System

Abstract

A system is provided.SOLUTION: The system includes a user interface means for inputting a request from a customer, a generation AI model means for generating optimal cocktails from a huge database on the basis of the input request, a display means for displaying recipes, appearances, and names of the generated cocktails, and a feedback collection means for collecting feedback from the user and reflecting it on the generation AI model to improve performances.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] It is necessary to provide a system that eliminates the difficulty bartenders face when creating original cocktails based on customer requests, allowing them to serve unique cocktails that accurately reflect customer desires. It is also necessary to make it easier to incorporate feedback to improve the quality of the cocktails created, thereby increasing customer satisfaction. [Means for solving the problem]

[0005] In order to solve the above problem, the system includes the following means:

[0006] 1. User interface means for inputting customer requests:

[0007] This allows bartenders to accurately input customer desires and send specific requests to the system.

[0008] 2. Generative AI model means to generate the optimal cocktail from a vast database based on the input request:

[0009] The AI ​​model then selects the best cocktail from a database to meet the request, generating the recipe, name, and appearance.

[0010] 3. Display means to show the recipe, appearance and name of the generated cocktail:

[0011] This provides the bartender with visual information about the cocktail that has been created, making it easier to actually create and serve the cocktail.

[0012] 4. A method for collecting user feedback and incorporating it into generative AI models to improve their performance:

[0013] This allows feedback from bartenders to be fed forward to the AI ​​model and reflected in future cocktail creations, improving accuracy and customer satisfaction.

[0014] By combining these means, a system is provided that allows bartenders to more efficiently create original cocktails that meet customers' requests and increase customer satisfaction.

[0015] "Customer" refers to the person ordering a cocktail and to whom the bartender serves.

[0016] A "request" is information that indicates the specific characteristics and requests of a cocktail that a customer wants from the bartender.

[0017] "User interface means" refers to a function that provides an interface for bartenders to input customer requests and feedback.

[0018] "Generative AI model means" refers to a model that uses machine learning and AI technology to generate the optimal cocktail based on a customer's request.

[0019] "Database" refers to data storage that stores information such as cocktail ingredients, recipes, images, and names.

[0020] A "recipe" is information that indicates the specific ingredients and steps for creating a cocktail.

[0021] "Appearance" refers to the visual appearance of the cocktail created, and is shown through images, illustrations, etc.

[0022] "Name" refers to the title or designation given to the created cocktail.

[0023] "Display means" refers to a device or group of devices that has the function of visually providing the bartender with information such as the recipe, appearance, and name of the created cocktail.

[0024] "Feedback collection means" refers to a means that has the function of collecting reactions and evaluations of cocktails from bartenders and reflecting them in the AI ​​model.

[0025] "Feedforward" refers to the process of using collected feedback to improve the AI ​​model for the next cocktail generation.

[0026] "Fine-tuning" refers to the process of adjusting the parameters of a generative AI model to improve its performance.

[0027] "System" refers to a set of devices and software consisting of a user interface means, a generative AI model means, a display means, and a feedback collection means. [Brief explanation of the drawings]

[0028] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0029] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0030] First, the terms used in the following description will be explained.

[0031] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0032] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0033] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0034] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0035] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0036] [First embodiment]

[0037] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0038] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0039] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0040] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0041] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0042] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0043] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0044] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0045] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0046] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0047] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0048] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0049] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers. The system configuration and specific processing flow are described below.

[0050] System configuration:

[0051] 1. User Interface Means (Terminal):

[0052] The bartender provides a graphical user interface (GUI) for inputting customer requests, for example, using an application installed on a tablet or desktop. The screen displays text boxes and options for customers to input their specific requests (e.g., fruit-based, less sweet, specific allergy information, etc.).

[0053] 2. Generative AI model means (server):

[0054] The system receives requests sent from the device and analyzes the request. Based on the analysis results, it runs an AI model that generates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[0055] 3. Database (server):

[0056] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[0057] 4. Display means (terminal):

[0058] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[0059] 5. Feedback collection means (terminal and server):

[0060] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[0061] Program flow:

[0062] User (Bartender):

[0063] The system listens to customer requests and inputs them into the terminal's user interface, for example, specific requests such as "a refreshing fruit-based cocktail" or "some surprise."

[0064] Device:

[0065] The input request information is formatted and sent to the server in an appropriate format such as JSON, which the server then receives and inputs into the generative AI model.

[0066] server:

[0067] The generative AI model analyzes the input request and references the database to generate the optimal cocktail. For example, if the request is for a "refreshing fruit-based cocktail," the AI ​​model selects the appropriate ingredients (e.g., vodka, grapefruit juice, tonic water) from the database and generates the recipe, appearance, and name.

[0068] The generated information (recipe, image of appearance, name) is sent to the terminal.

[0069] Device:

[0070] The received results are displayed to the bartender via a display, who then creates a cocktail based on this information.

[0071] User (Bartender):

[0072] The customer samples the proposed cocktail and inputs feedback based on their reaction, for example, specific comments such as "I wish it looked a little more showy" or "The flavor is a little weak" into the terminal.

[0073] Device:

[0074] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[0075] server:

[0076] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[0077] Examples:

[0078] For example, if a customer requests a "refreshing cocktail with citrus fruits," the bartender inputs this into the terminal. The terminal sends the request to the server, and the AI ​​model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Sunny Surprise") are displayed on the terminal. The bartender uses this information to create the cocktail and serve it to the customer. By collecting customer feedback and incorporating it into next suggestions, the system's accuracy and customer satisfaction can be improved.

[0079] In this way, bartenders can easily and efficiently serve original cocktails, increasing customer satisfaction.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] User (Bartender):

[0083] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can input specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[0084] Step 2:

[0085] Device:

[0086] The input request information is converted into JSON format and sent to the server.

[0087] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[0088] Step 3:

[0089] server:

[0090] Parse the received JSON formatted request and pass it as input to the generative AI model.

[0091] Based on the request, the generative AI model begins the predictive process to create the optimal cocktail.

[0092] Step 4:

[0093] Generative AI model means (server):

[0094] Based on the request, the generative AI model consults a database to select the best ingredients, recipe, appearance, and name.

[0095] For example, a cocktail recipe based on "vodka, blue curacao, and lime juice" can be generated from the database.

[0096] The generated results (recipe, name, and image of appearance) are formatted in JSON and sent to the terminal.

[0097] Step 5:

[0098] Device:

[0099] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[0100] Example: Generated cocktail name "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and image of the appearance.

[0101] Step 6:

[0102] User (Bartender):

[0103] Check the displayed results and create a cocktail.

[0104] Serve cocktails to customers and collect their reactions and feedback.

[0105] Step 7:

[0106] User (Bartender):

[0107] The collected feedback is entered into the device's feedback screen. For example, a specific comment such as "The taste is perfect, but I wish the appearance was a little simpler" is entered.

[0108] Step 8:

[0109] Device:

[0110] The input feedback information is converted into JSON format and sent again to the server.

[0111] Example: { "feedback": "Make it look a little simpler"}

[0112] Step 9:

[0113] server:

[0114] The received feedback is analyzed and used to improve the performance of the generative AI model.

[0115] The feedback information is used as training data for the model and added as new data points.

[0116] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[0117] This allows the system to continuously learn and, for future requests, become more accurate and more likely to suggest cocktails that are more in line with the customer's preferences.

[0118] Example 1

[0119] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0120] Conventional cocktail creation systems have difficulty quickly and accurately suggesting the optimal cocktail for a customer's request. Furthermore, they lack a means to effectively collect user feedback and improve the system's performance. This can lead to a decrease in customer satisfaction.

[0121] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0122] In this invention, the server includes an information input means for inputting requests from customers, a generative AI model means for generating an appropriate cocktail based on the input request, a display means for displaying the recipe, appearance, and name of the generated cocktail, and a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance. This makes it possible to quickly and accurately generate cocktails based on customer requests and improve system performance through feedback.

[0123] "Customer" means the ultimate user to whom the cocktail is served.

[0124] A "request" is information that indicates a customer's specific requests or wishes.

[0125] "Information input means" refers to a device or software for inputting a customer request through a user interface.

[0126] A "generative AI model means" is a means of analyzing input requests and generating optimal cocktails using machine learning and deep learning technologies.

[0127] A "cocktail database" is a collection of data that stores information such as cocktail ingredients, recipes, appearances, and names.

[0128] "Display means" refers to a device or software for visually presenting information about the cocktail created to the bartender.

[0129] "Feedback" means any opinion or comment provided by a customer or bartender regarding the quality or satisfaction of a cocktail.

[0130] The "feedback collection means" is a means for collecting feedback from users and using it to improve the performance of the system.

[0131] A "server" is a computer system that processes requests, runs generative AI models, and stores and manages data.

[0132] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers. The system configuration and specific processing flow are described below.

[0133] System configuration:

[0134] 1. User Interface Means (Terminal):

[0135] The bartender provides a graphical user interface (GUI) for inputting customer requests, for example, using an application installed on a tablet or desktop. The screen displays text boxes and options for customers to input their specific requests (e.g., fruit-based, less sweet, specific allergy information, etc.).

[0136] 2. Generative AI model means (server):

[0137] The system receives requests sent from the device and analyzes the request. Based on the analysis results, it runs an AI model that generates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[0138] 3. Database (server):

[0139] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[0140] 4. Display means (terminal):

[0141] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[0142] 5. Feedback collection means (terminal and server):

[0143] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[0144] Examples:

[0145] For example, if a customer requests a "refreshing cocktail with citrus fruits," the bartender inputs this into the terminal. The terminal sends the request to the server, and the generative AI model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Sunny Surprise") are displayed on the terminal. The bartender uses this information to create the cocktail and serve it to the customer. By collecting customer feedback and incorporating it into future suggestions, the system's accuracy and customer satisfaction can be improved.

[0146] Example prompt sentence:

[0147] "Create a refreshing fruit-based cocktail."

[0148] "Please suggest a refreshing cocktail using citrus fruits."

[0149] Through this system, bartenders can easily and efficiently serve original cocktails, increasing customer satisfaction.

[0150] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0151] Step 1:

[0152] User (Bartender):

[0153] It listens to customer requests and inputs them into the terminal's user interface. Examples of prompts include "a refreshing fruit-based cocktail" and "low-alcohol."

[0154] Specific behavior:

[0155] Operate tablet and desktop applications and enter information in text boxes and select options.

[0156] input:

[0157] Customer's specific request (text request)

[0158] output:

[0159] Request information entered on the terminal

[0160] Step 2:

[0161] Device:

[0162] The input request information is formatted into an appropriate format such as JSON and sent to the server.

[0163] Specific behavior:

[0164] The input request information is formatted and sent to the server as a "POST" request.

[0165] input:

[0166] Request information entered by the user

[0167] output:

[0168] JSON formatted request information sent to the server

[0169] Step 3:

[0170] server:

[0171] The server inputs the received request information into a generative AI model. The generative AI model analyzes the request and generates the optimal cocktail by referencing a cocktail database. For example, for a request such as "fruit-based, low-alcohol," it generates a recipe by combining suitable ingredients.

[0172] Specific behavior:

[0173] The server parses the request information and inputs it into a generative AI model.

[0174] The AI ​​model analyzes the request and searches a database to select the appropriate ingredients (e.g., lemon juice, orange liqueur, soda).

[0175] input:

[0176] JSON formatted request information sent to the server

[0177] output:

[0178] Recipe, name, and visual image of the generated cocktail

[0179] Step 4:

[0180] server:

[0181] The generated cocktail information (ingredients, recipe, name, appearance) is sent to the terminal.

[0182] Specific behavior:

[0183] The generated results are compiled in JSON format and sent to the terminal as a response.

[0184] input:

[0185] Cocktail information generated by a generative AI model

[0186] output:

[0187] JSON formatted generation result information sent to the device

[0188] Step 5:

[0189] Device:

[0190] The received generated results are displayed to the bartender via a display means.

[0191] Specific behavior:

[0192] It parses the JSON response and displays the information in a UI component, such as the recipe text, the name of the cocktail, and an image of its appearance.

[0193] input:

[0194] JSON formatted generation result information sent from the server

[0195] output:

[0196] Cocktail information displayed on the device screen

[0197] Step 6:

[0198] User (Bartender):

[0199] Create a cocktail based on the information provided and serve it to the customer.

[0200] Specific behavior:

[0201] The bartender mixes the cocktail according to the displayed recipe and serves the finished cocktail to the customer.

[0202] input:

[0203] Cocktail recipes, names, and images of their appearance displayed on the device

[0204] output:

[0205] The actual cocktail

[0206] Step 7:

[0207] User (Bartender):

[0208] Customers can input feedback based on their reactions to the proposed cocktails, for example, by entering specific comments such as "I wish it looked a little more showy" or "The flavor is a little weak."

[0209] Specific behavior:

[0210] Enter specific improvements and customer reactions in the feedback section.

[0211] input:

[0212] Customer reactions and bartender feedback (textual feedback)

[0213] output:

[0214] Feedback information entered on the device

[0215] Step 8:

[0216] Device:

[0217] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[0218] Specific behavior:

[0219] The feedback information is formatted and sent to the server as a "POST" request.

[0220] input:

[0221] User-entered feedback information

[0222] output:

[0223] Feedback information sent to the server in JSON format

[0224] Step 9:

[0225] server:

[0226] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[0227] Specific behavior:

[0228] The feedback information is stored in a database and analytical algorithms are used to update the AI ​​model, for example by using machine learning libraries to adjust the model parameters.

[0229] input:

[0230] Feedback information sent to the server in JSON format

[0231] output:

[0232] Fine-tuned generative AI models

[0233] The above is the specific flow of the system program processing.

[0234] (Application example 1)

[0235] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0236] Traditionally, the original cocktails that bartenders offer to customers have depended on the bartender's own experience and creativity, making it difficult to quickly and accurately meet the diverse needs of customers. Furthermore, there are limited services that allow customers to enjoy original cocktails at home, making it difficult to increase customer satisfaction. The present invention aims to solve these problems.

[0237] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0238] In this invention, the server includes a user interface means for inputting requests from customers, a generative AI model means for generating optimal cocktails from a vast database based on the input requests, a display means for displaying the recipe, appearance, and name of the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance, and a delivery means for ordering the suggested cocktail via smartphone and delivering it via a delivery service. This enables bartenders to respond quickly and accurately to the diverse needs of customers, and further increases customer satisfaction by providing a delivery service that allows customers to enjoy original cocktails at home.

[0239] The "user interface means" is an interface for inputting requests from customers, which can be operated via a terminal such as a smartphone.

[0240] "Generative AI model means" refers to an AI model that generates the optimal cocktail from a huge database based on an input request, and uses machine learning and deep learning technologies.

[0241] The "display means" is a display device for visually presenting the recipe, appearance, and name of the created cocktail.

[0242] "Feedback collection means" is a general term for the interface that collects feedback from users and reflects it as learning data for the generative AI model, and the system that analyzes it.

[0243] "Delivery method" refers to the method by which the suggested cocktail is ordered via smartphone and delivered to the customer via a delivery service.

[0244] A "generative AI model" is an algorithm or machine learning model used to analyze a customer request and generate the appropriate cocktail ingredients, recipe, appearance, and name.

[0245] The "database" is an information aggregation system that stores information such as cocktail ingredients, recipes, images, and names.

[0246] A "request" is information about the characteristics or elements of a cocktail desired by a customer.

[0247] A "recipe" is a set of specific steps and ingredient combinations for creating a cocktail.

[0248] A "smartphone" is a mobile device used by customers to order cocktails.

[0249] A "display device" is an electronic device for visually displaying information.

[0250] The system of this invention is designed to propose the optimal original cocktail based on a customer's request and deliver that cocktail to the customer through a delivery service. The system configuration and specific processing flow are described below.

[0251] System Configuration

[0252] 1. User Interface Methods

[0253] This is an interface that allows customers to input their requests using their smartphones, with text boxes and options to input their specific preferences (e.g., fruit-based, less sweet, specific allergy information, etc.).

[0254] 2. Generative AI Model Means

[0255] An AI model installed on the server receives and analyzes requests sent from smartphones. Based on the analysis results, it creates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[0256] 3. Database

[0257] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[0258] 4. Display means

[0259] The generated cocktail information is displayed on the smartphone screen, including the cocktail's recipe, name, and appearance (image).

[0260] 5. Feedback Collection Methods

[0261] It provides an interface for customers to input feedback about cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[0262] 6. Delivery Method

[0263] It is a system that allows customers to order suggested cocktails and have them delivered through a delivery service.

[0264] Program processing

[0265] User (customer)

[0266] Customers open a cocktail delivery app on their smartphone and enter their request, such as a "refreshing fruit-based cocktail" or "I'd like something surprising."

[0267] Device (smartphone)

[0268] The input request information is formatted and sent to the server in an appropriate format such as JSON, which the server then receives and inputs into the generative AI model.

[0269] server

[0270] The generative AI model analyzes the input request and references the database to generate the optimal cocktail. For example, if the request is for a "refreshing fruit-based cocktail," the AI ​​model selects appropriate ingredients from the database (e.g., vodka, grapefruit juice, tonic water), generates a recipe, appearance, and name, and then sends the generated information (recipe, image of appearance, and name) to the device.

[0271] Device (smartphone)

[0272] The generated results are then displayed to the customer via a display device, who then orders a cocktail based on this information.

[0273] User (customer)

[0274] Customers receive the suggested cocktail, sample it, and then provide feedback on the cocktail, such as specific comments like "I wish it looked a little more showy" or "It tastes a little bland," into the app.

[0275] Device (smartphone)

[0276] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[0277] server

[0278] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[0279] Specific examples

[0280] For example, if a customer requests a "refreshing cocktail with citrus fruits," they input this using their smartphone. The device sends the request to the server, and the AI ​​model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Citrus Breeze") are displayed on the device. The customer uses this information to order the cocktail and receive it through a delivery service. Customers can sample the cocktail and provide feedback, which will help improve suggestions for future visits.

[0281] Prompt Sentence Examples

[0282] "Customer Request: A refreshing cocktail using citrus fruits"

[0283] "Suggested cocktail name: Citrus Breeze"

[0284] "Ingredients: Lemon juice, orange liqueur, soda"

[0285] Recipe: Mix ingredients, chill and pour into a glass.

[0286] "Image: URL / Image"

[0287] As described above, the present invention makes it possible to provide customers with an efficient and highly accurate original cocktail proposal and delivery service, thereby increasing customer satisfaction.

[0288] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0289] Step 1:

[0290] A user (customer) launches a cocktail delivery app on their smartphone and inputs a cocktail request. For example, they might input, "I'd like a refreshing fruit-based cocktail." The device formats this request information and converts it into JSON-formatted data. The input is the customer's request, and the output is the JSON-formatted request data.

[0291] Step 2:

[0292] The terminal (smartphone) transmits the formatted request data to the server. The transmitted data is the customer's request information, and the terminal transfers the request data to the server using a communication means.

[0293] Step 3:

[0294] The server analyzes the request data received from the terminal. The input is the request data in JSON format, and the output is the analyzed request information. This analysis includes parsing and data decomposition.

[0295] Step 4:

[0296] The server's generative AI model selects the appropriate cocktail ingredients, recipe, image, and name from a database based on the analyzed request information. The generative AI model uses machine learning and deep learning algorithms, and the input is the analyzed request information, and the output is the generated cocktail information.

[0297] Step 5:

[0298] The server sends the generated cocktail information (recipe, image of appearance, name) to the terminal. This information is sent in JSON format, the input is the cocktail information from the generative AI model, and the output is the cocktail information sent to the terminal.

[0299] Step 6:

[0300] The terminal (smartphone) displays the received cocktail information on the user interface. The user checks this displayed information and orders a cocktail. The input is the cocktail information received from the server, and the output is the cocktail information displayed on the user interface.

[0301] Step 7:

[0302] The user (customer) confirms the delivery order based on the displayed cocktail information. The input is the cocktail information, and the output is the confirmation of the delivery order.

[0303] Step 8:

[0304] The delivery vehicle prepares and delivers a cocktail to the customer based on the user's order information. The input is the confirmed delivery order information, and the output is the cocktail delivered to the customer.

[0305] Step 9:

[0306] The user (customer) tastes the cocktail they receive and enters their feedback in the app. The input is the customer's feedback information, and the output is formatted feedback data.

[0307] Step 10:

[0308] The terminal (smartphone) formats the feedback information and sends it to the server in JSON format. The input is the customer feedback information, and the output is the feedback data sent to the server.

[0309] Step 11:

[0310] The server analyzes the received feedback information and uses it as data to fine-tune the generative AI model. The input is the feedback data in JSON format, and the output is the updated parameters of the generative AI model. This will result in more accurate cocktail generation results from the next time onwards.

[0311] The above is the specific processing flow of this program.

[0312] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0313] The system of the present invention is designed to enable bartenders to propose optimal original cocktails to customers, and the system configuration and specific processing flow will be described in detail below.

[0314] System configuration:

[0315] 1. User Interface Means (Terminal):

[0316] It provides a graphical user interface (GUI) for bartenders to input requests from customers, and in addition to the existing interface, it also integrates a camera and microphone to recognize the user's facial expressions and tone of voice.

[0317] 2. Generative AI model means (server):

[0318] The system receives requests sent from devices, analyzes the content of the requests, and then operates an AI model that generates cocktails based on the analysis results by combining suitable ingredients, recipes, appearances, and names from a vast database.

[0319] 3. Database (server):

[0320] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[0321] 4. Display means (terminal):

[0322] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[0323] 5. Feedback collection means (terminal and server):

[0324] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[0325] 6. Emotion engine means (server):

[0326] It is an engine for recognizing user emotions, collecting emotional data through facial expressions, voice tone, and language analysis. The emotional data is analyzed along with feedback and reflected in the AI ​​model.

[0327] Program flow:

[0328] User (Bartender):

[0329] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can enter specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[0330] Device:

[0331] The input request information is converted into JSON format and sent to the server.

[0332] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[0333] In addition, the device's camera and microphone collect the user's facial expressions and vocal tone and send them to the emotion engine.

[0334] server:

[0335] Parse the received JSON formatted request and pass it as input to the generative AI model.

[0336] The emotion engine analyzes the collected data and determines the user's emotions.

[0337] Based on the request and sentiment data, the generative AI model begins the predictive process to create the optimal cocktail.

[0338] Generative AI model means (server):

[0339] Based on the request, the generative AI model consults a database to select the best ingredients, recipe, appearance, and name.

[0340] For example, a cocktail recipe based on "vodka, blue curacao, and lime juice" can be generated from the database.

[0341] The generated results (recipe, name, and image of appearance) are formatted in JSON and sent to the terminal.

[0342] Device:

[0343] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[0344] Example: Generated cocktail name "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and image of the appearance.

[0345] User (Bartender):

[0346] Check the displayed results and create a cocktail.

[0347] Serve cocktails to customers and collect their reactions and feedback.

[0348] Device:

[0349] The collected feedback is converted into JSON format and sent back to the server.

[0350] Example: { "feedback": "Make it look a little simpler"}

[0351] Additionally, the emotion engine transmits any additional emotion data collected back to the server.

[0352] server:

[0353] The received feedback and sentiment data is analyzed and used to improve the performance of the generative AI model.

[0354] The feedback information is used as training data for the model and added as new data points.

[0355] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[0356] This allows the system to continuously learn, and for future requests, it will be able to suggest cocktails that are more accurate and take into account both the customer's wishes and emotions. For example, if a customer requests a "refreshing and energizing cocktail" and the emotion engine detects the customer's excited state, the generative AI model will suggest a "citrus and mint-based energy booster cocktail" and provide the result to the bartender. In this way, more personalized cocktails can be offered.

[0357] The processing flow will be explained below.

[0358] Step 1:

[0359] User (Bartender):

[0360] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can input specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[0361] Step 2:

[0362] Device:

[0363] The input request information is converted into JSON format and sent to the server.

[0364] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[0365] In addition, the device's camera and microphone are used to capture the user's (bartender's) facial expressions and voice tone in real time and send the data to the emotion engine.

[0366] Step 3:

[0367] server:

[0368] Parse the received JSON formatted request and pass it as input to the generative AI model.

[0369] The emotion engine analyzes the collected facial expressions and voice tones to determine the user's emotional state. For example, the emotion engine can detect the user's excitement or satisfaction.

[0370] Step 4:

[0371] Generative AI model means (server):

[0372] Based on the request and emotional data, the AI ​​model consults a database to generate the optimal cocktail.

[0373] For example, it generates cocktail recipes based on "vodka, blue curacao, and lime juice" from the database and combines them, including their appearance and names.

[0374] Step 5:

[0375] Device:

[0376] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[0377] The generated results include the cocktail name "Blue Harmony", the recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and an image of its appearance.

[0378] Step 6:

[0379] User (Bartender):

[0380] Check the displayed results and create a cocktail.

[0381] Serve cocktails to customers and collect their reactions and feedback.

[0382] Step 7:

[0383] User (Bartender):

[0384] Customer feedback is entered into the device's feedback screen. For example, specific comments such as "It looks too flashy" or "The flavor is a little weak" are entered.

[0385] Step 8:

[0386] Device:

[0387] The input feedback information is converted into JSON format and sent to the server.

[0388] Example: { "feedback": "Make it look a little simpler"}

[0389] Additionally, any additional emotional data collected by the emotion engine (e.g., customer smiles or changes in voice tone) is sent back to the server.

[0390] Step 9:

[0391] server:

[0392] The received feedback and sentiment data is analyzed and used to improve the performance of the generative AI model.

[0393] Feedback information and emotion data are used as training data for the model and added as new data points.

[0394] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[0395] This allows the system to continuously learn, and for future requests, it will be able to suggest cocktails that are more accurate and take into account both the customer's wishes and emotions. For example, if a customer requests a "refreshing and energizing cocktail" and the emotion engine detects the customer's excited state, the generative AI model will suggest a "citrus and mint-based energy booster cocktail" and provide the result to the bartender. In this way, more personalized cocktails can be offered.

[0396] Example 2

[0397] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0398] Conventional cocktail recommendation systems are based solely on customer requests and do not fully consider customer sentiment or real-time feedback. This makes it difficult to recommend cocktails that will increase customer satisfaction. Furthermore, the collection and application of feedback is insufficient, limiting improvements to the system's performance.

[0399] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0400] In this invention, the server includes an information input means for inputting requests from customers, an input analysis means for converting the input request into JSON format and collecting user emotional data according to the request, an emotional analysis means for analyzing the collected emotional data and passing it as input to a generative AI model, a generative AI model means for generating an optimal cocktail based on the input request and emotional data, a result display means for displaying the recipe, appearance, and name of the generated cocktail, and a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance. This enables personalized cocktail suggestions that take customer emotions into consideration and continuous performance improvement of the system by reflecting feedback in real time.

[0401] The "information input means" is an interface for receiving requests from customers, and includes a graphical user interface (GUI) and a voice input device.

[0402] An "input analysis means" is a device or software that has the function of converting input requests into JSON format and collecting customer emotional data in response to the requests.

[0403] An "emotion analysis means" is a device or software that has the function of analyzing collected emotional data and inputting the results into a generative AI model.

[0404] The "generative AI model means" is an artificial intelligence model for generating optimal cocktails based on input requests and emotional data.

[0405] The "result display means" is a display or other display device for displaying the recipe, appearance, and name of the created cocktail.

[0406] A "feedback collection means" is a device or software that collects feedback from users and reflects that information in the generative AI model.

[0407] The system of the present invention is designed to enable bartenders to propose the perfect original cocktail to each customer. The system is mainly composed of a terminal, a server, and various related means. Each component will be described in detail below.

[0408] Information input means (terminal)

[0409] This is an interface through which bartenders can input requests from customers. Specifically, a graphical user interface (GUI) is provided, through which bartenders can input customer requests. Furthermore, it is equipped with a camera and microphone, and can also collect emotional data such as facial expressions and voice tone of the customer.

[0410] Input analysis means (terminal)

[0411] It converts input requests into JSON format and analyzes the collected emotional data. This data is sent to a server (described later) and used as input for a generative AI model.

[0412] Emotion analysis means (server)

[0413] The server analyzes the received emotional data, which includes facial expression recognition and voice tone analysis, to determine the customer's emotional state.

[0414] Generative AI model means (server)

[0415] The generative AI model on the server generates the optimal cocktail based on the input request and emotional data, referencing information stored in a database such as ingredients, recipe, appearance, and name to generate the most suitable cocktail recipe.

[0416] Result display means (terminal)

[0417] This is a display device for presenting information about the created cocktail to the bartender. The cocktail recipe, name, and image of the appearance sent from the server are displayed.

[0418] Feedback collection means (terminals and servers)

[0419] The bartender collects customer feedback and sends it to the server via their device. The server analyzes this feedback and uses it as training data for the generative AI model. This feedback allows the system to continuously learn and is reflected in future cocktail creations.

[0420] For example, if a customer requests, "Please recommend a fruit-based cocktail with a moderate sweetness," the bartender enters this information into the terminal interface. The terminal converts the input information into JSON format and sends it to the server. At the same time, the terminal collects the customer's facial expressions and voice, which are also sent to the server. An emotion analysis method on the server analyzes this data, and a generative AI model generates the optimal cocktail. The generated cocktail information is sent back to the terminal and displayed to the bartender. The bartender creates a cocktail based on this information and serves it to the customer.

[0421] In this way, the system makes personalized cocktail suggestions that take into account the customer's request and emotional state, and continuously improves the system's performance based on collected feedback, resulting in higher customer satisfaction.

[0422] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0423] Step 1:

[0424] User (Bartender):

[0425] The cocktail request is taken from the customer and entered into the terminal's information input means.

[0426] (Input): Customer request (e.g., "A fruit-based cocktail with a moderate sweetness")

[0427] (Output): Text data entered into the interface

[0428] (Specific action): The bartender enters "a fruit-based cocktail with a moderate sweetness" into the GUI screen.

[0429] Step 2:

[0430] Device:

[0431] The system converts the input request into JSON format and sends it to the server, and also uses the device's camera and microphone to collect the customer's facial expressions and voice tone.

[0432] (Input): Text data entered into the interface

[0433] (Output): Request data and emotion data in JSON format (e.g., { "request": "A fruit-based cocktail with a moderate sweetness", "emotion": "neutral"})

[0434] (Specific operation): The device converts the request into the format { "request": "A fruit-based, lightly sweetened cocktail"}, captures the customer's face and voice data, and sends it to the server.

[0435] Step 3:

[0436] server:

[0437] The transmitted request and emotion data are received, and the emotion data is analyzed by emotion analysis means.

[0438] (Input): Request data and emotion data in JSON format

[0439] (Output): Parsed emotion information (e.g. "neutral")

[0440] (Specific behavior): The server analyzes the received data and determines the request for a "fruit-based, lightly sweetened cocktail" and the emotional state as "neutral."

[0441] Step 4:

[0442] server:

[0443] Based on the analysis results, a generative AI model creates the optimal cocktail.

[0444] (Input): Request data (e.g., "A fruit-based cocktail with a moderate sweetness") and sentiment data (e.g., "neutral")

[0445] (Output): Cocktail recipe, name, and image (e.g. "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice")

[0446] (Specific operation): The generative AI model references the database, generates a cocktail that matches the request, converts the information into JSON format, and sends it to the terminal.

[0447] Step 5:

[0448] Device:

[0449] The generated results received from the server are analyzed and displayed on the user interface.

[0450] (Input): Cocktail creation data in JSON format (e.g., { "name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image": "image_url"})

[0451] (Output): Cocktail information in display format

[0452] (Specific operation): The device analyzes the received data and displays the cocktail name "Blue Harmony," its recipe, and an image of its appearance on the display.

[0453] Step 6:

[0454] User (Bartender):

[0455] Based on the displayed cocktail information, the specified cocktail is created and served to the customer.

[0456] (Input): Cocktail recipe, name, and image (e.g., "Blue Harmony" with recipe "50ml vodka, 20ml blue curacao, 30ml lime juice")

[0457] (Output): Finished cocktail

[0458] (Specific action): The bartender creates a cocktail based on the displayed recipe by mixing 50ml of vodka, 20ml of blue curacao, and 30ml of lime juice.

[0459] Step 7:

[0460] User (Bartender):

[0461] Serve cocktails to customers and collect their reactions and feedback.

[0462] (Input): Customer feedback (e.g., "Please make it look a little simpler")

[0463] (Output): Collected feedback

[0464] (Specific action): The bartender listens to the customer's feedback and enters it into the terminal.

[0465] Step 8:

[0466] Device:

[0467] The collected feedback is converted into JSON format and sent to the server.

[0468] (Input): Customer feedback (e.g., "Please make it look a little simpler")

[0469] (Output): Feedback data in JSON format (e.g., { "feedback": "I'd like it to look a little simpler"})

[0470] (Specific operation): The device converts the feedback into JSON format and sends it to the server.

[0471] Step 9:

[0472] server:

[0473] The feedback received is analyzed and used to improve the generative AI model.

[0474] (Input): Feedback data in JSON format (e.g., { "feedback": "I'd like it to look a little simpler"})

[0475] (Output): Updated generative AI model

[0476] (Specific operation): The generative AI model is fine-tuned based on the feedback data and reflected in the system's next cocktail generation.

[0477] (Application example 2)

[0478] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0479] While conventional systems can reflect specific customer requests, it is difficult to incorporate the customer's emotions and preferences. Therefore, there is a need for a method that can analyze the customer's emotions from their facial expressions and tone of voice to suggest more personalized cocktails. It is necessary to solve these issues and improve customer satisfaction.

[0480] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0481] In this invention, the server includes a user interface means for inputting requests from customers, a generative AI model means for generating optimal cocktails based on the input requests and customer emotion data, a display means for displaying the recipe, appearance, and name of the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance, and an emotion engine means for analyzing facial expressions and voice tones to collect emotion data, thereby enabling more personalized cocktail suggestions that reflect the customer's emotions and preferences.

[0482] The "user interface means" is a means for a customer to input a request, and provides a graphical user interface or a voice input interface.

[0483] "Generative AI model means" refers to an artificial intelligence model that generates the optimal cocktail from a vast database based on input requests and customer emotional data.

[0484] "Display means" refers to a display device or screen that visually shows information such as the recipe, appearance, and name of the created cocktail to the bartender and customer.

[0485] The "feedback collection means" is a means for collecting feedback from users (bartenders or customers) and sending it to the server, which contributes to improving the performance of the generative AI model.

[0486] The "emotion engine means" is a means for analyzing the customer's facial expressions and voice tone and collecting emotional data.

[0487] A "request" is information describing the conditions and characteristics of the cocktail a customer desires, and refers to the data entered into the system.

[0488] "Cocktail generation" refers to the process of determining the optimal cocktail ingredients, recipe, appearance, and name based on the input request and emotional data.

[0489] The "database" refers to data storage that accumulates information such as cocktail ingredients, recipes, images, and names, and is used as a reference for the generative AI model.

[0490] "Facial Expression" is a visual representation of a customer's emotional state that is analyzed by a camera and / or emotion engine means.

[0491] "Voice Tone" is an acoustic expression that indicates the customer's emotional state and is analyzed by the microphone and emotion engine means.

[0492] The system for carrying out this invention includes the following main components and procedures: an interface means for a user to input a request, a generative AI model means for generating an optimal cocktail based on the request and emotional data, a display means for displaying information about the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model, and an emotion engine means for analyzing the facial expressions and voice tones of customers to collect emotional data.

[0493] The server achieves these functions by using the following means:

[0494] 1. User Interface Means

[0495] A graphical user interface (GUI) is implemented on devices such as smartphones and tablets, allowing customers to input their cocktail requests. The devices are also equipped with cameras and microphones, allowing them to simultaneously collect customers' facial expressions and vocal tones, thereby obtaining emotional data.

[0496] 2. Generative AI Model Means

[0497] The server analyzes the received request and emotional data using algorithms that analyze natural language processing, facial expressions, and voice tones. The analyzed data is then input into a generative AI model, which then selects from a vast database of cocktails to create a cocktail that combines the optimal ingredients, recipe, appearance, and name.

[0498] 3. Display means

[0499] The generated cocktail information (recipe, appearance, name) is displayed on the smartphone or tablet screen in a visually appealing format for bartenders and customers to review at a glance.

[0500] 4. Feedback Collection Methods

[0501] Users (bartenders or customers) input their ratings and feedback on cocktails. This feedback is sent from the device to the server and analyzed. The results of the analysis of the feedback are added as training data for the generative AI model, contributing to performance improvement.

[0502] 5. Emotional Engine Means

[0503] The server uses data collected from cameras and microphones to recognize the customer's emotions. Using algorithms that analyze facial expressions and vocal tones, detailed emotional data is extracted, which is then used as part of the cocktail creation process.

[0504] Specific examples

[0505] For example, if a customer requests a "fruit-based cocktail with a moderate sweetness," the system operates as follows:

[0506] 1. The customer types in their request, and their facial expressions and voice tone are collected by a camera and microphone.

[0507] 2. The server analyzes the request and emotion data and inputs it into a generative AI model.

[0508] 3. The generative AI model selects the optimal cocktail, "Blue Harmony," from the database and generates a recipe and visual information.

[0509] 4. This information will be displayed on your smartphone or tablet screen.

[0510] Prompt Sentence Examples

[0511] Request: Fruit-based cocktail with a moderate sweetness

[0512] Emotion data: facial expressions and vocal tones

[0513] In this way, the system can generate and display personalized cocktails based on the customer's emotions and requests.

[0514] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0515] Step 1:

[0516] When a user (customer) orders a cocktail at a bar, they input their cocktail request using the user interface on their smartphone or tablet.

[0517] Input: The request entered by the customer (e.g., "A fruit-based cocktail with a moderate sweetness").

[0518] Output: Request data in JSON format (e.g., {"request": "A fruit-based cocktail with a moderate sweetness"}).

[0519] Step 2:

[0520] The device's camera and microphone collect the customer's facial expressions and voice tone, and this data is sent to the emotion engine means.

[0521] Input: Raw facial expression and speech tone data.

[0522] Output: Emotion data (e.g., {"emotion": "happiness"}).

[0523] Step 3:

[0524] The device combines the request data and emotion data, converts them into JSON format, and sends them to the server.

[0525] Input: Request data and emotion data.

[0526] Output: Combined data in JSON format (e.g., {"request": "Fruit-based cocktail with a moderate sweetness", "emotion": "happiness"}).

[0527] Step 4:

[0528] The server parses the received JSON-formatted data and inputs it into the generative AI model.

[0529] Input: The combined data in JSON format.

[0530] Output: The input data (request and sentiment data converted into internal data structures) in a format suitable for the generative AI model.

[0531] Step 5:

[0532] A generative AI model references the database and generates the optimal cocktail ingredients, recipe, name, and appearance.

[0533] Input: Parsed request and sentiment data.

[0534] Output: Information about the generated cocktail (e.g., {"name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image_url": " / images / blue_harmony.jpg"}).

[0535] Step 6:

[0536] The server converts the cocktail creation results into JSON format and sends it to the terminal.

[0537] Input: Generated cocktail information (internal data structure).

[0538] Output: JSON formatted result data (e.g., {"name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image_url": " / images / blue_harmony.jpg"}).

[0539] Step 7:

[0540] The terminal analyzes the received JSON formatted generated result and converts it into a format to be displayed on the user interface.

[0541] Input: The generated result data in JSON format.

[0542] Output: Format displayed in the user interface (visual cocktail information).

[0543] Step 8:

[0544] The user (bartender) checks the displayed results and creates a cocktail. The user serves the cocktail to customers and collects their reactions and feedback.

[0545] Input: Cocktail information displayed in the user interface.

[0546] Output: Actual cocktails and customer feedback.

[0547] Step 9:

[0548] The device converts the collected feedback into JSON format and sends it back to the server.

[0549] Input: Customer feedback.

[0550] Output: Feedback data in JSON format (e.g. {"feedback": "Make it look a little simpler"}).

[0551] Step 10:

[0552] The server analyzes the received feedback and additional emotional data and uses it to improve the performance of the generative AI model.

[0553] Input: Feedback and sentiment data in JSON format.

[0554] Output: A fine-tuned generative AI model.

[0555] These processing steps allow the system to make more personalized cocktail suggestions based on customer sentiment and requests.

[0556] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0557] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0558] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0559] [Second embodiment]

[0560] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0561] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0562] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0563] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0564] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0565] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0566] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0567] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0568] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0569] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0570] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0571] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0572] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers. The system configuration and specific processing flow are described below.

[0573] System configuration:

[0574] 1. User Interface Means (Terminal):

[0575] The bartender provides a graphical user interface (GUI) for inputting customer requests, for example, using an application installed on a tablet or desktop. The screen displays text boxes and options for customers to input their specific requests (e.g., fruit-based, less sweet, specific allergy information, etc.).

[0576] 2. Generative AI model means (server):

[0577] The system receives requests sent from the device and analyzes the request. Based on the analysis results, it runs an AI model that generates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[0578] 3. Database (server):

[0579] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[0580] 4. Display means (terminal):

[0581] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[0582] 5. Feedback collection means (terminal and server):

[0583] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[0584] Program flow:

[0585] User (Bartender):

[0586] The system listens to customer requests and inputs them into the terminal's user interface, for example, specific requests such as "a refreshing fruit-based cocktail" or "some surprise."

[0587] Device:

[0588] The input request information is formatted and sent to the server in an appropriate format such as JSON, which the server then receives and inputs into the generative AI model.

[0589] server:

[0590] The generative AI model analyzes the input request and references the database to generate the optimal cocktail. For example, if the request is for a "refreshing fruit-based cocktail," the AI ​​model selects the appropriate ingredients (e.g., vodka, grapefruit juice, tonic water) from the database and generates the recipe, appearance, and name.

[0591] The generated information (recipe, image of appearance, name) is sent to the terminal.

[0592] Device:

[0593] The received results are displayed to the bartender via a display, who then creates a cocktail based on this information.

[0594] User (Bartender):

[0595] Customers can taste the proposed cocktails and input their feedback based on their reactions, such as "I wish it looked a little more showy" or "The flavor is a little weak."

[0596] Device:

[0597] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[0598] server:

[0599] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[0600] Examples:

[0601] For example, if a customer requests a "refreshing cocktail with citrus fruits," the bartender inputs this into the terminal. The terminal sends the request to the server, and the AI ​​model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Sunny Surprise") are displayed on the terminal. The bartender uses this information to create the cocktail and serve it to the customer. Feedback from customers is collected and reflected in future suggestions, improving the system's accuracy and customer satisfaction.

[0602] In this way, bartenders can easily and efficiently serve original cocktails, increasing customer satisfaction.

[0603] The processing flow will be explained below.

[0604] Step 1:

[0605] User (Bartender):

[0606] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can input specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[0607] Step 2:

[0608] Device:

[0609] The input request information is converted into JSON format and sent to the server.

[0610] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[0611] Step 3:

[0612] server:

[0613] Parse the received JSON formatted request and pass it as input to the generative AI model.

[0614] Based on the request, the generative AI model begins the predictive process to create the optimal cocktail.

[0615] Step 4:

[0616] Generative AI model means (server):

[0617] Based on the request, the generative AI model consults a database to select the best ingredients, recipe, appearance, and name.

[0618] For example, a cocktail recipe based on "vodka, blue curacao, and lime juice" can be generated from the database.

[0619] The generated results (recipe, name, and image of appearance) are formatted in JSON and sent to the terminal.

[0620] Step 5:

[0621] Device:

[0622] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[0623] Example: Generated cocktail name "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and image of the appearance.

[0624] Step 6:

[0625] User (Bartender):

[0626] Check the displayed results and create a cocktail.

[0627] Serve cocktails to customers and collect their reactions and feedback.

[0628] Step 7:

[0629] User (Bartender):

[0630] The collected feedback is entered into the device's feedback screen. For example, a specific comment such as "The taste is perfect, but I wish the appearance was a little simpler" is entered.

[0631] Step 8:

[0632] Device:

[0633] The input feedback information is converted into JSON format and sent again to the server.

[0634] Example: { "feedback": "Make it look a little simpler"}

[0635] Step 9:

[0636] server:

[0637] The received feedback is analyzed and used to improve the performance of the generative AI model.

[0638] The feedback information is used as training data for the model and added as new data points.

[0639] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[0640] This allows the system to continuously learn and, for future requests, become more accurate and more likely to suggest cocktails that are more in line with the customer's preferences.

[0641] Example 1

[0642] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0643] Conventional cocktail creation systems have difficulty quickly and accurately suggesting the best cocktail for a customer's request. Furthermore, they lack a means to effectively collect user feedback and improve the system's performance. This can lead to a decrease in customer satisfaction.

[0644] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0645] In this invention, the server includes an information input means for inputting requests from customers, a generative AI model means for generating an appropriate cocktail based on the input request, a display means for displaying the recipe, appearance, and name of the generated cocktail, and a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance. This makes it possible to quickly and accurately generate cocktails based on customer requests and improve system performance through feedback.

[0646] "Customer" means the ultimate user to whom the cocktail is served.

[0647] A "request" is information that indicates a customer's specific requests or wishes.

[0648] "Information input means" refers to a device or software for inputting a customer request through a user interface.

[0649] A "generative AI model means" is a means of analyzing input requests and generating optimal cocktails using machine learning and deep learning technologies.

[0650] A "cocktail database" is a collection of data that stores information such as cocktail ingredients, recipes, appearances, and names.

[0651] "Display means" refers to a device or software for visually presenting information about the cocktail created to the bartender.

[0652] "Feedback" means any opinion or comment provided by a customer or bartender regarding the quality or satisfaction of a cocktail.

[0653] The "feedback collection means" is a means for collecting feedback from users and using it to improve the performance of the system.

[0654] A "server" is a computer system that processes requests, runs generative AI models, and stores and manages data.

[0655] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers. The system configuration and specific processing flow are described below.

[0656] System configuration:

[0657] 1. User Interface Means (Terminal):

[0658] The bartender provides a graphical user interface (GUI) for inputting customer requests, for example, using an application installed on a tablet or desktop. The screen displays text boxes and options for customers to input their specific requests (e.g., fruit-based, less sweet, specific allergy information, etc.).

[0659] 2. Generative AI model means (server):

[0660] The system receives requests sent from the device and analyzes the request. Based on the analysis results, it runs an AI model that generates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[0661] 3. Database (server):

[0662] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[0663] 4. Display means (terminal):

[0664] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[0665] 5. Feedback collection means (terminal and server):

[0666] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[0667] Examples:

[0668] For example, if a customer requests a "refreshing cocktail with citrus fruits," the bartender inputs this into the terminal. The terminal sends the request to the server, and the generative AI model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Sunny Surprise") are displayed on the terminal. The bartender uses this information to create the cocktail and serve it to the customer. By collecting customer feedback and incorporating it into future suggestions, the system's accuracy and customer satisfaction can be improved.

[0669] Example prompt sentence:

[0670] "Create a refreshing fruit-based cocktail."

[0671] "Please suggest a refreshing cocktail using citrus fruits."

[0672] Through this system, bartenders can easily and efficiently serve original cocktails, increasing customer satisfaction.

[0673] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0674] Step 1:

[0675] User (Bartender):

[0676] It listens to customer requests and inputs them into the terminal's user interface. Examples of prompts include "a refreshing fruit-based cocktail" and "low-alcohol."

[0677] Specific behavior:

[0678] Operate tablet and desktop applications and enter information in text boxes and select options.

[0679] input:

[0680] Customer's specific request (text request)

[0681] output:

[0682] Request information entered on the terminal

[0683] Step 2:

[0684] Device:

[0685] The input request information is formatted into an appropriate format such as JSON and sent to the server.

[0686] Specific behavior:

[0687] The input request information is formatted and sent to the server as a "POST" request.

[0688] input:

[0689] Request information entered by the user

[0690] output:

[0691] JSON formatted request information sent to the server

[0692] Step 3:

[0693] server:

[0694] The server inputs the received request information into a generative AI model. The generative AI model analyzes the request and generates the optimal cocktail by referencing a cocktail database. For example, for a request such as "fruit-based, low-alcohol," it generates a recipe by combining suitable ingredients.

[0695] Specific behavior:

[0696] The server parses the request information and inputs it into a generative AI model.

[0697] The AI ​​model analyzes the request and searches a database to select the appropriate ingredients (e.g., lemon juice, orange liqueur, soda).

[0698] input:

[0699] JSON formatted request information sent to the server

[0700] output:

[0701] Recipe, name, and visual image of the generated cocktail

[0702] Step 4:

[0703] server:

[0704] The generated cocktail information (ingredients, recipe, name, appearance) is sent to the terminal.

[0705] Specific behavior:

[0706] The generated results are compiled in JSON format and sent to the terminal as a response.

[0707] input:

[0708] Cocktail information generated by a generative AI model

[0709] output:

[0710] JSON formatted generation result information sent to the device

[0711] Step 5:

[0712] Device:

[0713] The received generated results are displayed to the bartender via a display means.

[0714] Specific behavior:

[0715] It parses the JSON response and displays the information in a UI component, such as the recipe text, the name of the cocktail, and an image of its appearance.

[0716] input:

[0717] JSON formatted generation result information sent from the server

[0718] output:

[0719] Cocktail information displayed on the device screen

[0720] Step 6:

[0721] User (Bartender):

[0722] Create a cocktail based on the information provided and serve it to the customer.

[0723] Specific behavior:

[0724] The bartender mixes the cocktail according to the displayed recipe and serves the finished cocktail to the customer.

[0725] input:

[0726] Cocktail recipes, names, and images of their appearance displayed on the device

[0727] output:

[0728] The actual cocktail

[0729] Step 7:

[0730] User (Bartender):

[0731] Customers can input feedback based on their reactions to the proposed cocktails, for example, by entering specific comments such as "I wish it looked a little more showy" or "The flavor is a little weak."

[0732] Specific behavior:

[0733] Enter specific improvements and customer reactions in the feedback section.

[0734] input:

[0735] Customer reactions and bartender feedback (textual feedback)

[0736] output:

[0737] Feedback information entered on the device

[0738] Step 8:

[0739] Device:

[0740] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[0741] Specific behavior:

[0742] The feedback information is formatted and sent to the server as a "POST" request.

[0743] input:

[0744] User-entered feedback information

[0745] output:

[0746] Feedback information sent to the server in JSON format

[0747] Step 9:

[0748] server:

[0749] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[0750] Specific behavior:

[0751] The feedback information is stored in a database and analytical algorithms are used to update the AI ​​model, for example by using machine learning libraries to adjust the model parameters.

[0752] input:

[0753] Feedback information sent to the server in JSON format

[0754] output:

[0755] Fine-tuned generative AI models

[0756] The above is the specific flow of the system program processing.

[0757] (Application example 1)

[0758] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0759] Traditionally, the original cocktails that bartenders offer to customers have depended on the bartender's own experience and creativity, making it difficult to quickly and accurately meet the diverse needs of customers. Furthermore, there are limited services that allow customers to enjoy original cocktails at home, making it difficult to increase customer satisfaction. The present invention aims to solve these problems.

[0760] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0761] In this invention, the server includes a user interface means for inputting requests from customers, a generative AI model means for generating optimal cocktails from a vast database based on the input requests, a display means for displaying the recipe, appearance, and name of the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance, and a delivery means for ordering the suggested cocktail via smartphone and delivering it via a delivery service. This enables bartenders to respond quickly and accurately to the diverse needs of customers, and further increases customer satisfaction by providing a delivery service that allows customers to enjoy original cocktails at home.

[0762] The "user interface means" is an interface for inputting requests from customers, which can be operated via a terminal such as a smartphone.

[0763] "Generative AI model means" refers to an AI model that generates the optimal cocktail from a huge database based on an input request, and uses machine learning and deep learning technologies.

[0764] The "display means" is a display device for visually presenting the recipe, appearance, and name of the created cocktail.

[0765] "Feedback collection means" is a general term for the interface that collects feedback from users and reflects it as learning data for the generative AI model, and the system that analyzes it.

[0766] "Delivery method" refers to the method by which the suggested cocktail is ordered via smartphone and delivered to the customer via a delivery service.

[0767] A "generative AI model" is an algorithm or machine learning model used to analyze a customer request and generate the appropriate cocktail ingredients, recipe, appearance, and name.

[0768] The "database" is an information aggregation system that stores information such as cocktail ingredients, recipes, images, and names.

[0769] A "request" is information about the characteristics or elements of a cocktail desired by a customer.

[0770] A "recipe" is a set of specific steps and ingredient combinations for creating a cocktail.

[0771] A "smartphone" is a mobile device used by customers to order cocktails.

[0772] A "display device" is an electronic device for visually displaying information.

[0773] The system of this invention is designed to propose the optimal original cocktail based on a customer's request and deliver that cocktail to the customer through a delivery service. The system configuration and specific processing flow are described below.

[0774] System Configuration

[0775] 1. User Interface Methods

[0776] This is an interface that allows customers to input their requests using their smartphones, with text boxes and options to input their specific preferences (e.g., fruit-based, less sweet, specific allergy information, etc.).

[0777] 2. Generative AI Model Means

[0778] An AI model installed on the server receives and analyzes requests sent from smartphones. Based on the analysis results, it creates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[0779] 3. Database

[0780] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[0781] 4. Display means

[0782] The generated cocktail information is displayed on the smartphone screen, including the cocktail's recipe, name, and appearance (image).

[0783] 5. Feedback Collection Methods

[0784] It provides an interface for customers to input feedback about cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[0785] 6. Delivery Method

[0786] It is a system that allows customers to order suggested cocktails and have them delivered through a delivery service.

[0787] Program processing

[0788] User (customer)

[0789] Customers open a cocktail delivery app on their smartphone and enter their request, such as a "refreshing fruit-based cocktail" or "I'd like something surprising."

[0790] Device (smartphone)

[0791] The input request information is formatted and sent to the server in an appropriate format such as JSON, which the server then receives and inputs into the generative AI model.

[0792] server

[0793] The generative AI model analyzes the input request and references the database to generate the optimal cocktail. For example, if the request is for a "refreshing fruit-based cocktail," the AI ​​model selects appropriate ingredients from the database (e.g., vodka, grapefruit juice, tonic water), generates a recipe, appearance, and name, and then sends the generated information (recipe, image of appearance, and name) to the device.

[0794] Device (smartphone)

[0795] The generated results are then displayed to the customer via a display device, who then orders a cocktail based on this information.

[0796] User (customer)

[0797] Customers receive the suggested cocktail, sample it, and then provide feedback on the cocktail, such as specific comments like "I wish it looked a little more showy" or "It tastes a little bland," into the app.

[0798] Device (smartphone)

[0799] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[0800] server

[0801] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[0802] Specific examples

[0803] For example, if a customer requests a "refreshing cocktail with citrus fruits," they input this using their smartphone. The device sends the request to the server, and the AI ​​model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Citrus Breeze") are displayed on the device. The customer uses this information to order the cocktail and receive it through a delivery service. Customers can sample the cocktail and provide feedback, which will help improve suggestions for future visits.

[0804] Prompt Sentence Examples

[0805] "Customer Request: A refreshing cocktail using citrus fruits"

[0806] "Suggested cocktail name: Citrus Breeze"

[0807] "Ingredients: Lemon juice, orange liqueur, soda"

[0808] Recipe: Mix ingredients, chill and pour into a glass.

[0809] "Image: URL / Image"

[0810] As described above, the present invention makes it possible to provide customers with an efficient and highly accurate original cocktail proposal and delivery service, thereby increasing customer satisfaction.

[0811] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0812] Step 1:

[0813] A user (customer) launches a cocktail delivery app on their smartphone and inputs a cocktail request. For example, they might input, "I'd like a refreshing fruit-based cocktail." The device formats this request information and converts it into JSON-formatted data. The input is the customer's request, and the output is the JSON-formatted request data.

[0814] Step 2:

[0815] The terminal (smartphone) transmits the formatted request data to the server. The transmitted data is the customer's request information, and the terminal transfers the request data to the server using a communication means.

[0816] Step 3:

[0817] The server analyzes the request data received from the terminal. The input is the request data in JSON format, and the output is the analyzed request information. This analysis includes parsing and data decomposition.

[0818] Step 4:

[0819] The server's generative AI model selects the appropriate cocktail ingredients, recipe, image, and name from a database based on the analyzed request information. The generative AI model uses machine learning and deep learning algorithms, and the input is the analyzed request information, and the output is the generated cocktail information.

[0820] Step 5:

[0821] The server sends the generated cocktail information (recipe, image of appearance, name) to the terminal. This information is sent in JSON format, the input is the cocktail information from the generative AI model, and the output is the cocktail information sent to the terminal.

[0822] Step 6:

[0823] The terminal (smartphone) displays the received cocktail information on the user interface. The user checks this displayed information and orders a cocktail. The input is the cocktail information received from the server, and the output is the cocktail information displayed on the user interface.

[0824] Step 7:

[0825] The user (customer) confirms the delivery order based on the displayed cocktail information. The input is the cocktail information, and the output is the confirmation of the delivery order.

[0826] Step 8:

[0827] The delivery vehicle prepares and delivers a cocktail to the customer based on the user's order information. The input is the confirmed delivery order information, and the output is the cocktail delivered to the customer.

[0828] Step 9:

[0829] The user (customer) tastes the cocktail they receive and enters their feedback in the app. The input is the customer's feedback information, and the output is formatted feedback data.

[0830] Step 10:

[0831] The terminal (smartphone) formats the feedback information and sends it to the server in JSON format. The input is the customer feedback information, and the output is the feedback data sent to the server.

[0832] Step 11:

[0833] The server analyzes the received feedback information and uses it as data to fine-tune the generative AI model. The input is the feedback data in JSON format, and the output is the updated parameters of the generative AI model. This will result in more accurate cocktail generation results from the next time onwards.

[0834] The above is the specific processing flow of this program.

[0835] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0836] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers, and the configuration of the system and the specific processing flow will be described in detail below.

[0837] System configuration:

[0838] 1. User Interface Means (Terminal):

[0839] It provides a graphical user interface (GUI) for bartenders to input requests from customers, and in addition to the existing interface, it also integrates a camera and microphone to recognize the user's facial expressions and tone of voice.

[0840] 2. Generative AI model means (server):

[0841] The system receives requests sent from devices, analyzes the content of the requests, and then operates an AI model that generates cocktails based on the analysis results by combining suitable ingredients, recipes, appearances, and names from a vast database.

[0842] 3. Database (server):

[0843] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[0844] 4. Display means (terminal):

[0845] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[0846] 5. Feedback collection means (terminal and server):

[0847] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[0848] 6. Emotion engine means (server):

[0849] It is an engine for recognizing user emotions, collecting emotional data through facial expressions, voice tone, and language analysis. The emotional data is analyzed along with feedback and reflected in the AI ​​model.

[0850] Program flow:

[0851] User (Bartender):

[0852] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can enter specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[0853] Device:

[0854] The input request information is converted into JSON format and sent to the server.

[0855] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[0856] In addition, the device's camera and microphone collect the user's facial expressions and vocal tone and send them to the emotion engine.

[0857] server:

[0858] Parse the received JSON formatted request and pass it as input to the generative AI model.

[0859] The emotion engine analyzes the collected data and determines the user's emotions.

[0860] Based on the request and sentiment data, the generative AI model begins the predictive process to create the optimal cocktail.

[0861] Generative AI model means (server):

[0862] Based on the request, the generative AI model consults a database to select the best ingredients, recipe, appearance, and name.

[0863] For example, a cocktail recipe based on "vodka, blue curacao, and lime juice" can be generated from the database.

[0864] The generated results (recipe, name, and image of appearance) are formatted in JSON and sent to the terminal.

[0865] Device:

[0866] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[0867] Example: Generated cocktail name "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and image of the appearance.

[0868] User (Bartender):

[0869] Check the displayed results and create a cocktail.

[0870] Serve cocktails to customers and collect their reactions and feedback.

[0871] Device:

[0872] The collected feedback is converted into JSON format and sent back to the server.

[0873] Example: { "feedback": "Make it look a little simpler"}

[0874] Additionally, the emotion engine transmits any additional emotion data collected back to the server.

[0875] server:

[0876] The received feedback and sentiment data is analyzed and used to improve the performance of the generative AI model.

[0877] The feedback information is used as training data for the model and added as new data points.

[0878] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[0879] This allows the system to continuously learn, and for future requests, it will be able to suggest cocktails that are more accurate and take into account both the customer's wishes and emotions. For example, if a customer requests a "refreshing and energizing cocktail" and the emotion engine detects the customer's excited state, the generative AI model will suggest a "citrus and mint-based energy booster cocktail" and provide the result to the bartender. In this way, more personalized cocktails can be offered.

[0880] The processing flow will be explained below.

[0881] Step 1:

[0882] User (Bartender):

[0883] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can input specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[0884] Step 2:

[0885] Device:

[0886] The input request information is converted into JSON format and sent to the server.

[0887] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[0888] In addition, the device's camera and microphone are used to capture the user's (bartender's) facial expressions and voice tone in real time and send the data to the emotion engine.

[0889] Step 3:

[0890] server:

[0891] Parse the received JSON formatted request and pass it as input to the generative AI model.

[0892] The emotion engine analyzes the collected facial expressions and voice tones to determine the user's emotional state. For example, the emotion engine can detect the user's excitement or satisfaction.

[0893] Step 4:

[0894] Generative AI model means (server):

[0895] Based on the request and emotional data, the AI ​​model consults a database to generate the optimal cocktail.

[0896] For example, it generates cocktail recipes based on "vodka, blue curacao, and lime juice" from the database and combines them, including their appearance and names.

[0897] Step 5:

[0898] Device:

[0899] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[0900] The generated results include the cocktail name "Blue Harmony", the recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and an image of its appearance.

[0901] Step 6:

[0902] User (Bartender):

[0903] Check the displayed results and create a cocktail.

[0904] Serve cocktails to customers and collect their reactions and feedback.

[0905] Step 7:

[0906] User (Bartender):

[0907] Customer feedback is entered into the device's feedback screen. For example, specific comments such as "It looks too flashy" or "The flavor is a little weak" are entered.

[0908] Step 8:

[0909] Device:

[0910] The input feedback information is converted into JSON format and sent to the server.

[0911] Example: { "feedback": "Make it look a little simpler"}

[0912] Additionally, any additional emotional data collected by the emotion engine (e.g., customer smiles or changes in voice tone) is sent back to the server.

[0913] Step 9:

[0914] server:

[0915] The received feedback and sentiment data is analyzed and used to improve the performance of the generative AI model.

[0916] Feedback information and emotion data are used as training data for the model and added as new data points.

[0917] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[0918] This allows the system to continuously learn, and for future requests, it will be able to suggest cocktails that are more accurate and take into account both the customer's wishes and emotions. For example, if a customer requests a "refreshing and energizing cocktail" and the emotion engine detects the customer's excited state, the generative AI model will suggest a "citrus and mint-based energy booster cocktail" and provide the result to the bartender. In this way, more personalized cocktails can be offered.

[0919] Example 2

[0920] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0921] Conventional cocktail recommendation systems are based solely on customer requests and do not fully consider customer sentiment or real-time feedback. This makes it difficult to recommend cocktails that will increase customer satisfaction. Furthermore, the collection and application of feedback is insufficient, limiting improvements to the system's performance.

[0922] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0923] In this invention, the server includes an information input means for inputting requests from customers, an input analysis means for converting the input request into JSON format and collecting user emotional data according to the request, an emotional analysis means for analyzing the collected emotional data and passing it as input to a generative AI model, a generative AI model means for generating an optimal cocktail based on the input request and emotional data, a result display means for displaying the recipe, appearance, and name of the generated cocktail, and a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance. This enables personalized cocktail suggestions that take customer emotions into consideration and continuous performance improvement of the system by reflecting feedback in real time.

[0924] The "information input means" is an interface for receiving requests from customers, and includes a graphical user interface (GUI) and a voice input device.

[0925] "Input analysis means" refers to a device or software that has the function of converting input requests into JSON format and collecting customer emotional data in response to the requests.

[0926] An "emotion analysis means" is a device or software that has the function of analyzing collected emotional data and inputting the results into a generative AI model.

[0927] The "generative AI model means" is an artificial intelligence model for generating optimal cocktails based on input requests and emotional data.

[0928] The "result display means" is a display or other display device for displaying the recipe, appearance, and name of the created cocktail.

[0929] A "feedback collection means" is a device or software that collects feedback from users and reflects that information in the generative AI model.

[0930] The system of the present invention is designed to enable bartenders to propose the perfect original cocktail to each customer. The system is mainly composed of a terminal, a server, and various related means. Each component will be described in detail below.

[0931] Information input means (terminal)

[0932] This is an interface through which bartenders can input requests from customers. Specifically, a graphical user interface (GUI) is provided, through which bartenders can input customer requests. Furthermore, it is equipped with a camera and microphone, and can also collect emotional data such as facial expressions and voice tone of the customer.

[0933] Input analysis means (terminal)

[0934] It converts input requests into JSON format and analyzes the collected emotional data. This data is sent to a server (described later) and used as input for a generative AI model.

[0935] Emotion analysis means (server)

[0936] The server analyzes the received emotional data, which includes facial expression recognition and voice tone analysis, to determine the customer's emotional state.

[0937] Generative AI model means (server)

[0938] The generative AI model on the server generates the optimal cocktail based on the input request and emotional data, referencing information stored in a database such as ingredients, recipe, appearance, and name to generate the most suitable cocktail recipe.

[0939] Result display means (terminal)

[0940] This is a display device for presenting information about the created cocktail to the bartender. The cocktail recipe, name, and image of the appearance sent from the server are displayed.

[0941] Feedback collection means (terminals and servers)

[0942] The bartender collects customer feedback and sends it to the server via their device. The server analyzes this feedback and uses it as training data for the generative AI model. This feedback allows the system to continuously learn and is reflected in future cocktail creations.

[0943] For example, if a customer requests, "Please recommend a fruit-based cocktail with a moderate sweetness," the bartender enters this information into the terminal interface. The terminal converts the input information into JSON format and sends it to the server. At the same time, the terminal collects the customer's facial expressions and voice, which are also sent to the server. An emotion analysis method on the server analyzes this data, and a generative AI model generates the optimal cocktail. The generated cocktail information is sent back to the terminal and displayed to the bartender. The bartender creates a cocktail based on this information and serves it to the customer.

[0944] In this way, the system makes personalized cocktail suggestions that take into account the customer's request and emotional state, and continuously improves the system's performance based on collected feedback, resulting in higher customer satisfaction.

[0945] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0946] Step 1:

[0947] User (Bartender):

[0948] The cocktail request is taken from the customer and entered into the terminal's information input means.

[0949] (Input): Customer request (e.g., "A fruit-based cocktail with a moderate sweetness")

[0950] (Output): Text data entered into the interface

[0951] (Specific action): The bartender enters "a fruit-based cocktail with a moderate sweetness" into the GUI screen.

[0952] Step 2:

[0953] Device:

[0954] The system converts the input request into JSON format and sends it to the server, and also uses the device's camera and microphone to collect the customer's facial expressions and voice tone.

[0955] (Input): Text data entered into the interface

[0956] (Output): Request data and emotion data in JSON format (e.g., { "request": "A fruit-based cocktail with a moderate sweetness", "emotion": "neutral"})

[0957] (Specific operation): The device converts the request into the format { "request": "A fruit-based, lightly sweetened cocktail"}, captures the customer's face and voice data, and sends it to the server.

[0958] Step 3:

[0959] server:

[0960] The transmitted request and emotion data are received, and the emotion data is analyzed by emotion analysis means.

[0961] (Input): Request data and emotion data in JSON format

[0962] (Output): Parsed emotion information (e.g. "neutral")

[0963] (Specific behavior): The server analyzes the received data and determines the request for a "fruit-based, lightly sweetened cocktail" and the emotional state as "neutral."

[0964] Step 4:

[0965] server:

[0966] Based on the analysis results, a generative AI model creates the optimal cocktail.

[0967] (Input): Request data (e.g., "A fruit-based cocktail with a moderate sweetness") and sentiment data (e.g., "neutral")

[0968] (Output): Cocktail recipe, name, and image (e.g. "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice")

[0969] (Specific operation): The generative AI model references the database, generates a cocktail that matches the request, converts the information into JSON format, and sends it to the terminal.

[0970] Step 5:

[0971] Device:

[0972] The generated results received from the server are analyzed and displayed on the user interface.

[0973] (Input): Cocktail creation data in JSON format (e.g., { "name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image": "image_url"})

[0974] (Output): Cocktail information in display format

[0975] (Specific operation): The device analyzes the received data and displays the cocktail name "Blue Harmony," its recipe, and an image of its appearance on the display.

[0976] Step 6:

[0977] User (Bartender):

[0978] Based on the displayed cocktail information, the specified cocktail is created and served to the customer.

[0979] (Input): Cocktail recipe, name, and image (e.g., "Blue Harmony" with recipe "50ml vodka, 20ml blue curacao, 30ml lime juice")

[0980] (Output): Finished cocktail

[0981] (Specific action): The bartender creates a cocktail based on the displayed recipe by mixing 50ml of vodka, 20ml of blue curacao, and 30ml of lime juice.

[0982] Step 7:

[0983] User (Bartender):

[0984] Serve cocktails to customers and collect their reactions and feedback.

[0985] (Input): Customer feedback (e.g., "Please make it look a little simpler")

[0986] (Output): Collected feedback

[0987] (Specific action): The bartender listens to the customer's feedback and enters it into the terminal.

[0988] Step 8:

[0989] Device:

[0990] The collected feedback is converted into JSON format and sent to the server.

[0991] (Input): Customer feedback (e.g., "Please make it look a little simpler")

[0992] (Output): Feedback data in JSON format (e.g., { "feedback": "I'd like it to look a little simpler"})

[0993] (Specific operation): The device converts the feedback into JSON format and sends it to the server.

[0994] Step 9:

[0995] server:

[0996] The feedback received is analyzed and used to improve the generative AI model.

[0997] (Input): Feedback data in JSON format (e.g., { "feedback": "I'd like it to look a little simpler"})

[0998] (Output): Updated generative AI model

[0999] (Specific operation): The generative AI model is fine-tuned based on the feedback data and reflected in the system's next cocktail generation.

[1000] (Application example 2)

[1001] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1002] While conventional systems can reflect specific customer requests, it is difficult to incorporate the customer's emotions and preferences. Therefore, there is a need for a method that can analyze the customer's emotions from their facial expressions and tone of voice to suggest more personalized cocktails. It is necessary to solve these issues and improve customer satisfaction.

[1003] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1004] In this invention, the server includes a user interface means for inputting requests from customers, a generative AI model means for generating optimal cocktails based on the input requests and customer emotion data, a display means for displaying the recipe, appearance, and name of the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance, and an emotion engine means for analyzing facial expressions and voice tones to collect emotion data, thereby enabling more personalized cocktail suggestions that reflect the customer's emotions and preferences.

[1005] The "user interface means" is a means for a customer to input a request, and provides a graphical user interface or a voice input interface.

[1006] "Generative AI model means" refers to an artificial intelligence model that generates the optimal cocktail from a vast database based on input requests and customer emotional data.

[1007] "Display means" refers to a display device or screen that visually shows information such as the recipe, appearance, and name of the created cocktail to the bartender and customer.

[1008] The "feedback collection means" is a means for collecting feedback from users (bartenders or customers) and sending it to the server, which contributes to improving the performance of the generative AI model.

[1009] The "emotion engine means" is a means for analyzing the customer's facial expressions and voice tone and collecting emotional data.

[1010] A "request" is information describing the conditions and characteristics of the cocktail a customer desires, and refers to the data entered into the system.

[1011] "Cocktail generation" refers to the process of determining the optimal cocktail ingredients, recipe, appearance, and name based on the input request and emotional data.

[1012] The "database" refers to data storage that accumulates information such as cocktail ingredients, recipes, images, and names, and is used as a reference for the generative AI model.

[1013] "Facial Expression" is a visual representation of a customer's emotional state that is analyzed by a camera and / or emotion engine means.

[1014] "Voice Tone" is an acoustic expression that indicates the customer's emotional state and is analyzed by the microphone and emotion engine means.

[1015] The system for carrying out this invention includes the following main components and procedures: an interface means for a user to input a request, a generative AI model means for generating an optimal cocktail based on the request and emotional data, a display means for displaying information about the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model, and an emotion engine means for analyzing the facial expressions and voice tones of customers to collect emotional data.

[1016] The server achieves these functions by using the following means:

[1017] 1. User Interface Means

[1018] A graphical user interface (GUI) is implemented on devices such as smartphones and tablets, allowing customers to input their cocktail requests. The devices are also equipped with cameras and microphones, allowing them to simultaneously collect customers' facial expressions and vocal tones, thereby obtaining emotional data.

[1019] 2. Generative AI Model Means

[1020] The server analyzes the received request and emotional data using algorithms that analyze natural language processing, facial expressions, and voice tones. The analyzed data is then input into a generative AI model, which then selects from a vast database of cocktails to create a cocktail that combines the optimal ingredients, recipe, appearance, and name.

[1021] 3. Display means

[1022] The generated cocktail information (recipe, appearance, name) is displayed on the smartphone or tablet screen in a visually appealing format for bartenders and customers to review at a glance.

[1023] 4. Feedback Collection Methods

[1024] Users (bartenders or customers) input their ratings and feedback on cocktails. This feedback is sent from the device to the server and analyzed. The results of the analysis of the feedback are added as training data for the generative AI model, contributing to performance improvement.

[1025] 5. Emotional Engine Means

[1026] The server uses data collected from cameras and microphones to recognize the customer's emotions. Using algorithms that analyze facial expressions and vocal tones, detailed emotional data is extracted, which is then used as part of the cocktail creation process.

[1027] Specific examples

[1028] For example, if a customer requests a "fruit-based cocktail with a moderate sweetness," the system operates as follows:

[1029] 1. The customer types in their request, and their facial expressions and voice tone are collected by a camera and microphone.

[1030] 2. The server analyzes the request and emotion data and inputs it into a generative AI model.

[1031] 3. The generative AI model selects the optimal cocktail, "Blue Harmony," from the database and generates a recipe and visual information.

[1032] 4. This information will be displayed on your smartphone or tablet screen.

[1033] Prompt Sentence Examples

[1034] Request: Fruit-based cocktail with a moderate sweetness

[1035] Emotion data: facial expressions and vocal tones

[1036] In this way, the system can generate and display personalized cocktails based on the customer's emotions and requests.

[1037] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1038] Step 1:

[1039] When a user (customer) orders a cocktail at a bar, they input their cocktail request using the user interface on their smartphone or tablet.

[1040] Input: The request entered by the customer (e.g., "A fruit-based cocktail with a moderate sweetness").

[1041] Output: Request data in JSON format (e.g., {"request": "A fruit-based cocktail with a moderate sweetness"}).

[1042] Step 2:

[1043] The device's camera and microphone collect the customer's facial expressions and voice tone, and this data is sent to the emotion engine means.

[1044] Input: Raw facial expression and speech tone data.

[1045] Output: Emotion data (e.g., {"emotion": "happiness"}).

[1046] Step 3:

[1047] The device combines the request data and emotion data, converts them into JSON format, and sends them to the server.

[1048] Input: Request data and emotion data.

[1049] Output: Combined data in JSON format (e.g., {"request": "Fruit-based cocktail with a moderate sweetness", "emotion": "happiness"}).

[1050] Step 4:

[1051] The server parses the received JSON-formatted data and inputs it into the generative AI model.

[1052] Input: The combined data in JSON format.

[1053] Output: The input data (request and sentiment data converted into internal data structures) in a format suitable for the generative AI model.

[1054] Step 5:

[1055] A generative AI model references the database and generates the optimal cocktail ingredients, recipe, name, and appearance.

[1056] Input: Parsed request and sentiment data.

[1057] Output: Information about the generated cocktail (e.g., {"name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image_url": " / images / blue_harmony.jpg"}).

[1058] Step 6:

[1059] The server converts the cocktail creation results into JSON format and sends it to the terminal.

[1060] Input: Generated cocktail information (internal data structure).

[1061] Output: JSON formatted result data (e.g., {"name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image_url": " / images / blue_harmony.jpg"}).

[1062] Step 7:

[1063] The terminal analyzes the received JSON formatted generated result and converts it into a format to be displayed on the user interface.

[1064] Input: The generated result data in JSON format.

[1065] Output: Format displayed in the user interface (visual cocktail information).

[1066] Step 8:

[1067] The user (bartender) checks the displayed results and creates a cocktail. The user serves the cocktail to customers and collects their reactions and feedback.

[1068] Input: Cocktail information displayed in the user interface.

[1069] Output: Actual cocktails and customer feedback.

[1070] Step 9:

[1071] The device converts the collected feedback into JSON format and sends it back to the server.

[1072] Input: Customer feedback.

[1073] Output: Feedback data in JSON format (e.g. {"feedback": "Make it look a little simpler"}).

[1074] Step 10:

[1075] The server analyzes the received feedback and additional emotional data and uses it to improve the performance of the generative AI model.

[1076] Input: Feedback and sentiment data in JSON format.

[1077] Output: A fine-tuned generative AI model.

[1078] These processing steps allow the system to make more personalized cocktail suggestions based on customer sentiment and requests.

[1079] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1080] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1081] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1082] [Third embodiment]

[1083] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1084] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1085] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1086] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1087] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1088] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1089] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1090] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1091] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1092] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1093] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1094] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1095] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers. The system configuration and specific processing flow are described below.

[1096] System configuration:

[1097] 1. User Interface Means (Terminal):

[1098] The bartender provides a graphical user interface (GUI) for inputting customer requests, for example, using an application installed on a tablet or desktop. The screen displays text boxes and options for customers to input their specific requests (e.g., fruit-based, less sweet, specific allergy information, etc.).

[1099] 2. Generative AI model means (server):

[1100] The system receives requests sent from the device and analyzes the request. Based on the analysis results, it runs an AI model that generates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[1101] 3. Database (server):

[1102] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[1103] 4. Display means (terminal):

[1104] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[1105] 5. Feedback collection means (terminal and server):

[1106] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[1107] Program flow:

[1108] User (Bartender):

[1109] The system listens to customer requests and inputs them into the terminal's user interface, for example, specific requests such as "a refreshing fruit-based cocktail" or "some surprise."

[1110] Device:

[1111] The input request information is formatted and sent to the server in an appropriate format such as JSON, which the server then receives and inputs into the generative AI model.

[1112] server:

[1113] The generative AI model analyzes the input request and references the database to generate the optimal cocktail. For example, if the request is for a "refreshing fruit-based cocktail," the AI ​​model selects the appropriate ingredients (e.g., vodka, grapefruit juice, tonic water) from the database and generates the recipe, appearance, and name.

[1114] The generated information (recipe, image of appearance, name) is sent to the terminal.

[1115] Device:

[1116] The received results are displayed to the bartender via a display, who then creates a cocktail based on this information.

[1117] User (Bartender):

[1118] Customers can taste the proposed cocktails and input their feedback based on their reactions, such as "I wish it looked a little more showy" or "The flavor is a little weak."

[1119] Device:

[1120] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[1121] server:

[1122] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[1123] Examples:

[1124] For example, if a customer requests a "refreshing cocktail with citrus fruits," the bartender inputs this into the terminal. The terminal sends the request to the server, and the AI ​​model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Sunny Surprise") are displayed on the terminal. The bartender uses this information to create the cocktail and serve it to the customer. Feedback from customers is collected and reflected in future suggestions, improving the system's accuracy and customer satisfaction.

[1125] In this way, bartenders can easily and efficiently serve original cocktails, increasing customer satisfaction.

[1126] The processing flow will be explained below.

[1127] Step 1:

[1128] User (Bartender):

[1129] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can input specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[1130] Step 2:

[1131] Device:

[1132] The input request information is converted into JSON format and sent to the server.

[1133] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[1134] Step 3:

[1135] server:

[1136] Parse the received JSON formatted request and pass it as input to the generative AI model.

[1137] Based on the request, the generative AI model begins the predictive process to create the optimal cocktail.

[1138] Step 4:

[1139] Generative AI model means (server):

[1140] Based on the request, the generative AI model consults a database to select the best ingredients, recipe, appearance, and name.

[1141] For example, a cocktail recipe based on "vodka, blue curacao, and lime juice" can be generated from the database.

[1142] The generated results (recipe, name, and image of appearance) are formatted in JSON and sent to the terminal.

[1143] Step 5:

[1144] Device:

[1145] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[1146] Example: Generated cocktail name "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and image of the appearance.

[1147] Step 6:

[1148] User (Bartender):

[1149] Check the displayed results and create a cocktail.

[1150] Serve cocktails to customers and collect their reactions and feedback.

[1151] Step 7:

[1152] User (Bartender):

[1153] The collected feedback is entered into the device's feedback screen. For example, a specific comment such as "The taste is perfect, but I wish the appearance was a little simpler" is entered.

[1154] Step 8:

[1155] Device:

[1156] The input feedback information is converted into JSON format and sent again to the server.

[1157] Example: { "feedback": "Make it look a little simpler"}

[1158] Step 9:

[1159] server:

[1160] The received feedback is analyzed and used to improve the performance of the generative AI model.

[1161] The feedback information is used as training data for the model and added as new data points.

[1162] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[1163] This allows the system to continuously learn and, for future requests, become more accurate and more likely to suggest cocktails that are more in line with the customer's preferences.

[1164] Example 1

[1165] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1166] Conventional cocktail creation systems have difficulty quickly and accurately suggesting the best cocktail for a customer's request. Furthermore, they lack a means to effectively collect user feedback and improve the system's performance. This can lead to a decrease in customer satisfaction.

[1167] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1168] In this invention, the server includes an information input means for inputting requests from customers, a generative AI model means for generating an appropriate cocktail based on the input request, a display means for displaying the recipe, appearance, and name of the generated cocktail, and a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance. This makes it possible to quickly and accurately generate cocktails based on customer requests and improve system performance through feedback.

[1169] "Customer" means the ultimate user to whom the cocktail is served.

[1170] A "request" is information that indicates a customer's specific requests or wishes.

[1171] "Information input means" refers to a device or software for inputting a customer request through a user interface.

[1172] A "generative AI model means" is a means of analyzing input requests and generating optimal cocktails using machine learning and deep learning technologies.

[1173] A "cocktail database" is a collection of data that stores information such as cocktail ingredients, recipes, appearances, and names.

[1174] "Display means" refers to a device or software for visually presenting information about the cocktail created to the bartender.

[1175] "Feedback" means any opinion or comment provided by a customer or bartender regarding the quality or satisfaction of a cocktail.

[1176] The "feedback collection means" is a means for collecting feedback from users and using it to improve the performance of the system.

[1177] A "server" is a computer system that processes requests, runs generative AI models, and stores and manages data.

[1178] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers. The system configuration and specific processing flow are described below.

[1179] System configuration:

[1180] 1. User Interface Means (Terminal):

[1181] The bartender provides a graphical user interface (GUI) for inputting customer requests, for example, using an application installed on a tablet or desktop. The screen displays text boxes and options for customers to input their specific requests (e.g., fruit-based, less sweet, specific allergy information, etc.).

[1182] 2. Generative AI model means (server):

[1183] The system receives requests sent from the device and analyzes the request. Based on the analysis results, it runs an AI model that generates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[1184] 3. Database (server):

[1185] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[1186] 4. Display means (terminal):

[1187] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[1188] 5. Feedback collection means (terminal and server):

[1189] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[1190] Examples:

[1191] For example, if a customer requests a "refreshing cocktail with citrus fruits," the bartender inputs this into the terminal. The terminal sends the request to the server, and the generative AI model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Sunny Surprise") are displayed on the terminal. The bartender uses this information to create the cocktail and serve it to the customer. By collecting customer feedback and incorporating it into future suggestions, the system's accuracy and customer satisfaction can be improved.

[1192] Example prompt sentence:

[1193] "Create a refreshing fruit-based cocktail."

[1194] "Please suggest a refreshing cocktail using citrus fruits."

[1195] Through this system, bartenders can easily and efficiently serve original cocktails, increasing customer satisfaction.

[1196] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1197] Step 1:

[1198] User (Bartender):

[1199] It listens to customer requests and inputs them into the terminal's user interface. Examples of prompts include "a refreshing fruit-based cocktail" and "low-alcohol."

[1200] Specific behavior:

[1201] Operate tablet and desktop applications and enter information in text boxes and select options.

[1202] input:

[1203] Customer's specific request (text request)

[1204] output:

[1205] Request information entered on the terminal

[1206] Step 2:

[1207] Device:

[1208] The input request information is formatted into an appropriate format such as JSON and sent to the server.

[1209] Specific behavior:

[1210] The input request information is formatted and sent to the server as a "POST" request.

[1211] input:

[1212] Request information entered by the user

[1213] output:

[1214] JSON formatted request information sent to the server

[1215] Step 3:

[1216] server:

[1217] The server inputs the received request information into a generative AI model. The generative AI model analyzes the request and generates the optimal cocktail by referencing a cocktail database. For example, for a request such as "fruit-based, low-alcohol," it generates a recipe by combining suitable ingredients.

[1218] Specific behavior:

[1219] The server parses the request information and inputs it into a generative AI model.

[1220] The AI ​​model analyzes the request and searches a database to select the appropriate ingredients (e.g., lemon juice, orange liqueur, soda).

[1221] input:

[1222] JSON formatted request information sent to the server

[1223] output:

[1224] Recipe, name, and visual image of the generated cocktail

[1225] Step 4:

[1226] server:

[1227] The generated cocktail information (ingredients, recipe, name, appearance) is sent to the terminal.

[1228] Specific behavior:

[1229] The generated results are compiled in JSON format and sent to the terminal as a response.

[1230] input:

[1231] Cocktail information generated by a generative AI model

[1232] output:

[1233] JSON formatted generation result information sent to the device

[1234] Step 5:

[1235] Device:

[1236] The received generated results are displayed to the bartender via a display means.

[1237] Specific behavior:

[1238] It parses the JSON response and displays the information in a UI component, such as the recipe text, the name of the cocktail, and an image of its appearance.

[1239] input:

[1240] JSON formatted generation result information sent from the server

[1241] output:

[1242] Cocktail information displayed on the device screen

[1243] Step 6:

[1244] User (Bartender):

[1245] Create a cocktail based on the information provided and serve it to the customer.

[1246] Specific behavior:

[1247] The bartender mixes the cocktail according to the displayed recipe and serves the finished cocktail to the customer.

[1248] input:

[1249] Cocktail recipes, names, and images of their appearance displayed on the device

[1250] output:

[1251] The actual cocktail

[1252] Step 7:

[1253] User (Bartender):

[1254] Customers can input feedback based on their reactions to the proposed cocktails, for example, by entering specific comments such as "I wish it looked a little more showy" or "The flavor is a little weak."

[1255] Specific behavior:

[1256] Enter specific improvements and customer reactions in the feedback section.

[1257] input:

[1258] Customer reactions and bartender feedback (textual feedback)

[1259] output:

[1260] Feedback information entered on the device

[1261] Step 8:

[1262] Device:

[1263] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[1264] Specific behavior:

[1265] The feedback information is formatted and sent to the server as a "POST" request.

[1266] input:

[1267] User-entered feedback information

[1268] output:

[1269] Feedback information sent to the server in JSON format

[1270] Step 9:

[1271] server:

[1272] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[1273] Specific behavior:

[1274] The feedback information is stored in a database and analytical algorithms are used to update the AI ​​model, for example by using machine learning libraries to adjust the model parameters.

[1275] input:

[1276] Feedback information sent to the server in JSON format

[1277] output:

[1278] Fine-tuned generative AI models

[1279] The above is the specific flow of the system program processing.

[1280] (Application example 1)

[1281] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1282] Traditionally, the original cocktails that bartenders offer to customers have depended on the bartender's own experience and creativity, making it difficult to quickly and accurately meet the diverse needs of customers. Furthermore, there are limited services that allow customers to enjoy original cocktails at home, making it difficult to increase customer satisfaction. The present invention aims to solve these problems.

[1283] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1284] In this invention, the server includes a user interface means for inputting requests from customers, a generative AI model means for generating optimal cocktails from a vast database based on the input requests, a display means for displaying the recipe, appearance, and name of the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance, and a delivery means for ordering the suggested cocktail via smartphone and delivering it via a delivery service. This enables bartenders to respond quickly and accurately to the diverse needs of customers, and further increases customer satisfaction by providing a delivery service that allows customers to enjoy original cocktails at home.

[1285] The "user interface means" is an interface for inputting requests from customers, which can be operated via a terminal such as a smartphone.

[1286] "Generative AI model means" refers to an AI model that generates the optimal cocktail from a huge database based on an input request, and uses machine learning and deep learning technologies.

[1287] The "display means" is a display device for visually presenting the recipe, appearance, and name of the created cocktail.

[1288] "Feedback collection means" is a general term for the interface that collects feedback from users and reflects it as learning data for the generative AI model, and the system that analyzes it.

[1289] "Delivery method" refers to the method by which the suggested cocktail is ordered via smartphone and delivered to the customer via a delivery service.

[1290] A "generative AI model" is an algorithm or machine learning model used to analyze a customer request and generate the appropriate cocktail ingredients, recipe, appearance, and name.

[1291] The "database" is an information aggregation system that stores information such as cocktail ingredients, recipes, images, and names.

[1292] A "request" is information about the characteristics or elements of a cocktail desired by a customer.

[1293] A "recipe" is a set of specific steps and ingredient combinations for creating a cocktail.

[1294] A "smartphone" is a mobile device used by customers to order cocktails.

[1295] A "display device" is an electronic device for visually displaying information.

[1296] The system of this invention is designed to propose the optimal original cocktail based on a customer's request and deliver that cocktail to the customer through a delivery service. The system configuration and specific processing flow are described below.

[1297] System Configuration

[1298] 1. User Interface Methods

[1299] This is an interface that allows customers to input their requests using their smartphones, with text boxes and options to input their specific preferences (e.g., fruit-based, less sweet, specific allergy information, etc.).

[1300] 2. Generative AI Model Means

[1301] An AI model installed on the server receives and analyzes requests sent from smartphones. Based on the analysis results, it creates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[1302] 3. Database

[1303] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[1304] 4. Display means

[1305] The generated cocktail information is displayed on the smartphone screen, including the cocktail's recipe, name, and appearance (image).

[1306] 5. Feedback Collection Methods

[1307] It provides an interface for customers to input feedback about cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[1308] 6. Delivery Method

[1309] It is a system that allows customers to order suggested cocktails and have them delivered through a delivery service.

[1310] Program processing

[1311] User (customer)

[1312] Customers open a cocktail delivery app on their smartphone and enter their request, such as a "refreshing fruit-based cocktail" or "I'd like something surprising."

[1313] Device (smartphone)

[1314] The input request information is formatted and sent to the server in an appropriate format such as JSON, which the server then receives and inputs into the generative AI model.

[1315] server

[1316] The generative AI model analyzes the input request and references the database to generate the optimal cocktail. For example, if the request is for a "refreshing fruit-based cocktail," the AI ​​model selects appropriate ingredients from the database (e.g., vodka, grapefruit juice, tonic water), generates a recipe, appearance, and name, and then sends the generated information (recipe, image of appearance, and name) to the device.

[1317] Device (smartphone)

[1318] The generated results are then displayed to the customer via a display device, who then orders a cocktail based on this information.

[1319] User (customer)

[1320] Customers receive the suggested cocktail, sample it, and then provide feedback on the cocktail, such as specific comments like "I wish it looked a little more showy" or "It tastes a little bland," into the app.

[1321] Device (smartphone)

[1322] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[1323] server

[1324] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[1325] Specific examples

[1326] For example, if a customer requests a "refreshing cocktail with citrus fruits," they input this using their smartphone. The device sends the request to the server, and the AI ​​model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Citrus Breeze") are displayed on the device. The customer uses this information to order the cocktail and receive it through a delivery service. Customers can sample the cocktail and provide feedback, which will help improve suggestions for future visits.

[1327] Prompt Sentence Examples

[1328] "Customer Request: A refreshing cocktail using citrus fruits"

[1329] "Suggested cocktail name: Citrus Breeze"

[1330] "Ingredients: Lemon juice, orange liqueur, soda"

[1331] Recipe: Mix ingredients, chill and pour into a glass.

[1332] "Image: URL / Image"

[1333] As described above, the present invention makes it possible to provide customers with an efficient and highly accurate original cocktail proposal and delivery service, thereby increasing customer satisfaction.

[1334] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1335] Step 1:

[1336] A user (customer) launches a cocktail delivery app on their smartphone and inputs a cocktail request. For example, they might input, "I'd like a refreshing fruit-based cocktail." The device formats this request information and converts it into JSON-formatted data. The input is the customer's request, and the output is the JSON-formatted request data.

[1337] Step 2:

[1338] The terminal (smartphone) transmits the formatted request data to the server. The transmitted data is the customer's request information, and the terminal transfers the request data to the server using a communication means.

[1339] Step 3:

[1340] The server analyzes the request data received from the terminal. The input is the request data in JSON format, and the output is the analyzed request information. This analysis includes parsing and data decomposition.

[1341] Step 4:

[1342] The server's generative AI model selects the appropriate cocktail ingredients, recipe, image, and name from a database based on the analyzed request information. The generative AI model uses machine learning and deep learning algorithms, and the input is the analyzed request information, and the output is the generated cocktail information.

[1343] Step 5:

[1344] The server sends the generated cocktail information (recipe, image of appearance, name) to the terminal. This information is sent in JSON format, the input is the cocktail information from the generative AI model, and the output is the cocktail information sent to the terminal.

[1345] Step 6:

[1346] The terminal (smartphone) displays the received cocktail information on the user interface. The user checks this displayed information and orders a cocktail. The input is the cocktail information received from the server, and the output is the cocktail information displayed on the user interface.

[1347] Step 7:

[1348] The user (customer) confirms the delivery order based on the displayed cocktail information. The input is the cocktail information, and the output is the confirmation of the delivery order.

[1349] Step 8:

[1350] The delivery vehicle prepares and delivers a cocktail to the customer based on the user's order information. The input is the confirmed delivery order information, and the output is the cocktail delivered to the customer.

[1351] Step 9:

[1352] The user (customer) tastes the cocktail they receive and enters their feedback in the app. The input is the customer's feedback information, and the output is formatted feedback data.

[1353] Step 10:

[1354] The terminal (smartphone) formats the feedback information and sends it to the server in JSON format. The input is the customer feedback information, and the output is the feedback data sent to the server.

[1355] Step 11:

[1356] The server analyzes the received feedback information and uses it as data to fine-tune the generative AI model. The input is the feedback data in JSON format, and the output is the updated parameters of the generative AI model. This will result in more accurate cocktail generation results from the next time onwards.

[1357] The above is the specific processing flow of this program.

[1358] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1359] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers, and the configuration of the system and the specific processing flow will be described in detail below.

[1360] System configuration:

[1361] 1. User Interface Means (Terminal):

[1362] It provides a graphical user interface (GUI) for bartenders to input requests from customers, and in addition to the existing interface, it also integrates a camera and microphone to recognize the user's facial expressions and tone of voice.

[1363] 2. Generative AI model means (server):

[1364] The system receives requests sent from devices, analyzes the content of the requests, and then operates an AI model that generates cocktails based on the analysis results by combining suitable ingredients, recipes, appearances, and names from a vast database.

[1365] 3. Database (server):

[1366] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[1367] 4. Display means (terminal):

[1368] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[1369] 5. Feedback collection means (terminal and server):

[1370] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[1371] 6. Emotion engine means (server):

[1372] It is an engine for recognizing user emotions, collecting emotional data through facial expressions, voice tone, and language analysis. The emotional data is analyzed along with feedback and reflected in the AI ​​model.

[1373] Program flow:

[1374] User (Bartender):

[1375] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can enter specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[1376] Device:

[1377] The input request information is converted into JSON format and sent to the server.

[1378] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[1379] In addition, the device's camera and microphone collect the user's facial expressions and vocal tone and send them to the emotion engine.

[1380] server:

[1381] Parse the received JSON formatted request and pass it as input to the generative AI model.

[1382] The emotion engine analyzes the collected data and determines the user's emotions.

[1383] Based on the request and sentiment data, the generative AI model begins the predictive process to create the optimal cocktail.

[1384] Generative AI model means (server):

[1385] Based on the request, the generative AI model consults a database to select the best ingredients, recipe, appearance, and name.

[1386] For example, a cocktail recipe based on "vodka, blue curacao, and lime juice" can be generated from the database.

[1387] The generated results (recipe, name, and image of appearance) are formatted in JSON and sent to the terminal.

[1388] Device:

[1389] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[1390] Example: Generated cocktail name "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and image of the appearance.

[1391] User (Bartender):

[1392] Check the displayed results and create a cocktail.

[1393] Serve cocktails to customers and collect their reactions and feedback.

[1394] Device:

[1395] The collected feedback is converted into JSON format and sent back to the server.

[1396] Example: { "feedback": "Make it look a little simpler"}

[1397] Additionally, the emotion engine transmits any additional emotion data collected back to the server.

[1398] server:

[1399] The received feedback and sentiment data is analyzed and used to improve the performance of the generative AI model.

[1400] The feedback information is used as training data for the model and added as new data points.

[1401] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[1402] This allows the system to continuously learn, and for future requests, it will be able to suggest cocktails that are more accurate and take into account both the customer's wishes and emotions. For example, if a customer requests a "refreshing and energizing cocktail" and the emotion engine detects the customer's excited state, the generative AI model will suggest a "citrus and mint-based energy booster cocktail" and provide the result to the bartender. In this way, more personalized cocktails can be offered.

[1403] The processing flow will be explained below.

[1404] Step 1:

[1405] User (Bartender):

[1406] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can input specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[1407] Step 2:

[1408] Device:

[1409] The input request information is converted into JSON format and sent to the server.

[1410] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[1411] In addition, the device's camera and microphone are used to capture the user's (bartender's) facial expressions and voice tone in real time and send the data to the emotion engine.

[1412] Step 3:

[1413] server:

[1414] Parse the received JSON formatted request and pass it as input to the generative AI model.

[1415] The emotion engine analyzes the collected facial expressions and voice tones to determine the user's emotional state. For example, the emotion engine can detect the user's excitement or satisfaction.

[1416] Step 4:

[1417] Generative AI model means (server):

[1418] Based on the request and emotional data, the AI ​​model consults a database to generate the optimal cocktail.

[1419] For example, it generates cocktail recipes based on "vodka, blue curacao, and lime juice" from the database and combines them, including their appearance and names.

[1420] Step 5:

[1421] Device:

[1422] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[1423] The generated results include the cocktail name "Blue Harmony", the recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and an image of its appearance.

[1424] Step 6:

[1425] User (Bartender):

[1426] Check the displayed results and create a cocktail.

[1427] Serve cocktails to customers and collect their reactions and feedback.

[1428] Step 7:

[1429] User (Bartender):

[1430] Customer feedback is entered into the device's feedback screen. For example, specific comments such as "It looks too flashy" or "The flavor is a little weak" are entered.

[1431] Step 8:

[1432] Device:

[1433] The input feedback information is converted into JSON format and sent to the server.

[1434] Example: { "feedback": "Make it look a little simpler"}

[1435] Additionally, any additional emotional data collected by the emotion engine (e.g., customer smiles or changes in voice tone) is sent back to the server.

[1436] Step 9:

[1437] server:

[1438] The received feedback and sentiment data is analyzed and used to improve the performance of the generative AI model.

[1439] Feedback information and emotion data are used as training data for the model and added as new data points.

[1440] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[1441] This allows the system to continuously learn, and for future requests, it will be able to suggest cocktails that are more accurate and take into account both the customer's wishes and emotions. For example, if a customer requests a "refreshing and energizing cocktail" and the emotion engine detects the customer's excited state, the generative AI model will suggest a "citrus and mint-based energy booster cocktail" and provide the result to the bartender. In this way, more personalized cocktails can be offered.

[1442] Example 2

[1443] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1444] Conventional cocktail recommendation systems are based solely on customer requests and do not fully consider customer sentiment or real-time feedback. This makes it difficult to recommend cocktails that will increase customer satisfaction. Furthermore, the collection and application of feedback is insufficient, limiting improvements to the system's performance.

[1445] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1446] In this invention, the server includes an information input means for inputting requests from customers, an input analysis means for converting the input request into JSON format and collecting user emotional data according to the request, an emotional analysis means for analyzing the collected emotional data and passing it as input to a generative AI model, a generative AI model means for generating an optimal cocktail based on the input request and emotional data, a result display means for displaying the recipe, appearance, and name of the generated cocktail, and a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance. This enables personalized cocktail suggestions that take customer emotions into consideration and continuous performance improvement of the system by reflecting feedback in real time.

[1447] The "information input means" is an interface for receiving requests from customers, and includes a graphical user interface (GUI) and a voice input device.

[1448] "Input analysis means" refers to a device or software that has the function of converting input requests into JSON format and collecting customer emotional data in response to the requests.

[1449] An "emotion analysis means" is a device or software that has the function of analyzing collected emotional data and inputting the results into a generative AI model.

[1450] The "generative AI model means" is an artificial intelligence model for generating optimal cocktails based on input requests and emotional data.

[1451] The "result display means" is a display or other display device for displaying the recipe, appearance, and name of the created cocktail.

[1452] A "feedback collection means" is a device or software that collects feedback from users and reflects that information in the generative AI model.

[1453] The system of the present invention is designed to enable bartenders to propose the perfect original cocktail to each customer. The system is mainly composed of a terminal, a server, and various related means. Each component will be described in detail below.

[1454] Information input means (terminal)

[1455] This is an interface through which bartenders can input requests from customers. Specifically, a graphical user interface (GUI) is provided, through which bartenders can input customer requests. Furthermore, it is equipped with a camera and microphone, and can also collect emotional data such as facial expressions and voice tone of the customer.

[1456] Input analysis means (terminal)

[1457] It converts input requests into JSON format and analyzes the collected emotional data. This data is sent to a server (described later) and used as input for a generative AI model.

[1458] Emotion analysis means (server)

[1459] The server analyzes the received emotional data, which includes facial expression recognition and voice tone analysis, to determine the customer's emotional state.

[1460] Generative AI model means (server)

[1461] The generative AI model on the server generates the optimal cocktail based on the input request and emotional data, referencing information stored in a database such as ingredients, recipe, appearance, and name to generate the most suitable cocktail recipe.

[1462] Result display means (terminal)

[1463] This is a display device for presenting information about the created cocktail to the bartender. The cocktail recipe, name, and image of the appearance sent from the server are displayed.

[1464] Feedback collection means (terminals and servers)

[1465] The bartender collects customer feedback and sends it to the server via their device. The server analyzes this feedback and uses it as training data for the generative AI model. This feedback allows the system to continuously learn and is reflected in future cocktail creations.

[1466] For example, if a customer requests, "Please recommend a fruit-based cocktail with a moderate sweetness," the bartender enters this information into the terminal interface. The terminal converts the input information into JSON format and sends it to the server. At the same time, the terminal collects the customer's facial expressions and voice, which are also sent to the server. An emotion analysis method on the server analyzes this data, and a generative AI model generates the optimal cocktail. The generated cocktail information is sent back to the terminal and displayed to the bartender. The bartender creates a cocktail based on this information and serves it to the customer.

[1467] In this way, the system makes personalized cocktail suggestions that take into account the customer's request and emotional state, and continuously improves the system's performance based on collected feedback, resulting in higher customer satisfaction.

[1468] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1469] Step 1:

[1470] User (Bartender):

[1471] The cocktail request is taken from the customer and entered into the terminal's information input means.

[1472] (Input): Customer request (e.g., "A fruit-based cocktail with a moderate sweetness")

[1473] (Output): Text data entered into the interface

[1474] (Specific action): The bartender enters "a fruit-based cocktail with a moderate sweetness" into the GUI screen.

[1475] Step 2:

[1476] Device:

[1477] The system converts the input request into JSON format and sends it to the server, and also uses the device's camera and microphone to collect the customer's facial expressions and voice tone.

[1478] (Input): Text data entered into the interface

[1479] (Output): Request data and emotion data in JSON format (e.g., { "request": "A fruit-based cocktail with a moderate sweetness", "emotion": "neutral"})

[1480] (Specific operation): The device converts the request into the format { "request": "A fruit-based, lightly sweetened cocktail"}, captures the customer's face and voice data, and sends it to the server.

[1481] Step 3:

[1482] server:

[1483] The transmitted request and emotion data are received, and the emotion data is analyzed by emotion analysis means.

[1484] (Input): Request data and emotion data in JSON format

[1485] (Output): Parsed emotion information (e.g. "neutral")

[1486] (Specific behavior): The server analyzes the received data and determines the request for a "fruit-based, lightly sweetened cocktail" and the emotional state as "neutral."

[1487] Step 4:

[1488] server:

[1489] Based on the analysis results, a generative AI model creates the optimal cocktail.

[1490] (Input): Request data (e.g., "A fruit-based cocktail with a moderate sweetness") and sentiment data (e.g., "neutral")

[1491] (Output): Cocktail recipe, name, and image (e.g. "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice")

[1492] (Specific operation): The generative AI model references the database, generates a cocktail that matches the request, converts the information into JSON format, and sends it to the terminal.

[1493] Step 5:

[1494] Device:

[1495] The generated results received from the server are analyzed and displayed on the user interface.

[1496] (Input): Cocktail creation data in JSON format (e.g., { "name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image": "image_url"})

[1497] (Output): Cocktail information in display format

[1498] (Specific operation): The device analyzes the received data and displays the cocktail name "Blue Harmony," its recipe, and an image of its appearance on the display.

[1499] Step 6:

[1500] User (Bartender):

[1501] Based on the displayed cocktail information, the specified cocktail is created and served to the customer.

[1502] (Input): Cocktail recipe, name, and image (e.g., "Blue Harmony" with recipe "50ml vodka, 20ml blue curacao, 30ml lime juice")

[1503] (Output): Finished cocktail

[1504] (Specific action): The bartender creates a cocktail based on the displayed recipe by mixing 50ml of vodka, 20ml of blue curacao, and 30ml of lime juice.

[1505] Step 7:

[1506] User (Bartender):

[1507] Serve cocktails to customers and collect their reactions and feedback.

[1508] (Input): Customer feedback (e.g., "Please make it look a little simpler")

[1509] (Output): Collected feedback

[1510] (Specific action): The bartender listens to the customer's feedback and enters it into the terminal.

[1511] Step 8:

[1512] Device:

[1513] The collected feedback is converted into JSON format and sent to the server.

[1514] (Input): Customer feedback (e.g., "Please make it look a little simpler")

[1515] (Output): Feedback data in JSON format (e.g., { "feedback": "I'd like it to look a little simpler"})

[1516] (Specific operation): The device converts the feedback into JSON format and sends it to the server.

[1517] Step 9:

[1518] server:

[1519] The feedback received is analyzed and used to improve the generative AI model.

[1520] (Input): Feedback data in JSON format (e.g., { "feedback": "I'd like it to look a little simpler"})

[1521] (Output): Updated generative AI model

[1522] (Specific operation): The generative AI model is fine-tuned based on the feedback data and reflected in the system's next cocktail generation.

[1523] (Application example 2)

[1524] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1525] While conventional systems can reflect specific customer requests, it is difficult to incorporate the customer's emotions and preferences. Therefore, there is a need for a method that can analyze the customer's emotions from their facial expressions and tone of voice to suggest more personalized cocktails. It is necessary to solve these issues and improve customer satisfaction.

[1526] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1527] In this invention, the server includes a user interface means for inputting requests from customers, a generative AI model means for generating optimal cocktails based on the input requests and customer emotion data, a display means for displaying the recipe, appearance, and name of the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance, and an emotion engine means for analyzing facial expressions and voice tones to collect emotion data, thereby enabling more personalized cocktail suggestions that reflect the customer's emotions and preferences.

[1528] The "user interface means" is a means for a customer to input a request, and provides a graphical user interface or a voice input interface.

[1529] "Generative AI model means" refers to an artificial intelligence model that generates the optimal cocktail from a vast database based on input requests and customer emotional data.

[1530] "Display means" refers to a display device or screen that visually shows information such as the recipe, appearance, and name of the created cocktail to the bartender and customer.

[1531] The "feedback collection means" is a means for collecting feedback from users (bartenders or customers) and sending it to the server, which contributes to improving the performance of the generative AI model.

[1532] The "emotion engine means" is a means for analyzing the customer's facial expressions and voice tone and collecting emotional data.

[1533] A "request" is information describing the conditions and characteristics of the cocktail a customer desires, and refers to the data entered into the system.

[1534] "Cocktail generation" refers to the process of determining the optimal cocktail ingredients, recipe, appearance, and name based on the input request and emotional data.

[1535] The "database" refers to data storage that accumulates information such as cocktail ingredients, recipes, images, and names, and is used as a reference for the generative AI model.

[1536] "Facial Expression" is a visual representation of a customer's emotional state that is analyzed by a camera and / or emotion engine means.

[1537] "Voice Tone" is an acoustic expression that indicates the customer's emotional state and is analyzed by the microphone and emotion engine means.

[1538] The system for carrying out this invention includes the following main components and procedures: an interface means for a user to input a request, a generative AI model means for generating an optimal cocktail based on the request and emotional data, a display means for displaying information about the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model, and an emotion engine means for analyzing the facial expressions and voice tones of customers to collect emotional data.

[1539] The server achieves these functions by using the following means:

[1540] 1. User Interface Means

[1541] A graphical user interface (GUI) is implemented on devices such as smartphones and tablets, allowing customers to input their cocktail requests. The devices are also equipped with cameras and microphones, allowing them to simultaneously collect customers' facial expressions and vocal tones, thereby obtaining emotional data.

[1542] 2. Generative AI Model Means

[1543] The server analyzes the received request and emotional data using algorithms that analyze natural language processing, facial expressions, and voice tones. The analyzed data is then input into a generative AI model, which then selects from a vast database of cocktails to create a cocktail that combines the optimal ingredients, recipe, appearance, and name.

[1544] 3. Display means

[1545] The generated cocktail information (recipe, appearance, name) is displayed on the smartphone or tablet screen in a visually appealing format for bartenders and customers to review at a glance.

[1546] 4. Feedback Collection Methods

[1547] Users (bartenders or customers) input their cocktail ratings and feedback. This feedback is sent from the device to the server and analyzed. The results of the feedback analysis are added as training data for the generative AI model, contributing to performance improvement.

[1548] 5. Emotional Engine Means

[1549] The server uses data collected from cameras and microphones to recognize the customer's emotions. Using algorithms that analyze facial expressions and vocal tones, detailed emotional data is extracted, which is then used as part of the cocktail creation process.

[1550] Specific examples

[1551] For example, if a customer requests a "fruit-based cocktail with a moderate sweetness," the system operates as follows:

[1552] 1. The customer types in their request, and their facial expressions and voice tone are collected by a camera and microphone.

[1553] 2. The server analyzes the request and emotion data and inputs it into a generative AI model.

[1554] 3. The generative AI model selects the optimal cocktail, "Blue Harmony," from the database and generates a recipe and visual information.

[1555] 4. This information will be displayed on your smartphone or tablet screen.

[1556] Prompt Sentence Examples

[1557] Request: Fruit-based cocktail with a moderate sweetness

[1558] Emotional data: facial expressions and vocal tones

[1559] In this way, the system can generate and display personalized cocktails based on the customer's emotions and requests.

[1560] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1561] Step 1:

[1562] When a user (customer) orders a cocktail at a bar, they input their cocktail request using the user interface on their smartphone or tablet.

[1563] Input: The request entered by the customer (e.g., "A fruit-based cocktail with a moderate sweetness").

[1564] Output: Request data in JSON format (e.g., {"request": "A fruit-based cocktail with a moderate sweetness"}).

[1565] Step 2:

[1566] The device's camera and microphone collect the customer's facial expressions and voice tone, and this data is sent to the emotion engine means.

[1567] Input: Raw facial expression and speech tone data.

[1568] Output: Emotion data (e.g., {"emotion": "happiness"}).

[1569] Step 3:

[1570] The device combines the request data and emotion data, converts them into JSON format, and sends them to the server.

[1571] Input: Request data and emotion data.

[1572] Output: Combined data in JSON format (e.g., {"request": "Fruit-based cocktail with a moderate sweetness", "emotion": "happiness"}).

[1573] Step 4:

[1574] The server parses the received JSON-formatted data and inputs it into the generative AI model.

[1575] Input: The combined data in JSON format.

[1576] Output: The input data (request and sentiment data converted into internal data structures) in a format suitable for the generative AI model.

[1577] Step 5:

[1578] A generative AI model references the database and generates the optimal cocktail ingredients, recipe, name, and appearance.

[1579] Input: Parsed request and sentiment data.

[1580] Output: Information about the generated cocktail (e.g., {"name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image_url": " / images / blue_harmony.jpg"}).

[1581] Step 6:

[1582] The server converts the cocktail creation results into JSON format and sends it to the terminal.

[1583] Input: Generated cocktail information (internal data structure).

[1584] Output: JSON formatted result data (e.g., {"name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image_url": " / images / blue_harmony.jpg"}).

[1585] Step 7:

[1586] The terminal analyzes the received JSON formatted generated result and converts it into a format to be displayed on the user interface.

[1587] Input: The generated result data in JSON format.

[1588] Output: Format displayed in the user interface (visual cocktail information).

[1589] Step 8:

[1590] The user (bartender) checks the displayed results and creates a cocktail. The user serves the cocktail to the customer and collects their reaction and feedback.

[1591] Input: Cocktail information displayed in the user interface.

[1592] Output: Actual cocktails and customer feedback.

[1593] Step 9:

[1594] The device converts the collected feedback into JSON format and sends it back to the server.

[1595] Input: Customer feedback.

[1596] Output: Feedback data in JSON format (e.g. {"feedback": "Make it look a little simpler"}).

[1597] Step 10:

[1598] The server analyzes the received feedback and additional emotional data and uses it to improve the performance of the generative AI model.

[1599] Input: Feedback and sentiment data in JSON format.

[1600] Output: A fine-tuned generative AI model.

[1601] These processing steps allow the system to make more personalized cocktail suggestions based on customer sentiment and requests.

[1602] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1603] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1604] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1605] [Fourth embodiment]

[1606] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1607] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1608] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1609] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1610] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1611] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1612] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1613] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1614] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1615] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1616] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1617] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1618] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1619] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers. The system configuration and specific processing flow are described below.

[1620] System configuration:

[1621] 1. User Interface Means (Terminal):

[1622] The bartender provides a graphical user interface (GUI) for inputting customer requests, for example, using an application installed on a tablet or desktop. The screen displays text boxes and options for customers to input their specific requests (e.g., fruit-based, less sweet, specific allergy information, etc.).

[1623] 2. Generative AI model means (server):

[1624] The system receives requests sent from the device and analyzes the request. Based on the analysis results, it runs an AI model that generates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[1625] 3. Database (server):

[1626] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[1627] 4. Display means (terminal):

[1628] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[1629] 5. Feedback collection means (terminal and server):

[1630] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[1631] Program flow:

[1632] User (Bartender):

[1633] The system listens to customer requests and inputs them into the terminal's user interface, for example, specific requests such as "a refreshing fruit-based cocktail" or "some surprise."

[1634] Device:

[1635] The input request information is formatted and sent to the server in an appropriate format such as JSON, which the server then receives and inputs into the generative AI model.

[1636] server:

[1637] The generative AI model analyzes the input request and references the database to generate the optimal cocktail. For example, if the request is for a "refreshing fruit-based cocktail," the AI ​​model selects the appropriate ingredients (e.g., vodka, grapefruit juice, tonic water) from the database and generates the recipe, appearance, and name.

[1638] The generated information (recipe, image of appearance, name) is sent to the terminal.

[1639] Device:

[1640] The received results are displayed to the bartender via a display, who then creates a cocktail based on this information.

[1641] User (Bartender):

[1642] Customers can taste the proposed cocktails and input their feedback based on their reactions, such as "I wish it looked a little more showy" or "The flavor is a little weak."

[1643] Device:

[1644] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[1645] server:

[1646] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[1647] Examples:

[1648] For example, if a customer requests a "refreshing cocktail with citrus fruits," the bartender inputs this into the terminal. The terminal sends the request to the server, and the AI ​​model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Sunny Surprise") are displayed on the terminal. The bartender uses this information to create the cocktail and serve it to the customer. Feedback from customers is collected and reflected in future suggestions, improving the system's accuracy and customer satisfaction.

[1649] In this way, bartenders can easily and efficiently serve original cocktails, increasing customer satisfaction.

[1650] The processing flow will be explained below.

[1651] Step 1:

[1652] User (Bartender):

[1653] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can input specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[1654] Step 2:

[1655] Device:

[1656] The input request information is converted into JSON format and sent to the server.

[1657] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[1658] Step 3:

[1659] server:

[1660] Parse the received JSON formatted request and pass it as input to the generative AI model.

[1661] Based on the request, the generative AI model begins the predictive process to create the optimal cocktail.

[1662] Step 4:

[1663] Generative AI model means (server):

[1664] Based on the request, the generative AI model consults a database to select the best ingredients, recipe, appearance, and name.

[1665] For example, a cocktail recipe based on "vodka, blue curacao, and lime juice" can be generated from the database.

[1666] The generated results (recipe, name, and image of appearance) are formatted in JSON and sent to the terminal.

[1667] Step 5:

[1668] Device:

[1669] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[1670] Example: Generated cocktail name "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and image of the appearance.

[1671] Step 6:

[1672] User (Bartender):

[1673] Check the displayed results and create a cocktail.

[1674] Serve cocktails to customers and collect their reactions and feedback.

[1675] Step 7:

[1676] User (Bartender):

[1677] The collected feedback is entered into the device's feedback screen. For example, a specific comment such as "The taste is perfect, but I wish the appearance was a little simpler" is entered.

[1678] Step 8:

[1679] Device:

[1680] The input feedback information is converted into JSON format and sent again to the server.

[1681] Example: { "feedback": "Make it look a little simpler"}

[1682] Step 9:

[1683] server:

[1684] The received feedback is analyzed and used to improve the performance of the generative AI model.

[1685] The feedback information is used as training data for the model and added as new data points.

[1686] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[1687] This allows the system to continuously learn and, for future requests, become more accurate and more likely to suggest cocktails that are more in line with the customer's preferences.

[1688] Example 1

[1689] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1690] Conventional cocktail creation systems have difficulty quickly and accurately suggesting the best cocktail for a customer's request. Furthermore, they lack a means to effectively collect user feedback and improve the system's performance. This can lead to a decrease in customer satisfaction.

[1691] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1692] In this invention, the server includes an information input means for inputting requests from customers, a generative AI model means for generating an appropriate cocktail based on the input request, a display means for displaying the recipe, appearance, and name of the generated cocktail, and a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance. This makes it possible to quickly and accurately generate cocktails based on customer requests and improve system performance through feedback.

[1693] "Customer" means the ultimate user to whom the cocktail is served.

[1694] A "request" is information that indicates a customer's specific requests or wishes.

[1695] "Information input means" refers to a device or software for inputting a customer request through a user interface.

[1696] A "generative AI model means" is a means of analyzing input requests and generating optimal cocktails using machine learning and deep learning technologies.

[1697] A "cocktail database" is a collection of data that stores information such as cocktail ingredients, recipes, appearances, and names.

[1698] "Display means" refers to a device or software for visually presenting information about the cocktail created to the bartender.

[1699] "Feedback" means any opinion or comment provided by a customer or bartender regarding the quality or satisfaction of a cocktail.

[1700] The "feedback collection means" is a means for collecting feedback from users and using it to improve the performance of the system.

[1701] A "server" is a computer system that processes requests, runs generative AI models, and stores and manages data.

[1702] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers. The system configuration and specific processing flow are described below.

[1703] System configuration:

[1704] 1. User Interface Means (Terminal):

[1705] The bartender provides a graphical user interface (GUI) for inputting customer requests, for example, using an application installed on a tablet or desktop. The screen displays text boxes and options for customers to input their specific requests (e.g., fruit-based, less sweet, specific allergy information, etc.).

[1706] 2. Generative AI model means (server):

[1707] The system receives requests sent from the device and analyzes the request. Based on the analysis results, it runs an AI model that generates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[1708] 3. Database (server):

[1709] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[1710] 4. Display means (terminal):

[1711] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[1712] 5. Feedback collection means (terminal and server):

[1713] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[1714] Examples:

[1715] For example, if a customer requests a "refreshing cocktail with citrus fruits," the bartender inputs this into the terminal. The terminal sends the request to the server, and the generative AI model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Sunny Surprise") are displayed on the terminal. The bartender uses this information to create the cocktail and serve it to the customer. By collecting customer feedback and incorporating it into future suggestions, the system's accuracy and customer satisfaction can be improved.

[1716] Example prompt sentence:

[1717] "Create a refreshing fruit-based cocktail."

[1718] "Please suggest a refreshing cocktail using citrus fruits."

[1719] Through this system, bartenders can easily and efficiently serve original cocktails, increasing customer satisfaction.

[1720] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1721] Step 1:

[1722] User (Bartender):

[1723] It listens to customer requests and inputs them into the terminal's user interface. Examples of prompts include "a refreshing fruit-based cocktail" and "low-alcohol."

[1724] Specific behavior:

[1725] Operate tablet and desktop applications and enter information in text boxes and select options.

[1726] input:

[1727] Customer's specific request (text request)

[1728] output:

[1729] Request information entered on the terminal

[1730] Step 2:

[1731] Device:

[1732] The input request information is formatted into an appropriate format such as JSON and sent to the server.

[1733] Specific behavior:

[1734] The input request information is formatted and sent to the server as a "POST" request.

[1735] input:

[1736] Request information entered by the user

[1737] output:

[1738] JSON formatted request information sent to the server

[1739] Step 3:

[1740] server:

[1741] The server inputs the received request information into a generative AI model. The generative AI model analyzes the request and generates the optimal cocktail by referencing a cocktail database. For example, for a request such as "fruit-based, low-alcohol," it generates a recipe by combining suitable ingredients.

[1742] Specific behavior:

[1743] The server parses the request information and inputs it into a generative AI model.

[1744] The AI ​​model analyzes the request and searches a database to select the appropriate ingredients (e.g., lemon juice, orange liqueur, soda).

[1745] input:

[1746] JSON formatted request information sent to the server

[1747] output:

[1748] Recipe, name, and visual image of the generated cocktail

[1749] Step 4:

[1750] server:

[1751] The generated cocktail information (ingredients, recipe, name, appearance) is sent to the terminal.

[1752] Specific behavior:

[1753] The generated results are compiled in JSON format and sent to the terminal as a response.

[1754] input:

[1755] Cocktail information generated by a generative AI model

[1756] output:

[1757] JSON formatted generation result information sent to the device

[1758] Step 5:

[1759] Device:

[1760] The received generated results are displayed to the bartender via a display means.

[1761] Specific behavior:

[1762] It parses the JSON response and displays the information in a UI component, such as the recipe text, the name of the cocktail, and an image of its appearance.

[1763] input:

[1764] JSON formatted generation result information sent from the server

[1765] output:

[1766] Cocktail information displayed on the device screen

[1767] Step 6:

[1768] User (Bartender):

[1769] Create a cocktail based on the information provided and serve it to the customer.

[1770] Specific behavior:

[1771] The bartender mixes the cocktail according to the displayed recipe and serves the finished cocktail to the customer.

[1772] input:

[1773] Cocktail recipes, names, and images of their appearance displayed on the device

[1774] output:

[1775] The actual cocktail

[1776] Step 7:

[1777] User (Bartender):

[1778] Customers can input feedback based on their reactions to the proposed cocktails, for example, by entering specific comments such as "I wish it looked a little more showy" or "The flavor is a little weak."

[1779] Specific behavior:

[1780] Enter specific improvements and customer reactions in the feedback section.

[1781] input:

[1782] Customer reactions and bartender feedback (textual feedback)

[1783] output:

[1784] Feedback information entered on the device

[1785] Step 8:

[1786] Device:

[1787] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[1788] Specific behavior:

[1789] The feedback information is formatted and sent to the server as a "POST" request.

[1790] input:

[1791] User-entered feedback information

[1792] output:

[1793] Feedback information sent to the server in JSON format

[1794] Step 9:

[1795] server:

[1796] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[1797] Specific behavior:

[1798] The feedback information is stored in a database and analytical algorithms are used to update the AI ​​model, for example by using machine learning libraries to adjust the model parameters.

[1799] input:

[1800] Feedback information sent to the server in JSON format

[1801] output:

[1802] Fine-tuned generative AI models

[1803] The above is the specific flow of the system program processing.

[1804] (Application example 1)

[1805] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1806] Traditionally, the original cocktails that bartenders offer to customers have depended on the bartender's own experience and creativity, making it difficult to quickly and accurately meet the diverse needs of customers. Furthermore, there are limited services that allow customers to enjoy original cocktails at home, making it difficult to increase customer satisfaction. The present invention aims to solve these problems.

[1807] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1808] In this invention, the server includes a user interface means for inputting requests from customers, a generative AI model means for generating optimal cocktails from a vast database based on the input requests, a display means for displaying the recipe, appearance, and name of the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance, and a delivery means for ordering the suggested cocktail via smartphone and delivering it via a delivery service. This enables bartenders to respond quickly and accurately to the diverse needs of customers, and further increases customer satisfaction by providing a delivery service that allows customers to enjoy original cocktails at home.

[1809] The "user interface means" is an interface for inputting requests from customers, which can be operated via a terminal such as a smartphone.

[1810] "Generative AI model means" refers to an AI model that generates the optimal cocktail from a huge database based on an input request, and uses machine learning and deep learning technologies.

[1811] The "display means" is a display device for visually presenting the recipe, appearance, and name of the created cocktail.

[1812] "Feedback collection means" is a general term for the interface that collects feedback from users and reflects it as learning data for the generative AI model, and the system that analyzes it.

[1813] "Delivery method" refers to the method by which the suggested cocktail is ordered via smartphone and delivered to the customer via a delivery service.

[1814] A "generative AI model" is an algorithm or machine learning model used to analyze a customer request and generate the appropriate cocktail ingredients, recipe, appearance, and name.

[1815] The "database" is an information aggregation system that stores information such as cocktail ingredients, recipes, images, and names.

[1816] A "request" is information about the characteristics or elements of a cocktail desired by a customer.

[1817] A "recipe" is a set of specific steps and ingredient combinations for creating a cocktail.

[1818] A "smartphone" is a mobile device used by customers to order cocktails.

[1819] A "display device" is an electronic device for visually displaying information.

[1820] The system of this invention is designed to propose the optimal original cocktail based on a customer's request and deliver that cocktail to the customer through a delivery service. The system configuration and specific processing flow are described below.

[1821] System Configuration

[1822] 1. User Interface Methods

[1823] This is an interface that allows customers to input their requests using their smartphones, with text boxes and options to input their specific preferences (e.g., fruit-based, less sweet, specific allergy information, etc.).

[1824] 2. Generative AI Model Means

[1825] An AI model installed on the server receives and analyzes requests sent from smartphones. Based on the analysis results, it creates cocktails by combining suitable ingredients, recipes, appearances, and names from a vast database. This AI model uses machine learning and deep learning technologies.

[1826] 3. Database

[1827] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[1828] 4. Display means

[1829] The generated cocktail information is displayed on the smartphone screen, including the cocktail's recipe, name, and appearance (image).

[1830] 5. Feedback Collection Methods

[1831] It provides an interface for customers to input feedback about cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[1832] 6. Delivery Method

[1833] It is a system that allows customers to order suggested cocktails and have them delivered through a delivery service.

[1834] Program processing

[1835] User (customer)

[1836] Customers open a cocktail delivery app on their smartphone and enter their request, such as a "refreshing fruit-based cocktail" or "I'd like something surprising."

[1837] Device (smartphone)

[1838] The input request information is formatted and sent to the server in an appropriate format such as JSON, which the server then receives and inputs into the generative AI model.

[1839] server

[1840] The generative AI model analyzes the input request and references the database to generate the optimal cocktail. For example, if the request is for a "refreshing fruit-based cocktail," the AI ​​model selects appropriate ingredients from the database (e.g., vodka, grapefruit juice, tonic water), generates a recipe, appearance, and name, and then sends the generated information (recipe, image of appearance, and name) to the device.

[1841] Device (smartphone)

[1842] The generated results are then displayed to the customer via a display device, who then orders a cocktail based on this information.

[1843] User (customer)

[1844] Customers receive the suggested cocktail, sample it, and then provide feedback on the cocktail, such as specific comments like "I wish it looked a little more showy" or "It tastes a little bland," into the app.

[1845] Device (smartphone)

[1846] The feedback information is formatted and sent to the server in an appropriate format, such as JSON.

[1847] server

[1848] The received feedback is analyzed and used as data to fine-tune the generative AI model, resulting in more accurate cocktail generation results in future.

[1849] Specific examples

[1850] For example, if a customer requests a "refreshing cocktail with citrus fruits," they input this using their smartphone. The device sends the request to the server, and the AI ​​model analyzes the request and generates a recipe combining "lemon juice, orange liqueur, and soda." The appearance and name of the generated cocktail (for example, "Citrus Breeze") are displayed on the device. The customer uses this information to order the cocktail and receive it through a delivery service. Customers can sample the cocktail and provide feedback, which will help improve suggestions for future visits.

[1851] Prompt Sentence Examples

[1852] "Customer Request: A refreshing cocktail using citrus fruits"

[1853] "Suggested cocktail name: Citrus Breeze"

[1854] "Ingredients: Lemon juice, orange liqueur, soda"

[1855] Recipe: Mix ingredients, chill and pour into a glass.

[1856] "Image: URL / Image"

[1857] As described above, the present invention makes it possible to provide customers with an efficient and highly accurate original cocktail proposal and delivery service, thereby increasing customer satisfaction.

[1858] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1859] Step 1:

[1860] A user (customer) launches a cocktail delivery app on their smartphone and inputs a cocktail request. For example, they might input, "I'd like a refreshing fruit-based cocktail." The device formats this request information and converts it into JSON-formatted data. The input is the customer's request, and the output is the JSON-formatted request data.

[1861] Step 2:

[1862] The terminal (smartphone) transmits the formatted request data to the server. The transmitted data is the customer's request information, and the terminal transfers the request data to the server using a communication means.

[1863] Step 3:

[1864] The server analyzes the request data received from the terminal. The input is the request data in JSON format, and the output is the analyzed request information. This analysis includes parsing and data decomposition.

[1865] Step 4:

[1866] The server's generative AI model selects the appropriate cocktail ingredients, recipe, image, and name from a database based on the analyzed request information. The generative AI model uses machine learning and deep learning algorithms, and the input is the analyzed request information, and the output is the generated cocktail information.

[1867] Step 5:

[1868] The server sends the generated cocktail information (recipe, image of appearance, name) to the terminal. This information is sent in JSON format, the input is the cocktail information from the generative AI model, and the output is the cocktail information sent to the terminal.

[1869] Step 6:

[1870] The terminal (smartphone) displays the received cocktail information on the user interface. The user checks this displayed information and orders a cocktail. The input is the cocktail information received from the server, and the output is the cocktail information displayed on the user interface.

[1871] Step 7:

[1872] The user (customer) confirms the delivery order based on the displayed cocktail information. The input is the cocktail information, and the output is the confirmation of the delivery order.

[1873] Step 8:

[1874] The delivery vehicle prepares and delivers a cocktail to the customer based on the user's order information. The input is the confirmed delivery order information, and the output is the cocktail delivered to the customer.

[1875] Step 9:

[1876] The user (customer) tastes the cocktail they receive and enters their feedback in the app. The input is the customer's feedback information, and the output is formatted feedback data.

[1877] Step 10:

[1878] The terminal (smartphone) formats the feedback information and sends it to the server in JSON format. The input is the customer feedback information, and the output is the feedback data sent to the server.

[1879] Step 11:

[1880] The server analyzes the received feedback information and uses it as data to fine-tune the generative AI model. The input is the feedback data in JSON format, and the output is the updated parameters of the generative AI model. This will result in more accurate cocktail generation results from the next time onwards.

[1881] The above is the specific processing flow of this program.

[1882] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1883] The system of the present invention is designed to enable bartenders to propose the best original cocktails to customers, and the configuration of the system and the specific processing flow will be described in detail below.

[1884] System configuration:

[1885] 1. User Interface Means (Terminal):

[1886] It provides a graphical user interface (GUI) for bartenders to input requests from customers, and in addition to the existing interface, it also integrates a camera and microphone to recognize the user's facial expressions and tone of voice.

[1887] 2. Generative AI model means (server):

[1888] The system receives requests sent from devices, analyzes the content of the requests, and then operates an AI model that generates cocktails based on the analysis results by combining suitable ingredients, recipes, appearances, and names from a vast database.

[1889] 3. Database (server):

[1890] It stores information such as cocktail ingredients, recipes, images, and names, and the generative AI model references this database to generate cocktail combinations.

[1891] 4. Display means (terminal):

[1892] This is a display device that presents information about the generated cocktail to the bartender. The generated cocktail's recipe, name, and appearance (image) are displayed.

[1893] 5. Feedback collection means (terminal and server):

[1894] It provides an interface for bartenders to input feedback on cocktails and send it to the server. The server analyzes the received feedback and feeds it forward as learning data for the AI ​​model. As a result, the accuracy of the generative AI model improves and is reflected in future cocktail generation.

[1895] 6. Emotion engine means (server):

[1896] It is an engine for recognizing user emotions, collecting emotional data through facial expressions, voice tone, and language analysis. The emotional data is analyzed along with feedback and reflected in the AI ​​model.

[1897] Program flow:

[1898] User (Bartender):

[1899] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can enter specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[1900] Device:

[1901] The input request information is converted into JSON format and sent to the server.

[1902] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[1903] In addition, the device's camera and microphone collect the user's facial expressions and vocal tone and send them to the emotion engine.

[1904] server:

[1905] Parse the received JSON formatted request and pass it as input to the generative AI model.

[1906] The emotion engine analyzes the collected data and determines the user's emotions.

[1907] Based on the request and sentiment data, the generative AI model begins the predictive process to create the optimal cocktail.

[1908] Generative AI model means (server):

[1909] Based on the request, the generative AI model consults a database to select the best ingredients, recipe, appearance, and name.

[1910] For example, a cocktail recipe based on "vodka, blue curacao, and lime juice" can be generated from the database.

[1911] The generated results (recipe, name, and image of appearance) are formatted in JSON and sent to the terminal.

[1912] Device:

[1913] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[1914] Example: Generated cocktail name "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and image of the appearance.

[1915] User (Bartender):

[1916] Check the displayed results and create a cocktail.

[1917] Serve cocktails to customers and collect their reactions and feedback.

[1918] Device:

[1919] The collected feedback is converted into JSON format and sent back to the server.

[1920] Example: { "feedback": "Make it look a little simpler"}

[1921] Additionally, the emotion engine transmits any additional emotion data collected back to the server.

[1922] server:

[1923] The received feedback and sentiment data is analyzed and used to improve the performance of the generative AI model.

[1924] The feedback information is used as training data for the model and added as new data points.

[1925] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[1926] This allows the system to continuously learn, and for future requests, it will be able to suggest cocktails that are more accurate and take into account both the customer's wishes and emotions. For example, if a customer requests a "refreshing and energizing cocktail" and the emotion engine detects the customer's excited state, the generative AI model will suggest a "citrus and mint-based energy booster cocktail" and provide the result to the bartender. In this way, more personalized cocktails can be offered.

[1927] The processing flow will be explained below.

[1928] Step 1:

[1929] User (Bartender):

[1930] The system listens to the customer's cocktail request and inputs it into the terminal's user interface. For example, the user can input specific requests such as "a fruit-based cocktail with a moderate sweetness" or "a drink with a distinctive blue color."

[1931] Step 2:

[1932] Device:

[1933] The input request information is converted into JSON format and sent to the server.

[1934] Example: { "request": "A fruit-based cocktail with a moderate sweetness", "color": "blue"}

[1935] In addition, the device's camera and microphone are used to capture the user's (bartender's) facial expressions and voice tone in real time and send the data to the emotion engine.

[1936] Step 3:

[1937] server:

[1938] Parse the received JSON formatted request and pass it as input to the generative AI model.

[1939] The emotion engine analyzes the collected facial expressions and voice tones to determine the user's emotional state. For example, the emotion engine can detect the user's excitement or satisfaction.

[1940] Step 4:

[1941] Generative AI model means (server):

[1942] Based on the request and emotional data, the AI ​​model consults a database to generate the optimal cocktail.

[1943] For example, it generates cocktail recipes based on "vodka, blue curacao, and lime juice" from the database and combines them, including their appearance and names.

[1944] Step 5:

[1945] Device:

[1946] The generated JSON format result received from the server is analyzed and converted into a format to be displayed in the user interface.

[1947] The generated results include the cocktail name "Blue Harmony", the recipe "50ml vodka, 20ml blue curacao, 30ml lime juice", and an image of its appearance.

[1948] Step 6:

[1949] User (Bartender):

[1950] Check the displayed results and create a cocktail.

[1951] Serve cocktails to customers and collect their reactions and feedback.

[1952] Step 7:

[1953] User (Bartender):

[1954] Customer feedback is entered into the device's feedback screen. For example, specific comments such as "It looks too flashy" or "The flavor is a little weak" are entered.

[1955] Step 8:

[1956] Device:

[1957] The input feedback information is converted into JSON format and sent to the server.

[1958] Example: { "feedback": "Make it look a little simpler"}

[1959] Additionally, any additional emotional data collected by the emotion engine (e.g., customer smiles or changes in voice tone) is sent back to the server.

[1960] Step 9:

[1961] server:

[1962] The received feedback and sentiment data is analyzed and used to improve the performance of the generative AI model.

[1963] Feedback information and emotion data are used as training data for the model and added as new data points.

[1964] The generative AI model is fine-tuned and the results are reflected in the next cocktail generation.

[1965] This allows the system to continuously learn, and for future requests, it will be able to suggest cocktails that are more accurate and take into account both the customer's wishes and emotions. For example, if a customer requests a "refreshing and energizing cocktail" and the emotion engine detects the customer's excited state, the generative AI model will suggest a "citrus and mint-based energy booster cocktail" and provide the result to the bartender. In this way, more personalized cocktails can be offered.

[1966] Example 2

[1967] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1968] Conventional cocktail recommendation systems are based solely on customer requests and do not fully consider customer sentiment or real-time feedback. This makes it difficult to recommend cocktails that will increase customer satisfaction. Furthermore, the collection and application of feedback is insufficient, limiting improvements to the system's performance.

[1969] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1970] In this invention, the server includes an information input means for inputting requests from customers, an input analysis means for converting the input request into JSON format and collecting user emotional data according to the request, an emotional analysis means for analyzing the collected emotional data and passing it as input to a generative AI model, a generative AI model means for generating an optimal cocktail based on the input request and emotional data, a result display means for displaying the recipe, appearance, and name of the generated cocktail, and a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance. This enables personalized cocktail suggestions that take customer emotions into consideration and continuous performance improvement of the system by reflecting feedback in real time.

[1971] The "information input means" is an interface for receiving requests from customers, and includes a graphical user interface (GUI) and a voice input device.

[1972] "Input analysis means" refers to a device or software that has the function of converting input requests into JSON format and collecting customer emotional data in response to the requests.

[1973] An "emotion analysis means" is a device or software that has the function of analyzing collected emotional data and inputting the results into a generative AI model.

[1974] The "generative AI model means" is an artificial intelligence model for generating optimal cocktails based on input requests and emotional data.

[1975] The "result display means" is a display or other display device for displaying the recipe, appearance, and name of the created cocktail.

[1976] A "feedback collection means" is a device or software that collects feedback from users and reflects that information in the generative AI model.

[1977] The system of the present invention is designed to enable bartenders to propose the perfect original cocktail to each customer. The system is mainly composed of a terminal, a server, and various related means. Each component will be described in detail below.

[1978] Information input means (terminal)

[1979] This is an interface through which bartenders can input requests from customers. Specifically, a graphical user interface (GUI) is provided, through which bartenders can input customer requests. Furthermore, it is equipped with a camera and microphone, and can also collect emotional data such as facial expressions and voice tone of the customer.

[1980] Input analysis means (terminal)

[1981] It converts input requests into JSON format and analyzes the collected emotional data. This data is sent to a server (described later) and used as input for a generative AI model.

[1982] Emotion analysis means (server)

[1983] The server analyzes the received emotional data, which includes facial expression recognition and voice tone analysis, to determine the customer's emotional state.

[1984] Generative AI model means (server)

[1985] The generative AI model on the server generates the optimal cocktail based on the input request and emotional data, referencing information stored in a database such as ingredients, recipe, appearance, and name to generate the most suitable cocktail recipe.

[1986] Result display means (terminal)

[1987] This is a display device for presenting information about the created cocktail to the bartender. The cocktail recipe, name, and image of the appearance sent from the server are displayed.

[1988] Feedback collection means (terminals and servers)

[1989] The bartender collects customer feedback and sends it to the server via their device. The server analyzes this feedback and uses it as training data for the generative AI model. This feedback allows the system to continuously learn and is reflected in future cocktail creations.

[1990] For example, if a customer requests, "Please recommend a fruit-based cocktail with a moderate sweetness," the bartender enters this information into the terminal interface. The terminal converts the input information into JSON format and sends it to the server. At the same time, the terminal collects the customer's facial expressions and voice, which are also sent to the server. An emotion analysis method on the server analyzes this data, and a generative AI model generates the optimal cocktail. The generated cocktail information is sent back to the terminal and displayed to the bartender. The bartender creates a cocktail based on this information and serves it to the customer.

[1991] In this way, the system makes personalized cocktail suggestions that take into account the customer's request and emotional state, and continuously improves the system's performance based on collected feedback, resulting in higher customer satisfaction.

[1992] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1993] Step 1:

[1994] User (Bartender):

[1995] The cocktail request is taken from the customer and entered into the terminal's information input means.

[1996] (Input): Customer request (e.g., "A fruit-based cocktail with a moderate sweetness")

[1997] (Output): Text data entered into the interface

[1998] (Specific action): The bartender enters "a fruit-based cocktail with a moderate sweetness" into the GUI screen.

[1999] Step 2:

[2000] Device:

[2001] The system converts the input request into JSON format and sends it to the server, and also uses the device's camera and microphone to collect the customer's facial expressions and voice tone.

[2002] (Input): Text data entered into the interface

[2003] (Output): Request data and emotion data in JSON format (e.g., { "request": "A fruit-based cocktail with a moderate sweetness", "emotion": "neutral"})

[2004] (Specific operation): The device converts the request into the format { "request": "A fruit-based, lightly sweetened cocktail"}, captures the customer's face and voice data, and sends it to the server.

[2005] Step 3:

[2006] server:

[2007] The transmitted request and emotion data are received, and the emotion data is analyzed by emotion analysis means.

[2008] (Input): Request data and emotion data in JSON format

[2009] (Output): Parsed emotion information (e.g. "neutral")

[2010] (Specific behavior): The server analyzes the received data and determines the request for a "fruit-based, lightly sweetened cocktail" and the emotional state as "neutral."

[2011] Step 4:

[2012] server:

[2013] Based on the analysis results, a generative AI model creates the optimal cocktail.

[2014] (Input): Request data (e.g., "A fruit-based cocktail with a moderate sweetness") and sentiment data (e.g., "neutral")

[2015] (Output): Cocktail recipe, name, and image (e.g. "Blue Harmony", recipe "50ml vodka, 20ml blue curacao, 30ml lime juice")

[2016] (Specific operation): The generative AI model references the database, generates a cocktail that matches the request, converts the information into JSON format, and sends it to the terminal.

[2017] Step 5:

[2018] Device:

[2019] The generated results received from the server are analyzed and displayed on the user interface.

[2020] (Input): Cocktail creation data in JSON format (e.g., { "name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image": "image_url"})

[2021] (Output): Cocktail information in display format

[2022] (Specific operation): The device analyzes the received data and displays the cocktail name "Blue Harmony," its recipe, and an image of its appearance on the display.

[2023] Step 6:

[2024] User (Bartender):

[2025] Based on the displayed cocktail information, the specified cocktail is created and served to the customer.

[2026] (Input): Cocktail recipe, name, and image (e.g., "Blue Harmony" with recipe "50ml vodka, 20ml blue curacao, 30ml lime juice")

[2027] (Output): Finished cocktail

[2028] (Specific action): The bartender creates a cocktail based on the displayed recipe by mixing 50ml of vodka, 20ml of blue curacao, and 30ml of lime juice.

[2029] Step 7:

[2030] User (Bartender):

[2031] Serve cocktails to customers and collect their reactions and feedback.

[2032] (Input): Customer feedback (e.g., "Please make it look a little simpler")

[2033] (Output): Collected feedback

[2034] (Specific action): The bartender listens to the customer's feedback and enters it into the terminal.

[2035] Step 8:

[2036] Device:

[2037] The collected feedback is converted into JSON format and sent to the server.

[2038] (Input): Customer feedback (e.g., "Please make it look a little simpler")

[2039] (Output): Feedback data in JSON format (e.g., { "feedback": "I'd like it to look a little simpler"})

[2040] (Specific operation): The device converts the feedback into JSON format and sends it to the server.

[2041] Step 9:

[2042] server:

[2043] The feedback received is analyzed and used to improve the generative AI model.

[2044] (Input): Feedback data in JSON format (e.g., { "feedback": "I'd like it to look a little simpler"})

[2045] (Output): Updated generative AI model

[2046] (Specific operation): The generative AI model is fine-tuned based on the feedback data and reflected in the system's next cocktail generation.

[2047] (Application example 2)

[2048] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2049] While conventional systems can reflect specific customer requests, it is difficult to incorporate the customer's emotions and preferences. Therefore, there is a need for a method that can analyze the customer's emotions from their facial expressions and tone of voice to suggest more personalized cocktails. It is necessary to solve these issues and improve customer satisfaction.

[2050] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2051] In this invention, the server includes a user interface means for inputting requests from customers, a generative AI model means for generating optimal cocktails based on the input requests and customer emotion data, a display means for displaying the recipe, appearance, and name of the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve performance, and an emotion engine means for analyzing facial expressions and voice tones to collect emotion data, thereby enabling more personalized cocktail suggestions that reflect the customer's emotions and preferences.

[2052] The "user interface means" is a means for a customer to input a request, and provides a graphical user interface or a voice input interface.

[2053] "Generative AI model means" refers to an artificial intelligence model that generates the optimal cocktail from a vast database based on input requests and customer emotional data.

[2054] "Display means" refers to a display device or screen that visually shows information such as the recipe, appearance, and name of the created cocktail to the bartender and customer.

[2055] The "feedback collection means" is a means for collecting feedback from users (bartenders or customers) and sending it to the server, which contributes to improving the performance of the generative AI model.

[2056] The "emotion engine means" is a means for analyzing the customer's facial expressions and voice tone and collecting emotional data.

[2057] A "request" is information describing the conditions and characteristics of the cocktail a customer desires, and refers to the data entered into the system.

[2058] "Cocktail generation" refers to the process of determining the optimal cocktail ingredients, recipe, appearance, and name based on the input request and emotional data.

[2059] The "database" refers to data storage that accumulates information such as cocktail ingredients, recipes, images, and names, and is used as a reference for the generative AI model.

[2060] "Facial Expression" is a visual representation of a customer's emotional state that is analyzed by a camera and / or emotion engine means.

[2061] "Voice Tone" is an acoustic expression that indicates the customer's emotional state and is analyzed by the microphone and emotion engine means.

[2062] The system for carrying out this invention includes the following main components and procedures: an interface means for a user to input a request, a generative AI model means for generating an optimal cocktail based on the request and emotional data, a display means for displaying information about the generated cocktail, a feedback collection means for collecting feedback from users and reflecting it in the generative AI model, and an emotion engine means for analyzing the facial expressions and voice tones of customers to collect emotional data.

[2063] The server achieves these functions by using the following means:

[2064] 1. User Interface Means

[2065] A graphical user interface (GUI) is implemented on devices such as smartphones and tablets, allowing customers to input their cocktail requests. The devices are also equipped with cameras and microphones, allowing them to simultaneously collect customers' facial expressions and vocal tones, thereby obtaining emotional data.

[2066] 2. Generative AI Model Means

[2067] The server analyzes the received request and emotional data using algorithms that analyze natural language processing, facial expressions, and voice tones. The analyzed data is then input into a generative AI model, which then selects from a vast database of cocktails to create a cocktail that combines the optimal ingredients, recipe, appearance, and name.

[2068] 3. Display means

[2069] The generated cocktail information (recipe, appearance, name) is displayed on the smartphone or tablet screen in a visually appealing format for bartenders and customers to review at a glance.

[2070] 4. Feedback Collection Methods

[2071] Users (bartenders or customers) input their cocktail ratings and feedback. This feedback is sent from the device to the server and analyzed. The results of the feedback analysis are added as training data for the generative AI model, contributing to performance improvement.

[2072] 5. Emotional Engine Means

[2073] The server uses data collected from cameras and microphones to recognize the customer's emotions. Using algorithms that analyze facial expressions and vocal tones, detailed emotional data is extracted, which is then used as part of the cocktail creation process.

[2074] Specific examples

[2075] For example, if a customer requests a "fruit-based cocktail with a moderate sweetness," the system operates as follows:

[2076] 1. The customer types in their request, and their facial expressions and voice tone are collected by a camera and microphone.

[2077] 2. The server analyzes the request and emotion data and inputs it into a generative AI model.

[2078] 3. The generative AI model selects the optimal cocktail, "Blue Harmony," from the database and generates a recipe and visual information.

[2079] 4. This information will be displayed on your smartphone or tablet screen.

[2080] Prompt Sentence Examples

[2081] Request: Fruit-based cocktail with a moderate sweetness

[2082] Emotional data: facial expressions and vocal tones

[2083] In this way, the system can generate and display personalized cocktails based on the customer's emotions and requests.

[2084] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2085] Step 1:

[2086] When a user (customer) orders a cocktail at a bar, they input their cocktail request using the user interface on their smartphone or tablet.

[2087] Input: The request entered by the customer (e.g., "A fruit-based cocktail with a moderate sweetness").

[2088] Output: Request data in JSON format (e.g., {"request": "A fruit-based cocktail with a moderate sweetness"}).

[2089] Step 2:

[2090] The device's camera and microphone collect the customer's facial expressions and voice tone, and this data is sent to the emotion engine means.

[2091] Input: Raw facial expression and speech tone data.

[2092] Output: Emotion data (e.g., {"emotion": "happiness"}).

[2093] Step 3:

[2094] The device combines the request data and emotion data, converts them into JSON format, and sends them to the server.

[2095] Input: Request data and emotion data.

[2096] Output: Combined data in JSON format (e.g., {"request": "Fruit-based cocktail with a moderate sweetness", "emotion": "happiness"}).

[2097] Step 4:

[2098] The server parses the received JSON-formatted data and inputs it into the generative AI model.

[2099] Input: The combined data in JSON format.

[2100] Output: The input data (request and sentiment data converted into internal data structures) in a format suitable for the generative AI model.

[2101] Step 5:

[2102] A generative AI model references the database and generates the optimal cocktail ingredients, recipe, name, and appearance.

[2103] Input: Parsed request and sentiment data.

[2104] Output: Information about the generated cocktail (e.g., {"name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image_url": " / images / blue_harmony.jpg"}).

[2105] Step 6:

[2106] The server converts the cocktail creation results into JSON format and sends it to the terminal.

[2107] Input: Generated cocktail information (internal data structure).

[2108] Output: JSON formatted result data (e.g., {"name": "Blue Harmony", "recipe": "50ml vodka, 20ml Blue Curacao, 30ml lime juice", "image_url": " / images / blue_harmony.jpg"}).

[2109] Step 7:

[2110] The terminal analyzes the received JSON formatted generated result and converts it into a format to be displayed on the user interface.

[2111] Input: The generated result data in JSON format.

[2112] Output: Format displayed in the user interface (visual cocktail information).

[2113] Step 8:

[2114] The user (bartender) checks the displayed results and creates a cocktail. The user serves the cocktail to the customer and collects their reaction and feedback.

[2115] Input: Cocktail information displayed in the user interface.

[2116] Output: Actual cocktails and customer feedback.

[2117] Step 9:

[2118] The device converts the collected feedback into JSON format and sends it back to the server.

[2119] Input: Customer feedback.

[2120] Output: Feedback data in JSON format (e.g. {"feedback": "Make it look a little simpler"}).

[2121] Step 10:

[2122] The server analyzes the received feedback and additional emotional data and uses it to improve the performance of the generative AI model.

[2123] Input: Feedback and sentiment data in JSON format.

[2124] Output: A fine-tuned generative AI model.

[2125] These processing steps allow the system to make more personalized cocktail suggestions based on customer sentiment and requests.

[2126] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2127] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2128] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2129] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2130] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2131] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2132] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2133] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2134] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2135] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2136] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2137] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2138] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2139] 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.

[2140] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2141] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2142] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2143] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2144] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2145] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2146] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2147] The following is further disclosed regarding the above embodiment.

[2148] (Claim 1)

[2149] a user interface means for inputting requests from customers;

[2150] A generative AI model that generates the optimal cocktail from a vast database based on the input request, and

[2151] a display means for displaying the recipe, appearance, and name of the generated cocktail;

[2152] A feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance;

[2153] A system including:

[2154] (Claim 2)

[2155] 10. The system of claim 1,

[2156] The system is characterized in that the generative AI model means analyzes the request and generates a cocktail by combining appropriate ingredients, recipes, images, and names from a database.

[2157] (Claim 3)

[2158] 10. The system of claim 1,

[2159] The feedback collection means analyzes the feedback entered by the user and fine-tunes the generative AI model based on the analysis results.

[2160] "Example 1"

[2161] (Claim 1)

[2162] an information input means for inputting a request from a customer;

[2163] A generative AI model means for generating an appropriate cocktail based on an input request;

[2164] a display means for displaying the recipe, appearance, and name of the generated cocktail;

[2165] A feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance;

[2166] A system including:

[2167] (Claim 2)

[2168] A means of formatting the input request information in JSON format and sending it to the server;

[2169] The system of claim 1, characterized in that the server inputs request information into a generative AI model and refers to a cocktail database to generate an optimal cocktail.

[2170] (Claim 3)

[2171] The feedback collection means formats the feedback input by the user in JSON format and transmits it to a server;

[2172] The system of claim 1, wherein the server fine-tunes the generative AI model based on the analysis results.

[2173] "Application Example 1"

[2174] (Claim 1)

[2175] a user interface means for inputting requests from customers;

[2176] A generative AI model that generates the optimal cocktail from a vast database based on the input request, and

[2177] a display means for displaying the recipe, appearance, and name of the generated cocktail;

[2178] A feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance;

[2179] A delivery method for ordering the suggested cocktails via smartphone and having them delivered through a delivery service;

[2180] A system including:

[2181] (Claim 2)

[2182] The system of claim 1, wherein the generative AI model means analyzes the request and generates a cocktail by combining appropriate ingredients, recipes, images, and names from a database.

[2183] (Claim 3)

[2184] The system according to claim 1, characterized in that the feedback collection means analyzes the feedback input by the user and fine-tunes the generative AI model based on the analysis results.

[2185] "Example 2: Combining Emotion Engines"

[2186] (Claim 1)

[2187] an information input means for inputting a request from a customer;

[2188] an input analysis means for converting an input request into a JSON format and collecting user emotion data according to the request;

[2189] An emotion analysis means that analyzes the collected emotion data and passes it as input to the generative AI model;

[2190] A generative AI model means for generating an optimal cocktail based on input requests and emotional data;

[2191] a result display means for displaying the recipe, appearance, and name of the generated cocktail;

[2192] A feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance;

[2193] A system including:

[2194] (Claim 2)

[2195] The system of claim 1, wherein the generative AI model means analyzes the request and generates a cocktail by combining appropriate ingredients, recipes, images, and names from a database.

[2196] (Claim 3)

[2197] The system according to claim 1, characterized in that the feedback collection means analyzes the feedback input by the user and fine-tunes the generative AI model based on the analysis results.

[2198] "Application example 2 when combining emotion engines"

[2199] (Claim 1)

[2200] a user interface means for inputting requests from customers;

[2201] A generative AI model means for generating the optimal cocktail based on the input request and customer sentiment data;

[2202] a display means for displaying the recipe, appearance, and name of the generated cocktail;

[2203] A feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance;

[2204] emotion engine means for analyzing facial expressions and voice tones to collect emotion data;

[2205] A system including:

[2206] (Claim 2)

[2207] The system according to claim 1, wherein the generative AI model means analyzes the request and emotional data and generates a cocktail by combining appropriate ingredients, recipes, images, and names from a database.

[2208] (Claim 3)

[2209] The system according to claim 1, characterized in that the feedback collection means analyzes the feedback input by the user and fine-tunes the generative AI model based on the analysis results. [Explanation of symbols]

[2210] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a user interface means for inputting requests from customers; A generative AI model that generates the optimal cocktail from a vast database based on the input request, and a display means for displaying the recipe, appearance, and name of the generated cocktail; A feedback collection means for collecting feedback from users and reflecting it in the generative AI model to improve its performance; A system including:

2. 10. The system of claim 1, The system is characterized in that the generative AI model means analyzes the request and generates a cocktail by combining appropriate ingredients, recipes, images, and names from a database.

3. 10. The system of claim 1, The feedback collection means analyzes the feedback entered by the user and fine-tunes the generative AI model based on the analysis results.

Images