recognition and voice analysis.

[0171] A "cocktail recipe" is information that shows the ingredients and steps required to make a cocktail.

[0172] "Data storage" refers to a storage device or database used to store cocktail recipes and other related data.

[0173] "Generative methods" refer to methods that use AI models and machine learning techniques to process data and automatically create new cocktail recipes.

[0174] "Visual data" refers to information used to visually represent cocktail recipes for presentation to users, and includes images and videos.

[0175] "Evaluation information" refers to feedback information such as users' impressions and satisfaction levels regarding the cocktails presented.

[0176] This cocktail suggestion system consists of a user, a server, and a terminal. The user provides their preference and emotional information via the terminal. This emotional information is acquired using facial recognition software and voice analysis software installed on the terminal. Specifically, general image analysis technology is used for facial recognition, and voice recognition technology is used for voice analysis.

[0177] The device collects this information and then transmits it to the server via the internet. SSL / TLS encryption technology is used to ensure data security.

[0178] The server analyzes the user's emotional state using an emotion engine based on the received preference and emotion information. This analysis utilizes natural language processing technologies such as a text analysis engine. The analysis results are used to search for the corresponding cocktail recipe from the cocktail data storage.

[0179] Furthermore, the server uses a generative AI model to generate a cocktail recipe best suited to the user's mood. This model, for example, employs generative AI technology and is given a prompt such as, "Generate a cocktail recipe suitable for a user who wants to relax."

[0180] The generated cocktail recipes are accompanied by a visual presentation, so the server converts them into visual data and transmits it to the terminal. This visual data is created using HTML and CSS and presented in image format.

[0181] Users view visual data and names of suggested cocktails through their devices, and provide feedback after actually trying the cocktails. This feedback information is sent to a server via the device and used to update the generating AI model.

[0182] For example, if a user desires relaxation, the emotion engine detects "calmness." The server then generates a cocktail recipe called "Midnight Calm," using lavender and chamomile, and offers it to the user. In this way, the system provides individually optimized cocktail suggestions based on the user's emotional state.

[0183] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0184] Step 1:

[0185] The user inputs preference and emotional information using a terminal. The terminal uses facial recognition and voice analysis software to obtain emotional information from the user's facial expressions and voice tone. The acquired information is converted into text format and stored in the terminal's memory. The input is raw data indicating the user's preference information and emotional state at that time, while the output is in the format required for analysis.

[0186] Step 2:

[0187] The terminal sends the collected data to the server. A communication protocol is used in the transmission path, and encryption technology is employed to ensure data integrity and security. The input for this step is preference and emotion information formatted on the terminal, and the output is data packets received on the server side.

[0188] Step 3:

[0189] The server analyzes the received data and uses an emotion engine to analyze the user's emotional state. This analysis expresses the user's current emotional state as a numerical value or category. The input data is emotional information sent from the terminal, and the output is the analyzed emotional data. Specifically, natural language processing and data mining techniques are used to convert emotional information into numerical indicators.

[0190] Step 4:

[0191] The server searches its data storage for relevant cocktail recipes based on the analysis results. At this stage, it narrows down the list to several recipes that best suit the user's preferences and emotional state. The input is the analyzed emotional data and preference information, and the output is a list of highly relevant cocktail recipes.

[0192] Step 5:

[0193] The server uses a generative AI model to generate prompts and create new cocktail recipes. The generative AI model makes new suggestions based on existing recipes and the user's state. The input is the selected recipe and analysis results, and the output is a new cocktail recipe to suggest to the user. Specifically, the prompt "Generate a cocktail recipe suitable for a user who wants to relax" is passed to the model, and a new recipe is called.

[0194] Step 6:

[0195] The server constructs the generated recipe as visual data and sends it to the terminal. HTML / CSS is used to organize the recipe into a visually easy-to-understand format. The input is the generated cocktail recipe, and the output is a visual presentation of the recipe.

[0196] Step 7:

[0197] The user receives cocktail suggestions from their device and inputs feedback. This feedback is evaluation information regarding the taste of the cocktail and the suitability of the suggestion. The input consists of visual data sent from the server and the user's impressions of the cocktail they actually drank, while the output is evaluation information.

[0198] Step 8:

[0199] The device sends feedback information back to the server. The server uses this information to update the generative AI model, improving the accuracy of future suggestions. The input is user feedback information, and the output is the updated generative model. By reflecting the feedback in the model's training dataset, subsequent suggestions become more accurate and personalized.

[0200] (Application Example 2)

[0201] 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".

[0202] In today's food and beverage industry, there is a growing demand for providing customers with more personalized experiences. Especially in establishments like bars and cocktail bars, offering service tailored to the emotional state of each customer is crucial for increasing customer satisfaction and encouraging repeat business. However, traditional methods present a challenge in instantly understanding a customer's emotional state and suggesting cocktails accordingly.

[0203] 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.

[0204] In this invention, the server includes means for receiving user preference information and positive states, means for analyzing emotional states based on image recognition and voice analysis, and means for displaying the provided information on the display of a glasses-type terminal. This makes it possible to instantly analyze the emotions of customers who visit the store from their facial expressions and voice, and quickly suggest a cocktail that is appropriate for their emotional state.

[0205] "User preference information" refers to data that shows a specific individual's preferences and tastes regarding food and drink.

[0206] "Positive state" refers to information that describes the customer's current psychological or emotional state.

[0207] "Image recognition" is a technology that uses a camera to analyze visual data and extract specific information.

[0208] "Voice analysis" is the process of analyzing voice data to understand its content and emotions.

[0209] A "glasses-type terminal" is a type of wearable device that provides visual information to the user.

[0210] The system for implementing this invention mainly consists of a glasses-type terminal worn by the user and a server in the cloud. The glasses-type terminal is equipped with a camera and microphone, making it possible to capture images of the user's face and voice in real time. This allows for accurate and immediate analysis of the customer's emotional state from their facial expressions and voice.

[0211] The glasses-type terminal uses the OpenCV library for facial recognition technology and the Google® Speech-to-Text API for speech analysis. These technologies allow the terminal to extract customer emotional information and send it to a server in the cloud. Based on the received emotional data, the server uses a generative AI model to generate the optimal cocktail recipe.

[0212] The cocktail recipe, visual data, and title generated by the server are displayed on the display of a glasses-type terminal. Based on this information, the bartender can quickly suggest the most suitable cocktail to the customer.

[0213] As an example, when a customer visits a bar and a glasses-type terminal detects an expression indicating a desire for a relaxing drink, the server generates a "calming recipe" in real time and sends it to the terminal. For example, a cocktail called "Lavender Infused Sunset" might be suggested. In this way, service tailored to the customer's emotions becomes possible.

[0214] An example of a prompt for a generative AI model is: "The customer's current emotional state is calm. Please generate a cocktail recipe that matches this emotion. Use ingredients that have a relaxing effect." Based on this information, the system will create a personalized cocktail suggestion that meets the customer's needs.

[0215] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0216] Step 1:

[0217] The device uses a camera to capture images of the user's face and a microphone to simultaneously acquire audio data. The input consists of image data of the user's facial expressions and audio data. This data is used to analyze emotional information.

[0218] Step 2:

[0219] The device analyzes facial image data acquired using the OpenCV library. Specifically, it extracts features that characterize a person's facial expression from the image data and identifies their emotional state. This process outputs emotional information through feature extraction and facial expression classification.

[0220] Step 3:

[0221] The device uses the Google Speech-to-Text API to convert acquired audio data into text and performs natural language processing for sentiment analysis. By taking the audio data as input, extracting keywords related to emotions, and integrating them with emotional information from facial expression data, it outputs a more accurate emotional state.

[0222] Step 4:

[0223] The server receives emotional information and user preference information sent from the terminal. Using this data as input, a generative AI model generates prompt sentences. Cocktail recipes are then generated based on these prompt sentences.

[0224] Step 5:

[0225] The server uses prompt messages and a generative AI model to generate the optimal cocktail recipe. This process involves data processing that takes emotional and preference information into account, resulting in a cocktail recipe as output.

[0226] Step 6:

[0227] The server sends the generated cocktail recipe, its visual data, and its title to the terminal. The output data includes the cocktail name, recipe, and visual data.

[0228] Step 7:

[0229] The terminal displays the received cocktail information on the user's glasses-type display. Based on the displayed information, the user performs an action to suggest the most suitable cocktail to the customer.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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".

[0246] This invention is implemented as a platform that enables cocktail suggestions tailored to the user's preferences throughout the entire system. The details of its form, including program processing and specific examples, are described below.

[0247] The user first uses a terminal to input their specific cocktail preferences. These preferences cover a wide range of details, including the flavor profile, the type of alcohol and ingredients they want to use, and the theme of the cocktail. The terminal sends this information to the server, which then receives the user's request.

[0248] The server searches a database based on the information it receives and collects the relevant cocktail recipes. This database includes past cocktail recipes, ingredient information, and even customer feedback. The server then uses a generative model to analyze the search results and generate the cocktail recipe that best matches the user's preferences.

[0249] The generated recipe consists of visual data and instructions. The server generates image data representing the appearance of the cocktail and provides a video demonstrating how to make it. Furthermore, it generates a unique cocktail name and transmits all of this information to the terminal.

[0250] The terminal presents the received information to the user and completes the cocktail suggestion. When the user provides feedback on the suggestion, the terminal sends that information back to the server. The server uses this feedback to update the generative model and further improve the accuracy of future suggestions.

[0251] For example, if a user requests a "vibrantly-looking cocktail with tropical flavors," the server will create a cocktail called "Tropical Sunset," primarily flavored with mango and coconut, and featuring a blue and orange gradient. The name, recipe, and a video demonstrating the creation process are provided to the user, allowing interested users to enjoy this cocktail.

[0252] Thus, the present invention realizes a cocktail suggestion system that continuously learns and evolves based on information tailored to the user's preferences.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] Users use a terminal to input their cocktail preferences. This includes taste preferences, desired ingredients, and event themes. This helps to specify the user's desired conditions.

[0256] Step 2:

[0257] The terminal transmits the entered preference information to the server. The transmitted data is used as basic information for cocktail suggestions.

[0258] Step 3:

[0259] Based on the received preference information, the server searches its internal cocktail database for relevant recipes. The database contains past recipes, ingredient information, and customer feedback.

[0260] Step 4:

[0261] The server launches a generative model and analyzes the retrieved data. The generative model creates candidate cocktail recipes that best suit the user's preferences and selects the best one from the generated recipes.

[0262] Step 5:

[0263] The server generates visual data (image format) based on the optimal cocktail recipe. This visually represents the appearance of the cocktail, and the preparation steps are created in video format.

[0264] Step 6:

[0265] The server generates a unique name suitable for the cocktail. The generated name reflects the cocktail's characteristics and enhances the overall quality of the suggestion.

[0266] Step 7:

[0267] The server sends the generated cocktail recipe, visual data, name, and video to the terminal.

[0268] Step 8:

[0269] The terminal presents the user with the provided information and suggests cocktails. The user can review these suggestions and, if interested, try making a cocktail based on the recipe.

[0270] Step 9:

[0271] Users enter feedback about the suggested cocktail into the terminal. This feedback may include evaluations of taste and appearance, as well as suggestions for improvement.

[0272] Step 10:

[0273] The device sends the feedback received from the user to the server.

[0274] Step 11:

[0275] The server analyzes the feedback and fine-tunes the generative model. This process improves the accuracy of the system's suggestions, which can be used to improve future cocktail recommendations.

[0276] (Example 1)

[0277] 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."

[0278] Conventional cocktail suggestion systems have difficulty suggesting the optimal cocktail based on the user's preferences, and the recipes and visual information provided often fail to meet user expectations. In particular, there is a need to provide suggestions that reflect individual user preferences while being visual and dynamic.

[0279] 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.

[0280] In this invention, the server includes means for receiving preference information from a user, means for retrieving a cocktail recipe from an information aggregate based on the received preference information, means for analyzing the search results using a generation model and generating an optimal cocktail recipe tailored to the user's preferences, means for generating image data based on the generated cocktail recipe, means for generating a name for identifying the cocktail, and means for providing the generated cocktail recipe, image data, and name to the user, as well as means for receiving opinions from the user and updating them to improve the accuracy of the generation model. Thereby, it becomes possible to visually and dynamically provide an optimal cocktail proposal according to the user's preferences.

[0281] The "user" is the entity that operates the cocktail proposal system and provides individual preference information.

[0282] The "preference information" is data indicating individual hopes and desires regarding the user's taste and themes.

[0283] The "information aggregate" is a database including past cocktail recipes, information on ingredients, and customer feedback.

[0284] The "generation model" is an algorithm for performing analysis and optimization based on the input data and outputting an optimal cocktail recipe tailored to the user's preferences.

[0285] The "image data" is a visual representation created based on the generated cocktail recipe.

[0286] The "name" is a unique title given to identify the generated cocktail.

[0287] The "opinion" is feedback information including the user's feelings and improvement points regarding the proposed cocktail.

[0288] "Updating to improve accuracy" is a process of incorporating user feedback into the generative model to improve the quality of future suggestions.

[0289] This invention comprises a technology for generating an optimal cocktail based on the user's preferences in a cocktail suggestion system. In embodiments of this invention, the system primarily operates around three elements: a server, a terminal, and a user.

[0290] The user uses a terminal to input information about their desired cocktail, i.e., their preferences. This input includes the flavor profile, the type of alcohol and ingredients they want to use, and the theme of the cocktail. This information is sent to the server via the terminal.

[0291] The server searches a database based on the received preference information. This database contains past cocktail recipes, ingredient information, and customer feedback. The server processes this information and uses a generative AI model to generate a cocktail recipe that best matches the user's preferences. The generative AI model is built using Python and machine learning libraries, and it specifically reflects the user's requests through prompt messages.

[0292] As a concrete example, consider a prompt message in which the user enters "a cocktail with tropical flavors and a vibrant appearance." Based on this information, the server searches the database and uses a generative AI model to generate a cocktail called "Tropical Sunset," which primarily features mango and coconut flavors.

[0293] The generated recipes are visualized as images, and the cocktail-making process is provided in video format. This allows the device to present cocktail suggestions to the user in a visually easy-to-understand manner. The user can then refer to this while enjoying the preparation and presentation of the cocktail.

[0294] Ultimately, the user inputs feedback on the suggestions into the device, and the device sends that data back to the server. The server uses this feedback to update the generative model, which improves the accuracy of future suggestions. In this way, the system can continuously learn and evolve.

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The user uses a terminal to input cocktail preference information. Specifically, they input information such as the flavor profile, desired ingredients and alcohol, and theme as text through the terminal's interface. The entered data is converted to JSON format and sent to the server as an API request.

[0298] Step 2:

[0299] The server starts a database search based on the preference information received from the terminal. At this time, the server parses the input JSON data and generates an SQL query. The database contains past cocktail recipes, ingredients used, and feedback information, and the server extracts relevant cocktail recipes as a list from this information. The output is a list of the relevant recipes.

[0300] Step 3:

[0301] The server uses a generative AI model to analyze the already acquired recipe list. This process generates further prompts for the selected recipes and inputs them into the AI ​​model. The model selects the recipe that best matches the user's preferences and outputs it as newly generated data. The output includes information on the optimal cocktail recipe.

[0302] Step 4:

[0303] The server creates visual data using an image generation tool based on the generated cocktail recipe. The program inputs the specified recipe information and outputs image data through the process of generating an image of the cocktail. Also, using video editing software, a video explaining the cocktail mixing procedure is generated and output in a viewable format.

[0304] Step 5:

[0305] The server sends the content of the cocktail recipe, the image, the video, and the generated name to the terminal. The terminal displays the received data on the screen so that the user can view it. Here, the UI layout is utilized to present the data neatly, enabling the user to intuitively grasp the overall picture of the cocktail.

[0306] Step 6:

[0307] The user inputs feedback on the proposed cocktail via the terminal. Specifically, the satisfaction level and improvement points are filled in a dedicated feedback form, and the data is sent back to the server. The terminal collects the received feedback and sends it to the server in JSON format.

[0308] Step 7:

[0309] The server analyzes the feedback and reflects the data in the learning algorithm of the generative AI model. This improves the accuracy of subsequent cocktail proposals. The updated model can more precisely respond to the user's preferences. The output is the state of the updated model.

[0310] (Application Example 1)

[0311] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] There is a need to efficiently propose personalized beverage preparation procedures based on user preferences and provide appropriate visual information, enabling cooks to prepare beverages quickly and accurately. To effectively utilize this system in real-world settings (e.g., physical stores), technology is required to provide information in a visually verifiable format using visual display devices.

[0313] 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.

[0314] In this invention, the server includes means for receiving preference information from the user, means for searching a database for beverage preparation procedures based on the received preference information, means for analyzing the search results using a generative model to generate the optimal beverage preparation procedure, and means for visualizing the information using a visual display device on a terminal. This enables personalized beverage suggestions that meet the user's needs.

[0315] A "user" is an individual or organization that uses this system to receive beverage recommendations.

[0316] "Preference information" refers to information indicating the user's preferences and requests regarding beverages.

[0317] "Beverage preparation instructions" refer to the ingredients and detailed steps required to prepare a specified beverage.

[0318] A "database" is a source of information that stores data such as past beverage preparation procedures, ingredient information, and user feedback.

[0319] A "generative model" is an algorithm or system that analyzes input information and makes optimal suggestions.

[0320] "Visual information" refers to data used to visually represent the appearance of a beverage, and may include images and video formats.

[0321] A "visual display device" is a device that displays information so that it can be visually confirmed, and includes devices such as eyeglasses-type displays and monitors.

[0322] A "terminal" is a device used by users to input information or receive suggestions from a system.

[0323] "Feedback" refers to evaluations and opinions that users provide regarding system suggestions, and these are used to improve the system.

[0324] The system that realizes this application utilizes a multi-layered data processing and generative AI model. First, the user inputs preference information using a terminal. This information concerns preferred flavors, ingredients used, and the visual theme of the cocktail. The input information is sent to a server, which searches a database based on this data. The database stores preparation procedures, ingredient information, and past feedback for various beverages.

[0325] The server utilizes a generative AI model to analyze search results and generate the most suitable beverage preparation instructions for the user's preferences. The generated instructions are comprised of visual information and instructional videos. The visual information, for example, represents the colors and arrangement of the cocktail in image format. The instructional videos are videos that visualize the creation process at each step.

[0326] Next, the generated information is sent to a terminal and presented to the user via a visual display device. In some cases, smart glasses or other display terminals can be used to allow the cook to check the beverage preparation method in real time. This supports the quick and accurate preparation of beverages. Furthermore, when the user provides feedback on the provided suggestions, the server uses this feedback to improve the generation model, thereby increasing accuracy in subsequent attempts.

[0327] For example, if a user inputs a request to "create a refreshing, tangy beverage," the server generates a recipe including lime and mint, and provides visual information of a beverage with a green tone. After the user confirms the visual information and image on their terminal, they can prepare the beverage accordingly.

[0328] An example of a prompt message is one that asks the user for information such as, "Please tell us what ingredients you will be using and when you would like to drink it."

[0329] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0330] Step 1:

[0331] The user uses a terminal to input preference information. This input includes preferred flavors, desired ingredients, and visual themes. The terminal converts the input information into data packets and sends them to the server. It is important that the input data is structured as text and converted into a format that the server can access.

[0332] Step 2:

[0333] The server searches the database based on preference information received from the terminal. The database used contains past beverage preparation procedures, ingredient lists, and past user feedback information. The server uses the received preference information as a query to retrieve relevant information from the database. The output consists of several possible preparation procedure candidates.

[0334] Step 3:

[0335] The server utilizes a generative AI model to analyze database search results. The input consists of candidate cooking procedures retrieved from the database. The generative AI model compares preference information with the search results to generate the optimal beverage cooking procedure. The output is a single cooking procedure that best matches the user's preferences. The generative model's automatic learning and optimization are crucial elements of this process.

[0336] Step 4:

[0337] The server creates visual information and procedural videos based on the generated cooking instructions. The input is the generated cooking instructions, and the output is the corresponding visual information (images) and procedural videos (videos). This allows the user to visually confirm the process, and the visualized information is sent to the terminal.

[0338] Step 5:

[0339] The terminal displays visual information and procedural videos received from the server on a visual display device. Smart glasses or display terminals are used here, allowing users to receive visual information in real time. Instructions are then provided to the user for creating the beverage based on the information.

[0340] Step 6:

[0341] The user creates a beverage based on a suggestion and inputs feedback on the result into a terminal. The terminal converts this feedback information into a data format and sends it to the server. The feedback serves as important improvement data for the system and is used to improve the accuracy of future suggestions.

[0342] 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.

[0343] This invention combines a cocktail suggestion system with an emotion engine, utilizing the user's emotional information to provide more personalized cocktail suggestions. The system uses the emotion engine to identify the user's emotional state and then suggests cocktails based on that information.

[0344] The user uses a device to input emotional information in addition to their usual preference information, through facial recognition and voice analysis. This emotional information represents the user's current emotional state, such as joy, sadness, or surprise. The device then transmits the preference and emotional information to the server.

[0345] The server uses the received information to analyze emotional information with its emotion engine. Based on the analysis results, it not only searches for relevant recipes from the cocktail database but also uses a generative model to generate a cocktail recipe that is best suited to the user's emotions.

[0346] The generated cocktail recipe is embodied in the form of visual data and video. The server generates the most suitable name for the cocktail and sends all the information to the terminal. The terminal presents this to the user, completing the cocktail suggestion process.

[0347] The device also receives feedback from users and sends it to the server along with sentiment information. The server updates the generative model based on the feedback, improving the accuracy of the suggestions.

[0348] For example, if a user requests a "relaxing cocktail" and the emotion engine detects "calmness," the server will create a relaxing cocktail called "Midnight Calm," which contains lavender and chamomile. The generated recipe, name, and preparation steps are then provided to the user.

[0349] Thus, by implementing the embodiments of the present invention, it becomes possible to propose more individually optimized cocktails tailored to the user's condition.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] Users use a device to input information about their cocktail preferences and emotions. Emotional information is collected via camera and microphone as data reflecting their current emotional state.

[0353] Step 2:

[0354] The terminal transmits user preference and emotional information to the server. This information serves as foundational data for further personalizing cocktail recommendations.

[0355] Step 3:

[0356] The server analyzes the received information and uses an emotion engine to analyze the user's emotional information in detail. It categorizes the information into specific emotional categories (e.g., stress, happiness, surprise) to understand the user's state.

[0357] Step 4:

[0358] The server integrates emotional and preference information and searches a cocktail database based on that information. It collects cocktail recipes that match the emotions and preferences.

[0359] Step 5:

[0360] The server uses a generative model to further analyze the search results and generate the optimal cocktail recipe for the user. This process takes into account factors such as flavor harmony, ingredient selection, and seasonality.

[0361] Step 6:

[0362] The server generates visual data (images) for the generated cocktail recipe and also prepares the creation procedure in video format.

[0363] Step 7:

[0364] The server generates a unique name that reflects the characteristics of the cocktail and sends it to the terminal along with the recipe, visual data, and video.

[0365] Step 8:

[0366] The terminal displays the received information to the user and suggests cocktails. The user can review the provided recipes and try making them.

[0367] Step 9:

[0368] The user enters feedback about the suggested cocktail into the device. This feedback includes an evaluation of how well the provided cocktail matched their emotional state.

[0369] Step 10:

[0370] The device sends user feedback, along with emotional information, to the server.

[0371] Step 11:

[0372] The server takes feedback into account and updates its sentiment engine and generative model. This update adjusts future suggestions to be more accurate.

[0373] (Example 2)

[0374] 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".

[0375] Conventional cocktail suggestion systems make suggestions based solely on user preference information, making it difficult to provide personalized suggestions that take into account the emotional state of individual users. This can lead to decreased user satisfaction. Therefore, there is a need for new technologies that enable suggestions that consider the emotional state of the user.

[0376] 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.

[0377] In this invention, the server includes means for acquiring preference information and emotional information from the user, means for analyzing the user's emotional state based on the acquired preference information and emotional information, and means for retrieving cocktail recipes from data storage based on the analysis results. This makes it possible to suggest the optimal cocktail recipe that reflects the user's current emotional state.

[0378] A "user" refers to an individual who uses the system to provide their preference and emotional information and receive cocktail suggestions.

[0379] "Preference information" refers to information about the tastes and types of drinks that users prefer.

[0380] "Emotional information" refers to data that indicates the user's current emotional state, and is acquired through facial recognition and voice analysis.

[0381] A "cocktail recipe" is information that shows the ingredients and steps required to make a cocktail.

[0382] "Data storage" refers to a storage device or database used to store cocktail recipes and other related data.

[0383] "Generative methods" refer to methods that use AI models and machine learning techniques to process data and automatically create new cocktail recipes.

[0384] "Visual data" refers to information used to visually represent cocktail recipes for presentation to users, and includes images and videos.

[0385] "Evaluation information" refers to feedback information such as users' impressions and satisfaction levels regarding the cocktails presented.

[0386] This cocktail suggestion system consists of a user, a server, and a terminal. The user provides their preference and emotional information via the terminal. This emotional information is acquired using facial recognition software and voice analysis software installed on the terminal. Specifically, general image analysis technology is used for facial recognition, and voice recognition technology is used for voice analysis.

[0387] The device collects this information and then transmits it to the server via the internet. SSL / TLS encryption technology is used to ensure data security.

[0388] The server analyzes the user's emotional state using an emotion engine based on the received preference and emotion information. This analysis utilizes natural language processing technologies such as a text analysis engine. The analysis results are used to search for the corresponding cocktail recipe from the cocktail data storage.

[0389] Furthermore, the server uses a generative AI model to generate a cocktail recipe best suited to the user's mood. This model, for example, employs generative AI technology and is given a prompt such as, "Generate a cocktail recipe suitable for a user who wants to relax."

[0390] The generated cocktail recipes are accompanied by a visual presentation, so the server converts them into visual data and transmits it to the terminal. This visual data is created using HTML and CSS and presented in image format.

[0391] Users view visual data and names of suggested cocktails through their devices, and provide feedback after actually trying the cocktails. This feedback information is sent to a server via the device and used to update the generating AI model.

[0392] For example, if a user desires relaxation, the emotion engine detects "calmness." The server then generates a cocktail recipe called "Midnight Calm," using lavender and chamomile, and offers it to the user. In this way, the system provides individually optimized cocktail suggestions based on the user's emotional state.

[0393] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0394] Step 1:

[0395] The user inputs preference and emotional information using a terminal. The terminal uses facial recognition and voice analysis software to obtain emotional information from the user's facial expressions and voice tone. The acquired information is converted into text format and stored in the terminal's memory. The input is raw data indicating the user's preference information and emotional state at that time, while the output is in the format required for analysis.

[0396] Step 2:

[0397] The terminal sends the collected data to the server. A communication protocol is used in the transmission path, and encryption technology is employed to ensure data integrity and security. The input for this step is preference and emotion information formatted on the terminal, and the output is data packets received on the server side.

[0398] Step 3:

[0399] The server analyzes the received data and uses an emotion engine to analyze the user's emotional state. This analysis expresses the user's current emotional state as a numerical value or category. The input data is emotional information sent from the terminal, and the output is the analyzed emotional data. Specifically, natural language processing and data mining techniques are used to convert emotional information into numerical indicators.

[0400] Step 4:

[0401] The server searches its data storage for relevant cocktail recipes based on the analysis results. At this stage, it narrows down the list to several recipes that best suit the user's preferences and emotional state. The input is the analyzed emotional data and preference information, and the output is a list of highly relevant cocktail recipes.

[0402] Step 5:

[0403] The server uses a generative AI model to generate prompts and create new cocktail recipes. The generative AI model makes new suggestions based on existing recipes and the user's state. The input is the selected recipe and analysis results, and the output is a new cocktail recipe to suggest to the user. Specifically, the prompt "Generate a cocktail recipe suitable for a user who wants to relax" is passed to the model, and a new recipe is called.

[0404] Step 6:

[0405] The server constructs the generated recipe as visual data and sends it to the terminal. HTML / CSS is used to organize the recipe into a visually easy-to-understand format. The input is the generated cocktail recipe, and the output is a visual presentation of the recipe.

[0406] Step 7:

[0407] The user receives cocktail suggestions from their device and inputs feedback. This feedback is evaluation information regarding the taste of the cocktail and the suitability of the suggestion. The input consists of visual data sent from the server and the user's impressions of the cocktail they actually drank, while the output is evaluation information.

[0408] Step 8:

[0409] The device sends feedback information back to the server. The server uses this information to update the generative AI model, improving the accuracy of future suggestions. The input is user feedback information, and the output is the updated generative model. By reflecting the feedback in the model's training dataset, subsequent suggestions become more accurate and personalized.

[0410] (Application Example 2)

[0411] 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 will be referred to as the "terminal."

[0412] In today's food and beverage industry, there is a growing demand for providing customers with more personalized experiences. Especially in establishments like bars and cocktail bars, offering service tailored to the emotional state of each customer is crucial for increasing customer satisfaction and encouraging repeat business. However, traditional methods present a challenge in instantly understanding a customer's emotional state and suggesting cocktails accordingly.

[0413] 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.

[0414] In this invention, the server includes means for receiving user preference information and positive states, means for analyzing emotional states based on image recognition and voice analysis, and means for displaying the provided information on the display of a glasses-type terminal. This makes it possible to instantly analyze the emotions of customers who visit the store from their facial expressions and voice, and quickly suggest a cocktail that is appropriate for their emotional state.

[0415] "User preference information" refers to data that shows a specific individual's preferences and tastes regarding food and drink.

[0416] "Positive state" refers to information that describes the customer's current psychological or emotional state.

[0417] "Image recognition" is a technology that uses a camera to analyze visual data and extract specific information.

[0418] "Voice analysis" is the process of analyzing voice data to understand its content and emotions.

[0419] A "glasses-type terminal" is a type of wearable device that provides visual information to the user.

[0420] The system for implementing this invention mainly consists of a glasses-type terminal worn by the user and a server in the cloud. The glasses-type terminal is equipped with a camera and microphone, making it possible to capture images of the user's face and voice in real time. This allows for accurate and immediate analysis of the customer's emotional state from their facial expressions and voice.

[0421] The glasses-type terminal uses the OpenCV library for facial recognition technology and the Google Speech-to-Text API for speech analysis. These technologies allow the terminal to extract customer emotional information and send it to a server in the cloud. Based on the received emotional data, the server uses a generative AI model to generate the optimal cocktail recipe.

[0422] The cocktail recipe, visual data, and title generated by the server are displayed on the display of a glasses-type terminal. Based on this information, the bartender can quickly suggest the most suitable cocktail to the customer.

[0423] As an example, when a customer visits a bar and a glasses-type terminal detects an expression indicating a desire for a relaxing drink, the server generates a "calming recipe" in real time and sends it to the terminal. For example, a cocktail called "Lavender Infused Sunset" might be suggested. In this way, service tailored to the customer's emotions becomes possible.

[0424] An example of a prompt for a generative AI model is: "The customer's current emotional state is calm. Please generate a cocktail recipe that matches this emotion. Use ingredients that have a relaxing effect." Based on this information, the system will create a personalized cocktail suggestion that meets the customer's needs.

[0425] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0426] Step 1:

[0427] The device uses a camera to capture images of the user's face and a microphone to simultaneously acquire audio data. The input consists of image data of the user's facial expressions and audio data. This data is used to analyze emotional information.

[0428] Step 2:

[0429] The device analyzes facial image data acquired using the OpenCV library. Specifically, it extracts features that characterize a person's facial expression from the image data and identifies their emotional state. This process outputs emotional information through feature extraction and facial expression classification.

[0430] Step 3:

[0431] The device uses the Google Speech-to-Text API to convert acquired audio data into text and performs natural language processing for sentiment analysis. By taking the audio data as input, extracting keywords related to emotions, and integrating them with emotional information from facial expression data, it outputs a more accurate emotional state.

[0432] Step 4:

[0433] The server receives emotional information and user preference information sent from the terminal. Using this data as input, a generative AI model generates prompt sentences. Cocktail recipes are then generated based on these prompt sentences.

[0434] Step 5:

[0435] The server uses prompt messages and a generative AI model to generate the optimal cocktail recipe. This process involves data processing that takes emotional and preference information into account, resulting in a cocktail recipe as output.

[0436] Step 6:

[0437] The server sends the generated cocktail recipe, its visual data, and its title to the terminal. The output data includes the cocktail name, recipe, and visual data.

[0438] Step 7:

[0439] The terminal displays the received cocktail information on the user's glasses-type display. Based on the displayed information, the user performs an action to suggest the most suitable cocktail to the customer.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Third Embodiment]

[0444] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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".

[0456] This invention is implemented as a platform that enables cocktail suggestions tailored to the user's preferences throughout the entire system. The details of its form, including program processing and specific examples, are described below.

[0457] The user first uses a terminal to input their specific cocktail preferences. These preferences cover a wide range of details, including the flavor profile, the type of alcohol and ingredients they want to use, and the theme of the cocktail. The terminal sends this information to the server, which then receives the user's request.

[0458] The server searches a database based on the information it receives and collects the relevant cocktail recipes. This database includes past cocktail recipes, ingredient information, and even customer feedback. The server then uses a generative model to analyze the search results and generate the cocktail recipe that best matches the user's preferences.

[0459] The generated recipe consists of visual data and instructions. The server generates image data representing the appearance of the cocktail and provides a video demonstrating how to make it. Furthermore, it generates a unique cocktail name and transmits all of this information to the terminal.

[0460] The terminal presents the received information to the user and completes the cocktail suggestion. When the user provides feedback on the suggestion, the terminal sends that information back to the server. The server uses this feedback to update the generative model and further improve the accuracy of future suggestions.

[0461] For example, if a user requests a "vibrantly-looking cocktail with tropical flavors," the server will create a cocktail called "Tropical Sunset," primarily flavored with mango and coconut, and featuring a blue and orange gradient. The name, recipe, and a video demonstrating the creation process are provided to the user, allowing interested users to enjoy this cocktail.

[0462] Thus, the present invention realizes a cocktail suggestion system that continuously learns and evolves based on information tailored to the user's preferences.

[0463] The following describes the processing flow.

[0464] Step 1:

[0465] Users use a terminal to input their cocktail preferences. This includes taste preferences, desired ingredients, and event themes. This helps to specify the user's desired conditions.

[0466] Step 2:

[0467] The terminal transmits the entered preference information to the server. The transmitted data is used as basic information for cocktail suggestions.

[0468] Step 3:

[0469] Based on the received preference information, the server searches its internal cocktail database for relevant recipes. The database contains past recipes, ingredient information, and customer feedback.

[0470] Step 4:

[0471] The server launches a generative model and analyzes the retrieved data. The generative model creates candidate cocktail recipes that best suit the user's preferences and selects the best one from the generated recipes.

[0472] Step 5:

[0473] The server generates visual data (image format) based on the optimal cocktail recipe. This visually represents the appearance of the cocktail, and the preparation steps are created in video format.

[0474] Step 6:

[0475] The server generates a unique name suitable for the cocktail. The generated name reflects the cocktail's characteristics and enhances the overall quality of the suggestion.

[0476] Step 7:

[0477] The server sends the generated cocktail recipe, visual data, name, and video to the terminal.

[0478] Step 8:

[0479] The terminal presents the user with the provided information and suggests cocktails. The user can review these suggestions and, if interested, try making a cocktail based on the recipe.

[0480] Step 9:

[0481] Users enter feedback about the suggested cocktail into the terminal. This feedback may include evaluations of taste and appearance, as well as suggestions for improvement.

[0482] Step 10:

[0483] The device sends the feedback received from the user to the server.

[0484] Step 11:

[0485] The server analyzes the feedback and fine-tunes the generative model. This process improves the accuracy of the system's suggestions, which can be used to improve future cocktail recommendations.

[0486] (Example 1)

[0487] 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."

[0488] Conventional cocktail suggestion systems have difficulty suggesting the optimal cocktail based on the user's preferences, and the recipes and visual information provided often fail to meet user expectations. In particular, there is a need to provide suggestions that reflect individual user preferences while being visual and dynamic.

[0489] 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.

[0490] In this invention, the server includes means for receiving preference information from a user, means for searching for cocktail recipes from an information set based on the received preference information, means for analyzing the search results using a generative model and generating an optimal cocktail recipe that suits the user's preferences, means for generating image data based on the generated cocktail recipe, means for generating a name to identify the cocktail, means for providing the user with the generated cocktail recipe, image data, and name, and means for receiving feedback from the user and updating the generative model to improve its accuracy. This makes it possible to visually and dynamically provide optimal cocktail suggestions that match the user's preferences.

[0491] A "user" is the entity that operates the cocktail suggestion system and provides individual preference information.

[0492] "Preference information" refers to data that shows the individual preferences and requests of users regarding taste and themes.

[0493] An "information collection" is a database containing past cocktail recipes, information on ingredients, and customer feedback.

[0494] A "generative model" is an algorithm that analyzes and optimizes input data to output the optimal cocktail recipe tailored to the user's preferences.

[0495] "Image data" refers to a visual representation created based on the generated cocktail recipe.

[0496] The "name" is a unique designation given to identify the cocktail that is created.

[0497] "Opinions" refer to feedback information from users, including their thoughts and suggestions for improvement regarding the suggested cocktails.

[0498] "Updating to improve accuracy" is a process of incorporating user feedback into the generative model to improve the quality of future suggestions.

[0499] This invention comprises a technology for generating an optimal cocktail based on the user's preferences in a cocktail suggestion system. In embodiments of this invention, the system primarily operates around three elements: a server, a terminal, and a user.

[0500] The user uses a terminal to input information about their desired cocktail, i.e., their preferences. This input includes the flavor profile, the type of alcohol and ingredients they want to use, and the theme of the cocktail. This information is sent to the server via the terminal.

[0501] The server searches a database based on the received preference information. This database contains past cocktail recipes, ingredient information, and customer feedback. The server processes this information and uses a generative AI model to generate a cocktail recipe that best matches the user's preferences. The generative AI model is built using Python and machine learning libraries, and it specifically reflects the user's requests through prompt messages.

[0502] As a concrete example, consider a prompt message in which the user enters "a cocktail with tropical flavors and a vibrant appearance." Based on this information, the server searches the database and uses a generative AI model to generate a cocktail called "Tropical Sunset," which primarily features mango and coconut flavors.

[0503] The generated recipes are visualized as images, and the cocktail-making process is provided in video format. This allows the device to present cocktail suggestions to the user in a visually easy-to-understand manner. The user can then refer to this while enjoying the preparation and presentation of the cocktail.

[0504] Ultimately, the user inputs feedback on the suggestions into the device, and the device sends that data back to the server. The server uses this feedback to update the generative model, which improves the accuracy of future suggestions. In this way, the system can continuously learn and evolve.

[0505] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0506] Step 1:

[0507] The user uses a terminal to input cocktail preference information. Specifically, they input information such as the flavor profile, desired ingredients and alcohol, and theme as text through the terminal's interface. The entered data is converted to JSON format and sent to the server as an API request.

[0508] Step 2:

[0509] The server starts a database search based on the preference information received from the terminal. At this time, the server parses the input JSON data and generates an SQL query. The database contains past cocktail recipes, ingredients used, and feedback information, and the server extracts relevant cocktail recipes as a list from this information. The output is a list of the relevant recipes.

[0510] Step 3:

[0511] The server uses a generative AI model to analyze the already acquired recipe list. This process generates further prompts for the selected recipes and inputs them into the AI ​​model. The model selects the recipe that best matches the user's preferences and outputs it as newly generated data. The output includes information on the optimal cocktail recipe.

[0512] Step 4:

[0513] The server creates visual data using an image generation tool based on the generated cocktail recipe. The program takes the specified recipe information as input, goes through a process to generate an image of the cocktail, and outputs the image data. It also uses video editing software to generate a video explaining the cocktail mixing procedure and outputs it in a viewable format.

[0514] Step 5:

[0515] The server sends the cocktail recipe content, images, videos, and generated name to the device. The device displays the received data on its screen for the user to review. Here, the UI layout is used to present the data in an organized manner, allowing the user to intuitively grasp the overall picture of the cocktail.

[0516] Step 6:

[0517] Users input feedback on the suggested cocktail via a device. Specifically, they fill out a dedicated feedback form indicating their satisfaction level and areas for improvement, and send that data back to the server. The device collects the received feedback and sends it to the server in JSON format.

[0518] Step 7:

[0519] The server analyzes the feedback and incorporates the data into the learning algorithm of the AI ​​model that generates the data. This improves the accuracy of cocktail recommendations in subsequent attempts. The updated model will be able to respond more precisely to the user's preferences. The output is the state of the updated model.

[0520] (Application Example 1)

[0521] 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."

[0522] There is a need to efficiently propose personalized beverage preparation procedures based on user preferences and provide appropriate visual information, enabling cooks to prepare beverages quickly and accurately. To effectively utilize this system in real-world settings (e.g., physical stores), technology is required to provide information in a visually verifiable format using visual display devices.

[0523] 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.

[0524] In this invention, the server includes means for receiving preference information from the user, means for searching a database for beverage preparation procedures based on the received preference information, means for analyzing the search results using a generative model to generate the optimal beverage preparation procedure, and means for visualizing the information using a visual display device on a terminal. This enables personalized beverage suggestions that meet the user's needs.

[0525] A "user" is an individual or organization that uses this system to receive beverage recommendations.

[0526] "Preference information" refers to information indicating the user's preferences and requests regarding beverages.

[0527] "Beverage preparation instructions" refer to the ingredients and detailed steps required to prepare a specified beverage.

[0528] A "database" is a source of information that stores data such as past beverage preparation procedures, ingredient information, and user feedback.

[0529] A "generative model" is an algorithm or system that analyzes input information and makes optimal suggestions.

[0530] "Visual information" refers to data used to visually represent the appearance of a beverage, and may include images and video formats.

[0531] A "visual display device" is a device that displays information so that it can be visually confirmed, and includes devices such as eyeglasses-type displays and monitors.

[0532] A "terminal" is a device used by users to input information or receive suggestions from a system.

[0533] "Feedback" refers to evaluations and opinions that users provide regarding system suggestions, and these are used to improve the system.

[0534] The system that realizes this application utilizes a multi-layered data processing and generative AI model. First, the user inputs preference information using a terminal. This information concerns preferred flavors, ingredients used, and the visual theme of the cocktail. The input information is sent to a server, which searches a database based on this data. The database stores preparation procedures, ingredient information, and past feedback for various beverages.

[0535] The server utilizes a generative AI model to analyze search results and generate the most suitable beverage preparation instructions for the user's preferences. The generated instructions are comprised of visual information and instructional videos. The visual information, for example, represents the colors and arrangement of the cocktail in image format. The instructional videos are videos that visualize the creation process at each step.

[0536] Next, the generated information is sent to a terminal and presented to the user via a visual display device. In some cases, smart glasses or other display terminals can be used to allow the cook to check the beverage preparation method in real time. This supports the quick and accurate preparation of beverages. Furthermore, when the user provides feedback on the provided suggestions, the server uses this feedback to improve the generation model, thereby increasing accuracy in subsequent attempts.

[0537] For example, if a user inputs a request to "create a refreshing, tangy beverage," the server generates a recipe including lime and mint, and provides visual information of a beverage with a green tone. After the user confirms the visual information and image on their terminal, they can prepare the beverage accordingly.

[0538] An example of a prompt message is one that asks the user for information such as, "Please tell us what ingredients you will be using and when you would like to drink it."

[0539] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0540] Step 1:

[0541] The user uses a terminal to input preference information. This input includes preferred flavors, desired ingredients, and visual themes. The terminal converts the input information into data packets and sends them to the server. It is important that the input data is structured as text and converted into a format that the server can access.

[0542] Step 2:

[0543] The server searches the database based on preference information received from the terminal. The database used contains past beverage preparation procedures, ingredient lists, and past user feedback information. The server uses the received preference information as a query to retrieve relevant information from the database. The output consists of several possible preparation procedure candidates.

[0544] Step 3:

[0545] The server utilizes a generative AI model to analyze database search results. The input consists of candidate cooking procedures retrieved from the database. The generative AI model compares preference information with the search results to generate the optimal beverage cooking procedure. The output is a single cooking procedure that best matches the user's preferences. The generative model's automatic learning and optimization are crucial elements of this process.

[0546] Step 4:

[0547] The server creates visual information and procedural videos based on the generated cooking instructions. The input is the generated cooking instructions, and the output is the corresponding visual information (images) and procedural videos (videos). This allows the user to visually confirm the process, and the visualized information is sent to the terminal.

[0548] Step 5:

[0549] The terminal displays visual information and procedural videos received from the server on a visual display device. Smart glasses or display terminals are used here, allowing users to receive visual information in real time. Instructions are then provided to the user for creating the beverage based on the information.

[0550] Step 6:

[0551] The user creates a beverage based on a suggestion and inputs feedback on the result into a terminal. The terminal converts this feedback information into a data format and sends it to the server. The feedback serves as important improvement data for the system and is used to improve the accuracy of future suggestions.

[0552] 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.

[0553] This invention combines a cocktail suggestion system with an emotion engine, utilizing the user's emotional information to provide more personalized cocktail suggestions. The system uses the emotion engine to identify the user's emotional state and then suggests cocktails based on that information.

[0554] The user uses a device to input emotional information in addition to their usual preference information, through facial recognition and voice analysis. This emotional information represents the user's current emotional state, such as joy, sadness, or surprise. The device then transmits the preference and emotional information to the server.

[0555] The server uses the received information to analyze emotional information with its emotion engine. Based on the analysis results, it not only searches for relevant recipes from the cocktail database but also uses a generative model to generate a cocktail recipe that is best suited to the user's emotions.

[0556] The generated cocktail recipe is embodied in the form of visual data and video. The server generates the most suitable name for the cocktail and sends all the information to the terminal. The terminal presents this to the user, completing the cocktail suggestion process.

[0557] The device also receives feedback from users and sends it to the server along with sentiment information. The server updates the generative model based on the feedback, improving the accuracy of the suggestions.

[0558] For example, if a user requests a "relaxing cocktail" and the emotion engine detects "calmness," the server will create a relaxing cocktail called "Midnight Calm," which contains lavender and chamomile. The generated recipe, name, and preparation steps are then provided to the user.

[0559] Thus, by implementing the embodiments of the present invention, it becomes possible to propose more individually optimized cocktails tailored to the user's condition.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] Users use a device to input information about their cocktail preferences and emotions. Emotional information is collected via camera and microphone as data reflecting their current emotional state.

[0563] Step 2:

[0564] The terminal transmits user preference and emotional information to the server. This information serves as foundational data for further personalizing cocktail recommendations.

[0565] Step 3:

[0566] The server analyzes the received information and uses an emotion engine to analyze the user's emotional information in detail. It categorizes the information into specific emotional categories (e.g., stress, happiness, surprise) to understand the user's state.

[0567] Step 4:

[0568] The server integrates emotional and preference information and searches a cocktail database based on that information. It collects cocktail recipes that match the emotions and preferences.

[0569] Step 5:

[0570] The server uses a generative model to further analyze the search results and generate the optimal cocktail recipe for the user. This process takes into account factors such as flavor harmony, ingredient selection, and seasonality.

[0571] Step 6:

[0572] The server generates visual data (images) for the generated cocktail recipe and also prepares the creation procedure in video format.

[0573] Step 7:

[0574] The server generates a unique name that reflects the characteristics of the cocktail and sends it to the terminal along with the recipe, visual data, and video.

[0575] Step 8:

[0576] The terminal displays the received information to the user and suggests cocktails. The user can review the provided recipes and try making them.

[0577] Step 9:

[0578] The user enters feedback about the suggested cocktail into the device. This feedback includes an evaluation of how well the provided cocktail matched their emotional state.

[0579] Step 10:

[0580] The device sends user feedback, along with emotional information, to the server.

[0581] Step 11:

[0582] The server takes feedback into account and updates its sentiment engine and generative model. This update adjusts future suggestions to be more accurate.

[0583] (Example 2)

[0584] 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."

[0585] Conventional cocktail suggestion systems make suggestions based solely on user preference information, making it difficult to provide personalized suggestions that take into account the emotional state of individual users. This can lead to decreased user satisfaction. Therefore, there is a need for new technologies that enable suggestions that consider the emotional state of the user.

[0586] 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.

[0587] In this invention, the server includes means for acquiring preference information and emotional information from the user, means for analyzing the user's emotional state based on the acquired preference information and emotional information, and means for retrieving cocktail recipes from data storage based on the analysis results. This makes it possible to suggest the optimal cocktail recipe that reflects the user's current emotional state.

[0588] A "user" refers to an individual who uses the system to provide their preference and emotional information and receive cocktail suggestions.

[0589] "Preference information" refers to information about the tastes and types of drinks that users prefer.

[0590] "Emotional information" refers to data that indicates the user's current emotional state, and is acquired through facial recognition and voice analysis.

[0591] A "cocktail recipe" is information that shows the ingredients and steps required to make a cocktail.

[0592] "Data storage" refers to a storage device or database used to store cocktail recipes and other related data.

[0593] "Generative methods" refer to methods that use AI models and machine learning techniques to process data and automatically create new cocktail recipes.

[0594] "Visual data" refers to information used to visually represent cocktail recipes for presentation to users, and includes images and videos.

[0595] "Evaluation information" refers to feedback information such as users' impressions and satisfaction levels regarding the cocktails presented.

[0596] This cocktail suggestion system consists of a user, a server, and a terminal. The user provides their preference and emotional information via the terminal. This emotional information is acquired using facial recognition software and voice analysis software installed on the terminal. Specifically, general image analysis technology is used for facial recognition, and voice recognition technology is used for voice analysis.

[0597] The device collects this information and then transmits it to the server via the internet. SSL / TLS encryption technology is used to ensure data security.

[0598] The server analyzes the user's emotional state using an emotion engine based on the received preference and emotion information. This analysis utilizes natural language processing technologies such as a text analysis engine. The analysis results are used to search for the corresponding cocktail recipe from the cocktail data storage.

[0599] Furthermore, the server uses a generative AI model to generate a cocktail recipe best suited to the user's mood. This model, for example, employs generative AI technology and is given a prompt such as, "Generate a cocktail recipe suitable for a user who wants to relax."

[0600] The generated cocktail recipes are accompanied by a visual presentation, so the server converts them into visual data and transmits it to the terminal. This visual data is created using HTML and CSS and presented in image format.

[0601] Users view visual data and names of suggested cocktails through their devices, and provide feedback after actually trying the cocktails. This feedback information is sent to a server via the device and used to update the generating AI model.

[0602] For example, if a user desires relaxation, the emotion engine detects "calmness." The server then generates a cocktail recipe called "Midnight Calm," using lavender and chamomile, and offers it to the user. In this way, the system provides individually optimized cocktail suggestions based on the user's emotional state.

[0603] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0604] Step 1:

[0605] The user inputs preference and emotional information using a terminal. The terminal uses facial recognition and voice analysis software to obtain emotional information from the user's facial expressions and voice tone. The acquired information is converted into text format and stored in the terminal's memory. The input is raw data indicating the user's preference information and emotional state at that time, while the output is in the format required for analysis.

[0606] Step 2:

[0607] The terminal sends the collected data to the server. A communication protocol is used in the transmission path, and encryption technology is employed to ensure data integrity and security. The input for this step is preference and emotion information formatted on the terminal, and the output is data packets received on the server side.

[0608] Step 3:

[0609] The server analyzes the received data and uses an emotion engine to analyze the user's emotional state. This analysis expresses the user's current emotional state as a numerical value or category. The input data is emotional information sent from the terminal, and the output is the analyzed emotional data. Specifically, natural language processing and data mining techniques are used to convert emotional information into numerical indicators.

[0610] Step 4:

[0611] The server searches its data storage for relevant cocktail recipes based on the analysis results. At this stage, it narrows down the list to several recipes that best suit the user's preferences and emotional state. The input is the analyzed emotional data and preference information, and the output is a list of highly relevant cocktail recipes.

[0612] Step 5:

[0613] The server uses a generative AI model to generate prompts and create new cocktail recipes. The generative AI model makes new suggestions based on existing recipes and the user's state. The input is the selected recipe and analysis results, and the output is a new cocktail recipe to suggest to the user. Specifically, the prompt "Generate a cocktail recipe suitable for a user who wants to relax" is passed to the model, and a new recipe is called.

[0614] Step 6:

[0615] The server constructs the generated recipe as visual data and sends it to the terminal. HTML / CSS is used to organize the recipe into a visually easy-to-understand format. The input is the generated cocktail recipe, and the output is a visual presentation of the recipe.

[0616] Step 7:

[0617] The user receives cocktail suggestions from their device and inputs feedback. This feedback is evaluation information regarding the taste of the cocktail and the suitability of the suggestion. The input consists of visual data sent from the server and the user's impressions of the cocktail they actually drank, while the output is evaluation information.

[0618] Step 8:

[0619] The device sends feedback information back to the server. The server uses this information to update the generative AI model, improving the accuracy of future suggestions. The input is user feedback information, and the output is the updated generative model. By reflecting the feedback in the model's training dataset, subsequent suggestions become more accurate and personalized.

[0620] (Application Example 2)

[0621] 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."

[0622] In today's food and beverage industry, there is a growing demand for providing customers with more personalized experiences. Especially in establishments like bars and cocktail bars, offering service tailored to the emotional state of each customer is crucial for increasing customer satisfaction and encouraging repeat business. However, traditional methods present a challenge in instantly understanding a customer's emotional state and suggesting cocktails accordingly.

[0623] 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.

[0624] In this invention, the server includes means for receiving user preference information and positive states, means for analyzing emotional states based on image recognition and voice analysis, and means for displaying the provided information on the display of a glasses-type terminal. This makes it possible to instantly analyze the emotions of customers who visit the store from their facial expressions and voice, and quickly suggest a cocktail that is appropriate for their emotional state.

[0625] "User preference information" refers to data that shows a specific individual's preferences and tastes regarding food and drink.

[0626] "Positive state" refers to information that describes the customer's current psychological or emotional state.

[0627] "Image recognition" is a technology that uses a camera to analyze visual data and extract specific information.

[0628] "Voice analysis" is the process of analyzing voice data to understand its content and emotions.

[0629] A "glasses-type terminal" is a type of wearable device that provides visual information to the user.

[0630] The system for implementing this invention mainly consists of a glasses-type terminal worn by the user and a server in the cloud. The glasses-type terminal is equipped with a camera and microphone, making it possible to capture images of the user's face and voice in real time. This allows for accurate and immediate analysis of the customer's emotional state from their facial expressions and voice.

[0631] The glasses-type terminal uses the OpenCV library for facial recognition technology and the Google Speech-to-Text API for speech analysis. These technologies allow the terminal to extract customer emotional information and send it to a server in the cloud. Based on the received emotional data, the server uses a generative AI model to generate the optimal cocktail recipe.

[0632] The cocktail recipe, visual data, and title generated by the server are displayed on the display of a glasses-type terminal. Based on this information, the bartender can quickly suggest the most suitable cocktail to the customer.

[0633] As an example, when a customer visits a bar and a glasses-type terminal detects an expression indicating a desire for a relaxing drink, the server generates a "calming recipe" in real time and sends it to the terminal. For example, a cocktail called "Lavender Infused Sunset" might be suggested. In this way, service tailored to the customer's emotions becomes possible.

[0634] An example of a prompt for a generative AI model is: "The customer's current emotional state is calm. Please generate a cocktail recipe that matches this emotion. Use ingredients that have a relaxing effect." Based on this information, the system will create a personalized cocktail suggestion that meets the customer's needs.

[0635] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0636] Step 1:

[0637] The device uses a camera to capture images of the user's face and a microphone to simultaneously acquire audio data. The input consists of image data of the user's facial expressions and audio data. This data is used to analyze emotional information.

[0638] Step 2:

[0639] The device analyzes facial image data acquired using the OpenCV library. Specifically, it extracts features that characterize a person's facial expression from the image data and identifies their emotional state. This process outputs emotional information through feature extraction and facial expression classification.

[0640] Step 3:

[0641] The device uses the Google Speech-to-Text API to convert acquired audio data into text and performs natural language processing for sentiment analysis. By taking the audio data as input, extracting keywords related to emotions, and integrating them with emotional information from facial expression data, it outputs a more accurate emotional state.

[0642] Step 4:

[0643] The server receives emotional information and user preference information sent from the terminal. Using this data as input, a generative AI model generates prompt sentences. Cocktail recipes are then generated based on these prompt sentences.

[0644] Step 5:

[0645] The server uses prompt messages and a generative AI model to generate the optimal cocktail recipe. This process involves data processing that takes emotional and preference information into account, resulting in a cocktail recipe as output.

[0646] Step 6:

[0647] The server sends the generated cocktail recipe, its visual data, and its title to the terminal. The output data includes the cocktail name, recipe, and visual data.

[0648] Step 7:

[0649] The terminal displays the received cocktail information on the user's glasses-type display. Based on the displayed information, the user performs an action to suggest the most suitable cocktail to the customer.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] [Fourth Embodiment]

[0654] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0655] 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.

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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".

[0667] This invention is implemented as a platform that enables cocktail suggestions tailored to the user's preferences throughout the entire system. The details of its form, including program processing and specific examples, are described below.

[0668] The user first uses a terminal to input their specific cocktail preferences. These preferences cover a wide range of details, including the flavor profile, the type of alcohol and ingredients they want to use, and the theme of the cocktail. The terminal sends this information to the server, which then receives the user's request.

[0669] The server searches a database based on the information it receives and collects the relevant cocktail recipes. This database includes past cocktail recipes, ingredient information, and even customer feedback. The server then uses a generative model to analyze the search results and generate the cocktail recipe that best matches the user's preferences.

[0670] The generated recipe consists of visual data and instructions. The server generates image data representing the appearance of the cocktail and provides a video demonstrating how to make it. Furthermore, it generates a unique cocktail name and transmits all of this information to the terminal.

[0671] The terminal presents the received information to the user and completes the cocktail suggestion. When the user provides feedback on the suggestion, the terminal sends that information back to the server. The server uses this feedback to update the generative model and further improve the accuracy of future suggestions.

[0672] For example, if a user requests a "vibrantly-looking cocktail with tropical flavors," the server will create a cocktail called "Tropical Sunset," primarily flavored with mango and coconut, and featuring a blue and orange gradient. The name, recipe, and a video demonstrating the creation process are provided to the user, allowing interested users to enjoy this cocktail.

[0673] Thus, the present invention realizes a cocktail suggestion system that continuously learns and evolves based on information tailored to the user's preferences.

[0674] The following describes the processing flow.

[0675] Step 1:

[0676] Users use a terminal to input their cocktail preferences. This includes taste preferences, desired ingredients, and event themes. This helps to specify the user's desired conditions.

[0677] Step 2:

[0678] The terminal transmits the entered preference information to the server. The transmitted data is used as basic information for cocktail suggestions.

[0679] Step 3:

[0680] Based on the received preference information, the server searches its internal cocktail database for relevant recipes. The database contains past recipes, ingredient information, and customer feedback.

[0681] Step 4:

[0682] The server launches a generative model and analyzes the retrieved data. The generative model creates candidate cocktail recipes that best suit the user's preferences and selects the best one from the generated recipes.

[0683] Step 5:

[0684] The server generates visual data (image format) based on the optimal cocktail recipe. This visually represents the appearance of the cocktail, and the preparation steps are created in video format.

[0685] Step 6:

[0686] The server generates a unique name suitable for the cocktail. The generated name reflects the cocktail's characteristics and enhances the overall quality of the suggestion.

[0687] Step 7:

[0688] The server sends the generated cocktail recipe, visual data, name, and video to the terminal.

[0689] Step 8:

[0690] The terminal presents the user with the provided information and suggests cocktails. The user can review these suggestions and, if interested, try making a cocktail based on the recipe.

[0691] Step 9:

[0692] Users enter feedback about the suggested cocktail into the terminal. This feedback may include evaluations of taste and appearance, as well as suggestions for improvement.

[0693] Step 10:

[0694] The device sends the feedback received from the user to the server.

[0695] Step 11:

[0696] The server analyzes the feedback and fine-tunes the generative model. This process improves the accuracy of the system's suggestions, which can be used to improve future cocktail recommendations.

[0697] (Example 1)

[0698] 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".

[0699] Conventional cocktail suggestion systems have difficulty suggesting the optimal cocktail based on the user's preferences, and the recipes and visual information provided often fail to meet user expectations. In particular, there is a need to provide suggestions that reflect individual user preferences while being visual and dynamic.

[0700] 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.

[0701] In this invention, the server includes means for receiving preference information from a user, means for searching for cocktail recipes from an information set based on the received preference information, means for analyzing the search results using a generative model and generating an optimal cocktail recipe that suits the user's preferences, means for generating image data based on the generated cocktail recipe, means for generating a name to identify the cocktail, means for providing the user with the generated cocktail recipe, image data, and name, and means for receiving feedback from the user and updating the generative model to improve its accuracy. This makes it possible to visually and dynamically provide optimal cocktail suggestions that match the user's preferences.

[0702] A "user" is the entity that operates the cocktail suggestion system and provides individual preference information.

[0703] "Preference information" refers to data that shows the individual preferences and requests of users regarding taste and themes.

[0704] An "information collection" is a database containing past cocktail recipes, information on ingredients, and customer feedback.

[0705] A "generative model" is an algorithm that analyzes and optimizes input data to output the optimal cocktail recipe tailored to the user's preferences.

[0706] "Image data" refers to a visual representation created based on the generated cocktail recipe.

[0707] The "name" is a unique designation given to identify the cocktail that is created.

[0708] "Opinions" refer to feedback information from users, including their thoughts and suggestions for improvement regarding the suggested cocktails.

[0709] "Updating to improve accuracy" is a process of incorporating user feedback into the generative model to improve the quality of future suggestions.

[0710] This invention comprises a technology for generating an optimal cocktail based on the user's preferences in a cocktail suggestion system. In embodiments of this invention, the system primarily operates around three elements: a server, a terminal, and a user.

[0711] The user uses a terminal to input information about their desired cocktail, i.e., their preferences. This input includes the flavor profile, the type of alcohol and ingredients they want to use, and the theme of the cocktail. This information is sent to the server via the terminal.

[0712] The server searches a database based on the received preference information. This database contains past cocktail recipes, ingredient information, and customer feedback. The server processes this information and uses a generative AI model to generate a cocktail recipe that best matches the user's preferences. The generative AI model is built using Python and machine learning libraries, and it specifically reflects the user's requests through prompt messages.

[0713] As a concrete example, consider a prompt message in which the user enters "a cocktail with tropical flavors and a vibrant appearance." Based on this information, the server searches the database and uses a generative AI model to generate a cocktail called "Tropical Sunset," which primarily features mango and coconut flavors.

[0714] The generated recipes are visualized as images, and the cocktail-making process is provided in video format. This allows the device to present cocktail suggestions to the user in a visually easy-to-understand manner. The user can then refer to this while enjoying the preparation and presentation of the cocktail.

[0715] Ultimately, the user inputs feedback on the suggestions into the device, and the device sends that data back to the server. The server uses this feedback to update the generative model, which improves the accuracy of future suggestions. In this way, the system can continuously learn and evolve.

[0716] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0717] Step 1:

[0718] The user uses a terminal to input cocktail preference information. Specifically, they input information such as the flavor profile, desired ingredients and alcohol, and theme as text through the terminal's interface. The entered data is converted to JSON format and sent to the server as an API request.

[0719] Step 2:

[0720] The server starts a database search based on the preference information received from the terminal. At this time, the server parses the input JSON data and generates an SQL query. The database contains past cocktail recipes, ingredients used, and feedback information, and the server extracts relevant cocktail recipes as a list from this information. The output is a list of the relevant recipes.

[0721] Step 3:

[0722] The server uses a generative AI model to analyze the already acquired recipe list. This process generates further prompts for the selected recipes and inputs them into the AI ​​model. The model selects the recipe that best matches the user's preferences and outputs it as newly generated data. The output includes information on the optimal cocktail recipe.

[0723] Step 4:

[0724] The server creates visual data using an image generation tool based on the generated cocktail recipe. The program takes the specified recipe information as input, goes through a process to generate an image of the cocktail, and outputs the image data. It also uses video editing software to generate a video explaining the cocktail mixing procedure and outputs it in a viewable format.

[0725] Step 5:

[0726] The server sends the cocktail recipe content, images, videos, and generated name to the device. The device displays the received data on its screen for the user to review. Here, the UI layout is used to present the data in an organized manner, allowing the user to intuitively grasp the overall picture of the cocktail.

[0727] Step 6:

[0728] Users input feedback on the suggested cocktail via a device. Specifically, they fill out a dedicated feedback form indicating their satisfaction level and areas for improvement, and send that data back to the server. The device collects the received feedback and sends it to the server in JSON format.

[0729] Step 7:

[0730] The server analyzes the feedback and incorporates the data into the learning algorithm of the AI ​​model that generates the data. This improves the accuracy of cocktail recommendations in subsequent attempts. The updated model will be able to respond more precisely to the user's preferences. The output is the state of the updated model.

[0731] (Application Example 1)

[0732] 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".

[0733] There is a need to efficiently propose personalized beverage preparation procedures based on user preferences and provide appropriate visual information, enabling cooks to prepare beverages quickly and accurately. To effectively utilize this system in real-world settings (e.g., physical stores), technology is required to provide information in a visually verifiable format using visual display devices.

[0734] 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.

[0735] In this invention, the server includes means for receiving preference information from the user, means for searching a database for beverage preparation procedures based on the received preference information, means for analyzing the search results using a generative model to generate the optimal beverage preparation procedure, and means for visualizing the information using a visual display device on a terminal. This enables personalized beverage suggestions that meet the user's needs.

[0736] A "user" is an individual or organization that uses this system to receive beverage recommendations.

[0737] "Preference information" refers to information indicating the user's preferences and requests regarding beverages.

[0738] "Beverage preparation instructions" refer to the ingredients and detailed steps required to prepare a specified beverage.

[0739] A "database" is a source of information that stores data such as past beverage preparation procedures, ingredient information, and user feedback.

[0740] A "generative model" is an algorithm or system that analyzes input information and makes optimal suggestions.

[0741] "Visual information" refers to data used to visually represent the appearance of a beverage, and may include images and video formats.

[0742] A "visual display device" is a device that displays information so that it can be visually confirmed, and includes devices such as eyeglasses-type displays and monitors.

[0743] A "terminal" is a device used by users to input information or receive suggestions from a system.

[0744] "Feedback" refers to evaluations and opinions that users provide regarding system suggestions, and these are used to improve the system.

[0745] The system that realizes this application utilizes a multi-layered data processing and generative AI model. First, the user inputs preference information using a terminal. This information concerns preferred flavors, ingredients used, and the visual theme of the cocktail. The input information is sent to a server, which searches a database based on this data. The database stores preparation procedures, ingredient information, and past feedback for various beverages.

[0746] The server utilizes a generative AI model to analyze search results and generate the most suitable beverage preparation instructions for the user's preferences. The generated instructions are comprised of visual information and instructional videos. The visual information, for example, represents the colors and arrangement of the cocktail in image format. The instructional videos are videos that visualize the creation process at each step.

[0747] Next, the generated information is sent to a terminal and presented to the user via a visual display device. In some cases, smart glasses or other display terminals can be used to allow the cook to check the beverage preparation method in real time. This supports the quick and accurate preparation of beverages. Furthermore, when the user provides feedback on the provided suggestions, the server uses this feedback to improve the generation model, thereby increasing accuracy in subsequent attempts.

[0748] For example, if a user inputs a request to "create a refreshing, tangy beverage," the server generates a recipe including lime and mint, and provides visual information of a beverage with a green tone. After the user confirms the visual information and image on their terminal, they can prepare the beverage accordingly.

[0749] An example of a prompt message is one that asks the user for information such as, "Please tell us what ingredients you will be using and when you would like to drink it."

[0750] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0751] Step 1:

[0752] The user uses a terminal to input preference information. This input includes preferred flavors, desired ingredients, and visual themes. The terminal converts the input information into data packets and sends them to the server. It is important that the input data is structured as text and converted into a format that the server can access.

[0753] Step 2:

[0754] The server searches the database based on preference information received from the terminal. The database used contains past beverage preparation procedures, ingredient lists, and past user feedback information. The server uses the received preference information as a query to retrieve relevant information from the database. The output consists of several possible preparation procedure candidates.

[0755] Step 3:

[0756] The server utilizes a generative AI model to analyze database search results. The input consists of candidate cooking procedures retrieved from the database. The generative AI model compares preference information with the search results to generate the optimal beverage cooking procedure. The output is a single cooking procedure that best matches the user's preferences. The generative model's automatic learning and optimization are crucial elements of this process.

[0757] Step 4:

[0758] The server creates visual information and procedural videos based on the generated cooking instructions. The input is the generated cooking instructions, and the output is the corresponding visual information (images) and procedural videos (videos). This allows the user to visually confirm the process, and the visualized information is sent to the terminal.

[0759] Step 5:

[0760] The terminal displays visual information and procedural videos received from the server on a visual display device. Smart glasses or display terminals are used here, allowing users to receive visual information in real time. Instructions are then provided to the user for creating the beverage based on the information.

[0761] Step 6:

[0762] The user creates a beverage based on a suggestion and inputs feedback on the result into a terminal. The terminal converts this feedback information into a data format and sends it to the server. The feedback serves as important improvement data for the system and is used to improve the accuracy of future suggestions.

[0763] 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.

[0764] This invention combines a cocktail suggestion system with an emotion engine, utilizing the user's emotional information to provide more personalized cocktail suggestions. The system uses the emotion engine to identify the user's emotional state and then suggests cocktails based on that information.

[0765] The user uses a device to input emotional information in addition to their usual preference information, through facial recognition and voice analysis. This emotional information represents the user's current emotional state, such as joy, sadness, or surprise. The device then transmits the preference and emotional information to the server.

[0766] The server uses the received information to analyze emotional information with its emotion engine. Based on the analysis results, it not only searches for relevant recipes from the cocktail database but also uses a generative model to generate a cocktail recipe that is best suited to the user's emotions.

[0767] The generated cocktail recipe is embodied in the form of visual data and video. The server generates the most suitable name for the cocktail and sends all the information to the terminal. The terminal presents this to the user, completing the cocktail suggestion process.

[0768] The device also receives feedback from users and sends it to the server along with sentiment information. The server updates the generative model based on the feedback, improving the accuracy of the suggestions.

[0769] For example, if a user requests a "relaxing cocktail" and the emotion engine detects "calmness," the server will create a relaxing cocktail called "Midnight Calm," which contains lavender and chamomile. The generated recipe, name, and preparation steps are then provided to the user.

[0770] Thus, by implementing the embodiments of the present invention, it becomes possible to propose more individually optimized cocktails tailored to the user's condition.

[0771] The following describes the processing flow.

[0772] Step 1:

[0773] Users use a device to input information about their cocktail preferences and emotions. Emotional information is collected via camera and microphone as data reflecting their current emotional state.

[0774] Step 2:

[0775] The terminal transmits user preference and emotional information to the server. This information serves as foundational data for further personalizing cocktail recommendations.

[0776] Step 3:

[0777] The server analyzes the received information and uses an emotion engine to analyze the user's emotional information in detail. It categorizes the information into specific emotional categories (e.g., stress, happiness, surprise) to understand the user's state.

[0778] Step 4:

[0779] The server integrates emotional and preference information and searches a cocktail database based on that information. It collects cocktail recipes that match the emotions and preferences.

[0780] Step 5:

[0781] The server uses a generative model to further analyze the search results and generate the optimal cocktail recipe for the user. This process takes into account factors such as flavor harmony, ingredient selection, and seasonality.

[0782] Step 6:

[0783] The server generates visual data (images) for the generated cocktail recipe and also prepares the creation procedure in video format.

[0784] Step 7:

[0785] The server generates a unique name that reflects the characteristics of the cocktail and sends it to the terminal along with the recipe, visual data, and video.

[0786] Step 8:

[0787] The terminal displays the received information to the user and suggests cocktails. The user can review the provided recipes and try making them.

[0788] Step 9:

[0789] The user enters feedback about the suggested cocktail into the device. This feedback includes an evaluation of how well the provided cocktail matched their emotional state.

[0790] Step 10:

[0791] The device sends user feedback, along with emotional information, to the server.

[0792] Step 11:

[0793] The server takes feedback into account and updates its sentiment engine and generative model. This update adjusts future suggestions to be more accurate.

[0794] (Example 2)

[0795] 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".

[0796] Conventional cocktail suggestion systems make suggestions based solely on user preference information, making it difficult to provide personalized suggestions that take into account the emotional state of individual users. This can lead to decreased user satisfaction. Therefore, there is a need for new technologies that enable suggestions that consider the emotional state of the user.

[0797] 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.

[0798] In this invention, the server includes means for acquiring preference information and emotional information from the user, means for analyzing the user's emotional state based on the acquired preference information and emotional information, and means for retrieving cocktail recipes from data storage based on the analysis results. This makes it possible to suggest the optimal cocktail recipe that reflects the user's current emotional state.

[0799] A "user" refers to an individual who uses the system to provide their preference and emotional information and receive cocktail suggestions.

[0800] "Preference information" refers to information about the tastes and types of drinks that users prefer.

[0801] "Emotional information" refers to data that indicates the user's current emotional state, and is acquired through facial recognition and voice analysis.

[0802] A "cocktail recipe" is information that shows the ingredients and steps required to make a cocktail.

[0803] "Data storage" refers to a storage device or database used to store cocktail recipes and other related data.

[0804] "Generative methods" refer to methods that use AI models and machine learning techniques to process data and automatically create new cocktail recipes.

[0805] "Visual data" refers to information used to visually represent cocktail recipes for presentation to users, and includes images and videos.

[0806] "Evaluation information" refers to feedback information such as users' impressions and satisfaction levels regarding the cocktails presented.

[0807] This cocktail suggestion system consists of a user, a server, and a terminal. The user provides their preference and emotional information via the terminal. This emotional information is acquired using facial recognition software and voice analysis software installed on the terminal. Specifically, general image analysis technology is used for facial recognition, and voice recognition technology is used for voice analysis.

[0808] The device collects this information and then transmits it to the server via the internet. SSL / TLS encryption technology is used to ensure data security.

[0809] The server analyzes the user's emotional state using an emotion engine based on the received preference and emotion information. This analysis utilizes natural language processing technologies such as a text analysis engine. The analysis results are used to search for the corresponding cocktail recipe from the cocktail data storage.

[0810] Furthermore, the server uses a generative AI model to generate a cocktail recipe best suited to the user's mood. This model, for example, employs generative AI technology and is given a prompt such as, "Generate a cocktail recipe suitable for a user who wants to relax."

[0811] The generated cocktail recipes are accompanied by a visual presentation, so the server converts them into visual data and transmits it to the terminal. This visual data is created using HTML and CSS and presented in image format.

[0812] Users view visual data and names of suggested cocktails through their devices, and provide feedback after actually trying the cocktails. This feedback information is sent to a server via the device and used to update the generating AI model.

[0813] For example, if a user desires relaxation, the emotion engine detects "calmness." The server then generates a cocktail recipe called "Midnight Calm," using lavender and chamomile, and offers it to the user. In this way, the system provides individually optimized cocktail suggestions based on the user's emotional state.

[0814] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0815] Step 1:

[0816] The user inputs preference and emotional information using a terminal. The terminal uses facial recognition and voice analysis software to obtain emotional information from the user's facial expressions and voice tone. The acquired information is converted into text format and stored in the terminal's memory. The input is raw data indicating the user's preference information and emotional state at that time, while the output is in the format required for analysis.

[0817] Step 2:

[0818] The terminal sends the collected data to the server. A communication protocol is used in the transmission path, and encryption technology is employed to ensure data integrity and security. The input for this step is preference and emotion information formatted on the terminal, and the output is data packets received on the server side.

[0819] Step 3:

[0820] The server analyzes the received data and uses an emotion engine to analyze the user's emotional state. This analysis expresses the user's current emotional state as a numerical value or category. The input data is emotional information sent from the terminal, and the output is the analyzed emotional data. Specifically, natural language processing and data mining techniques are used to convert emotional information into numerical indicators.

[0821] Step 4:

[0822] The server searches its data storage for relevant cocktail recipes based on the analysis results. At this stage, it narrows down the list to several recipes that best suit the user's preferences and emotional state. The input is the analyzed emotional data and preference information, and the output is a list of highly relevant cocktail recipes.

[0823] Step 5:

[0824] The server uses a generative AI model to generate prompts and create new cocktail recipes. The generative AI model makes new suggestions based on existing recipes and the user's state. The input is the selected recipe and analysis results, and the output is a new cocktail recipe to suggest to the user. Specifically, the prompt "Generate a cocktail recipe suitable for a user who wants to relax" is passed to the model, and a new recipe is called.

[0825] Step 6:

[0826] The server constructs the generated recipe as visual data and sends it to the terminal. HTML / CSS is used to organize the recipe into a visually easy-to-understand format. The input is the generated cocktail recipe, and the output is a visual presentation of the recipe.

[0827] Step 7:

[0828] The user receives cocktail suggestions from their device and inputs feedback. This feedback is evaluation information regarding the taste of the cocktail and the suitability of the suggestion. The input consists of visual data sent from the server and the user's impressions of the cocktail they actually drank, while the output is evaluation information.

[0829] Step 8:

[0830] The device sends feedback information back to the server. The server uses this information to update the generative AI model, improving the accuracy of future suggestions. The input is user feedback information, and the output is the updated generative model. By reflecting the feedback in the model's training dataset, subsequent suggestions become more accurate and personalized.

[0831] (Application Example 2)

[0832] 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".

[0833] In today's food and beverage industry, there is a growing demand for providing customers with more personalized experiences. Especially in establishments like bars and cocktail bars, offering service tailored to the emotional state of each customer is crucial for increasing customer satisfaction and encouraging repeat business. However, traditional methods present a challenge in instantly understanding a customer's emotional state and suggesting cocktails accordingly.

[0834] 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.

[0835] In this invention, the server includes means for receiving user preference information and positive states, means for analyzing emotional states based on image recognition and voice analysis, and means for displaying the provided information on the display of a glasses-type terminal. This makes it possible to instantly analyze the emotions of customers who visit the store from their facial expressions and voice, and quickly suggest a cocktail that is appropriate for their emotional state.

[0836] "User preference information" refers to data that shows a specific individual's preferences and tastes regarding food and drink.

[0837] "Positive state" refers to information that describes the customer's current psychological or emotional state.

[0838] "Image recognition" is a technology that uses a camera to analyze visual data and extract specific information.

[0839] "Voice analysis" is the process of analyzing voice data to understand its content and emotions.

[0840] A "glasses-type terminal" is a type of wearable device that provides visual information to the user.

[0841] The system for implementing this invention mainly consists of a glasses-type terminal worn by the user and a server in the cloud. The glasses-type terminal is equipped with a camera and microphone, making it possible to capture images of the user's face and voice in real time. This allows for accurate and immediate analysis of the customer's emotional state from their facial expressions and voice.

[0842] The glasses-type terminal uses the OpenCV library for facial recognition technology and the Google Speech-to-Text API for speech analysis. These technologies allow the terminal to extract customer emotional information and send it to a server in the cloud. Based on the received emotional data, the server uses a generative AI model to generate the optimal cocktail recipe.

[0843] The cocktail recipe, visual data, and title generated by the server are displayed on the display of a glasses-type terminal. Based on this information, the bartender can quickly suggest the most suitable cocktail to the customer.

[0844] As an example, when a customer visits a bar and a glasses-type terminal detects an expression indicating a desire for a relaxing drink, the server generates a "calming recipe" in real time and sends it to the terminal. For example, a cocktail called "Lavender Infused Sunset" might be suggested. In this way, service tailored to the customer's emotions becomes possible.

[0845] An example of a prompt for a generative AI model is: "The customer's current emotional state is calm. Please generate a cocktail recipe that matches this emotion. Use ingredients that have a relaxing effect." Based on this information, the system will create a personalized cocktail suggestion that meets the customer's needs.

[0846] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0847] Step 1:

[0848] The device uses a camera to capture images of the user's face and a microphone to simultaneously acquire audio data. The input consists of image data of the user's facial expressions and audio data. This data is used to analyze emotional information.

[0849] Step 2:

[0850] The device analyzes facial image data acquired using the OpenCV library. Specifically, it extracts features that characterize a person's facial expression from the image data and identifies their emotional state. This process outputs emotional information through feature extraction and facial expression classification.

[0851] Step 3:

[0852] The device uses the Google Speech-to-Text API to convert acquired audio data into text and performs natural language processing for sentiment analysis. By taking the audio data as input, extracting keywords related to emotions, and integrating them with emotional information from facial expression data, it outputs a more accurate emotional state.

[0853] Step 4:

[0854] The server receives emotional information and user preference information sent from the terminal. Using this data as input, a generative AI model generates prompt sentences. Cocktail recipes are then generated based on these prompt sentences.

[0855] Step 5:

[0856] The server uses prompt messages and a generative AI model to generate the optimal cocktail recipe. This process involves data processing that takes emotional and preference information into account, resulting in a cocktail recipe as output.

[0857] Step 6:

[0858] The server sends the generated cocktail recipe, its visual data, and its title to the terminal. The output data includes the cocktail name, recipe, and visual data.

[0859] Step 7:

[0860] The terminal displays the received cocktail information on the user's glasses-type display. Based on the displayed information, the user performs an action to suggest the most suitable cocktail to the customer.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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."

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0882] The following is further disclosed regarding the embodiments described above.

[0883] (Claim 1)

[0884] A means of receiving preference information from users,

[0885] A means for searching a database for cocktail recipes based on received preference information,

[0886] A method for analyzing search results using a generative model and generating the optimal cocktail recipe,

[0887] Means for creating visual data and methods for generated cocktail recipes,

[0888] A means of generating cocktail names,

[0889] A means of providing users with the recipe, visual data, and name of the generated cocktail,

[0890] A means of receiving feedback from users and updating the generative model,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, which outputs the visual data of the generated cocktail recipe as an image.

[0894] (Claim 3)

[0895] The system according to claim 1, which outputs the method of generating a cocktail recipe in video format.

[0896] "Example 1"

[0897] (Claim 1)

[0898] A means of receiving preference information from users,

[0899] A means of searching for cocktail recipes from an information set based on received preference information,

[0900] A method for analyzing search results using a generative model and generating optimal cocktail recipes tailored to the user's preferences,

[0901] A means for generating image data based on the generated cocktail recipe,

[0902] A means of representing the cocktail-making process in video format,

[0903] A means for generating a name to identify a cocktail,

[0904] A means of providing users with the recipe, image data, and name of the generated cocktail,

[0905] A means of receiving feedback from users and updating the generative model to improve its accuracy,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, which outputs image data of the generated cocktail recipe as a visual representation.

[0909] (Claim 3)

[0910] The system according to claim 1, which outputs the steps of a generated cocktail recipe in video format.

[0911] "Application Example 1"

[0912] (Claim 1)

[0913] A means of receiving preference information from users,

[0914] A means for searching a database for beverage preparation procedures based on received preference information,

[0915] A means for analyzing search results using a generative model and generating the optimal beverage preparation procedure,

[0916] A means for creating visual information and procedures for the preparation of a generated beverage,

[0917] A means for generating the name of a beverage,

[0918] Means for providing users with the preparation instructions, visual information, and name of the generated beverage,

[0919] A means of visualizing information using a visual display device on a terminal,

[0920] A means of receiving feedback from users and updating the generative model,

[0921] A system that includes this.

[0922] (Claim 2)

[0923] The system according to claim 1, which outputs visual information of the preparation procedure for the generated beverage as an image.

[0924] (Claim 3)

[0925] The system according to claim 1, which outputs the preparation procedure for the generated beverage in video format.

[0926] "Example 2 of combining an emotion engine"

[0927] (Claim 1)

[0928] A means of obtaining preference information and emotional information from users,

[0929] A means for analyzing the user's emotional state based on acquired preference and emotional information,

[0930] Based on the analysis results, a means for searching for cocktail recipes from data storage,

[0931] A means for generating the optimal cocktail recipe from the analysis results using a generation method,

[0932] A means of creating visual data and methods for the generated cocktail recipe,

[0933] A means of generating cocktail names,

[0934] A means of providing users with the recipe, visual data, and name of the generated cocktail,

[0935] A means of obtaining user evaluation information and updating the generation method,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, which outputs the visual data of the generated cocktail recipe as an image.

[0939] (Claim 3)

[0940] The system according to claim 1, which outputs the method of generating a cocktail recipe in video format.

[0941] "Application example 2 when combining with an emotional engine"

[0942] (Claim 1)

[0943] Means for receiving user preference information and positive status,

[0944] A means for analyzing emotional states based on image recognition and voice analysis,

[0945] A means for searching a database for cocktail recipes based on received preference and emotional information,

[0946] A method for generating the optimal cocktail recipe by analyzing search results and sentiment information using a generative model,

[0947] Means for constructing visual data and methods related to generated cocktail recipes,

[0948] A means of generating cocktail titles,

[0949] A means of providing users with the generated cocktail recipe, visual data, and title,

[0950] A means of receiving feedback from users and modifying the generative model,

[0951] A means for displaying the provided information on the display unit of a glasses-type terminal,

[0952] A system that includes this.

[0953] (Claim 2)

[0954] The system according to claim 1, wherein the visual data of the generated cocktail recipe is output as an image format on a glasses-type terminal.

[0955] (Claim 3)

[0956] The system according to claim 1, which outputs the method of generating a cocktail recipe in video format to a glasses-type terminal. [Explanation of Symbols]

[0957] 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 receiving preference information from users, A means for searching a database for cocktail recipes based on received preference information, A method for analyzing search results using a generative model and generating the optimal cocktail recipe, Means for creating visual data and methods for generated cocktail recipes, A means of generating cocktail names, A means of providing users with the recipe, visual data, and name of the generated cocktail, A means of receiving feedback from users and updating the generative model, A system that includes this.

2. The system according to claim 1, which outputs the visual data of the generated cocktail recipe as an image.

3. The system according to claim 1, which outputs the method of generating a cocktail recipe in video format.

Images