System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving an image of a dish, a means for analyzing the received image and extracting features of the dish, a means for generating advice for improving the appearance of the dish based on the analysis result, a means for transmitting the generated advice to a user terminal, and a means for displaying the advice on the user terminal.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] Because people are unaware of ways to improve the appearance of home-cooked food, many people lack specialized knowledge about plating and selecting plates, and do not know how to make food look appetizing. As a result, home-cooked food looks less appealing and the enjoyment of eating is reduced. To solve this problem, there is a need to provide an easily accessible system that can improve the appearance of home-cooked food and make eating more enjoyable. [Means for solving the problem]

[0005] To solve the above problem, we provide a system including: means for receiving an image of a dish; means for analyzing the received image to extract characteristics of the dish; means for generating advice for improving the appearance of the dish based on the analysis results; means for transmitting the generated advice to a user terminal; and means for displaying the advice on the user terminal. By extracting the characteristics of the dish using an image analysis algorithm and generating specific advice regarding the addition of ingredients, the presentation method, and the color and shape of the plate to be used, users can easily improve the appearance of their dishes.

[0006] "Means for receiving food images" refers to a function that allows a user to send images of food taken using a device such as a smartphone or PC to a system such as a server, and then import the image data.

[0007] An "image analysis algorithm" is a computational method for processing an image of a dish as digital data and extracting specific information or characteristics from that image (such as the types of ingredients used or the arrangement of the food on the plate).

[0008] The "means for extracting food features" is a function for extracting specific information or features from food images using an image analysis algorithm.

[0009] "Advice for improving food presentation" is any suggestion or instruction to make a dish more visually appealing, including specific instructions regarding additional ingredients, presentation methods, and plate color or shape.

[0010] The "means for generating advice" is a function for generating specific advice or suggestions for improving the appearance of a dish based on the characteristics of the dish obtained through image analysis.

[0011] The "means for transmitting to the user terminal" refers to a communication means for delivering the generated advice to the user's terminal such as a smartphone or PC.

[0012] The "means for displaying advice on the user terminal" refers to a function for visually showing the advice sent to the user terminal to the user, and includes notifications, pop-ups, dedicated screens, etc. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a system that provides specific advice on how to improve the appearance of a dish simply by allowing a user to upload a photo of the dish. This system is composed of a server, a user's terminal, and a generating AI. The program processing and specific embodiments of this system are described below.

[0035] System Overview

[0036] 1. Receiving images

[0037] User

[0038] Users take photos of their food using their smartphone camera or PC webcam.

[0039] Upload the photos you take to the system via an application or web interface.

[0040] 2. Image Analysis

[0041] server

[0042] The server stores the received images and prepares them for passing to the generation AI for image analysis.

[0043] Generation AI

[0044] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, and more.

[0045] 3. Generating Advice

[0046] Generation AI

[0047] Based on the analyzed data, the system generates specific advice to improve the appearance of the dish, such as adding green onions, serving the food a little higher, or using a different color plate.

[0048] 4. Submitting Advice

[0049] server

[0050] The server receives the advice text from the generation AI and sends it to the user's device.

[0051] 5. Displaying Advice

[0052] Terminal

[0053] The user's smartphone or PC receives the advice and displays it to the user through an application or web interface.

[0054] Specific examples

[0055] Example 1: Upload a photo of curry rice

[0056] User operations

[0057] The user launches the smartphone app and takes a photo of the curry rice.

[0058] Tap the "Upload" button to send the photo to the application server.

[0059] Server Processing

[0060] The server receives the photos and stores them temporarily.

[0061] Send the saved photo to the generation AI.

[0062] Generative AI analysis and advice generation

[0063] The generative AI uses image analysis algorithms to extract characteristics of curry rice from photos, such as the color of the curry, the height of the serving, and any optional toppings used.

[0064] Based on this information, the generative AI generates specific advice such as "garnish with parsley," "serve the rice in a mound shape," and "use a blue plate."

[0065] Server Send

[0066] The server transmits the generated advice to the user's terminal.

[0067] Terminal display

[0068] The user's smartphone receives the advice and displays it in a pop-up format, including advice such as "Add parsley," "Serve the rice in a mound," and "Use a blue plate."

[0069] By using this system, users can easily improve the appearance of their food without any specialized knowledge. This system can also be applied to any type of food, making home cooking more enjoyable and visually satisfying.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] User

[0073] Users launch the application, take a photo of their food using the camera on their smartphone or PC, and then tap the "Upload" button to send the photo to the application.

[0074] Step 2:

[0075] server

[0076] The server receives photos of food uploaded by users, temporarily stores the images, and prepares them for image analysis.

[0077] Step 3:

[0078] server

[0079] The server prepares the stored images to be passed to the generation AI module and sends the image data to the generation AI, where it is converted into a format for analysis.

[0080] Step 4:

[0081] Generation AI

[0082] Generative AI uses image analysis algorithms to extract specific features from food images, including the type of food, the ingredients used, how it's presented, and the color and shape of the plate.

[0083] Step 5:

[0084] Generation AI

[0085] Based on the extracted features, the generative AI generates specific advice to improve the appearance of the dish, such as "garnish with green onions," "serve the rice in a mountain shape," and "use a blue plate."

[0086] Step 6:

[0087] server

[0088] The server receives the advice data from the generation AI and prepares it for transmission to the user's device. The advice data is converted into a format suitable for the user's device.

[0089] Step 7:

[0090] server

[0091] The server then sends the prepared advice data to the user's smartphone or PC via the Internet or cloud services.

[0092] Step 8:

[0093] Terminal

[0094] The user's device parses the advice data received from the server and converts it into a format that can be displayed via an application or web interface.

[0095] Step 9:

[0096] Terminal

[0097] The device displays specific advice to the user. For example, pop-up messages on the screen suggest advice such as "Serve with green onions," "Serve the rice in a mountain shape," and "Use a blue plate." By referring to these, the user can improve the appearance of their dish.

[0098] Example 1

[0099] 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."

[0100] It is difficult for people without specialized knowledge of cooking to easily obtain specific advice on how to improve the appearance of food. Furthermore, specialized knowledge and experience are required to know specific ways to improve visual elements, such as how to add ingredients, how to arrange food, and the color and shape of containers to use. There is a growing demand for a system that can easily provide methods for enhancing the visual appeal of everyday cooking.

[0101] 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.

[0102] In this invention, the server includes means for users to upload images of dishes, means for saving the received images of dishes, means for sending the saved image data to a generative AI model, means for the generative AI model to extract characteristics of the dishes using an image analysis algorithm, means for generating advice to improve the appearance of the dishes based on the analysis results, means for sending the generated advice from the server to a user terminal, and means for displaying the advice on the user terminal. This enables users to receive specific advice based on photos of dishes they have taken, even if they do not have specialized knowledge.

[0103] A "user" is someone who uses the system to upload images of their dishes and receive visual improvement advice.

[0104] The "server" is a computer system that receives, stores, and relays images of dishes to be passed to the generative AI model.

[0105] An "image analysis algorithm" is a calculation method for extracting characteristics of food from received images and analyzing the type, presentation, etc.

[0106] A "generative AI model" is an artificial intelligence model that uses image analysis algorithms to analyze the characteristics of food and generate specific advice to improve its appearance.

[0107] "Advice" is specific suggestions for improving the appearance of a dish, such as adding ingredients, plating methods, and the color and shape of the containers to use.

[0108] A "user terminal" is a device owned by a user, such as a smartphone or PC, that displays advice sent from the system.

[0109] "Uploading" refers to the act of sending an image of a dish taken by a user to a server.

[0110] "Saving" is a process in which the server temporarily stores the image of the dish received in a storage device.

[0111] "Sending" refers to the act of delivering advice created by the generative AI model to the user's device via the server.

[0112] "Display" refers to the act of visually providing advice on a user terminal.

[0113] This invention is a system that provides specific advice on how to improve the appearance of a dish simply by allowing the user to upload a photo of the dish. The system is composed of a server, a user's device, and a generative AI model.

[0114] System Overview

[0115] Users take photos of their dishes using their smartphones or PCs and upload them through an application or web interface. The uploaded images are sent to the generative AI model via the server. The generative AI model uses image analysis algorithms to analyze the characteristics of the dish and, based on the results, generates specific advice to improve the appearance of the dish. The generated advice is sent to the user's device via the server, where the user can receive it and view it via the application or web interface.

[0116] Specific implementation methods

[0117] A user takes a photo of a dish using a smartphone camera or a PC webcam. The photo is then uploaded using a dedicated application or web interface. For example, this involves launching a smartphone application, tapping the "Take Photo" button to take a photo of the dish, and then pressing the "Upload" button.

[0118] The uploaded images are temporarily stored by the server, which prepares them for sending to the generative AI model and converts them to the appropriate format and resolution, which includes reformatting and resizing the image files.

[0119] The generative AI model runs an image analysis algorithm using image data received from the server. The algorithm identifies the type of dish, the ingredients used, how it is presented, etc. For example, if the photo is of curry rice, it will analyze the color of the curry, how the rice is presented, and the type of ingredients. As an example of a prompt for the generative AI model, enter "Please provide some advice on how to improve the appearance of this dish."

[0120] Based on the analysis results, the generative AI model generates specific advice to improve the appearance of the dish. Specific advice includes "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate." The advice is sent to the server.

[0121] The server sends the advice text received from the generative AI model to the user's device. The server selects the appropriate communication method based on the user's ID and device information to send the data. If the user is using a smartphone app, the data is sent as a push notification or in-app message.

[0122] The user device will then display the received advice. For example, in the case of a smartphone app, a pop-up notification will appear, showing advice such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[0123] This allows users to receive specific advice based on photos of their food, even if they do not have specialized knowledge. This system allows users to easily receive advice on how to improve the appearance of their food, helping them to provide visually satisfying dishes. It is also highly versatile and can be applied to a wide range of cooking, from home cooking to cooking by professional chefs.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] Users take and upload images of their dishes

[0127] Specific operation: The user takes a photo of the food using the camera on their smartphone or the webcam on their PC, and uploads the photo to the system via a dedicated application or web interface.

[0128] Input: Image files of the photographed food.

[0129] Output: Image data uploaded to the system.

[0130] Step 2:

[0131] The server receives and stores the images

[0132] Specific operation: The server temporarily stores images uploaded by users. The image storage location is the specified database or storage.

[0133] Input: Uploaded image data.

[0134] Output: The file path and ID of the saved image data.

[0135] Step 3:

[0136] The server prepares the image to be sent to the generative AI model.

[0137] What it does: The server converts the stored images into the appropriate format and resolution for sending to the generative AI model. This conversion includes formatting and resizing the image files.

[0138] Input: The file path or ID of the saved image data.

[0139] Output: Image data in a format and resolution suitable for the generative AI model.

[0140] Step 4:

[0141] The server sends the image data to the generative AI model.

[0142] Specific operation: The server sends the converted image data to the generative AI model using an API request or similar.

[0143] Input: The transformed image data.

[0144] Output: Image data sent to the generative AI model for analysis.

[0145] Step 5:

[0146] Generative AI models run image analysis algorithms

[0147] How it works: The generative AI model uses the received image data to run an image analysis algorithm, which analyzes the type of food, the ingredients used, the presentation, and more.

[0148] Input: Image data for analysis.

[0149] Output: Analysis data including food characteristics, such as type of food, color, presentation, etc.

[0150] Step 6:

[0151] Generative AI models generate advice

[0152] Specific behavior: Based on the analysis, the generative AI model generates specific advice to improve the presentation of the dish, including suggestions on adding ingredients, plating methods, and the color and shape of the container to use.

[0153] Input: Parsed data containing dish characteristics.

[0154] Output: Specific advice text, such as "Serve with parsley," "Serve the rice in a mound," or "Use a blue plate."

[0155] Step 7:

[0156] The server sends the advice text to the user terminal.

[0157] Specific operation: The server sends the advice text received from the generative AI model to the user's device via push notifications, in-app messages, or other means.

[0158] Input: The generated advice text.

[0159] Output: Advice text sent to the user's terminal.

[0160] Step 8:

[0161] The device displays advice

[0162] Specific operation: The user device displays the received advice text. Specifically, in the case of a smartphone app, it is displayed as a pop-up notification or an in-app message.

[0163] Input: The advice text sent.

[0164] Output: Advice displayed on the user's screen, such as "Serve with parsley," "Serve the rice in a mountain shape," and "Use a blue plate."

[0165] (Application example 1)

[0166] 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."

[0167] The appearance of food has a significant impact on how it is evaluated, and is directly linked to customer satisfaction and increased repeat customers, especially in brick-and-mortar restaurants. However, if kitchen staff and chefs do not have specialized knowledge about food presentation and presentation, it is difficult to maximize the visual appeal of the food. To solve this problem, a system is needed that provides specific advice in real time on how to improve the appearance of food.

[0168] 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.

[0169] In this invention, the server includes means for receiving images of dishes, means for analyzing the received images to extract characteristics of the dishes, means for generating advice to improve the appearance of the dishes based on the analysis results, means for transmitting the generated advice to a user terminal, means for displaying specific advice to improve the appearance of the dishes on the user terminal, means for receiving images via a smart device used in a physical store, and means for analyzing the images using a generative AI model and generating advice to improve the appearance of the dishes using prompt sentences. This allows cooking staff and chefs to receive specific advice in real time even if they do not have specialized knowledge about the appearance of dishes, thereby improving customer satisfaction.

[0170] "Food images" are photographic data of food taken with a digital camera or smartphone.

[0171] The "receiving means" is an interface or protocol that allows a server or smart device to receive images of dishes sent by a user.

[0172] "Means for analyzing and extracting food characteristics" refers to a system or software that uses an image analysis algorithm to automatically identify and extract characteristics such as the type of food, the height of the presentation, and the ingredients used.

[0173] "Means for generating advice" refers to functionality or software that uses a generative AI model based on the analysis results to create specific suggestions or improvements to improve the presentation of food.

[0174] "User terminal" refers to a device, such as a smartphone, tablet, or computer, that a user operates to receive and display advice.

[0175] The "display means" refers to a function such as an application, web interface, or pop-up for visually displaying the advice generated on the user terminal.

[0176] A "physical store" is a business location, such as a restaurant or cafe, where customers actually visit and food is served.

[0177] A "smart device" is a device that has internet connectivity and is capable of taking and transmitting images, and examples include smartphones and tablets.

[0178] A "generative AI model" is an artificial intelligence system that specializes in image analysis and advice generation using technologies such as deep learning.

[0179] A "prompt" is an instruction or data that a user inputs into an application, or an instruction text that a generation AI uses when creating advice.

[0180] The system for implementing this invention comprises a server, a smart device, and a user. The server has the function of receiving images of dishes, analyzing the received images, and extracting the characteristics of the dishes. Then, using a generative AI model, it generates advice for improving the appearance of the dishes based on the analysis results. The generated advice is sent to the user's terminal, and the specific advice is displayed on the user's terminal.

[0181] Hardware and software configuration:

[0182] The server has high-performance computing resources for processing images and has installed the necessary software libraries to run the generative AI model, such as a Python web server using Flask and external generative AI services (e.g., Google® Cloud Vision or Amazon Rekognition).

[0183] The user terminals may be smartphones, tablets, computers, etc. These terminals have a camera function and can run an application to take images and send them to a server.

[0184] Data processing and calculation:

[0185] The server receives and temporarily stores image data sent by the user. The received image is analyzed using an image analysis algorithm to extract features such as the type of food, how it is presented, and the ingredients used. Based on the results of this analysis, a generative AI model generates advice.

[0186] Specific advice includes "serve with fresh herbs," "serve the rice in a mountain shape," "use a blue plate," etc. These pieces of advice are sent from the server to the user's device and displayed to the user through the application.

[0187] Examples:

[0188] For example, imagine a restaurant chef takes a photo of a dish using a smartphone app. The chef taps the "upload" button to send the photo to the server. The server analyzes the received image, and the generative AI model generates advice such as "garnish with fresh herbs" or "serve the rice in a mountain shape" based on the analysis results, and sends this to the chef's device. The chef can receive the advice through the application and follow the instructions to improve the appearance of the dish.

[0189] Example prompt sentence:

[0190] "Take a photo of your food and upload it. Use it for dishes you're not confident about plating, like pasta or steak."

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] Users take photos of their food using their smartphones or tablets.

[0194] Input: Image data of food taken with a smartphone or tablet camera.

[0195] Output: Captured image data.

[0196] Specific operation: The user takes a photo of the food using a camera app or a dedicated app.

[0197] Step 2:

[0198] The user uploads the captured images to the server through the application.

[0199] Input: Captured image data.

[0200] Output: Image data sent to the server.

[0201] Specific operation: The user selects an image of a dish and taps the "Upload" button in the application to send the image data to the server.

[0202] Step 3:

[0203] The server temporarily stores the received images and prepares them for image analysis.

[0204] Input: Image data sent to the server.

[0205] Output: Saved image file.

[0206] Specific operation: The server temporarily stores the image data in storage and prepares it for analysis.

[0207] Step 4:

[0208] The server analyzes the stored images using a generative AI model.

[0209] Input: A saved image file.

[0210] Output: Food feature data (e.g., serving height, type of ingredients, etc.).

[0211] Specific operation: The server uses an image analysis algorithm (e.g., Google Cloud Vision or Amazon Rekognition) to analyze the food and extract its characteristics.

[0212] Step 5:

[0213] Based on the analyzed data, the server uses a generative AI model to generate advice to improve the presentation of the dish.

[0214] Input: Food feature data.

[0215] Output: The generated advice (e.g., "Serve with fresh herbs" or "Serve the rice in a mound").

[0216] Specific operation: The server runs the generative AI model, inputs the dish's characteristic data as prompts, and generates advice.

[0217] Step 6:

[0218] The server transmits the generated advice to the user terminal.

[0219] Input: The generated advice.

[0220] Output: Advice message sent to user terminal.

[0221] Specific operation: The server sends the generated advice as text data to the user's smartphone or tablet.

[0222] Step 7:

[0223] The user terminal displays the received advice.

[0224] Input: The advice message sent by the server.

[0225] Output: The advice that is displayed to the user.

[0226] Specific operation: The user device will display the advice in the form of a pop-up or notification through the application, visually communicating it to the user.

[0227] 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.

[0228] This invention is a system that analyzes images of food to generate advice for improving the appearance of the food, and further combines it with an emotion engine that recognizes the user's emotions. By providing optimal advice based on the user's emotional state, this system can improve the appearance of the food and increase user satisfaction. Below, we will explain the program processing and specific embodiments of this system.

[0229] System Overview

[0230] 1. Receiving images

[0231] User

[0232] Users take photos of their food using the camera on their smartphone or PC, then upload the photos to the system via an application or web interface.

[0233] 2. Image Analysis

[0234] server

[0235] The server receives photos of dishes uploaded by users and temporarily stores them.

[0236] The server passes the saved images to the generative AI module.

[0237] Generation AI

[0238] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, and more.

[0239] 3. Emotional Recognition

[0240] Terminal

[0241] The user's device uses a camera and microphone to input the user's facial expressions and voice into the emotion engine, which then recognizes the user's current emotional state (happiness, sadness, surprise, etc.).

[0242] Emotion Engine

[0243] The emotion engine analyzes and recognizes emotions from the user's facial expressions and voice, and sends that data to the server.

[0244] It also learns from past user reaction data to provide advice optimized for each individual user.

[0245] 4. Generating Advice

[0246] Generation AI

[0247] Combining image analysis and emotion engine data, it generates specific recommendations to improve the presentation of dishes, such as adding green onions, serving rice in a mountain shape, and using blue plates.

[0248] Based on information from the emotion engine, the system tailors advice to the user's emotional state. For example, if the user is feeling down, the system provides gentle, easy-to-understand advice.

[0249] 5. Submitting Advice

[0250] server

[0251] The server receives the advice data from the generation AI and prepares it for transmission to the user's terminal.

[0252] 6. Displaying Advice

[0253] Terminal

[0254] The user's device analyzes the advice data received from the server and displays it to the user through an application or web interface.

[0255] Specific examples

[0256] Example 1: Upload a photo of curry rice

[0257] User operations

[0258] The user launches the smartphone app and takes a photo of the curry rice.

[0259] Tap the "Upload" button to send the photo to the application server.

[0260] Server Processing

[0261] The server receives the photos and stores them temporarily.

[0262] Pass the saved photo to the generation AI module.

[0263] Collaboration between generative AI and emotion engine

[0264] Generation AI

[0265] The generative AI analyzes the photo and extracts the characteristics of the curry rice (for example, the color of the curry, the height of the serving, etc.).

[0266] Emotion Engine

[0267] The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state, such as whether they are happy, sad, or excited.

[0268] The recognized emotion data is sent to the generation AI.

[0269] Generating and Sending Advice

[0270] Generation AI

[0271] Based on emotion data and food feature data, specific advice such as "garnish with parsley," "serve the rice in a mound shape," and "use a blue plate" is generated.

[0272] If the user is feeling down, advice might include suggestions such as "add some uplifting colors."

[0273] server

[0274] The server transmits the generated advice to the user's terminal.

[0275] Terminal display

[0276] Terminal

[0277] The user's smartphone or PC will then display the received advice, such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[0278] This system allows users to easily improve the appearance of their food without any specialized knowledge, and also provides optimal advice based on their emotions, making home cooking even more enjoyable and satisfying.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] User

[0282] Users take a photo of the dish with their smartphone camera and tap the "upload" button through the application to send the photo to the system.

[0283] Step 2:

[0284] server

[0285] The server receives the uploaded photos of the dishes and temporarily stores them in storage.

[0286] Step 3:

[0287] server

[0288] The server sends the saved image data to the generation AI module and prepares it for analysis.

[0289] Step 4:

[0290] Generation AI

[0291] The generative AI uses image analysis algorithms to extract features such as the type of food, the ingredients used, the arrangement of the presentation, and the color and shape of the plate.

[0292] Step 5:

[0293] Terminal

[0294] The user's device uses a camera and microphone to collect the user's facial expressions and voice in real time and transmits them to the emotion engine.

[0295] Step 6:

[0296] Emotion Engine

[0297] The emotion engine analyzes the user's emotional state (e.g., joy, sadness, surprise, excitement, etc.) from their facial expressions and voice, and sends the recognized emotional data to the generation AI.

[0298] Step 7:

[0299] Generation AI

[0300] Based on the received emotion data and food feature data, the generative AI generates specific advice to improve the appearance of the food, such as adding ingredients, plating methods, or changing the color of the plate to improve the food's appearance.

[0301] Step 8:

[0302] Generation AI

[0303] The generative AI tailors its advice based on the user's emotional state: for example, if the user is feeling down, it will create gentle advice with encouraging words.

[0304] Step 9:

[0305] server

[0306] The server receives the generated advice data and prepares it for transmission to the user terminal.

[0307] Step 10:

[0308] server

[0309] The server sends the prepared advice data to the user's terminal, and uses the Internet or cloud services as a means of communication.

[0310] Step 11:

[0311] Terminal

[0312] The user's device analyzes the received advice data and converts it into a display format through an application or web interface.

[0313] Step 12:

[0314] Terminal

[0315] The device displays specific advice to the user, such as "serve with green onions," "serve the rice in a mountain shape," and "use a blue plate." The user can use this advice to improve the appearance of their dish.

[0316] Example 2

[0317] 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."

[0318] Conventional cooking analysis systems can provide advice on improving the appearance of dishes, but they are unable to provide optimal advice that takes into account the user's emotional state. As a result, users are unable to receive advice that is tailored to their psychological state and preferences, making it difficult to increase user satisfaction. The objective of this invention is to improve the appearance of dishes and increase user satisfaction by recognizing the user's emotional state and providing optimal advice based on that state.

[0319] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an image of a dish, means for analyzing the received image to extract characteristics of the dish, means for generating advice to improve the appearance of the dish based on the analysis results, means for recognizing the user's emotional state, means for adjusting the optimal advice based on the emotional state, means for transmitting the generated advice to the user terminal, and means for displaying the advice on the user terminal. This makes it possible to provide advice to improve the appearance of a dish that takes into account the user's emotional state.

[0320] The "means for receiving food images" refers to an interface for users to upload photos of food taken by them to the system.

[0321] "Means for analyzing received images and extracting characteristics of food" refers to algorithms or software that analyze received images of food and extract characteristics such as the type of food, ingredients used, and presentation.

[0322] "Means for generating advice to improve the appearance of food based on the analysis results" refers to a mechanism for generating specific advice to improve the visual appearance of food based on the analyzed characteristics of the food.

[0323] "Means for recognizing the user's emotional state" refers to a camera, microphone, and analysis algorithm for analyzing the user's facial expressions and voice to recognize the psychological emotional state at that time.

[0324] "Means for adjusting optimal advice based on emotional state" refers to a mechanism for adjusting advice to improve the appearance of food according to the recognized emotional state of the user and providing it in an optimal form for each individual user.

[0325] "Means for transmitting the generated advice to the user terminal" refers to the communication means or protocol for transmitting the generated advice to the user's terminal such as a smartphone or PC.

[0326] "Means for displaying advice on a user terminal" refers to an application or web interface for displaying received advice on the user's terminal.

[0327] This invention is a system that analyzes images of food, generates advice for improving the appearance, and combines it with an emotion engine that recognizes the user's emotional state. This system provides optimal advice based on the user's emotional state, improves the appearance of the food, and increases user satisfaction.

[0328] System Overview

[0329] This system mainly uses the following hardware and software.

[0330] 1. Receiving images

[0331] Users take photos of their food using their smartphone or PC camera and upload them to the system via an application or web interface.

[0332] 2. Image Analysis

[0333] The server receives photos of dishes uploaded by users and temporarily stores them. The stored images are then passed to the generation AI module. This can be done using an S3 bucket on Amazon Web Services (AWS (registered trademark)).

[0334] The generative AI uses image analysis algorithms to analyze the type of food, ingredients used, presentation, etc. It uses the Tensorflow (registered trademark) model to perform a detailed analysis of the elements in the image.

[0335] 3. Emotional Recognition

[0336] The device uses a camera and microphone to input the user's facial expressions and voice into the emotion engine. The camera is used to analyze facial expressions, and the microphone is used to collect the content and tone of speech. It can utilize iPhone (registered trademark) Face ID and ANDROID (registered trademark) facial recognition functions.

[0337] The emotion engine analyzes and recognizes emotions from the user's facial expressions and voice, and sends the data to the server. Analysis is performed using Microsoft® Azure®'s Emotion API. It also learns the user's individual reaction patterns from past data.

[0338] 4. Generating Advice

[0339] The generative AI combines image analysis and emotion engine data to generate specific advice to improve the appearance of the dish. Examples include "garnish with green onions," "serve the rice in a mountain shape," and "use a blue plate." Based on the information from the emotion engine, the advice is tailored to the user's emotional state. For example, if the user is feeling down, the AI ​​will provide gentle, easy-to-understand advice.

[0340] 5. Submitting Advice

[0341] The server receives the advice data from the generation AI and prepares it for transmission to the user device. Data transfer is managed using AWS S3 and DynamoDB.

[0342] 6. Displaying Advice

[0343] The device analyzes the advice data received from the server and displays it to the user through an application or web interface. Specifically, advice such as "garnish with parsley," "serve rice in a mountain shape," and "use a blue plate" is displayed on a smartphone app or PC web browser.

[0344] Specific examples

[0345] Example 1: Upload a photo of curry rice

[0346] User operations

[0347] The user launches the smartphone app, takes a photo of the curry rice, and taps the "Upload" button to send the photo to the application server.

[0348] Server Processing

[0349] The server receives the photos and temporarily stores them in an AWS S3 bucket, after which the stored photos are passed to the generative AI module.

[0350] Collaboration between generative AI and emotion engine

[0351] Generation AI

[0352] The generative AI uses TensorFlow to analyze the characteristics of the food in the photo (for example, the color of the curry or the height of the presentation).

[0353] Emotion Engine

[0354] The emotion engine uses Microsoft Azure's Emotion API to recognize emotions from the user's facial expressions and voice, and sends the recognition results to the generation AI.

[0355] Generating and Sending Advice

[0356] Generation AI

[0357] The generative AI combines emotion data with dish characteristics data to generate specific advice. For example, it might include suggestions such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate." If the user is feeling down, it might also suggest "adding cheerful colors."

[0358] server

[0359] The server sends the generated advice to the user's device, efficiently queuing messages using AWS SQS.

[0360] Terminal display

[0361] Terminal

[0362] The user's smartphone or PC will then display the received advice, such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[0363] Prompt Sentence Examples

[0364] "Analyze a photo of curry rice and generate specific advice on how to make it look better. If the user's emotional state is depressed, add some uplifting advice."

[0365] This system allows users to easily improve the appearance of their food without any specialized knowledge, and also provides optimal advice based on their emotions, further increasing the enjoyment and satisfaction of home cooking.

[0366] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0367] Step 1: Receiving the image

[0368] (input)

[0369] Users take photos of their food using the camera on their smartphone or PC and upload them to the system via an application or web interface.

[0370] (process)

[0371] When the user taps the "Upload" button, the captured image is sent to the cloud (e.g., AWS S3). The server confirms receipt of the image and temporarily stores it.

[0372] (output)

[0373] Image files of food stored on the server.

[0374] (Specific actions)

[0375] When a user uploads a photo of the food they have taken with their smartphone, the photo is transferred to the server, where it is temporarily stored.

[0376] Step 2: Analyze the images

[0377] (input)

[0378] The server receives the temporarily stored image files of the food.

[0379] (process)

[0380] The server passes the received image to the generative AI module, which uses image analysis algorithms to analyze the type of food in the image, the ingredients used, the presentation, etc. For example, TensorFlow can be used to perform a detailed analysis of each element in the image.

[0381] (output)

[0382] Analyzed food feature data (e.g., ingredient list, presentation balance, color, etc.).

[0383] (Specific actions)

[0384] The server passes the saved image to a generative AI model, which uses TensorFlow to analyze features in the image and extract detailed data about the dish.

[0385] Step 3: Recognize emotions

[0386] (input)

[0387] The device collects the user's facial and voice data using a camera and microphone.

[0388] (process)

[0389] Data collected from the camera and microphone is input into the emotion engine, which uses Microsoft Azure's Emotion API to analyze and recognize the user's emotional state from their facial expressions and voice. It also references past data to learn the user's individual reaction patterns and improve accuracy.

[0390] (output)

[0391] Recognized user emotion data (happiness, sadness, surprise, etc.).

[0392] (Specific actions)

[0393] When a user uploads an image of a dish, the device's camera and microphone collect data on the user's facial expressions and voice, which is then passed to the emotion engine for analysis.

[0394] Step 4: Generating Advice

[0395] (input)

[0396] The generative AI receives analyzed food feature data and recognized user emotion data.

[0397] (process)

[0398] The generative AI combines the dish's feature data with emotion data to generate specific advice for improving its appearance. For example, it might include "garnish with green onions," "serve the rice in a mountain shape," or "use a blue plate." If the user is feeling down, it might also provide empathetic advice such as "add some cheery colors."

[0399] (output)

[0400] Specific advice generated.

[0401] (Specific actions)

[0402] The generative AI model generates appropriate advice based on the characteristics of the dish and the user's emotions, including specific methods to improve the appearance of the dish.

[0403] Step 5: Submitting Advice

[0404] (input)

[0405] The server receives the specific advice received from the generating AI.

[0406] (process)

[0407] The server prepares to send the generated advice data to the user device, using AWS SQS or similar to efficiently queue messages and transfer data.

[0408] (output)

[0409] Advice data sent to the user terminal.

[0410] (Specific actions)

[0411] The server receives the generated advice and transmits it to the user's device using an efficient message queuing technique.

[0412] Step 6: Viewing Advice

[0413] (input)

[0414] The terminal receives the advice data received from the server.

[0415] (process)

[0416] The device analyzes the received advice data and displays it to the user through an application or web interface in an easy-to-read format that is easy for the user to understand.

[0417] (output)

[0418] Specific advice displayed on the user's device.

[0419] (Specific actions)

[0420] The device analyzes the advice received from the server and displays advice such as "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate" on the smartphone screen or PC web browser.

[0421] (Application example 2)

[0422] 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."

[0423] There is a need for a simple method to improve the appearance of food without specialized knowledge. There is also a need for a method to provide a more satisfying experience by taking into account the user's emotional state when receiving advice on how to improve the appearance of food.

[0424] 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.

[0425] In this invention, the server includes means for receiving an image of a dish, means for analyzing the received image to extract characteristics of the dish, means for recognizing the emotional state of the user, means for generating advice to improve the appearance of the dish based on the analysis result and the emotional state, means for transmitting the generated advice to the user terminal, and means for displaying the advice on the user terminal. This makes it possible to easily improve the appearance of a dish without specialized knowledge and receive optimal advice according to the user's emotional state.

[0426] The "means for receiving food images" is a function for transmitting and receiving food images taken by the user to the system.

[0427] The "means for analyzing received images and extracting characteristics of food" is a function that applies an image processing algorithm to received images of food to identify characteristics such as the type of food, presentation, and color.

[0428] The "means for recognizing the user's emotional state" is a function for analyzing the user's emotions from their facial expressions and voice and determining their emotional state.

[0429] The "means for generating advice to improve the appearance of food based on the analysis results and the user's emotional state" is a function that combines the analyzed characteristics of food with the user's emotional state to create advice to optimally improve the appearance of food.

[0430] The "means for transmitting generated advice to a user terminal" is a function for transmitting advice generated within the system to a terminal such as a user's smartphone or tablet.

[0431] The "means for displaying advice on the user terminal" is a function for visually displaying advice received on the user terminal.

[0432] The system related to this invention is an application that allows food delivery service providers (restaurants and cafes) to upload photos of their dishes and receive advice on how to improve their presentation. The system also recognizes the user's emotional state and provides optimal advice. Below, we will explain the detailed program processing and hardware and software used in this system.

[0433] Program Overview

[0434] Upload a photo

[0435] A user takes a photo of a dish using the smartphone camera and sends it to the server. The application can use the smartphone's camera API or network communication API (e.g., Camera2 API or Volley library for Android).

[0436] Image analysis

[0437] The server analyzes the received food images using generative AI models, including advanced image analysis algorithms such as OpenAI's DALL-E and CLIP models, to extract data about the food's characteristics and appearance.

[0438] emotion recognition

[0439] The system utilizes the smartphone's camera and microphone to recognize the user's emotions. The emotion recognition engine uses existing emotion recognition software such as the Affectiva SDK. Emotional data is extracted from the user's facial expressions and voice and sent to the server.

[0440] Advice Generation

[0441] The generative AI generates advice by combining image analysis data of the food and user emotion recognition data. For example, it generates specific advice such as "add brightly colored vegetables" or "change the plate to a different color."

[0442] Sending and displaying advice

[0443] The server sends the generated advice to the user's device, where the smartphone application displays the advice. The application uses a user interface (UI) to present the advice in an easy-to-understand manner.

[0444] Specific examples

[0445] Example 1: Upload a photo of curry rice

[0446] User operations

[0447] A restaurant employee launches the app and takes a photo of the curry rice.

[0448] Tap the "Upload" button to send the photo to the application server.

[0449] Server Processing

[0450] The server receives the photos and stores them temporarily.

[0451] Pass the saved photo to the generation AI module.

[0452] Collaboration between generative AI and emotion engine

[0453] Generation AI:

[0454] The generative AI analyzes the photo and extracts the characteristics of the curry rice (for example, the color of the curry, the height of the serving, etc.).

[0455] Emotion Engine:

[0456] The emotion engine analyzes employees' facial expressions and voices to recognize their emotional state (e.g., tired, happy, etc.).

[0457] The recognized emotion data is sent to the generation AI.

[0458] Generating and Sending Advice

[0459] Generation AI:

[0460] Based on emotion data and food feature data, specific advice such as "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate" is generated.

[0461] If employees are tired, offer them some quick and easy advice.

[0462] server:

[0463] The server transmits the generated advice to the user's terminal.

[0464] Terminal display

[0465] Device:

[0466] Advice such as "Add parsley," "Serve the rice in a mountain shape," and "Use blue plates" will be displayed on employees' smartphones.

[0467] Example prompt sentences (examples of input to generative AI models)

[0468] Prompt statement:

[0469] Analyze the following food photo and offer specific suggestions for improving presentation. Adjust your suggestions based on your employees' emotional state.

[0470] Food photos:

[0471] [Image of curry rice]

[0472] Employee emotional state:

[0473] [Tired]

[0474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0475] Step 1:

[0476] A user takes a photo of a dish using the smartphone camera.

[0477] Input: Physical image of the dish

[0478] Output: Digital image data

[0479] Specific behavior: The user launches the smartphone app and uses the camera to take a photo of the food.

[0480] Step 2:

[0481] The terminal transmits the photograph of the food taken to the application server.

[0482] Input: Digital image data

[0483] Output: Upload image data to the server

[0484] Specific operation: The device uses a network communication API to send image data to the server.

[0485] Step 3:

[0486] The server temporarily stores the received image and passes it to the generation AI module.

[0487] Input: Image data uploaded to the server

[0488] Output: Transfer of image data to the generative AI module

[0489] Specific operation: The server uses the storage function to save the data, and then passes the image data to the generation AI module.

[0490] Step 4:

[0491] The generative AI analyzes the image and extracts the characteristics of the dish.

[0492] Input: Image data passed to the generation AI

[0493] Output: Extracted food feature data

[0494] How it works: Generative AI (e.g., OpenAI's DALL-E or CLIP models) uses image analysis algorithms to identify features such as food type, presentation, and color.

[0495] Step 5:

[0496] The device uses a camera and microphone to recognize the user's emotional state and transmits the emotional data to a server.

[0497] Input: User's facial expressions and voice

[0498] Output: Upload emotion data to the server

[0499] Specific operation: The device uses an emotion recognition engine (e.g., Affectiva SDK) to analyze the user's facial expressions and voice to determine their emotional state. The result is then sent to the server via a network communication API.

[0500] Step 6:

[0501] Generative AI combines image analysis data and emotion recognition data to generate advice.

[0502] Input: Extracted food feature data and user emotion data

[0503] Output: Advice data for improving appearance

[0504] Specific behavior: The generative AI makes adjustments based on the prompt text and generates specific advice (e.g., "garnish with parsley," "serve the rice in a mound shape," "use a blue plate") based on the analysis results and emotional data.

[0505] Step 7:

[0506] The server transmits the generated advice to the user terminal.

[0507] Input: Advice data generated by generative AI

[0508] Output: Sending advice data to the user's terminal

[0509] Specific operation: The server uses a network communication API to send advice data to the user terminal.

[0510] Step 8:

[0511] The terminal displays the received advice through a user interface.

[0512] Input: Submitted advice data

[0513] Output: Visually displayed advice

[0514] Specific operation: The device displays the received advice using the user interface (UI) and provides it to the user.

[0515] 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.

[0516] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0517] 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.

[0518] [Second embodiment]

[0519] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0520] 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.

[0521] 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).

[0522] 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.

[0523] 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.

[0524] 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).

[0525] 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. 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.

[0526] 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.

[0527] 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.

[0528] 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.

[0529] In the smart glasses 214, 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.

[0530] 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."

[0531] This invention is a system that provides specific advice on how to improve the appearance of a dish simply by allowing a user to upload a photo of the dish. This system is composed of a server, a user's terminal, and a generating AI. The program processing and specific embodiments of this system are described below.

[0532] System Overview

[0533] 1. Receiving images

[0534] User

[0535] Users take photos of their food using their smartphone camera or PC webcam.

[0536] Upload the photos you take to the system via an application or web interface.

[0537] 2. Image Analysis

[0538] server

[0539] The server stores the received images and prepares them for passing to the generation AI for image analysis.

[0540] Generation AI

[0541] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, and more.

[0542] 3. Generating Advice

[0543] Generation AI

[0544] Based on the analyzed data, the system generates specific advice to improve the appearance of the dish, such as adding green onions, serving the food a little higher, or using a different color plate.

[0545] 4. Submitting Advice

[0546] server

[0547] The server receives the advice text from the generation AI and sends it to the user's device.

[0548] 5. Displaying Advice

[0549] Terminal

[0550] The user's smartphone or PC receives the advice and displays it to the user through an application or web interface.

[0551] Specific examples

[0552] Example 1: Upload a photo of curry rice

[0553] User operations

[0554] The user launches the smartphone app and takes a photo of the curry rice.

[0555] Tap the "Upload" button to send the photo to the application server.

[0556] Server Processing

[0557] The server receives the photos and stores them temporarily.

[0558] Send the saved photo to the generation AI.

[0559] Generative AI analysis and advice generation

[0560] The generative AI uses image analysis algorithms to extract characteristics of curry rice from photos, such as the color of the curry, the height of the serving, and any optional toppings used.

[0561] Based on this information, the generative AI generates specific advice such as "garnish with parsley," "serve the rice in a mound shape," and "use a blue plate."

[0562] Server Send

[0563] The server transmits the generated advice to the user's terminal.

[0564] Terminal display

[0565] The user's smartphone receives the advice and displays it in a pop-up format, including advice such as "Add parsley," "Serve the rice in a mound," and "Use a blue plate."

[0566] By using this system, users can easily improve the appearance of their food without any specialized knowledge. This system can also be applied to any type of food, making home cooking more enjoyable and visually satisfying.

[0567] The processing flow will be explained below.

[0568] Step 1:

[0569] User

[0570] Users launch the application, take a photo of their food using the camera on their smartphone or PC, and then tap the "Upload" button to send the photo to the application.

[0571] Step 2:

[0572] server

[0573] The server receives photos of food uploaded by users, temporarily stores the images, and prepares them for image analysis.

[0574] Step 3:

[0575] server

[0576] The server prepares the stored images to be passed to the generation AI module and sends the image data to the generation AI, where it is converted into a format for analysis.

[0577] Step 4:

[0578] Generation AI

[0579] Generative AI uses image analysis algorithms to extract specific features from food images, including the type of food, the ingredients used, how it's presented, and the color and shape of the plate.

[0580] Step 5:

[0581] Generation AI

[0582] Based on the extracted features, the generative AI generates specific advice to improve the appearance of the dish, such as "garnish with green onions," "serve the rice in a mountain shape," and "use a blue plate."

[0583] Step 6:

[0584] server

[0585] The server receives the advice data from the generation AI and prepares it for transmission to the user's device. The advice data is converted into a format suitable for the user's device.

[0586] Step 7:

[0587] server

[0588] The server then sends the prepared advice data to the user's smartphone or PC via the Internet or cloud services.

[0589] Step 8:

[0590] Terminal

[0591] The user's device parses the advice data received from the server and converts it into a format that can be displayed via an application or web interface.

[0592] Step 9:

[0593] Terminal

[0594] The device displays specific advice to the user. For example, pop-up messages on the screen suggest advice such as "Serve with green onions," "Serve the rice in a mountain shape," and "Use a blue plate." By referring to these, the user can improve the appearance of their dish.

[0595] Example 1

[0596] 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."

[0597] It is difficult for people without specialized knowledge of cooking to easily obtain specific advice on how to improve the appearance of food. Furthermore, specialized knowledge and experience are required to know specific ways to improve visual elements, such as how to add ingredients, how to arrange food, and the color and shape of containers to use. There is a growing demand for a system that can easily provide methods for enhancing the visual appeal of everyday cooking.

[0598] 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.

[0599] In this invention, the server includes means for users to upload images of dishes, means for saving the received images of dishes, means for sending the saved image data to a generative AI model, means for the generative AI model to extract characteristics of the dishes using an image analysis algorithm, means for generating advice to improve the appearance of the dishes based on the analysis results, means for sending the generated advice from the server to a user terminal, and means for displaying the advice on the user terminal. This enables users to receive specific advice based on photos of dishes they have taken, even if they do not have specialized knowledge.

[0600] A "user" is someone who uses the system to upload images of their dishes and receive visual improvement advice.

[0601] The "server" is a computer system that receives, stores, and relays images of dishes to be passed to the generative AI model.

[0602] An "image analysis algorithm" is a calculation method for extracting characteristics of food from received images and analyzing the type, presentation, etc.

[0603] A "generative AI model" is an artificial intelligence model that uses image analysis algorithms to analyze the characteristics of food and generate specific advice to improve its appearance.

[0604] "Advice" is specific suggestions for improving the appearance of a dish, such as adding ingredients, plating methods, and the color and shape of the containers to use.

[0605] A "user terminal" is a device owned by a user, such as a smartphone or PC, that displays advice sent from the system.

[0606] "Uploading" refers to the act of sending an image of a dish taken by a user to a server.

[0607] "Saving" is a process in which the server temporarily stores the image of the dish received in a storage device.

[0608] "Sending" refers to the act of delivering advice created by the generative AI model to the user's device via the server.

[0609] "Display" refers to the act of visually providing advice on a user terminal.

[0610] This invention is a system that provides specific advice on how to improve the appearance of a dish simply by allowing the user to upload a photo of the dish. The system is composed of a server, a user's device, and a generative AI model.

[0611] System Overview

[0612] Users take photos of their dishes using their smartphones or PCs and upload them through an application or web interface. The uploaded images are sent to the generative AI model via the server. The generative AI model uses image analysis algorithms to analyze the characteristics of the dish and, based on the results, generates specific advice to improve the appearance of the dish. The generated advice is sent to the user's device via the server, where the user can receive it and view it via the application or web interface.

[0613] Specific implementation methods

[0614] A user takes a photo of a dish using a smartphone camera or a PC webcam. The photo is then uploaded using a dedicated application or web interface. For example, this involves launching a smartphone application, tapping the "Take Photo" button to take a photo of the dish, and then pressing the "Upload" button.

[0615] The uploaded images are temporarily stored by the server, which prepares them for sending to the generative AI model and converts them to the appropriate format and resolution, which includes reformatting and resizing the image files.

[0616] The generative AI model runs an image analysis algorithm using image data received from the server. The algorithm identifies the type of dish, the ingredients used, how it is presented, etc. For example, if the photo is of curry rice, it will analyze the color of the curry, how the rice is presented, and the type of ingredients. As an example of a prompt for the generative AI model, enter "Please provide some advice on how to improve the appearance of this dish."

[0617] Based on the analysis results, the generative AI model generates specific advice to improve the appearance of the dish. Specific advice includes "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate." The advice is sent to the server.

[0618] The server sends the advice text received from the generative AI model to the user's device. The server selects the appropriate communication method based on the user's ID and device information to send the data. If the user is using a smartphone app, the data is sent as a push notification or in-app message.

[0619] The user device will then display the received advice. For example, in the case of a smartphone app, a pop-up notification will appear, showing advice such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[0620] This allows users to receive specific advice based on photos of their food, even if they do not have specialized knowledge. This system allows users to easily receive advice on how to improve the appearance of their food, helping them to provide visually satisfying dishes. It is also highly versatile and can be applied to a wide range of cooking, from home cooking to cooking by professional chefs.

[0621] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0622] Step 1:

[0623] Users take and upload images of their dishes

[0624] Specific operation: The user takes a photo of the food using the camera on their smartphone or the webcam on their PC, and uploads the photo to the system via a dedicated application or web interface.

[0625] Input: Image files of the photographed food.

[0626] Output: Image data uploaded to the system.

[0627] Step 2:

[0628] The server receives and stores the images

[0629] Specific operation: The server temporarily stores images uploaded by users. The image storage location is the specified database or storage.

[0630] Input: Uploaded image data.

[0631] Output: The file path and ID of the saved image data.

[0632] Step 3:

[0633] The server prepares the image to be sent to the generative AI model.

[0634] What it does: The server converts the stored images into the appropriate format and resolution for sending to the generative AI model. This conversion includes formatting and resizing the image files.

[0635] Input: The file path or ID of the saved image data.

[0636] Output: Image data in a format and resolution suitable for the generative AI model.

[0637] Step 4:

[0638] The server sends the image data to the generative AI model.

[0639] Specific operation: The server sends the converted image data to the generative AI model using an API request or similar.

[0640] Input: The transformed image data.

[0641] Output: Image data sent to the generative AI model for analysis.

[0642] Step 5:

[0643] Generative AI models run image analysis algorithms

[0644] How it works: The generative AI model uses the received image data to run an image analysis algorithm, which analyzes the type of food, the ingredients used, the presentation, and more.

[0645] Input: Image data for analysis.

[0646] Output: Analysis data including food characteristics, such as type of food, color, presentation, etc.

[0647] Step 6:

[0648] Generative AI models generate advice

[0649] Specific behavior: Based on the analysis, the generative AI model generates specific advice to improve the presentation of the dish, including suggestions on adding ingredients, plating methods, and the color and shape of the container to use.

[0650] Input: Parsed data containing dish characteristics.

[0651] Output: Specific advice text, such as "Serve with parsley," "Serve the rice in a mound," or "Use a blue plate."

[0652] Step 7:

[0653] The server sends the advice text to the user terminal.

[0654] Specific operation: The server sends the advice text received from the generative AI model to the user's device via push notifications, in-app messages, or other means.

[0655] Input: The generated advice text.

[0656] Output: Advice text sent to the user's terminal.

[0657] Step 8:

[0658] The device displays advice

[0659] Specific operation: The user device displays the received advice text. Specifically, in the case of a smartphone app, it is displayed as a pop-up notification or an in-app message.

[0660] Input: The advice text sent.

[0661] Output: Advice displayed on the user's screen, such as "Serve with parsley," "Serve the rice in a mountain shape," and "Use a blue plate."

[0662] (Application example 1)

[0663] 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."

[0664] The appearance of food has a significant impact on how it is evaluated, and is directly linked to customer satisfaction and increased repeat customers, especially in brick-and-mortar restaurants. However, if kitchen staff and chefs do not have specialized knowledge about food presentation and presentation, it is difficult to maximize the visual appeal of the food. To solve this problem, a system is needed that provides specific advice in real time on how to improve the appearance of food.

[0665] 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.

[0666] In this invention, the server includes means for receiving images of dishes, means for analyzing the received images to extract characteristics of the dishes, means for generating advice to improve the appearance of the dishes based on the analysis results, means for transmitting the generated advice to a user terminal, means for displaying specific advice to improve the appearance of the dishes on the user terminal, means for receiving images via a smart device used in a physical store, and means for analyzing the images using a generative AI model and generating advice to improve the appearance of the dishes using prompt sentences. This allows cooking staff and chefs to receive specific advice in real time even if they do not have specialized knowledge about the appearance of dishes, thereby improving customer satisfaction.

[0667] "Food images" are photographic data of food taken with a digital camera or smartphone.

[0668] The "receiving means" is an interface or protocol that allows a server or smart device to receive images of dishes sent by a user.

[0669] "Means for analyzing and extracting food characteristics" refers to a system or software that uses an image analysis algorithm to automatically identify and extract characteristics such as the type of food, the height of the presentation, and the ingredients used.

[0670] "Means for generating advice" refers to functionality or software that uses a generative AI model based on the analysis results to create specific suggestions or improvements to improve the presentation of food.

[0671] "User terminal" refers to a device, such as a smartphone, tablet, or computer, that a user operates to receive and display advice.

[0672] The "display means" refers to a function such as an application, web interface, or pop-up for visually displaying the advice generated on the user terminal.

[0673] A "physical store" is a business location, such as a restaurant or cafe, where customers actually visit and food is served.

[0674] A "smart device" is a device that has internet connectivity and is capable of taking and transmitting images, and examples include smartphones and tablets.

[0675] A "generative AI model" is an artificial intelligence system that specializes in image analysis and advice generation using technologies such as deep learning.

[0676] A "prompt" is an instruction or data that a user inputs into an application, or an instruction text that a generation AI uses when creating advice.

[0677] The system for implementing this invention comprises a server, a smart device, and a user. The server has the function of receiving images of dishes, analyzing the received images, and extracting the characteristics of the dishes. Then, using a generative AI model, it generates advice for improving the appearance of the dishes based on the analysis results. The generated advice is sent to the user's terminal, and the specific advice is displayed on the user's terminal.

[0678] Hardware and software configuration:

[0679] The server has high-performance computing resources to process the images and installs the necessary software libraries to run the generative AI model, such as a Python web server using Flask and external generative AI services (e.g., Google Cloud Vision or Amazon Rekognition).

[0680] The user terminals may be smartphones, tablets, computers, etc. These terminals have a camera function and can run an application to take images and send them to a server.

[0681] Data processing and calculation:

[0682] The server receives and temporarily stores image data sent by the user. The received image is analyzed using an image analysis algorithm to extract features such as the type of food, how it is presented, and the ingredients used. Based on the results of this analysis, a generative AI model generates advice.

[0683] Specific advice includes "serve with fresh herbs," "serve the rice in a mountain shape," "use a blue plate," etc. These pieces of advice are sent from the server to the user's device and displayed to the user through the application.

[0684] Examples:

[0685] For example, imagine a restaurant chef takes a photo of a dish using a smartphone app. The chef taps the "upload" button to send the photo to the server. The server analyzes the received image, and the generative AI model generates advice such as "garnish with fresh herbs" or "serve the rice in a mountain shape" based on the analysis results, and sends this to the chef's device. The chef can receive the advice through the application and follow the instructions to improve the appearance of the dish.

[0686] Example prompt sentence:

[0687] "Take a photo of your food and upload it. Use it for dishes you're not confident about plating, like pasta or steak."

[0688] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0689] Step 1:

[0690] Users take photos of their food using their smartphones or tablets.

[0691] Input: Image data of food taken with a smartphone or tablet camera.

[0692] Output: Captured image data.

[0693] Specific operation: The user takes a photo of the food using a camera app or a dedicated app.

[0694] Step 2:

[0695] The user uploads the captured images to the server through the application.

[0696] Input: Captured image data.

[0697] Output: Image data sent to the server.

[0698] Specific operation: The user selects an image of a dish and taps the "Upload" button in the application to send the image data to the server.

[0699] Step 3:

[0700] The server temporarily stores the received images and prepares them for image analysis.

[0701] Input: Image data sent to the server.

[0702] Output: Saved image file.

[0703] Specific operation: The server temporarily stores the image data in storage and prepares it for analysis.

[0704] Step 4:

[0705] The server analyzes the stored images using a generative AI model.

[0706] Input: A saved image file.

[0707] Output: Food feature data (e.g., serving height, type of ingredients, etc.).

[0708] Specific operation: The server uses an image analysis algorithm (e.g., Google Cloud Vision or Amazon Rekognition) to analyze the food and extract its characteristics.

[0709] Step 5:

[0710] Based on the analyzed data, the server uses a generative AI model to generate advice to improve the presentation of the dish.

[0711] Input: Food feature data.

[0712] Output: The generated advice (e.g., "Serve with fresh herbs" or "Serve the rice in a mound").

[0713] Specific operation: The server runs the generative AI model, inputs the dish's characteristic data as prompts, and generates advice.

[0714] Step 6:

[0715] The server transmits the generated advice to the user terminal.

[0716] Input: The generated advice.

[0717] Output: Advice message sent to user terminal.

[0718] Specific operation: The server sends the generated advice as text data to the user's smartphone or tablet.

[0719] Step 7:

[0720] The user terminal displays the received advice.

[0721] Input: The advice message sent by the server.

[0722] Output: The advice that is displayed to the user.

[0723] Specific operation: The user device will display the advice in the form of a pop-up or notification through the application, visually communicating it to the user.

[0724] 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.

[0725] This invention is a system that analyzes images of food to generate advice for improving the appearance of the food, and further combines it with an emotion engine that recognizes the user's emotions. By providing optimal advice based on the user's emotional state, this system can improve the appearance of the food and increase user satisfaction. Below, we will explain the program processing and specific embodiments of this system.

[0726] System Overview

[0727] 1. Receiving images

[0728] User

[0729] Users take photos of their food using the camera on their smartphone or PC, then upload the photos to the system via an application or web interface.

[0730] 2. Image Analysis

[0731] server

[0732] The server receives photos of dishes uploaded by users and temporarily stores them.

[0733] The server passes the saved images to the generative AI module.

[0734] Generation AI

[0735] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, and more.

[0736] 3. Emotional Recognition

[0737] Terminal

[0738] The user's device uses a camera and microphone to input the user's facial expressions and voice into the emotion engine, which then recognizes the user's current emotional state (happiness, sadness, surprise, etc.).

[0739] Emotion Engine

[0740] The emotion engine analyzes and recognizes emotions from the user's facial expressions and voice, and sends that data to the server.

[0741] It also learns from past user reaction data to provide advice optimized for each individual user.

[0742] 4. Generating Advice

[0743] Generation AI

[0744] Combining image analysis and emotion engine data, it generates specific recommendations to improve the presentation of dishes, such as adding green onions, serving rice in a mountain shape, and using blue plates.

[0745] Based on information from the emotion engine, the system tailors advice to the user's emotional state. For example, if the user is feeling down, the system provides gentle, easy-to-understand advice.

[0746] 5. Submitting Advice

[0747] server

[0748] The server receives the advice data from the generation AI and prepares it for transmission to the user's terminal.

[0749] 6. Displaying Advice

[0750] Terminal

[0751] The user's device analyzes the advice data received from the server and displays it to the user through an application or web interface.

[0752] Specific examples

[0753] Example 1: Upload a photo of curry rice

[0754] User operations

[0755] The user launches the smartphone app and takes a photo of the curry rice.

[0756] Tap the "Upload" button to send the photo to the application server.

[0757] Server Processing

[0758] The server receives the photos and stores them temporarily.

[0759] Pass the saved photo to the generation AI module.

[0760] Collaboration between generative AI and emotion engine

[0761] Generation AI

[0762] The generative AI analyzes the photo and extracts the characteristics of the curry rice (for example, the color of the curry, the height of the serving, etc.).

[0763] Emotion Engine

[0764] The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state, such as whether they are happy, sad, or excited.

[0765] The recognized emotion data is sent to the generation AI.

[0766] Generating and Sending Advice

[0767] Generation AI

[0768] Based on emotion data and food feature data, specific advice such as "garnish with parsley," "serve the rice in a mound shape," and "use a blue plate" is generated.

[0769] If the user is feeling down, advice might include suggestions such as "add some uplifting colors."

[0770] server

[0771] The server transmits the generated advice to the user's terminal.

[0772] Terminal display

[0773] Terminal

[0774] The user's smartphone or PC will then display the received advice, such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[0775] This system allows users to easily improve the appearance of their food without any specialized knowledge, and also provides optimal advice based on their emotions, making home cooking even more enjoyable and satisfying.

[0776] The processing flow will be explained below.

[0777] Step 1:

[0778] User

[0779] Users take a photo of the dish with their smartphone camera and tap the "upload" button through the application to send the photo to the system.

[0780] Step 2:

[0781] server

[0782] The server receives the uploaded photos of the dishes and temporarily stores them in storage.

[0783] Step 3:

[0784] server

[0785] The server sends the saved image data to the generation AI module and prepares it for analysis.

[0786] Step 4:

[0787] Generation AI

[0788] The generative AI uses image analysis algorithms to extract features such as the type of food, the ingredients used, the arrangement of the presentation, and the color and shape of the plate.

[0789] Step 5:

[0790] Terminal

[0791] The user's device uses a camera and microphone to collect the user's facial expressions and voice in real time and transmits them to the emotion engine.

[0792] Step 6:

[0793] Emotion Engine

[0794] The emotion engine analyzes the user's emotional state (e.g., joy, sadness, surprise, excitement, etc.) from their facial expressions and voice, and sends the recognized emotional data to the generation AI.

[0795] Step 7:

[0796] Generation AI

[0797] Based on the received emotion data and food feature data, the generative AI generates specific advice to improve the appearance of the food, such as adding ingredients, plating methods, or changing the color of the plate to improve the food's appearance.

[0798] Step 8:

[0799] Generation AI

[0800] The generative AI tailors its advice based on the user's emotional state: for example, if the user is feeling down, it will create gentle advice with encouraging words.

[0801] Step 9:

[0802] server

[0803] The server receives the generated advice data and prepares it for transmission to the user terminal.

[0804] Step 10:

[0805] server

[0806] The server sends the prepared advice data to the user's terminal, and uses the Internet or cloud services as a means of communication.

[0807] Step 11:

[0808] Terminal

[0809] The user's device analyzes the received advice data and converts it into a display format through an application or web interface.

[0810] Step 12:

[0811] Terminal

[0812] The device displays specific advice to the user, such as "serve with green onions," "serve the rice in a mountain shape," and "use a blue plate." The user can use this advice to improve the appearance of their dish.

[0813] Example 2

[0814] 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."

[0815] Conventional cooking analysis systems can provide advice on improving the appearance of dishes, but they are unable to provide optimal advice that takes into account the user's emotional state. As a result, users are unable to receive advice that is tailored to their psychological state and preferences, making it difficult to increase user satisfaction. The objective of this invention is to improve the appearance of dishes and increase user satisfaction by recognizing the user's emotional state and providing optimal advice based on that state.

[0816] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an image of a dish, means for analyzing the received image to extract characteristics of the dish, means for generating advice to improve the appearance of the dish based on the analysis results, means for recognizing the user's emotional state, means for adjusting the optimal advice based on the emotional state, means for transmitting the generated advice to the user terminal, and means for displaying the advice on the user terminal. This makes it possible to provide advice to improve the appearance of a dish that takes into account the user's emotional state.

[0817] The "means for receiving food images" refers to an interface for users to upload photos of food taken by them to the system.

[0818] "Means for analyzing received images and extracting characteristics of food" refers to algorithms or software that analyze received images of food and extract characteristics such as the type of food, ingredients used, and presentation.

[0819] "Means for generating advice to improve the appearance of food based on the analysis results" refers to a mechanism for generating specific advice to improve the visual appearance of food based on the analyzed characteristics of the food.

[0820] "Means for recognizing the user's emotional state" refers to a camera, microphone, and analysis algorithm for analyzing the user's facial expressions and voice to recognize the psychological emotional state at that time.

[0821] "Means for adjusting optimal advice based on emotional state" refers to a mechanism for adjusting advice to improve the appearance of food according to the recognized emotional state of the user and providing it in an optimal form for each individual user.

[0822] "Means for transmitting the generated advice to the user terminal" refers to the communication means or protocol for transmitting the generated advice to the user's terminal such as a smartphone or PC.

[0823] "Means for displaying advice on a user terminal" refers to an application or web interface for displaying received advice on the user's terminal.

[0824] This invention is a system that analyzes images of food, generates advice for improving the appearance, and combines it with an emotion engine that recognizes the user's emotional state. This system provides optimal advice based on the user's emotional state, improves the appearance of the food, and increases user satisfaction.

[0825] System Overview

[0826] This system mainly uses the following hardware and software.

[0827] 1. Receiving images

[0828] Users take photos of their food using their smartphone or PC camera and upload them to the system via an application or web interface.

[0829] 2. Image Analysis

[0830] The server receives photos of dishes uploaded by users and temporarily stores them. The stored images are then passed to the generative AI module. This can be done using an S3 bucket on Amazon Web Services (AWS).

[0831] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, etc. It uses TensorFlow models to perform a detailed analysis of the elements in the image.

[0832] 3. Emotional Recognition

[0833] The device uses a camera and microphone to input the user's facial expressions and voice into the emotion engine. The camera is used to analyze facial expressions, and the microphone is used to collect the content and tone of speech. It can use iPhone's Face ID or Android's facial recognition function.

[0834] The emotion engine analyzes and recognizes emotions from the user's facial expressions and voice, and sends the data to a server. The analysis is performed using Microsoft Azure's Emotion API. It also learns the user's individual reaction patterns from past data.

[0835] 4. Generating Advice

[0836] The generative AI combines image analysis and emotion engine data to generate specific advice to improve the appearance of the dish. Examples include "garnish with green onions," "serve the rice in a mountain shape," and "use a blue plate." Based on the information from the emotion engine, the advice is tailored to the user's emotional state. For example, if the user is feeling down, the AI ​​will provide gentle, easy-to-understand advice.

[0837] 5. Submitting Advice

[0838] The server receives the advice data from the generation AI and prepares it for transmission to the user device. Data transfer is managed using AWS S3 and DynamoDB.

[0839] 6. Displaying Advice

[0840] The device analyzes the advice data received from the server and displays it to the user through an application or web interface. Specifically, advice such as "garnish with parsley," "serve rice in a mountain shape," and "use a blue plate" is displayed on a smartphone app or PC web browser.

[0841] Specific examples

[0842] Example 1: Upload a photo of curry rice

[0843] User operations

[0844] The user launches the smartphone app, takes a photo of the curry rice, and taps the "Upload" button to send the photo to the application server.

[0845] Server Processing

[0846] The server receives the photos and temporarily stores them in an AWS S3 bucket, after which the stored photos are passed to the generative AI module.

[0847] Collaboration between generative AI and emotion engine

[0848] Generation AI

[0849] The generative AI uses TensorFlow to analyze the characteristics of the food in the photo (for example, the color of the curry or the height of the presentation).

[0850] Emotion Engine

[0851] The emotion engine uses Microsoft Azure's Emotion API to recognize emotions from the user's facial expressions and voice, and sends the recognition results to the generation AI.

[0852] Generating and Sending Advice

[0853] Generation AI

[0854] The generative AI combines emotion data with dish characteristics data to generate specific advice. For example, it might include suggestions such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate." If the user is feeling down, it might also suggest "adding cheerful colors."

[0855] server

[0856] The server sends the generated advice to the user's device, efficiently queuing messages using AWS SQS.

[0857] Terminal display

[0858] Terminal

[0859] The user's smartphone or PC will then display the received advice, such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[0860] Prompt Sentence Examples

[0861] "Analyze a photo of curry rice and generate specific advice on how to make it look better. If the user's emotional state is depressed, add some uplifting advice."

[0862] This system allows users to easily improve the appearance of their food without any specialized knowledge, and also provides optimal advice based on their emotions, further increasing the enjoyment and satisfaction of home cooking.

[0863] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0864] Step 1: Receiving the image

[0865] (input)

[0866] Users take photos of their food using the camera on their smartphone or PC and upload them to the system via an application or web interface.

[0867] (process)

[0868] When the user taps the "Upload" button, the captured image is sent to the cloud (e.g., AWS S3). The server confirms receipt of the image and temporarily stores it.

[0869] (output)

[0870] Image files of food stored on the server.

[0871] (Specific actions)

[0872] When a user uploads a photo of the food they have taken with their smartphone, the photo is transferred to the server, where it is temporarily stored.

[0873] Step 2: Analyze the images

[0874] (input)

[0875] The server receives the temporarily stored image files of the food.

[0876] (process)

[0877] The server passes the received image to the generative AI module, which uses image analysis algorithms to analyze the type of food in the image, the ingredients used, the presentation, etc. For example, TensorFlow can be used to perform a detailed analysis of each element in the image.

[0878] (output)

[0879] Analyzed food feature data (e.g., ingredient list, presentation balance, color, etc.).

[0880] (Specific actions)

[0881] The server passes the saved image to a generative AI model, which uses TensorFlow to analyze features in the image and extract detailed data about the dish.

[0882] Step 3: Recognize emotions

[0883] (input)

[0884] The device collects the user's facial and voice data using a camera and microphone.

[0885] (process)

[0886] Data collected from the camera and microphone is input into the emotion engine, which uses Microsoft Azure's Emotion API to analyze and recognize the user's emotional state from their facial expressions and voice. It also references past data to learn the user's individual reaction patterns and improve accuracy.

[0887] (output)

[0888] Recognized user emotion data (happiness, sadness, surprise, etc.).

[0889] (Specific actions)

[0890] When a user uploads an image of a dish, the device's camera and microphone collect data on the user's facial expressions and voice, which is then passed to the emotion engine for analysis.

[0891] Step 4: Generating Advice

[0892] (input)

[0893] The generative AI receives analyzed food feature data and recognized user emotion data.

[0894] (process)

[0895] The generative AI combines the dish's feature data with emotion data to generate specific advice for improving its appearance. For example, it might include "garnish with green onions," "serve the rice in a mountain shape," or "use a blue plate." If the user is feeling down, it might also provide empathetic advice such as "add some cheery colors."

[0896] (output)

[0897] Specific advice generated.

[0898] (Specific actions)

[0899] The generative AI model generates appropriate advice based on the characteristics of the dish and the user's emotions, including specific methods to improve the appearance of the dish.

[0900] Step 5: Submitting Advice

[0901] (input)

[0902] The server receives the specific advice received from the generating AI.

[0903] (process)

[0904] The server prepares to send the generated advice data to the user device, using AWS SQS or similar to efficiently queue messages and transfer data.

[0905] (output)

[0906] Advice data sent to the user terminal.

[0907] (Specific actions)

[0908] The server receives the generated advice and transmits it to the user's device using an efficient message queuing technique.

[0909] Step 6: Viewing Advice

[0910] (input)

[0911] The terminal receives the advice data received from the server.

[0912] (process)

[0913] The device analyzes the received advice data and displays it to the user through an application or web interface in an easy-to-read format that is easy for the user to understand.

[0914] (output)

[0915] Specific advice displayed on the user's device.

[0916] (Specific actions)

[0917] The device analyzes the advice received from the server and displays advice such as "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate" on the smartphone screen or PC web browser.

[0918] (Application example 2)

[0919] 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."

[0920] There is a need for a simple method to improve the appearance of food without specialized knowledge. There is also a need for a method to provide a more satisfying experience by taking into account the user's emotional state when receiving advice on how to improve the appearance of food.

[0921] 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.

[0922] In this invention, the server includes means for receiving an image of a dish, means for analyzing the received image to extract characteristics of the dish, means for recognizing the emotional state of the user, means for generating advice to improve the appearance of the dish based on the analysis result and the emotional state, means for transmitting the generated advice to the user terminal, and means for displaying the advice on the user terminal. This makes it possible to easily improve the appearance of a dish without specialized knowledge and receive optimal advice according to the user's emotional state.

[0923] The "means for receiving food images" is a function for transmitting and receiving food images taken by the user to the system.

[0924] The "means for analyzing received images and extracting characteristics of food" is a function that applies an image processing algorithm to received images of food to identify characteristics such as the type of food, presentation, and color.

[0925] The "means for recognizing the user's emotional state" is a function for analyzing the user's emotions from their facial expressions and voice and determining their emotional state.

[0926] The "means for generating advice to improve the appearance of food based on the analysis results and the user's emotional state" is a function that combines the analyzed characteristics of food with the user's emotional state to create advice to optimally improve the appearance of food.

[0927] The "means for transmitting generated advice to a user terminal" is a function for transmitting advice generated within the system to a terminal such as a user's smartphone or tablet.

[0928] The "means for displaying advice on the user terminal" is a function for visually displaying advice received on the user terminal.

[0929] The system related to this invention is an application that allows food delivery service providers (restaurants and cafes) to upload photos of their dishes and receive advice on how to improve their presentation. The system also recognizes the user's emotional state and provides optimal advice. Below, we will explain the detailed program processing and hardware and software used in this system.

[0930] Program Overview

[0931] Upload a photo

[0932] A user takes a photo of a dish using the smartphone camera and sends it to the server. The application can use the smartphone's camera API or network communication API (e.g., Camera2 API or Volley library for Android).

[0933] Image analysis

[0934] The server analyzes the received food images using a generative AI model, which includes advanced image analysis algorithms such as OpenAI's DALL-E and CLIP models, to extract data about the food's characteristics and appearance.

[0935] emotion recognition

[0936] The system utilizes the smartphone's camera and microphone to recognize the user's emotions. The emotion recognition engine uses existing emotion recognition software such as the Affectiva SDK. Emotional data is extracted from the user's facial expressions and voice and sent to the server.

[0937] Advice Generation

[0938] The generative AI generates advice by combining image analysis data of the food and user emotion recognition data. For example, it generates specific advice such as "add brightly colored vegetables" or "change the plate to a different color."

[0939] Sending and displaying advice

[0940] The server sends the generated advice to the user's device, where the smartphone application displays the advice. The application uses a user interface (UI) to present the advice in an easy-to-understand manner.

[0941] Specific examples

[0942] Example 1: Upload a photo of curry rice

[0943] User operations

[0944] A restaurant employee launches the app and takes a photo of the curry rice.

[0945] Tap the "Upload" button to send the photo to the application server.

[0946] Server Processing

[0947] The server receives the photos and stores them temporarily.

[0948] Pass the saved photo to the generation AI module.

[0949] Collaboration between generative AI and emotion engine

[0950] Generation AI:

[0951] The generative AI analyzes the photo and extracts the characteristics of the curry rice (for example, the color of the curry, the height of the serving, etc.).

[0952] Emotion Engine:

[0953] The emotion engine analyzes employees' facial expressions and voices to recognize their emotional state (e.g., tired, happy, etc.).

[0954] The recognized emotion data is sent to the generation AI.

[0955] Generating and Sending Advice

[0956] Generation AI:

[0957] Based on emotion data and food feature data, specific advice such as "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate" is generated.

[0958] If employees are tired, offer them some quick and easy advice.

[0959] server:

[0960] The server transmits the generated advice to the user's terminal.

[0961] Terminal display

[0962] Device:

[0963] Advice such as "Add parsley," "Serve the rice in a mountain shape," and "Use blue plates" will be displayed on employees' smartphones.

[0964] Example prompt sentences (examples of input to generative AI models)

[0965] Prompt statement:

[0966] Analyze the following food photo and offer specific suggestions for improving presentation. Adjust your suggestions based on your employees' emotional state.

[0967] Food photos:

[0968] [Image of curry rice]

[0969] Employee emotional state:

[0970] [Tired]

[0971] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0972] Step 1:

[0973] A user takes a photo of a dish using the smartphone camera.

[0974] Input: Physical image of the dish

[0975] Output: Digital image data

[0976] Specific behavior: The user launches the smartphone app and uses the camera to take a photo of the food.

[0977] Step 2:

[0978] The terminal transmits the photograph of the food taken to the application server.

[0979] Input: Digital image data

[0980] Output: Upload image data to the server

[0981] Specific operation: The device uses a network communication API to send image data to the server.

[0982] Step 3:

[0983] The server temporarily stores the received image and passes it to the generation AI module.

[0984] Input: Image data uploaded to the server

[0985] Output: Transfer of image data to the generative AI module

[0986] Specific operation: The server uses the storage function to save the data, and then passes the image data to the generation AI module.

[0987] Step 4:

[0988] The generative AI analyzes the image and extracts the characteristics of the dish.

[0989] Input: Image data passed to the generation AI

[0990] Output: Extracted food feature data

[0991] How it works: Generative AI (e.g., OpenAI's DALL-E or CLIP models) uses image analysis algorithms to identify features such as food type, presentation, and color.

[0992] Step 5:

[0993] The device uses a camera and microphone to recognize the user's emotional state and transmits the emotional data to a server.

[0994] Input: User's facial expressions and voice

[0995] Output: Upload emotion data to the server

[0996] Specific operation: The device uses an emotion recognition engine (e.g., Affectiva SDK) to analyze the user's facial expressions and voice to determine their emotional state. The result is then sent to the server via a network communication API.

[0997] Step 6:

[0998] Generative AI combines image analysis data and emotion recognition data to generate advice.

[0999] Input: Extracted food feature data and user emotion data

[1000] Output: Advice data for improving appearance

[1001] Specific behavior: The generative AI makes adjustments based on the prompt text and generates specific advice (e.g., "garnish with parsley," "serve the rice in a mound shape," "use a blue plate") based on the analysis results and emotional data.

[1002] Step 7:

[1003] The server transmits the generated advice to the user terminal.

[1004] Input: Advice data generated by generative AI

[1005] Output: Sending advice data to the user's terminal

[1006] Specific operation: The server uses a network communication API to send advice data to the user terminal.

[1007] Step 8:

[1008] The terminal displays the received advice through a user interface.

[1009] Input: Submitted advice data

[1010] Output: Visually displayed advice

[1011] Specific operation: The device displays the received advice using the user interface (UI) and provides it to the user.

[1012] 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.

[1013] 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.

[1014] 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.

[1015] [Third embodiment]

[1016] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1017] 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.

[1018] 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).

[1019] 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.

[1020] 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.

[1021] 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).

[1022] 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. 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.

[1023] 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.

[1024] 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.

[1025] 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.

[1026] 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.

[1027] 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."

[1028] This invention is a system that provides specific advice on how to improve the appearance of a dish simply by allowing a user to upload a photo of the dish. This system is composed of a server, a user's terminal, and a generating AI. The program processing and specific embodiments of this system are described below.

[1029] System Overview

[1030] 1. Receiving images

[1031] User

[1032] Users take photos of their food using their smartphone camera or PC webcam.

[1033] Upload the photos you take to the system via an application or web interface.

[1034] 2. Image Analysis

[1035] server

[1036] The server stores the received images and prepares them for passing to the generation AI for image analysis.

[1037] Generation AI

[1038] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, and more.

[1039] 3. Generating Advice

[1040] Generation AI

[1041] Based on the analyzed data, the system generates specific advice to improve the appearance of the dish, such as adding green onions, serving the food a little higher, or using a different color plate.

[1042] 4. Submitting Advice

[1043] server

[1044] The server receives the advice text from the generation AI and sends it to the user's device.

[1045] 5. Displaying Advice

[1046] Terminal

[1047] The user's smartphone or PC receives the advice and displays it to the user through an application or web interface.

[1048] Specific examples

[1049] Example 1: Upload a photo of curry rice

[1050] User operations

[1051] The user launches the smartphone app and takes a photo of the curry rice.

[1052] Tap the "Upload" button to send the photo to the application server.

[1053] Server Processing

[1054] The server receives the photos and stores them temporarily.

[1055] Send the saved photo to the generation AI.

[1056] Generative AI analysis and advice generation

[1057] The generative AI uses image analysis algorithms to extract characteristics of curry rice from photos, such as the color of the curry, the height of the serving, and any optional toppings used.

[1058] Based on this information, the generative AI generates specific advice such as "garnish with parsley," "serve the rice in a mound shape," and "use a blue plate."

[1059] Server Send

[1060] The server transmits the generated advice to the user's terminal.

[1061] Terminal display

[1062] The user's smartphone receives the advice and displays it in a pop-up format, including advice such as "Add parsley," "Serve the rice in a mound," and "Use a blue plate."

[1063] By using this system, users can easily improve the appearance of their food without any specialized knowledge. This system can also be applied to any type of food, making home cooking more enjoyable and visually satisfying.

[1064] The processing flow will be explained below.

[1065] Step 1:

[1066] User

[1067] Users launch the application, take a photo of their food using the camera on their smartphone or PC, and then tap the "Upload" button to send the photo to the application.

[1068] Step 2:

[1069] server

[1070] The server receives photos of food uploaded by users, temporarily stores the images, and prepares them for image analysis.

[1071] Step 3:

[1072] server

[1073] The server prepares the stored images to be passed to the generation AI module and sends the image data to the generation AI, where it is converted into a format for analysis.

[1074] Step 4:

[1075] Generation AI

[1076] Generative AI uses image analysis algorithms to extract specific features from food images, including the type of food, the ingredients used, how it's presented, and the color and shape of the plate.

[1077] Step 5:

[1078] Generation AI

[1079] Based on the extracted features, the generative AI generates specific advice to improve the appearance of the dish, such as "garnish with green onions," "serve the rice in a mountain shape," and "use a blue plate."

[1080] Step 6:

[1081] server

[1082] The server receives the advice data from the generation AI and prepares it for transmission to the user's device. The advice data is converted into a format suitable for the user's device.

[1083] Step 7:

[1084] server

[1085] The server then sends the prepared advice data to the user's smartphone or PC via the Internet or cloud services.

[1086] Step 8:

[1087] Terminal

[1088] The user's device parses the advice data received from the server and converts it into a format that can be displayed via an application or web interface.

[1089] Step 9:

[1090] Terminal

[1091] The device displays specific advice to the user. For example, pop-up messages on the screen suggest advice such as "Serve with green onions," "Serve the rice in a mountain shape," and "Use a blue plate." By referring to these, the user can improve the appearance of their dish.

[1092] Example 1

[1093] 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."

[1094] It is difficult for people without specialized knowledge of cooking to easily obtain specific advice on how to improve the appearance of food. Furthermore, specialized knowledge and experience are required to know specific ways to improve visual elements, such as how to add ingredients, how to arrange food, and the color and shape of containers to use. There is a growing demand for a system that can easily provide methods for enhancing the visual appeal of everyday cooking.

[1095] 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.

[1096] In this invention, the server includes means for users to upload images of dishes, means for saving the received images of dishes, means for sending the saved image data to a generative AI model, means for the generative AI model to extract characteristics of the dishes using an image analysis algorithm, means for generating advice to improve the appearance of the dishes based on the analysis results, means for sending the generated advice from the server to a user terminal, and means for displaying the advice on the user terminal. This enables users to receive specific advice based on photos of dishes they have taken, even if they do not have specialized knowledge.

[1097] A "user" is someone who uses the system to upload images of their dishes and receive visual improvement advice.

[1098] The "server" is a computer system that receives, stores, and relays images of dishes to be passed to the generative AI model.

[1099] An "image analysis algorithm" is a calculation method for extracting characteristics of food from received images and analyzing the type, presentation, etc.

[1100] A "generative AI model" is an artificial intelligence model that uses image analysis algorithms to analyze the characteristics of food and generate specific advice to improve its appearance.

[1101] "Advice" is specific suggestions for improving the appearance of a dish, such as adding ingredients, plating methods, and the color and shape of the containers to use.

[1102] A "user terminal" is a device owned by a user, such as a smartphone or PC, that displays advice sent from the system.

[1103] "Uploading" refers to the act of sending an image of a dish taken by a user to a server.

[1104] "Saving" is a process in which the server temporarily stores the image of the dish received in a storage device.

[1105] "Sending" refers to the act of delivering advice created by the generative AI model to the user's device via the server.

[1106] "Display" refers to the act of visually providing advice on a user terminal.

[1107] This invention is a system that provides specific advice on how to improve the appearance of a dish simply by allowing the user to upload a photo of the dish. The system is composed of a server, a user's device, and a generative AI model.

[1108] System Overview

[1109] Users take photos of their dishes using their smartphones or PCs and upload them through an application or web interface. The uploaded images are sent to the generative AI model via the server. The generative AI model uses image analysis algorithms to analyze the characteristics of the dish and, based on the results, generates specific advice to improve the appearance of the dish. The generated advice is sent to the user's device via the server, where the user can receive it and view it via the application or web interface.

[1110] Specific implementation methods

[1111] A user takes a photo of a dish using a smartphone camera or a PC webcam. The photo is then uploaded using a dedicated application or web interface. For example, this involves launching a smartphone application, tapping the "Take Photo" button to take a photo of the dish, and then pressing the "Upload" button.

[1112] The uploaded images are temporarily stored by the server, which prepares them for sending to the generative AI model and converts them to the appropriate format and resolution, which includes reformatting and resizing the image files.

[1113] The generative AI model runs an image analysis algorithm using image data received from the server. The algorithm identifies the type of dish, the ingredients used, how it is presented, etc. For example, if the photo is of curry rice, it will analyze the color of the curry, how the rice is presented, and the type of ingredients. As an example of a prompt for the generative AI model, enter "Please provide some advice on how to improve the appearance of this dish."

[1114] Based on the analysis results, the generative AI model generates specific advice to improve the appearance of the dish. Specific advice includes "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate." The advice is sent to the server.

[1115] The server sends the advice text received from the generative AI model to the user's device. The server selects the appropriate communication method based on the user's ID and device information to send the data. If the user is using a smartphone app, the data is sent as a push notification or in-app message.

[1116] The user device will then display the received advice. For example, in the case of a smartphone app, a pop-up notification will appear, showing advice such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[1117] This allows users to receive specific advice based on photos of their food, even if they do not have specialized knowledge. This system allows users to easily receive advice on how to improve the appearance of their food, helping them to provide visually satisfying dishes. It is also highly versatile and can be applied to a wide range of cooking, from home cooking to cooking by professional chefs.

[1118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1119] Step 1:

[1120] Users take and upload images of their dishes

[1121] Specific operation: The user takes a photo of the food using the camera on their smartphone or the webcam on their PC, and uploads the photo to the system via a dedicated application or web interface.

[1122] Input: Image files of the photographed food.

[1123] Output: Image data uploaded to the system.

[1124] Step 2:

[1125] The server receives and stores the images

[1126] Specific operation: The server temporarily stores images uploaded by users. The image storage location is the specified database or storage.

[1127] Input: Uploaded image data.

[1128] Output: The file path and ID of the saved image data.

[1129] Step 3:

[1130] The server prepares the image to be sent to the generative AI model.

[1131] What it does: The server converts the stored images into the appropriate format and resolution for sending to the generative AI model. This conversion includes formatting and resizing the image files.

[1132] Input: The file path or ID of the saved image data.

[1133] Output: Image data in a format and resolution suitable for the generative AI model.

[1134] Step 4:

[1135] The server sends the image data to the generative AI model.

[1136] Specific operation: The server sends the converted image data to the generative AI model using an API request or similar.

[1137] Input: The transformed image data.

[1138] Output: Image data sent to the generative AI model for analysis.

[1139] Step 5:

[1140] Generative AI models run image analysis algorithms

[1141] How it works: The generative AI model uses the received image data to run an image analysis algorithm, which analyzes the type of food, the ingredients used, the presentation, and more.

[1142] Input: Image data for analysis.

[1143] Output: Analysis data including food characteristics, such as type of food, color, presentation, etc.

[1144] Step 6:

[1145] Generative AI models generate advice

[1146] Specific behavior: Based on the analysis, the generative AI model generates specific advice to improve the presentation of the dish, including suggestions on adding ingredients, plating methods, and the color and shape of the container to use.

[1147] Input: Parsed data containing dish characteristics.

[1148] Output: Specific advice text, such as "Serve with parsley," "Serve the rice in a mound," or "Use a blue plate."

[1149] Step 7:

[1150] The server sends the advice text to the user terminal.

[1151] Specific operation: The server sends the advice text received from the generative AI model to the user's device via push notifications, in-app messages, or other means.

[1152] Input: The generated advice text.

[1153] Output: Advice text sent to the user's terminal.

[1154] Step 8:

[1155] The device displays advice

[1156] Specific operation: The user device displays the received advice text. Specifically, in the case of a smartphone app, it is displayed as a pop-up notification or an in-app message.

[1157] Input: The advice text sent.

[1158] Output: Advice displayed on the user's screen, such as "Serve with parsley," "Serve the rice in a mountain shape," and "Use a blue plate."

[1159] (Application example 1)

[1160] 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."

[1161] The appearance of food has a significant impact on how it is evaluated, and is directly linked to customer satisfaction and increased repeat customers, especially in brick-and-mortar restaurants. However, if kitchen staff and chefs do not have specialized knowledge about food presentation and presentation, it is difficult to maximize the visual appeal of the food. To solve this problem, a system is needed that provides specific advice in real time on how to improve the appearance of food.

[1162] 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.

[1163] In this invention, the server includes means for receiving images of dishes, means for analyzing the received images to extract characteristics of the dishes, means for generating advice to improve the appearance of the dishes based on the analysis results, means for transmitting the generated advice to a user terminal, means for displaying specific advice to improve the appearance of the dishes on the user terminal, means for receiving images via a smart device used in a physical store, and means for analyzing the images using a generative AI model and generating advice to improve the appearance of the dishes using prompt sentences. This allows cooking staff and chefs to receive specific advice in real time even if they do not have specialized knowledge about the appearance of dishes, thereby improving customer satisfaction.

[1164] "Food images" are photographic data of food taken with a digital camera or smartphone.

[1165] The "receiving means" is an interface or protocol that allows a server or smart device to receive images of dishes sent by a user.

[1166] "Means for analyzing and extracting food characteristics" refers to a system or software that uses an image analysis algorithm to automatically identify and extract characteristics such as the type of food, the height of the presentation, and the ingredients used.

[1167] "Means for generating advice" refers to functionality or software that uses a generative AI model based on the analysis results to create specific suggestions or improvements to improve the presentation of food.

[1168] "User terminal" refers to a device, such as a smartphone, tablet, or computer, that a user operates to receive and display advice.

[1169] The "display means" refers to a function such as an application, web interface, or pop-up for visually displaying the advice generated on the user terminal.

[1170] A "physical store" is a business location, such as a restaurant or cafe, where customers actually visit and food is served.

[1171] A "smart device" is a device that has internet connectivity and is capable of taking and transmitting images, and examples include smartphones and tablets.

[1172] A "generative AI model" is an artificial intelligence system that specializes in image analysis and advice generation using technologies such as deep learning.

[1173] A "prompt" is an instruction or data that a user inputs into an application, or an instruction text that a generation AI uses when creating advice.

[1174] The system for implementing this invention comprises a server, a smart device, and a user. The server has the function of receiving images of dishes, analyzing the received images, and extracting the characteristics of the dishes. Then, using a generative AI model, it generates advice for improving the appearance of the dishes based on the analysis results. The generated advice is sent to the user's terminal, and the specific advice is displayed on the user's terminal.

[1175] Hardware and software configuration:

[1176] The server has high-performance computing resources to process the images and installs the necessary software libraries to run the generative AI model, such as a Python web server using Flask and external generative AI services (e.g., Google Cloud Vision or Amazon Rekognition).

[1177] The user terminals may be smartphones, tablets, computers, etc. These terminals have a camera function and can run an application to take images and send them to a server.

[1178] Data processing and calculation:

[1179] The server receives and temporarily stores image data sent by the user. The received image is analyzed using an image analysis algorithm to extract features such as the type of food, how it is presented, and the ingredients used. Based on the results of this analysis, a generative AI model generates advice.

[1180] Specific advice includes "serve with fresh herbs," "serve the rice in a mountain shape," "use a blue plate," etc. These pieces of advice are sent from the server to the user's device and displayed to the user through the application.

[1181] Examples:

[1182] For example, imagine a restaurant chef takes a photo of a dish using a smartphone app. The chef taps the "upload" button to send the photo to the server. The server analyzes the received image, and the generative AI model generates advice such as "garnish with fresh herbs" or "serve the rice in a mountain shape" based on the analysis results, and sends this to the chef's device. The chef can receive the advice through the application and follow the instructions to improve the appearance of the dish.

[1183] Example prompt sentence:

[1184] "Take a photo of your food and upload it. Use it for dishes you're not confident about plating, like pasta or steak."

[1185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1186] Step 1:

[1187] Users take photos of their food using their smartphones or tablets.

[1188] Input: Image data of food taken with a smartphone or tablet camera.

[1189] Output: Captured image data.

[1190] Specific operation: The user takes a photo of the food using a camera app or a dedicated app.

[1191] Step 2:

[1192] The user uploads the captured images to the server through the application.

[1193] Input: Captured image data.

[1194] Output: Image data sent to the server.

[1195] Specific operation: The user selects an image of a dish and taps the "Upload" button in the application to send the image data to the server.

[1196] Step 3:

[1197] The server temporarily stores the received images and prepares them for image analysis.

[1198] Input: Image data sent to the server.

[1199] Output: Saved image file.

[1200] Specific operation: The server temporarily stores the image data in storage and prepares it for analysis.

[1201] Step 4:

[1202] The server analyzes the stored images using a generative AI model.

[1203] Input: A saved image file.

[1204] Output: Food feature data (e.g., serving height, type of ingredients, etc.).

[1205] Specific operation: The server uses an image analysis algorithm (e.g., Google Cloud Vision or Amazon Rekognition) to analyze the food and extract its characteristics.

[1206] Step 5:

[1207] Based on the analyzed data, the server uses a generative AI model to generate advice to improve the presentation of the dish.

[1208] Input: Food feature data.

[1209] Output: The generated advice (e.g., "Serve with fresh herbs" or "Serve the rice in a mound").

[1210] Specific operation: The server runs the generative AI model, inputs the dish's characteristic data as prompts, and generates advice.

[1211] Step 6:

[1212] The server transmits the generated advice to the user terminal.

[1213] Input: The generated advice.

[1214] Output: Advice message sent to user terminal.

[1215] Specific operation: The server sends the generated advice as text data to the user's smartphone or tablet.

[1216] Step 7:

[1217] The user terminal displays the received advice.

[1218] Input: The advice message sent by the server.

[1219] Output: The advice that is displayed to the user.

[1220] Specific operation: The user device will display the advice in the form of a pop-up or notification through the application, visually communicating it to the user.

[1221] 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.

[1222] This invention is a system that analyzes images of food to generate advice for improving the appearance of the food, and further combines it with an emotion engine that recognizes the user's emotions. By providing optimal advice based on the user's emotional state, this system can improve the appearance of the food and increase user satisfaction. Below, we will explain the program processing and specific embodiments of this system.

[1223] System Overview

[1224] 1. Receiving images

[1225] User

[1226] Users take photos of their food using the camera on their smartphone or PC, then upload the photos to the system via an application or web interface.

[1227] 2. Image Analysis

[1228] server

[1229] The server receives photos of dishes uploaded by users and temporarily stores them.

[1230] The server passes the saved images to the generative AI module.

[1231] Generation AI

[1232] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, and more.

[1233] 3. Emotional Recognition

[1234] Terminal

[1235] The user's device uses a camera and microphone to input the user's facial expressions and voice into the emotion engine, which then recognizes the user's current emotional state (happiness, sadness, surprise, etc.).

[1236] Emotion Engine

[1237] The emotion engine analyzes and recognizes emotions from the user's facial expressions and voice, and sends that data to the server.

[1238] It also learns from past user reaction data to provide advice optimized for each individual user.

[1239] 4. Generating Advice

[1240] Generation AI

[1241] Combining image analysis and emotion engine data, it generates specific recommendations to improve the presentation of dishes, such as adding green onions, serving rice in a mountain shape, and using blue plates.

[1242] Based on information from the emotion engine, the system tailors advice to the user's emotional state. For example, if the user is feeling down, the system provides gentle, easy-to-understand advice.

[1243] 5. Submitting Advice

[1244] server

[1245] The server receives the advice data from the generation AI and prepares it for transmission to the user's terminal.

[1246] 6. Displaying Advice

[1247] Terminal

[1248] The user's device analyzes the advice data received from the server and displays it to the user through an application or web interface.

[1249] Specific examples

[1250] Example 1: Upload a photo of curry rice

[1251] User operations

[1252] The user launches the smartphone app and takes a photo of the curry rice.

[1253] Tap the "Upload" button to send the photo to the application server.

[1254] Server Processing

[1255] The server receives the photos and stores them temporarily.

[1256] Pass the saved photo to the generation AI module.

[1257] Collaboration between generative AI and emotion engine

[1258] Generation AI

[1259] The generative AI analyzes the photo and extracts the characteristics of the curry rice (for example, the color of the curry, the height of the serving, etc.).

[1260] Emotion Engine

[1261] The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state, such as whether they are happy, sad, or excited.

[1262] The recognized emotion data is sent to the generation AI.

[1263] Generating and Sending Advice

[1264] Generation AI

[1265] Based on emotion data and food feature data, specific advice such as "garnish with parsley," "serve the rice in a mound shape," and "use a blue plate" is generated.

[1266] If the user is feeling down, advice might include suggestions such as "add some uplifting colors."

[1267] server

[1268] The server transmits the generated advice to the user's terminal.

[1269] Terminal display

[1270] Terminal

[1271] The user's smartphone or PC will then display the received advice, such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[1272] This system allows users to easily improve the appearance of their food without any specialized knowledge, and also provides optimal advice based on their emotions, making home cooking even more enjoyable and satisfying.

[1273] The processing flow will be explained below.

[1274] Step 1:

[1275] User

[1276] Users take a photo of the dish with their smartphone camera and tap the "upload" button through the application to send the photo to the system.

[1277] Step 2:

[1278] server

[1279] The server receives the uploaded photos of the dishes and temporarily stores them in storage.

[1280] Step 3:

[1281] server

[1282] The server sends the saved image data to the generation AI module and prepares it for analysis.

[1283] Step 4:

[1284] Generation AI

[1285] The generative AI uses image analysis algorithms to extract features such as the type of food, the ingredients used, the arrangement of the presentation, and the color and shape of the plate.

[1286] Step 5:

[1287] Terminal

[1288] The user's device uses a camera and microphone to collect the user's facial expressions and voice in real time and transmits them to the emotion engine.

[1289] Step 6:

[1290] Emotion Engine

[1291] The emotion engine analyzes the user's emotional state (e.g., joy, sadness, surprise, excitement, etc.) from their facial expressions and voice, and sends the recognized emotional data to the generation AI.

[1292] Step 7:

[1293] Generation AI

[1294] Based on the received emotion data and food feature data, the generative AI generates specific advice to improve the appearance of the food, such as adding ingredients, plating methods, or changing the color of the plate to improve the food's appearance.

[1295] Step 8:

[1296] Generation AI

[1297] The generative AI tailors its advice based on the user's emotional state: for example, if the user is feeling down, it will create gentle advice with encouraging words.

[1298] Step 9:

[1299] server

[1300] The server receives the generated advice data and prepares it for transmission to the user terminal.

[1301] Step 10:

[1302] server

[1303] The server sends the prepared advice data to the user's terminal, and uses the Internet or cloud services as a means of communication.

[1304] Step 11:

[1305] Terminal

[1306] The user's device analyzes the received advice data and converts it into a display format through an application or web interface.

[1307] Step 12:

[1308] Terminal

[1309] The device displays specific advice to the user, such as "serve with green onions," "serve the rice in a mountain shape," and "use a blue plate." The user can use this advice to improve the appearance of their dish.

[1310] Example 2

[1311] 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."

[1312] Conventional cooking analysis systems can provide advice on improving the appearance of dishes, but they are unable to provide optimal advice that takes into account the user's emotional state. As a result, users are unable to receive advice that is tailored to their psychological state and preferences, making it difficult to increase user satisfaction. The objective of this invention is to improve the appearance of dishes and increase user satisfaction by recognizing the user's emotional state and providing optimal advice based on that state.

[1313] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an image of a dish, means for analyzing the received image to extract characteristics of the dish, means for generating advice to improve the appearance of the dish based on the analysis results, means for recognizing the user's emotional state, means for adjusting the optimal advice based on the emotional state, means for transmitting the generated advice to the user terminal, and means for displaying the advice on the user terminal. This makes it possible to provide advice to improve the appearance of a dish that takes into account the user's emotional state.

[1314] The "means for receiving food images" refers to an interface for users to upload photos of food taken by them to the system.

[1315] "Means for analyzing received images and extracting characteristics of food" refers to algorithms or software that analyze received images of food and extract characteristics such as the type of food, ingredients used, and presentation.

[1316] "Means for generating advice to improve the appearance of food based on the analysis results" refers to a mechanism for generating specific advice to improve the visual appearance of food based on the analyzed characteristics of the food.

[1317] "Means for recognizing the user's emotional state" refers to a camera, microphone, and analysis algorithm for analyzing the user's facial expressions and voice to recognize the psychological emotional state at that time.

[1318] "Means for adjusting optimal advice based on emotional state" refers to a mechanism for adjusting advice to improve the appearance of food according to the recognized emotional state of the user and providing it in an optimal form for each individual user.

[1319] "Means for transmitting the generated advice to the user terminal" refers to the communication means or protocol for transmitting the generated advice to the user's terminal such as a smartphone or PC.

[1320] "Means for displaying advice on a user terminal" refers to an application or web interface for displaying received advice on the user's terminal.

[1321] This invention is a system that analyzes images of food, generates advice for improving the appearance, and combines it with an emotion engine that recognizes the user's emotional state. This system provides optimal advice based on the user's emotional state, improves the appearance of the food, and increases user satisfaction.

[1322] System Overview

[1323] This system mainly uses the following hardware and software.

[1324] 1. Receiving images

[1325] Users take photos of their food using their smartphone or PC camera and upload them to the system via an application or web interface.

[1326] 2. Image Analysis

[1327] The server receives photos of dishes uploaded by users and temporarily stores them. The stored images are then passed to the generative AI module. This can be done using an S3 bucket on Amazon Web Services (AWS).

[1328] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, etc. It uses TensorFlow models to perform a detailed analysis of the elements in the image.

[1329] 3. Emotional Recognition

[1330] The device uses a camera and microphone to input the user's facial expressions and voice into the emotion engine. The camera is used to analyze facial expressions, and the microphone is used to collect the content and tone of speech. It can use iPhone's Face ID or Android's facial recognition function.

[1331] The emotion engine analyzes and recognizes emotions from the user's facial expressions and voice, and sends the data to a server. The analysis is performed using Microsoft Azure's Emotion API. It also learns the user's individual reaction patterns from past data.

[1332] 4. Generating Advice

[1333] The generative AI combines image analysis and emotion engine data to generate specific advice to improve the appearance of the dish. Examples include "garnish with green onions," "serve the rice in a mountain shape," and "use a blue plate." Based on the information from the emotion engine, the advice is tailored to the user's emotional state. For example, if the user is feeling down, the AI ​​will provide gentle, easy-to-understand advice.

[1334] 5. Submitting Advice

[1335] The server receives the advice data from the generation AI and prepares it for transmission to the user device. Data transfer is managed using AWS S3 and DynamoDB.

[1336] 6. Displaying Advice

[1337] The device analyzes the advice data received from the server and displays it to the user through an application or web interface. Specifically, advice such as "garnish with parsley," "serve rice in a mountain shape," and "use a blue plate" is displayed on a smartphone app or PC web browser.

[1338] Specific examples

[1339] Example 1: Upload a photo of curry rice

[1340] User operations

[1341] The user launches the smartphone app, takes a photo of the curry rice, and taps the "Upload" button to send the photo to the application server.

[1342] Server Processing

[1343] The server receives the photos and temporarily stores them in an AWS S3 bucket, after which the stored photos are passed to the generative AI module.

[1344] Collaboration between generative AI and emotion engine

[1345] Generation AI

[1346] The generative AI uses TensorFlow to analyze the characteristics of the food in the photo (for example, the color of the curry or the height of the presentation).

[1347] Emotion Engine

[1348] The emotion engine uses Microsoft Azure's Emotion API to recognize emotions from the user's facial expressions and voice, and sends the recognition results to the generation AI.

[1349] Generating and Sending Advice

[1350] Generation AI

[1351] The generative AI combines emotion data with dish characteristics data to generate specific advice. For example, it might include suggestions such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate." If the user is feeling down, it might also suggest "adding cheerful colors."

[1352] server

[1353] The server sends the generated advice to the user's device, efficiently queuing messages using AWS SQS.

[1354] Terminal display

[1355] Terminal

[1356] The user's smartphone or PC will then display the received advice, such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[1357] Prompt Sentence Examples

[1358] "Analyze a photo of curry rice and generate specific advice on how to make it look better. If the user's emotional state is depressed, add some uplifting advice."

[1359] This system allows users to easily improve the appearance of their food without any specialized knowledge, and also provides optimal advice based on their emotions, further increasing the enjoyment and satisfaction of home cooking.

[1360] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1361] Step 1: Receiving the image

[1362] (input)

[1363] Users take photos of their food using the camera on their smartphone or PC and upload them to the system via an application or web interface.

[1364] (process)

[1365] When the user taps the "Upload" button, the captured image is sent to the cloud (e.g., AWS S3). The server confirms receipt of the image and temporarily stores it.

[1366] (output)

[1367] Image files of food stored on the server.

[1368] (Specific actions)

[1369] When a user uploads a photo of the food they have taken with their smartphone, the photo is transferred to the server, where it is temporarily stored.

[1370] Step 2: Analyze the images

[1371] (input)

[1372] The server receives the temporarily stored image files of the food.

[1373] (process)

[1374] The server passes the received image to the generative AI module, which uses image analysis algorithms to analyze the type of food in the image, the ingredients used, the presentation, etc. For example, TensorFlow can be used to perform a detailed analysis of each element in the image.

[1375] (output)

[1376] Analyzed food feature data (e.g., ingredient list, presentation balance, color, etc.).

[1377] (Specific actions)

[1378] The server passes the saved image to a generative AI model, which uses TensorFlow to analyze features in the image and extract detailed data about the dish.

[1379] Step 3: Recognize emotions

[1380] (input)

[1381] The device collects the user's facial and voice data using a camera and microphone.

[1382] (process)

[1383] Data collected from the camera and microphone is input into the emotion engine, which uses Microsoft Azure's Emotion API to analyze and recognize the user's emotional state from their facial expressions and voice. It also references past data to learn the user's individual reaction patterns and improve accuracy.

[1384] (output)

[1385] Recognized user emotion data (happiness, sadness, surprise, etc.).

[1386] (Specific actions)

[1387] When a user uploads an image of a dish, the device's camera and microphone collect data on the user's facial expressions and voice, which is then passed to the emotion engine for analysis.

[1388] Step 4: Generating Advice

[1389] (input)

[1390] The generative AI receives analyzed food feature data and recognized user emotion data.

[1391] (process)

[1392] The generative AI combines the dish's feature data with emotion data to generate specific advice for improving its appearance. For example, it might include "garnish with green onions," "serve the rice in a mountain shape," or "use a blue plate." If the user is feeling down, it might also provide empathetic advice such as "add some cheery colors."

[1393] (output)

[1394] Specific advice generated.

[1395] (Specific actions)

[1396] The generative AI model generates appropriate advice based on the characteristics of the dish and the user's emotions, including specific methods to improve the appearance of the dish.

[1397] Step 5: Submitting Advice

[1398] (input)

[1399] The server receives the specific advice received from the generating AI.

[1400] (process)

[1401] The server prepares to send the generated advice data to the user device, using AWS SQS or similar to efficiently queue messages and transfer data.

[1402] (output)

[1403] Advice data sent to the user terminal.

[1404] (Specific actions)

[1405] The server receives the generated advice and transmits it to the user's device using an efficient message queuing technique.

[1406] Step 6: Viewing Advice

[1407] (input)

[1408] The terminal receives the advice data received from the server.

[1409] (process)

[1410] The device analyzes the received advice data and displays it to the user through an application or web interface in an easy-to-read format that is easy for the user to understand.

[1411] (output)

[1412] Specific advice displayed on the user's device.

[1413] (Specific actions)

[1414] The device analyzes the advice received from the server and displays advice such as "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate" on the smartphone screen or PC web browser.

[1415] (Application example 2)

[1416] 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."

[1417] There is a need for a simple method to improve the appearance of food without specialized knowledge. There is also a need for a method to provide a more satisfying experience by taking into account the user's emotional state when receiving advice on how to improve the appearance of food.

[1418] 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.

[1419] In this invention, the server includes means for receiving an image of a dish, means for analyzing the received image to extract characteristics of the dish, means for recognizing the emotional state of the user, means for generating advice to improve the appearance of the dish based on the analysis result and the emotional state, means for transmitting the generated advice to the user terminal, and means for displaying the advice on the user terminal. This makes it possible to easily improve the appearance of a dish without specialized knowledge and receive optimal advice according to the user's emotional state.

[1420] The "means for receiving food images" is a function for transmitting and receiving food images taken by the user to the system.

[1421] The "means for analyzing received images and extracting characteristics of food" is a function that applies an image processing algorithm to received images of food to identify characteristics such as the type of food, presentation, and color.

[1422] The "means for recognizing the user's emotional state" is a function for analyzing the user's emotions from their facial expressions and voice and determining their emotional state.

[1423] The "means for generating advice to improve the appearance of food based on the analysis results and the user's emotional state" is a function that combines the analyzed characteristics of food with the user's emotional state to create advice to optimally improve the appearance of food.

[1424] The "means for transmitting generated advice to a user terminal" is a function for transmitting advice generated within the system to a terminal such as a user's smartphone or tablet.

[1425] The "means for displaying advice on the user terminal" is a function for visually displaying advice received on the user terminal.

[1426] The system related to this invention is an application that allows food delivery service providers (restaurants and cafes) to upload photos of their dishes and receive advice on how to improve their presentation. The system also recognizes the user's emotional state and provides optimal advice. Below, we will explain the detailed program processing and hardware and software used in this system.

[1427] Program Overview

[1428] Upload a photo

[1429] A user takes a photo of a dish using the smartphone camera and sends it to the server. The application can use the smartphone's camera API or network communication API (e.g., Camera2 API or Volley library for Android).

[1430] Image analysis

[1431] The server analyzes the received food images using a generative AI model, which includes advanced image analysis algorithms such as OpenAI's DALL-E and CLIP models, to extract data about the food's characteristics and appearance.

[1432] emotion recognition

[1433] The system utilizes the smartphone's camera and microphone to recognize the user's emotions. The emotion recognition engine uses existing emotion recognition software such as the Affectiva SDK. Emotional data is extracted from the user's facial expressions and voice and sent to the server.

[1434] Advice Generation

[1435] The generative AI generates advice by combining image analysis data of the food and user emotion recognition data. For example, it generates specific advice such as "add brightly colored vegetables" or "change the plate to a different color."

[1436] Sending and displaying advice

[1437] The server sends the generated advice to the user's device, where the smartphone application displays the advice. The application uses a user interface (UI) to present the advice in an easy-to-understand manner.

[1438] Specific examples

[1439] Example 1: Upload a photo of curry rice

[1440] User operations

[1441] A restaurant employee launches the app and takes a photo of the curry rice.

[1442] Tap the "Upload" button to send the photo to the application server.

[1443] Server Processing

[1444] The server receives the photos and stores them temporarily.

[1445] Pass the saved photo to the generation AI module.

[1446] Collaboration between generative AI and emotion engine

[1447] Generation AI:

[1448] The generative AI analyzes the photo and extracts the characteristics of the curry rice (for example, the color of the curry, the height of the serving, etc.).

[1449] Emotion Engine:

[1450] The emotion engine analyzes employees' facial expressions and voices to recognize their emotional state (e.g., tired, happy, etc.).

[1451] The recognized emotion data is sent to the generation AI.

[1452] Generating and Sending Advice

[1453] Generation AI:

[1454] Based on emotion data and food feature data, specific advice such as "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate" is generated.

[1455] If employees are tired, offer them some quick and easy advice.

[1456] server:

[1457] The server transmits the generated advice to the user's terminal.

[1458] Terminal display

[1459] Device:

[1460] Advice such as "Add parsley," "Serve the rice in a mountain shape," and "Use blue plates" will be displayed on employees' smartphones.

[1461] Example prompt sentences (examples of input to generative AI models)

[1462] Prompt statement:

[1463] Analyze the following food photo and offer specific suggestions for improving presentation. Adjust your suggestions based on your employees' emotional state.

[1464] Food photos:

[1465] [Image of curry rice]

[1466] Employee emotional state:

[1467] [Tired]

[1468] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1469] Step 1:

[1470] A user takes a photo of a dish using the smartphone camera.

[1471] Input: Physical image of the dish

[1472] Output: Digital image data

[1473] Specific behavior: The user launches the smartphone app and uses the camera to take a photo of the food.

[1474] Step 2:

[1475] The terminal transmits the photograph of the food taken to the application server.

[1476] Input: Digital image data

[1477] Output: Upload image data to the server

[1478] Specific operation: The device uses a network communication API to send image data to the server.

[1479] Step 3:

[1480] The server temporarily stores the received image and passes it to the generation AI module.

[1481] Input: Image data uploaded to the server

[1482] Output: Transfer of image data to the generative AI module

[1483] Specific operation: The server uses the storage function to save the data, and then passes the image data to the generation AI module.

[1484] Step 4:

[1485] The generative AI analyzes the image and extracts the characteristics of the dish.

[1486] Input: Image data passed to the generation AI

[1487] Output: Extracted food feature data

[1488] How it works: Generative AI (e.g., OpenAI's DALL-E or CLIP models) uses image analysis algorithms to identify features such as food type, presentation, and color.

[1489] Step 5:

[1490] The device uses a camera and microphone to recognize the user's emotional state and transmits the emotional data to a server.

[1491] Input: User's facial expressions and voice

[1492] Output: Upload emotion data to the server

[1493] Specific operation: The device uses an emotion recognition engine (e.g., Affectiva SDK) to analyze the user's facial expressions and voice to determine their emotional state. The result is then sent to the server via a network communication API.

[1494] Step 6:

[1495] Generative AI combines image analysis data and emotion recognition data to generate advice.

[1496] Input: Extracted food feature data and user emotion data

[1497] Output: Advice data for improving appearance

[1498] Specific behavior: The generative AI makes adjustments based on the prompt text and generates specific advice (e.g., "garnish with parsley," "serve the rice in a mound shape," "use a blue plate") based on the analysis results and emotional data.

[1499] Step 7:

[1500] The server transmits the generated advice to the user terminal.

[1501] Input: Advice data generated by generative AI

[1502] Output: Sending advice data to the user's terminal

[1503] Specific operation: The server uses a network communication API to send advice data to the user terminal.

[1504] Step 8:

[1505] The terminal displays the received advice through a user interface.

[1506] Input: Submitted advice data

[1507] Output: Visually displayed advice

[1508] Specific operation: The device displays the received advice using the user interface (UI) and provides it to the user.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] [Fourth embodiment]

[1513] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1514] 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.

[1515] 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).

[1516] 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.

[1517] 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.

[1518] 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).

[1519] 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. 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.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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."

[1526] This invention is a system that provides specific advice on how to improve the appearance of a dish simply by allowing a user to upload a photo of the dish. This system is composed of a server, a user's terminal, and a generating AI. The program processing and specific embodiments of this system are described below.

[1527] System Overview

[1528] 1. Receiving images

[1529] User

[1530] Users take photos of their food using their smartphone camera or PC webcam.

[1531] Upload the photos you take to the system via an application or web interface.

[1532] 2. Image Analysis

[1533] server

[1534] The server stores the received images and prepares them for passing to the generation AI for image analysis.

[1535] Generation AI

[1536] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, and more.

[1537] 3. Generating Advice

[1538] Generation AI

[1539] Based on the analyzed data, the system generates specific advice to improve the appearance of the dish, such as adding green onions, serving the food a little higher, or using a different color plate.

[1540] 4. Submitting Advice

[1541] server

[1542] The server receives the advice text from the generation AI and sends it to the user's device.

[1543] 5. Displaying Advice

[1544] Terminal

[1545] The user's smartphone or PC receives the advice and displays it to the user through an application or web interface.

[1546] Specific examples

[1547] Example 1: Upload a photo of curry rice

[1548] User operations

[1549] The user launches the smartphone app and takes a photo of the curry rice.

[1550] Tap the "Upload" button to send the photo to the application server.

[1551] Server Processing

[1552] The server receives the photos and stores them temporarily.

[1553] Send the saved photo to the generation AI.

[1554] Generative AI analysis and advice generation

[1555] The generative AI uses image analysis algorithms to extract characteristics of curry rice from photos, such as the color of the curry, the height of the serving, and any optional toppings used.

[1556] Based on this information, the generative AI generates specific advice such as "garnish with parsley," "serve the rice in a mound shape," and "use a blue plate."

[1557] Server Send

[1558] The server transmits the generated advice to the user's terminal.

[1559] Terminal display

[1560] The user's smartphone receives the advice and displays it in a pop-up format, including advice such as "Add parsley," "Serve the rice in a mound," and "Use a blue plate."

[1561] By using this system, users can easily improve the appearance of their food without any specialized knowledge. This system can also be applied to any type of food, making home cooking more enjoyable and visually satisfying.

[1562] The processing flow will be explained below.

[1563] Step 1:

[1564] User

[1565] Users launch the application, take a photo of their food using the camera on their smartphone or PC, and then tap the "Upload" button to send the photo to the application.

[1566] Step 2:

[1567] server

[1568] The server receives photos of food uploaded by users, temporarily stores the images, and prepares them for image analysis.

[1569] Step 3:

[1570] server

[1571] The server prepares the stored images to be passed to the generation AI module and sends the image data to the generation AI, where it is converted into a format for analysis.

[1572] Step 4:

[1573] Generation AI

[1574] Generative AI uses image analysis algorithms to extract specific features from food images, including the type of food, the ingredients used, how it's presented, and the color and shape of the plate.

[1575] Step 5:

[1576] Generation AI

[1577] Based on the extracted features, the generative AI generates specific advice to improve the appearance of the dish, such as "garnish with green onions," "serve the rice in a mountain shape," and "use a blue plate."

[1578] Step 6:

[1579] server

[1580] The server receives the advice data from the generation AI and prepares it for transmission to the user's device. The advice data is converted into a format suitable for the user's device.

[1581] Step 7:

[1582] server

[1583] The server then sends the prepared advice data to the user's smartphone or PC via the Internet or cloud services.

[1584] Step 8:

[1585] Terminal

[1586] The user's device parses the advice data received from the server and converts it into a format that can be displayed via an application or web interface.

[1587] Step 9:

[1588] Terminal

[1589] The device displays specific advice to the user. For example, pop-up messages on the screen suggest advice such as "Serve with green onions," "Serve the rice in a mountain shape," and "Use a blue plate." By referring to these, the user can improve the appearance of their dish.

[1590] Example 1

[1591] 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."

[1592] It is difficult for people without specialized knowledge of cooking to easily obtain specific advice on how to improve the appearance of food. Furthermore, specialized knowledge and experience are required to know specific ways to improve visual elements, such as how to add ingredients, how to arrange food, and the color and shape of containers to use. There is a growing demand for a system that can easily provide methods for enhancing the visual appeal of everyday cooking.

[1593] 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.

[1594] In this invention, the server includes means for users to upload images of dishes, means for saving the received images of dishes, means for sending the saved image data to a generative AI model, means for the generative AI model to extract characteristics of the dishes using an image analysis algorithm, means for generating advice to improve the appearance of the dishes based on the analysis results, means for sending the generated advice from the server to a user terminal, and means for displaying the advice on the user terminal. This enables users to receive specific advice based on photos of dishes they have taken, even if they do not have specialized knowledge.

[1595] A "user" is someone who uses the system to upload images of their dishes and receive visual improvement advice.

[1596] The "server" is a computer system that receives, stores, and relays images of dishes to be passed to the generative AI model.

[1597] An "image analysis algorithm" is a calculation method for extracting characteristics of food from received images and analyzing the type, presentation, etc.

[1598] A "generative AI model" is an artificial intelligence model that uses image analysis algorithms to analyze the characteristics of food and generate specific advice to improve its appearance.

[1599] "Advice" is specific suggestions for improving the appearance of a dish, such as adding ingredients, plating methods, and the color and shape of the containers to use.

[1600] A "user terminal" is a device owned by a user, such as a smartphone or PC, that displays advice sent from the system.

[1601] "Uploading" refers to the act of sending an image of a dish taken by a user to a server.

[1602] "Saving" is a process in which the server temporarily stores the image of the dish received in a storage device.

[1603] "Sending" refers to the act of delivering advice created by the generative AI model to the user's device via the server.

[1604] "Display" refers to the act of visually providing advice on a user terminal.

[1605] This invention is a system that provides specific advice on how to improve the appearance of a dish simply by allowing the user to upload a photo of the dish. The system is composed of a server, a user's device, and a generative AI model.

[1606] System Overview

[1607] Users take photos of their dishes using their smartphones or PCs and upload them through an application or web interface. The uploaded images are sent to the generative AI model via the server. The generative AI model uses image analysis algorithms to analyze the characteristics of the dish and, based on the results, generates specific advice to improve the appearance of the dish. The generated advice is sent to the user's device via the server, where the user can receive it and view it via the application or web interface.

[1608] Specific implementation methods

[1609] A user takes a photo of a dish using a smartphone camera or a PC webcam. The photo is then uploaded using a dedicated application or web interface. For example, this involves launching a smartphone application, tapping the "Take Photo" button to take a photo of the dish, and then pressing the "Upload" button.

[1610] The uploaded images are temporarily stored by the server, which prepares them for sending to the generative AI model and converts them to the appropriate format and resolution, which includes reformatting and resizing the image files.

[1611] The generative AI model runs an image analysis algorithm using image data received from the server. The algorithm identifies the type of dish, the ingredients used, how it is presented, etc. For example, if the photo is of curry rice, it will analyze the color of the curry, how the rice is presented, and the type of ingredients. As an example of a prompt for the generative AI model, enter "Please provide some advice on how to improve the appearance of this dish."

[1612] Based on the analysis results, the generative AI model generates specific advice to improve the appearance of the dish. Specific advice includes "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate." The advice is sent to the server.

[1613] The server sends the advice text received from the generative AI model to the user's device. The server selects the appropriate communication method based on the user's ID and device information to send the data. If the user is using a smartphone app, the data is sent as a push notification or in-app message.

[1614] The user device will then display the received advice. For example, in the case of a smartphone app, a pop-up notification will appear, showing advice such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[1615] This allows users to receive specific advice based on photos of their food, even if they do not have specialized knowledge. This system allows users to easily receive advice on how to improve the appearance of their food, helping them to provide visually satisfying dishes. It is also highly versatile and can be applied to a wide range of cooking, from home cooking to cooking by professional chefs.

[1616] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1617] Step 1:

[1618] Users take and upload images of their dishes

[1619] Specific operation: The user takes a photo of the food using the camera on their smartphone or the webcam on their PC, and uploads the photo to the system via a dedicated application or web interface.

[1620] Input: Image files of the photographed food.

[1621] Output: Image data uploaded to the system.

[1622] Step 2:

[1623] The server receives and stores the images

[1624] Specific operation: The server temporarily stores images uploaded by users. The image storage location is the specified database or storage.

[1625] Input: Uploaded image data.

[1626] Output: The file path and ID of the saved image data.

[1627] Step 3:

[1628] The server prepares the image to be sent to the generative AI model.

[1629] What it does: The server converts the stored images into the appropriate format and resolution for sending to the generative AI model. This conversion includes formatting and resizing the image files.

[1630] Input: The file path or ID of the saved image data.

[1631] Output: Image data in a format and resolution suitable for the generative AI model.

[1632] Step 4:

[1633] The server sends the image data to the generative AI model.

[1634] Specific operation: The server sends the converted image data to the generative AI model using an API request or similar.

[1635] Input: The transformed image data.

[1636] Output: Image data sent to the generative AI model for analysis.

[1637] Step 5:

[1638] Generative AI models run image analysis algorithms

[1639] How it works: The generative AI model uses the received image data to run an image analysis algorithm, which analyzes the type of food, the ingredients used, the presentation, and more.

[1640] Input: Image data for analysis.

[1641] Output: Analysis data including food characteristics, such as type of food, color, presentation, etc.

[1642] Step 6:

[1643] Generative AI models generate advice

[1644] Specific behavior: Based on the analysis, the generative AI model generates specific advice to improve the presentation of the dish, including suggestions on adding ingredients, plating methods, and the color and shape of the container to use.

[1645] Input: Parsed data containing dish characteristics.

[1646] Output: Specific advice text, such as "Serve with parsley," "Serve the rice in a mound," or "Use a blue plate."

[1647] Step 7:

[1648] The server sends the advice text to the user terminal.

[1649] Specific operation: The server sends the advice text received from the generative AI model to the user's device via push notifications, in-app messages, or other means.

[1650] Input: The generated advice text.

[1651] Output: Advice text sent to the user's terminal.

[1652] Step 8:

[1653] The device displays advice

[1654] Specific operation: The user device displays the received advice text. Specifically, in the case of a smartphone app, it is displayed as a pop-up notification or an in-app message.

[1655] Input: The advice text sent.

[1656] Output: Advice displayed on the user's screen, such as "Serve with parsley," "Serve the rice in a mountain shape," and "Use a blue plate."

[1657] (Application example 1)

[1658] 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."

[1659] The appearance of food has a significant impact on how it is evaluated, and is directly linked to customer satisfaction and increased repeat customers, especially in brick-and-mortar restaurants. However, if kitchen staff and chefs do not have specialized knowledge about food presentation and presentation, it is difficult to maximize the visual appeal of the food. To solve this problem, a system is needed that provides specific advice in real time on how to improve the appearance of food.

[1660] 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.

[1661] In this invention, the server includes means for receiving images of dishes, means for analyzing the received images to extract characteristics of the dishes, means for generating advice to improve the appearance of the dishes based on the analysis results, means for transmitting the generated advice to a user terminal, means for displaying specific advice to improve the appearance of the dishes on the user terminal, means for receiving images via a smart device used in a physical store, and means for analyzing the images using a generative AI model and generating advice to improve the appearance of the dishes using prompt sentences. This allows cooking staff and chefs to receive specific advice in real time even if they do not have specialized knowledge about the appearance of dishes, thereby improving customer satisfaction.

[1662] "Food images" are photographic data of food taken with a digital camera or smartphone.

[1663] The "receiving means" is an interface or protocol that allows a server or smart device to receive images of dishes sent by a user.

[1664] "Means for analyzing and extracting food characteristics" refers to a system or software that uses an image analysis algorithm to automatically identify and extract characteristics such as the type of food, the height of the presentation, and the ingredients used.

[1665] "Means for generating advice" refers to functionality or software that uses a generative AI model based on the analysis results to create specific suggestions or improvements to improve the presentation of food.

[1666] "User terminal" refers to a device, such as a smartphone, tablet, or computer, that a user operates to receive and display advice.

[1667] The "display means" refers to a function such as an application, web interface, or pop-up for visually displaying the advice generated on the user terminal.

[1668] A "physical store" is a business location, such as a restaurant or cafe, where customers actually visit and food is served.

[1669] A "smart device" is a device that has internet connectivity and is capable of taking and transmitting images, and examples include smartphones and tablets.

[1670] A "generative AI model" is an artificial intelligence system that specializes in image analysis and advice generation using technologies such as deep learning.

[1671] A "prompt" is an instruction or data that a user inputs into an application, or an instruction text that a generation AI uses when creating advice.

[1672] The system for implementing this invention comprises a server, a smart device, and a user. The server has the function of receiving images of dishes, analyzing the received images, and extracting the characteristics of the dishes. Then, using a generative AI model, it generates advice for improving the appearance of the dishes based on the analysis results. The generated advice is sent to the user's terminal, and the specific advice is displayed on the user's terminal.

[1673] Hardware and software configuration:

[1674] The server has high-performance computing resources to process the images and installs the necessary software libraries to run the generative AI model, such as a Python web server using Flask and external generative AI services (e.g., Google Cloud Vision or Amazon Rekognition).

[1675] The user terminals may be smartphones, tablets, computers, etc. These terminals have a camera function and can run an application to take images and send them to a server.

[1676] Data processing and calculation:

[1677] The server receives and temporarily stores image data sent by the user. The received image is analyzed using an image analysis algorithm to extract features such as the type of food, how it is presented, and the ingredients used. Based on the results of this analysis, a generative AI model generates advice.

[1678] Specific advice includes "serve with fresh herbs," "serve the rice in a mountain shape," "use a blue plate," etc. These pieces of advice are sent from the server to the user's device and displayed to the user through the application.

[1679] Examples:

[1680] For example, imagine a restaurant chef takes a photo of a dish using a smartphone app. The chef taps the "upload" button to send the photo to the server. The server analyzes the received image, and the generative AI model generates advice such as "garnish with fresh herbs" or "serve the rice in a mountain shape" based on the analysis results, and sends this to the chef's device. The chef can receive the advice through the application and follow the instructions to improve the appearance of the dish.

[1681] Example prompt sentence:

[1682] "Take a photo of your food and upload it. Use it for dishes you're not confident about plating, like pasta or steak."

[1683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1684] Step 1:

[1685] Users take photos of their food using their smartphones or tablets.

[1686] Input: Image data of food taken with a smartphone or tablet camera.

[1687] Output: Captured image data.

[1688] Specific operation: The user takes a photo of the food using a camera app or a dedicated app.

[1689] Step 2:

[1690] The user uploads the captured images to the server through the application.

[1691] Input: Captured image data.

[1692] Output: Image data sent to the server.

[1693] Specific operation: The user selects an image of a dish and taps the "Upload" button in the application to send the image data to the server.

[1694] Step 3:

[1695] The server temporarily stores the received images and prepares them for image analysis.

[1696] Input: Image data sent to the server.

[1697] Output: Saved image file.

[1698] Specific operation: The server temporarily stores the image data in storage and prepares it for analysis.

[1699] Step 4:

[1700] The server analyzes the stored images using a generative AI model.

[1701] Input: A saved image file.

[1702] Output: Food feature data (e.g., serving height, type of ingredients, etc.).

[1703] Specific operation: The server uses an image analysis algorithm (e.g., Google Cloud Vision or Amazon Rekognition) to analyze the food and extract its characteristics.

[1704] Step 5:

[1705] Based on the analyzed data, the server uses a generative AI model to generate advice to improve the presentation of the dish.

[1706] Input: Food feature data.

[1707] Output: The generated advice (e.g., "Serve with fresh herbs" or "Serve the rice in a mound").

[1708] Specific operation: The server runs the generative AI model, inputs the dish's characteristic data as prompts, and generates advice.

[1709] Step 6:

[1710] The server transmits the generated advice to the user terminal.

[1711] Input: The generated advice.

[1712] Output: Advice message sent to user terminal.

[1713] Specific operation: The server sends the generated advice as text data to the user's smartphone or tablet.

[1714] Step 7:

[1715] The user terminal displays the received advice.

[1716] Input: The advice message sent by the server.

[1717] Output: The advice that is displayed to the user.

[1718] Specific operation: The user device will display the advice in the form of a pop-up or notification through the application, visually communicating it to the user.

[1719] 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.

[1720] This invention is a system that analyzes images of food to generate advice for improving the appearance of the food, and further combines it with an emotion engine that recognizes the user's emotions. By providing optimal advice based on the user's emotional state, this system can improve the appearance of the food and increase user satisfaction. Below, we will explain the program processing and specific embodiments of this system.

[1721] System Overview

[1722] 1. Receiving images

[1723] User

[1724] Users take photos of their food using the camera on their smartphone or PC, then upload the photos to the system via an application or web interface.

[1725] 2. Image Analysis

[1726] server

[1727] The server receives photos of dishes uploaded by users and temporarily stores them.

[1728] The server passes the saved images to the generative AI module.

[1729] Generation AI

[1730] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, and more.

[1731] 3. Emotional Recognition

[1732] Terminal

[1733] The user's device uses a camera and microphone to input the user's facial expressions and voice into the emotion engine, which then recognizes the user's current emotional state (happiness, sadness, surprise, etc.).

[1734] Emotion Engine

[1735] The emotion engine analyzes and recognizes emotions from the user's facial expressions and voice, and sends that data to the server.

[1736] It also learns from past user reaction data to provide advice optimized for each individual user.

[1737] 4. Generating Advice

[1738] Generation AI

[1739] Combining image analysis and emotion engine data, it generates specific recommendations to improve the presentation of dishes, such as adding green onions, serving rice in a mountain shape, and using blue plates.

[1740] Based on information from the emotion engine, the system tailors advice to the user's emotional state. For example, if the user is feeling down, the system provides gentle, easy-to-understand advice.

[1741] 5. Submitting Advice

[1742] server

[1743] The server receives the advice data from the generation AI and prepares it for transmission to the user's terminal.

[1744] 6. Displaying Advice

[1745] Terminal

[1746] The user's device analyzes the advice data received from the server and displays it to the user through an application or web interface.

[1747] Specific examples

[1748] Example 1: Upload a photo of curry rice

[1749] User operations

[1750] The user launches the smartphone app and takes a photo of the curry rice.

[1751] Tap the "Upload" button to send the photo to the application server.

[1752] Server Processing

[1753] The server receives the photos and stores them temporarily.

[1754] Pass the saved photo to the generation AI module.

[1755] Collaboration between generative AI and emotion engine

[1756] Generation AI

[1757] The generative AI analyzes the photo and extracts the characteristics of the curry rice (for example, the color of the curry, the height of the serving, etc.).

[1758] Emotion Engine

[1759] The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state, such as whether they are happy, sad, or excited.

[1760] The recognized emotion data is sent to the generation AI.

[1761] Generating and Sending Advice

[1762] Generation AI

[1763] Based on emotion data and food feature data, specific advice such as "garnish with parsley," "serve the rice in a mound shape," and "use a blue plate" is generated.

[1764] If the user is feeling down, advice might include suggestions such as "add some uplifting colors."

[1765] server

[1766] The server transmits the generated advice to the user's terminal.

[1767] Terminal display

[1768] Terminal

[1769] The user's smartphone or PC will then display the received advice, such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[1770] This system allows users to easily improve the appearance of their food without any specialized knowledge, and also provides optimal advice based on their emotions, making home cooking even more enjoyable and satisfying.

[1771] The processing flow will be explained below.

[1772] Step 1:

[1773] User

[1774] Users take a photo of the dish with their smartphone camera and tap the "upload" button through the application to send the photo to the system.

[1775] Step 2:

[1776] server

[1777] The server receives the uploaded photos of the dishes and temporarily stores them in storage.

[1778] Step 3:

[1779] server

[1780] The server sends the saved image data to the generation AI module and prepares it for analysis.

[1781] Step 4:

[1782] Generation AI

[1783] The generative AI uses image analysis algorithms to extract features such as the type of food, the ingredients used, the arrangement of the presentation, and the color and shape of the plate.

[1784] Step 5:

[1785] Terminal

[1786] The user's device uses a camera and microphone to collect the user's facial expressions and voice in real time and transmits them to the emotion engine.

[1787] Step 6:

[1788] Emotion Engine

[1789] The emotion engine analyzes the user's emotional state (e.g., joy, sadness, surprise, excitement, etc.) from their facial expressions and voice, and sends the recognized emotional data to the generation AI.

[1790] Step 7:

[1791] Generation AI

[1792] Based on the received emotion data and food feature data, the generative AI generates specific advice to improve the appearance of the food, such as adding ingredients, plating methods, or changing the color of the plate to improve the food's appearance.

[1793] Step 8:

[1794] Generation AI

[1795] The generative AI tailors its advice based on the user's emotional state: for example, if the user is feeling down, it will create gentle advice with encouraging words.

[1796] Step 9:

[1797] server

[1798] The server receives the generated advice data and prepares it for transmission to the user terminal.

[1799] Step 10:

[1800] server

[1801] The server sends the prepared advice data to the user's terminal, and uses the Internet or cloud services as a means of communication.

[1802] Step 11:

[1803] Terminal

[1804] The user's device analyzes the received advice data and converts it into a display format through an application or web interface.

[1805] Step 12:

[1806] Terminal

[1807] The device displays specific advice to the user, such as "serve with green onions," "serve the rice in a mountain shape," and "use a blue plate." The user can use this advice to improve the appearance of their dish.

[1808] Example 2

[1809] 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."

[1810] Conventional cooking analysis systems can provide advice on improving the appearance of dishes, but they are unable to provide optimal advice that takes into account the user's emotional state. As a result, users are unable to receive advice that is tailored to their psychological state and preferences, making it difficult to increase user satisfaction. The objective of this invention is to improve the appearance of dishes and increase user satisfaction by recognizing the user's emotional state and providing optimal advice based on that state.

[1811] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an image of a dish, means for analyzing the received image to extract characteristics of the dish, means for generating advice to improve the appearance of the dish based on the analysis results, means for recognizing the user's emotional state, means for adjusting the optimal advice based on the emotional state, means for transmitting the generated advice to the user terminal, and means for displaying the advice on the user terminal. This makes it possible to provide advice to improve the appearance of a dish that takes into account the user's emotional state.

[1812] The "means for receiving food images" refers to an interface for users to upload photos of food taken by them to the system.

[1813] "Means for analyzing received images and extracting characteristics of food" refers to algorithms or software that analyze received images of food and extract characteristics such as the type of food, ingredients used, and presentation.

[1814] "Means for generating advice to improve the appearance of food based on the analysis results" refers to a mechanism for generating specific advice to improve the visual appearance of food based on the analyzed characteristics of the food.

[1815] "Means for recognizing the user's emotional state" refers to a camera, microphone, and analysis algorithm for analyzing the user's facial expressions and voice to recognize the psychological emotional state at that time.

[1816] "Means for adjusting optimal advice based on emotional state" refers to a mechanism for adjusting advice to improve the appearance of food according to the recognized emotional state of the user and providing it in an optimal form for each individual user.

[1817] "Means for transmitting the generated advice to the user terminal" refers to the communication means or protocol for transmitting the generated advice to the user's terminal such as a smartphone or PC.

[1818] "Means for displaying advice on a user terminal" refers to an application or web interface for displaying received advice on the user's terminal.

[1819] This invention is a system that analyzes images of food, generates advice for improving the appearance, and combines it with an emotion engine that recognizes the user's emotional state. This system provides optimal advice based on the user's emotional state, improves the appearance of the food, and increases user satisfaction.

[1820] System Overview

[1821] This system mainly uses the following hardware and software.

[1822] 1. Receiving images

[1823] Users take photos of their food using their smartphone or PC camera and upload them to the system via an application or web interface.

[1824] 2. Image Analysis

[1825] The server receives photos of dishes uploaded by users and temporarily stores them. The stored images are then passed to the generative AI module. This can be done using an S3 bucket on Amazon Web Services (AWS).

[1826] The generative AI uses image analysis algorithms to analyze the type of food, the ingredients used, the presentation, etc. It uses TensorFlow models to perform a detailed analysis of the elements in the image.

[1827] 3. Emotional Recognition

[1828] The device uses a camera and microphone to input the user's facial expressions and voice into the emotion engine. The camera is used to analyze facial expressions, and the microphone is used to collect the content and tone of speech. It can use iPhone's Face ID or Android's facial recognition function.

[1829] The emotion engine analyzes and recognizes emotions from the user's facial expressions and voice, and sends the data to a server. The analysis is performed using Microsoft Azure's Emotion API. It also learns the user's individual reaction patterns from past data.

[1830] 4. Generating Advice

[1831] The generative AI combines image analysis and emotion engine data to generate specific advice to improve the appearance of the dish. Examples include "garnish with green onions," "serve the rice in a mountain shape," and "use a blue plate." Based on the information from the emotion engine, the advice is tailored to the user's emotional state. For example, if the user is feeling down, the AI ​​will provide gentle, easy-to-understand advice.

[1832] 5. Submitting Advice

[1833] The server receives the advice data from the generation AI and prepares it for transmission to the user device. Data transfer is managed using AWS S3 and DynamoDB.

[1834] 6. Displaying Advice

[1835] The device analyzes the advice data received from the server and displays it to the user through an application or web interface. Specifically, advice such as "garnish with parsley," "serve rice in a mountain shape," and "use a blue plate" is displayed on a smartphone app or PC web browser.

[1836] Specific examples

[1837] Example 1: Upload a photo of curry rice

[1838] User operations

[1839] The user launches the smartphone app, takes a photo of the curry rice, and taps the "Upload" button to send the photo to the application server.

[1840] Server Processing

[1841] The server receives the photos and temporarily stores them in an AWS S3 bucket, after which the stored photos are passed to the generative AI module.

[1842] Collaboration between generative AI and emotion engine

[1843] Generation AI

[1844] The generative AI uses TensorFlow to analyze the characteristics of the food in the photo (for example, the color of the curry or the height of the presentation).

[1845] Emotion Engine

[1846] The emotion engine uses Microsoft Azure's Emotion API to recognize emotions from the user's facial expressions and voice, and sends the recognition results to the generation AI.

[1847] Generating and Sending Advice

[1848] Generation AI

[1849] The generative AI combines emotion data with dish characteristics data to generate specific advice. For example, it might include suggestions such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate." If the user is feeling down, it might also suggest "adding cheerful colors."

[1850] server

[1851] The server sends the generated advice to the user's device, efficiently queuing messages using AWS SQS.

[1852] Terminal display

[1853] Terminal

[1854] The user's smartphone or PC will then display the received advice, such as "garnish with parsley," "serve the rice in a mound," and "use a blue plate."

[1855] Prompt Sentence Examples

[1856] "Analyze a photo of curry rice and generate specific advice on how to make it look better. If the user's emotional state is depressed, add some uplifting advice."

[1857] This system allows users to easily improve the appearance of their food without any specialized knowledge, and also provides optimal advice based on their emotions, further increasing the enjoyment and satisfaction of home cooking.

[1858] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1859] Step 1: Receiving the image

[1860] (input)

[1861] Users take photos of their food using the camera on their smartphone or PC and upload them to the system via an application or web interface.

[1862] (process)

[1863] When the user taps the "Upload" button, the captured image is sent to the cloud (e.g., AWS S3). The server confirms receipt of the image and temporarily stores it.

[1864] (output)

[1865] Image files of food stored on the server.

[1866] (Specific actions)

[1867] When a user uploads a photo of the food they have taken with their smartphone, the photo is transferred to the server, where it is temporarily stored.

[1868] Step 2: Analyze the images

[1869] (input)

[1870] The server receives the temporarily stored image files of the food.

[1871] (process)

[1872] The server passes the received image to the generative AI module, which uses image analysis algorithms to analyze the type of food in the image, the ingredients used, the presentation, etc. For example, TensorFlow can be used to perform a detailed analysis of each element in the image.

[1873] (output)

[1874] Analyzed food feature data (e.g., ingredient list, presentation balance, color, etc.).

[1875] (Specific actions)

[1876] The server passes the saved image to a generative AI model, which uses TensorFlow to analyze features in the image and extract detailed data about the dish.

[1877] Step 3: Recognize emotions

[1878] (input)

[1879] The device collects the user's facial and voice data using a camera and microphone.

[1880] (process)

[1881] Data collected from the camera and microphone is input into the emotion engine, which uses Microsoft Azure's Emotion API to analyze and recognize the user's emotional state from their facial expressions and voice. It also references past data to learn the user's individual reaction patterns and improve accuracy.

[1882] (output)

[1883] Recognized user emotion data (happiness, sadness, surprise, etc.).

[1884] (Specific actions)

[1885] When a user uploads an image of a dish, the device's camera and microphone collect data on the user's facial expressions and voice, which is then passed to the emotion engine for analysis.

[1886] Step 4: Generating Advice

[1887] (input)

[1888] The generative AI receives analyzed food feature data and recognized user emotion data.

[1889] (process)

[1890] The generative AI combines the dish's feature data with emotion data to generate specific advice for improving its appearance. For example, it might include "garnish with green onions," "serve the rice in a mountain shape," or "use a blue plate." If the user is feeling down, it might also provide empathetic advice such as "add some cheery colors."

[1891] (output)

[1892] Specific advice generated.

[1893] (Specific actions)

[1894] The generative AI model generates appropriate advice based on the characteristics of the dish and the user's emotions, including specific methods to improve the appearance of the dish.

[1895] Step 5: Submitting Advice

[1896] (input)

[1897] The server receives the specific advice received from the generating AI.

[1898] (process)

[1899] The server prepares to send the generated advice data to the user device, using AWS SQS or similar to efficiently queue messages and transfer data.

[1900] (output)

[1901] Advice data sent to the user terminal.

[1902] (Specific actions)

[1903] The server receives the generated advice and transmits it to the user's device using an efficient message queuing technique.

[1904] Step 6: Viewing Advice

[1905] (input)

[1906] The terminal receives the advice data received from the server.

[1907] (process)

[1908] The device analyzes the received advice data and displays it to the user through an application or web interface in an easy-to-read format that is easy for the user to understand.

[1909] (output)

[1910] Specific advice displayed on the user's device.

[1911] (Specific actions)

[1912] The device analyzes the advice received from the server and displays advice such as "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate" on the smartphone screen or PC web browser.

[1913] (Application example 2)

[1914] 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."

[1915] There is a need for a simple method to improve the appearance of food without specialized knowledge. There is also a need for a method to provide a more satisfying experience by taking into account the user's emotional state when receiving advice on how to improve the appearance of food.

[1916] 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.

[1917] In this invention, the server includes means for receiving an image of a dish, means for analyzing the received image to extract characteristics of the dish, means for recognizing the emotional state of the user, means for generating advice to improve the appearance of the dish based on the analysis result and the emotional state, means for transmitting the generated advice to the user terminal, and means for displaying the advice on the user terminal. This makes it possible to easily improve the appearance of a dish without specialized knowledge and receive optimal advice according to the user's emotional state.

[1918] The "means for receiving food images" is a function for transmitting and receiving food images taken by the user to the system.

[1919] The "means for analyzing received images and extracting characteristics of food" is a function that applies an image processing algorithm to received images of food to identify characteristics such as the type of food, presentation, and color.

[1920] The "means for recognizing the user's emotional state" is a function for analyzing the user's emotions from their facial expressions and voice and determining their emotional state.

[1921] The "means for generating advice to improve the appearance of food based on the analysis results and the user's emotional state" is a function that combines the analyzed characteristics of food with the user's emotional state to create advice to optimally improve the appearance of food.

[1922] The "means for transmitting generated advice to a user terminal" is a function for transmitting advice generated within the system to a terminal such as a user's smartphone or tablet.

[1923] The "means for displaying advice on the user terminal" is a function for visually displaying advice received on the user terminal.

[1924] The system related to this invention is an application that allows food delivery service providers (restaurants and cafes) to upload photos of their dishes and receive advice on how to improve their presentation. The system also recognizes the user's emotional state and provides optimal advice. Below, we will explain the detailed program processing and hardware and software used in this system.

[1925] Program Overview

[1926] Upload a photo

[1927] A user takes a photo of a dish using the smartphone camera and sends it to the server. The application can use the smartphone's camera API or network communication API (e.g., Camera2 API or Volley library for Android).

[1928] Image analysis

[1929] The server analyzes the received food images using a generative AI model, which includes advanced image analysis algorithms such as OpenAI's DALL-E and CLIP models, to extract data about the food's characteristics and appearance.

[1930] emotion recognition

[1931] The system utilizes the smartphone's camera and microphone to recognize the user's emotions. The emotion recognition engine uses existing emotion recognition software such as the Affectiva SDK. Emotional data is extracted from the user's facial expressions and voice and sent to the server.

[1932] Advice Generation

[1933] The generative AI generates advice by combining image analysis data of the food and user emotion recognition data. For example, it generates specific advice such as "add brightly colored vegetables" or "change the plate to a different color."

[1934] Sending and displaying advice

[1935] The server sends the generated advice to the user's device, where the smartphone application displays the advice. The application uses a user interface (UI) to present the advice in an easy-to-understand manner.

[1936] Specific examples

[1937] Example 1: Upload a photo of curry rice

[1938] User operations

[1939] A restaurant employee launches the app and takes a photo of the curry rice.

[1940] Tap the "Upload" button to send the photo to the application server.

[1941] Server Processing

[1942] The server receives the photos and stores them temporarily.

[1943] Pass the saved photo to the generation AI module.

[1944] Collaboration between generative AI and emotion engine

[1945] Generation AI:

[1946] The generative AI analyzes the photo and extracts the characteristics of the curry rice (for example, the color of the curry, the height of the serving, etc.).

[1947] Emotion Engine:

[1948] The emotion engine analyzes employees' facial expressions and voices to recognize their emotional state (e.g., tired, happy, etc.).

[1949] The recognized emotion data is sent to the generation AI.

[1950] Generating and Sending Advice

[1951] Generation AI:

[1952] Based on emotion data and food feature data, specific advice such as "garnish with parsley," "serve the rice in a mountain shape," and "use a blue plate" is generated.

[1953] If employees are tired, offer them some quick and easy advice.

[1954] server:

[1955] The server transmits the generated advice to the user's terminal.

[1956] Terminal display

[1957] Device:

[1958] Advice such as "Add parsley," "Serve the rice in a mountain shape," and "Use blue plates" will be displayed on employees' smartphones.

[1959] Example prompt sentences (examples of input to generative AI models)

[1960] Prompt statement:

[1961] Analyze the following food photo and offer specific suggestions for improving presentation. Adjust your suggestions based on your employees' emotional state.

[1962] Food photos:

[1963] [Image of curry rice]

[1964] Employee emotional state:

[1965] [Tired]

[1966] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1967] Step 1:

[1968] A user takes a photo of a dish using the smartphone camera.

[1969] Input: Physical image of the dish

[1970] Output: Digital image data

[1971] Specific behavior: The user launches the smartphone app and uses the camera to take a photo of the food.

[1972] Step 2:

[1973] The terminal transmits the photograph of the food taken to the application server.

[1974] Input: Digital image data

[1975] Output: Upload image data to the server

[1976] Specific operation: The device uses a network communication API to send image data to the server.

[1977] Step 3:

[1978] The server temporarily stores the received image and passes it to the generation AI module.

[1979] Input: Image data uploaded to the server

[1980] Output: Transfer of image data to the generative AI module

[1981] Specific operation: The server uses the storage function to save the data, and then passes the image data to the generation AI module.

[1982] Step 4:

[1983] The generative AI analyzes the image and extracts the characteristics of the dish.

[1984] Input: Image data passed to the generation AI

[1985] Output: Extracted food feature data

[1986] How it works: Generative AI (e.g., OpenAI's DALL-E or CLIP models) uses image analysis algorithms to identify features such as food type, presentation, and color.

[1987] Step 5:

[1988] The device uses a camera and microphone to recognize the user's emotional state and transmits the emotional data to a server.

[1989] Input: User's facial expressions and voice

[1990] Output: Upload emotion data to the server

[1991] Specific operation: The device uses an emotion recognition engine (e.g., Affectiva SDK) to analyze the user's facial expressions and voice to determine their emotional state. The result is then sent to the server via a network communication API.

[1992] Step 6:

[1993] Generative AI combines image analysis data and emotion recognition data to generate advice.

[1994] Input: Extracted food feature data and user emotion data

[1995] Output: Advice data for improving appearance

[1996] Specific behavior: The generative AI makes adjustments based on the prompt text and generates specific advice (e.g., "garnish with parsley," "serve the rice in a mound shape," "use a blue plate") based on the analysis results and emotional data.

[1997] Step 7:

[1998] The server transmits the generated advice to the user terminal.

[1999] Input: Advice data generated by generative AI

[2000] Output: Sending advice data to the user's terminal

[2001] Specific operation: The server uses a network communication API to send advice data to the user terminal.

[2002] Step 8:

[2003] The terminal displays the received advice through a user interface.

[2004] Input: Submitted advice data

[2005] Output: Visually displayed advice

[2006] Specific operation: The device displays the received advice using the user interface (UI) and provides it to the user.

[2007] 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.

[2008] 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.

[2009] 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.

[2010] 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.

[2011] 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.

[2012] 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.

[2013] 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).

[2014] 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.

[2015] 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."

[2016] 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.

[2017] 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).

[2018] 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.

[2019] 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.

[2020] 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.

[2021] 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.

[2022] 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.

[2023] 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.

[2024] 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.

[2025] 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.

[2026] 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.

[2027] 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.

[2028] The following is further disclosed regarding the above embodiment.

[2029] (Claim 1)

[2030] means for receiving an image of a dish;

[2031] A means for analyzing the received image and extracting characteristics of the food;

[2032] A means for generating advice for improving the presentation of food based on the analysis results;

[2033] means for transmitting the generated advice to a user terminal;

[2034] means for displaying advice on a user terminal;

[2035] A system including:

[2036] (Claim 2)

[2037] 2. The system of claim 1, wherein the means for extracting food characteristics uses an image analysis algorithm.

[2038] (Claim 3)

[2039] 10. The system of claim 1, wherein the advice for improving the presentation of the dish includes suggestions regarding additional ingredients, presentation methods, and the color and shape of the plate to use.

[2040] "Example 1"

[2041] (Claim 1)

[2042] a means for users to upload images of dishes;

[2043] A means for storing the image of the dish received by the server;

[2044] a means for transmitting the stored image data to the generative AI model;

[2045] A means by which the generative AI model extracts food features using image analysis algorithms; and

[2046] A means for generating advice for improving the appearance of food based on the analysis results;

[2047] means for transmitting the generated advice from the server to the user terminal;

[2048] means for displaying the advice on the user terminal;

[2049] A system including:

[2050] (Claim 2)

[2051] 10. The system of claim 1, wherein the generative AI model uses an image analysis algorithm.

[2052] (Claim 3)

[2053] 2. The system of claim 1, wherein the advice for improving the appearance of the dish includes suggestions regarding the addition of ingredients, presentation methods, and the color and shape of containers to use.

[2054] "Application Example 1"

[2055] (Claim 1)

[2056] means for receiving an image of a dish;

[2057] A means for analyzing the received image and extracting characteristics of the food;

[2058] A means for generating advice for improving the presentation of food based on the analysis results;

[2059] means for transmitting the generated advice to a user terminal;

[2060] means for displaying specific advice on the user terminal for improving the appearance of the dish;

[2061] A system including:

[2062] (Claim 2)

[2063] 2. The system of claim 1, wherein the means for extracting food characteristics uses an image analysis algorithm.

[2064] (Claim 3)

[2065] 10. The system of claim 1, wherein the advice for improving the presentation of the dish includes suggestions regarding additional ingredients, presentation methods, and the color and shape of the plate to use.

[2066] (Claim 4)

[2067] 2. The system of claim 1, wherein the means for receiving the image of the dish is executed via a smart device used in the physical store.

[2068] (Claim 5)

[2069] The system of claim 1, which uses a generative AI model to analyze images and generate advice to improve the appearance of food using prompt sentences.

[2070] "Example 2: Combining Emotion Engines"

[2071] (Claim 1)

[2072] means for receiving an image of a dish;

[2073] A means for analyzing the received image and extracting characteristics of the food;

[2074] A means for generating advice for improving the presentation of food based on the analysis results;

[2075] means for recognizing the emotional state of a user;

[2076] a means of tailoring optimal advice based on emotional state;

[2077] means for transmitting the generated advice to a user terminal;

[2078] means for displaying advice on a user terminal;

[2079] A system including:

[2080] (Claim 2)

[2081] 10. The system of claim 1, further comprising means for extracting food characteristics using an image analysis algorithm.

[2082] (Claim 3)

[2083] 10. The system of claim 1, wherein the advice for improving the presentation of the dish includes suggestions regarding additional ingredients, presentation methods, and the color and shape of the plate to use.

[2084] "Application example 2 when combining emotion engines"

[2085] (Claim 1)

[2086] means for receiving an image of a dish;

[2087] A means for analyzing the received image and extracting characteristics of the food;

[2088] means for recognizing the emotional state of a user;

[2089] means for generating advice for improving the presentation of the food based on the analysis results and the emotional state;

[2090] means for transmitting the generated advice to a user terminal;

[2091] means for displaying advice on a user terminal;

[2092] A system including:

[2093] (Claim 2)

[2094] 2. The system of claim 1, wherein the means for extracting food characteristics uses an image analysis algorithm.

[2095] (Claim 3)

[2096] 10. The system of claim 1, wherein the advice for improving the presentation of the dish includes suggestions regarding additional ingredients, presentation methods, and the color and shape of the plate to use. [Explanation of symbols]

[2097] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving an image of a dish; A means for analyzing the received image and extracting characteristics of the food; A means for generating advice for improving the presentation of food based on the analysis results; means for transmitting the generated advice to a user terminal; means for displaying advice on a user terminal; A system including:

2. 10. The system of claim 1, wherein the means for extracting food characteristics uses an image analysis algorithm.

3. 2. The system of claim 1, wherein the advice for improving the appearance of the dish includes suggestions regarding the addition of ingredients, the presentation method, and the color and shape of the plate to be used.

Images