system

Abstract

We provide the system. [Solution] Image analysis means that receives image data acquired from a user terminal and converts said image data into text data, An analytical means for analyzing preference information obtained from users and inferring the user's food preferences based on said preference information, A generation means that generates an appropriate meal menu based on text data obtained by the image analysis means and preference information obtained by the analysis means, A system including a search means for searching for cooking videos related to the generated meal menu and providing information on how to access said cooking videos.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In busy families such as dual-income families with children, the task of considering daily meal menus has become a heavy burden. Selecting a menu that suits the family's hobbies and preferences while considering the ingredients in the refrigerator and the special sale information at the supermarket is very time-consuming and causes a waste of time. In addition, although it is required to utilize ingredients without waste, it is difficult to efficiently use ingredients with existing recipe search methods.

Means for Solving the Problems

[0005] This invention includes an image analysis means that receives image data from a user terminal and analyzes the image to obtain information about ingredients. Furthermore, it includes an analysis means that analyzes past preference information transmitted by the user and infers the user's food preferences based on that information. This provides a generation means that generates an optimal meal menu based on the ingredients present in the user's refrigerator and their preferences. In addition, by constructing a system that includes a search means that searches for cooking videos related to the generated meal menu and provides them to the user, it reduces food waste and enables efficient meal preparation.

[0006] A "user terminal" is an electronic device that has the function of inputting and transmitting information, and mainly refers to smartphones and tablets.

[0007] "Image data" refers to visual information captured or acquired by a user, represented in digital format.

[0008] "Text data" refers to digital data that represents visual information, audio information, and other data as strings of characters.

[0009] "Image analysis means" refers to technical means that receive image data, identify the objects and information depicted therein, and convert them into text data.

[0010] "Preference information" refers to information about the types of ingredients and dishes a user prefers, inferred from their past behavior and preferences.

[0011] "Analysis methods" refer to technical techniques for processing acquired preference information and identifying user interests and tendencies.

[0012] "Generation method" refers to a technology that has the function of automatically selecting the optimal recipe or menu for the user based on the analyzed data.

[0013] "Search methods" refer to techniques for finding related information, particularly cooking videos and additional recipes, from the internet and databases based on the generated menu.

[0014] A "cooking video" is video content that visually demonstrates the steps and methods of cooking, and serves as a reference for users when they are cooking. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0018] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0020] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] The present invention relates to a system that streamlines user ingredient management and menu suggestion, and specific embodiments thereof are shown below.

[0037] The user uses a smartphone or other device to take a picture of the food in the refrigerator and sends the image to an account in a designated application or messenger service. The device then transfers the image data to the system's server.

[0038] The server processes the received image data using image analysis tools and extracts specific ingredients as text data. This analysis process applies existing image recognition techniques to recognize objects in the image and identify each ingredient.

[0039] Next, the server refers to a database containing the user's past preferences and uses analytical tools to identify the user's dietary preferences. For example, it can confirm from the user's previously saved recipes and chat history that they frequently choose spicy foods.

[0040] The server integrates ingredient information obtained through image analysis and preference information obtained through analysis, and uses a generation tool to create an optimal meal menu for the user. This generated menu takes into account the selected ingredients and the user's preferences.

[0041] Furthermore, the server uses search mechanisms to find cooking videos related to the generated menu from a database or online platform and provides the search results to the user's terminal. In this way, users can check the details of the suggested recipe on LINE or a dedicated application, and visually learn the specific cooking procedures by playing the cooking videos.

[0042] For example, if a user has chicken and broccoli in their refrigerator, they take pictures of these ingredients and send them to the system. The server analyzes these images to recognize the ingredients and learns from the user's past preferences that they like spicy food. As a result, the server suggests a menu item called "Spicy Chicken and Broccoli Stir-fry" and provides the user with a video link showing how to prepare it. The user accepts this suggestion and can smoothly begin cooking while following the recipe.

[0043] In this way, the present invention provides support that allows users to effectively utilize the ingredients they possess and easily prepare dishes that suit their individual preferences.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users take pictures of the food items in their refrigerator using their device and send them to the system. This transmission is done via LINE messages or a dedicated application.

[0047] Step 2:

[0048] The terminal transfers the transmitted image data to the server using a secure protocol. The transmission process includes optimization based on the image data's resolution and format.

[0049] Step 3:

[0050] The server processes the received image data using image analysis tools to identify objects in the image and extract the names of the ingredients as text data. For example, an AI-based image recognition algorithm is applied to obtain information such as "chicken" and "broccoli."

[0051] Step 4:

[0052] The server retrieves user preference information from the database and performs preference analysis based on past data. This analysis utilizes the user's past choices, purchase history, and saved recipes.

[0053] Step 5:

[0054] The server uses a generation mechanism to select the optimal menu based on the analyzed ingredient information and preference data. The generated menu includes options customized to the user's preferences.

[0055] Step 6:

[0056] The server uses search engines to search the internet and affiliated databases for cooking videos related to the generated menu, and retrieves relevant video and recipe URLs.

[0057] Step 7:

[0058] The server organizes the selected recipes and cooking video information and sends it to the device as a suggested menu. This information is then provided to the user via LINE message or in-app notification.

[0059] Step 8:

[0060] Users review the suggested menu received from their device, play the linked video, and visually confirm the specific cooking methods. This clarifies the cooking process and allows them to proceed with cooking quickly.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In modern households, it's crucial to effectively manage the ingredients in the refrigerator and suggest meal menus that suit the family's preferences. However, traditional methods require users to individually check ingredients, consider preferences, and search for recipes, making it time-consuming and difficult to efficiently create optimal menus.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes an image processing device that receives digital images acquired from the user's information device and converts the digital images into text data; an evaluation device that evaluates preference data acquired from the user and infers the user's food preferences based on the preference data; a generation device that generates an appropriate meal plan based on the text data from the image processing device and the preference data from the evaluation device; and a search device that searches for cooking videos related to the generated meal plan and provides access information to the cooking videos. This makes it possible to easily generate and provide efficient and optimal meal menus tailored to the ingredients and preferences of the user.

[0066] "User information device" refers to an electronic device used by the user, such as a smartphone, tablet, or personal computer, that has the function of acquiring and transmitting images of food ingredients.

[0067] A "digital image" refers to non-analog image data acquired by a camera or scanner and processed by a computer or other device.

[0068] "Text data" refers to text information stored in digital format, including ingredient names and other text information extracted through image analysis.

[0069] An "image processing device" refers to a hardware or software configuration that receives a digital image as input, analyzes it, and converts it into text data.

[0070] "Preference data" refers to information that indicates a user's preferences and tastes regarding food, and includes past eating history and saved preference information.

[0071] An "evaluation device" is a component of a system that analyzes preference data and performs processing to predict user preferences, and includes a predictive algorithm.

[0072] A "generation device" refers to a device or program that integrates information obtained from an image processing device and an evaluation device to generate an optimal meal plan for the user.

[0073] "Cooking videos" refer to video content that visually demonstrates how to prepare a specific meal, and are accessible on online platforms or databases.

[0074] A "search device" refers to a device or system that searches for cooking videos related to a provided meal plan and provides users with access information for viewing them.

[0075] This invention is a system for providing an optimal meal plan based on the ingredients a user possesses and their personal preferences. Specifically, the user uses an information device (such as a smartphone or tablet) to photograph the ingredients in their refrigerator. The device then transmits the captured digital image to the system's server.

[0076] The server receives this digital image via an image processing device and converts it into text data. Existing image recognition technologies such as TENSORFLOW® and OpenCV are used in this process. The names of the ingredients extracted through image analysis are then compared with an existing food database to improve accuracy.

[0077] Furthermore, the server analyzes user preference data through an evaluation device. This evaluation device refers to data including past meal history and conversation history to infer the user's preferences. Natural language processing technology is used to analyze preference trends from text data.

[0078] Subsequently, the server uses a generation device to integrate ingredient information from the image processing device and preference information from the evaluation device, and generates an optimal meal menu using an AI model. The generated menu can also be adjusted to take into account promotional information based on the user's location.

[0079] Finally, the server uses a search device to retrieve cooking videos from online platforms and dedicated databases, and provides relevant video links to the user's device. The user can then review the suggested recipes and videos and easily begin cooking.

[0080] For example, if a user has chicken and broccoli in their refrigerator, they take a picture of them and send it to the system. The server recognizes the ingredients and learns that the user likes spicy food. The server then generates a menu item called "Spicy Chicken and Broccoli Stir-fry" and provides the user with a video link showing how to prepare it.

[0081] An example of a prompt message might be, "Please suggest a recipe for a spicy dish that can be made with chicken and broccoli that I have in my refrigerator. Please also provide specific cooking instructions and a link to a helpful video." In this way, the present invention enables convenient and personalized meal preparation for the user.

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

[0083] Step 1:

[0084] The user uses an information device to photograph the food items inside the refrigerator. The terminal sends the captured digital image to the system's server. In this case, the input is a digital image, and the output is the transmission of image data to the server.

[0085] Step 2:

[0086] The server passes the received digital image as input to the image processing unit. The image processing unit analyzes the image using TensorFlow or OpenCV to recognize the food ingredients. The output of this process is text data containing the names of the food ingredients. Specifically, the pixel data in the image is analyzed using an algorithm to identify the outlines and shapes of the food ingredients.

[0087] Step 3:

[0088] The server uses the text data obtained through image processing to refer to the food database and match the objects. This uniquely identifies the names of the ingredients. The output of this step is a list of ingredients.

[0089] Step 4:

[0090] The server retrieves user preference data from a database and inputs it into the evaluation device. The evaluation device uses natural language processing technology to analyze past meal and conversation history to predict the user's food preferences. The input is preference data, and the output is information about the predicted food preferences.

[0091] Step 5:

[0092] The server passes the output of the image processing device and the output of the evaluation device to the generation device. The generation device uses an AI model to integrate this information and generate an optimal meal menu. In this case, the input is a list of ingredients and preference information, and the output is the generated meal menu.

[0093] Step 6:

[0094] The server sends cooking videos related to the generated meal menu to the search device. The search device searches online platforms and finds relevant video links. The input is the meal menu, and the output is the video link.

[0095] Step 7:

[0096] The server sends the found video link to the terminal, and the user reviews the provided recipe and video. The input for this step is the video link, and the output is the provision of visual information to the user. This allows the user to learn the specific cooking steps and begin cooking.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] In today's food retail and restaurant industries, there is a demand for quick and accurate responses to diverse customer needs. However, providing personalized recommendations based on customer preferences and purchase history is difficult with traditional methods. Furthermore, inventory management and customer information provision are labor-intensive, necessitating increased efficiency. Therefore, there is a need for an effective system that understands ingredient usage and provides optimal product recommendations and meal plans for individual customers.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes analysis means, prediction means, generation means, search means, and presentation means. This enables real-time inventory management using smart glasses and the presentation of optimal product and meal combinations tailored to customer preferences.

[0102] "Analysis means" refers to technology for converting image data acquired from a user terminal into text data.

[0103] "Inference methods" refer to technologies used to analyze and infer a user's food preferences based on preference information obtained from the user.

[0104] "Generation method" refers to a technology for creating an appropriate meal plan based on analyzed text data and inferred preference information.

[0105] "Search method" refers to technology for searching for instructional videos related to the generated meal plan and providing access information to them.

[0106] "Presentation means" refers to technology for directly presenting generated plans and search results to customers through a display device.

[0107] This invention provides a system that uses smart glasses in physical stores to streamline food management and product recommendations to customers. Specifically, it uses smart glasses as a server and user terminal to perform processing according to the following procedure.

[0108] The server uses image recognition software (e.g., OpenCV) as an analysis tool to receive video data of the food shelves transmitted from the smart glasses, analyze it, and convert it into text data. This process makes it possible to understand the types and quantities of resources on the shelves.

[0109] Next, the server uses inference tools to extract customer preference information from the database and uses data analysis software (e.g., Python's Pandas library) to identify the customer's food preferences. For example, it analyzes the products and taste trends the customer has chosen in the past.

[0110] The generation method generates optimal product suggestions and meal plans for the customer based on text data obtained from the analysis method and customer preference information identified by the inference method. Using a generation AI model (e.g., ChatGPT®), it creates product configuration proposals in natural language and displays them on the smart glasses' display via the presentation method.

[0111] As an example, when a store staff member wearing smart glasses scans potatoes and carrots on a shelf, a message such as "Today's recommendation is a spicy curry made with potatoes and carrots" appears on the display. An example of a prompt in this case would be, "Generate a spicy recipe using potatoes and carrots."

[0112] In this way, the system of the present invention enables real-time food inventory management and personalized product recommendations to improve the customer experience in physical stores.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The device (smart glasses) photographs the food items on the shelf and acquires image data. The captured image data is automatically sent to a server via the network. The input for this step is the video of the shelf, and the output is the image data sent to the server.

[0116] Step 2:

[0117] The server processes the received image data using analysis tools. Image recognition software (e.g., OpenCV) is used to recognize objects in the image and convert their corresponding resource names into text. The input for this step is the image data sent from the terminal, and the output is the text data of the recognized resource names.

[0118] Step 3:

[0119] The server extracts customer preference information from the database using inference methods. It then uses data analysis software (e.g., Python's Pandas library) to analyze past purchase history and preference patterns. The input is a user ID, and the output is data on the customer's preference patterns.

[0120] Step 4:

[0121] The server uses a generation method to generate optimal product suggestions based on the analyzed text data and inferred preference patterns. It uses a generation AI model (e.g., ChatGPT) to generate suggestion text in natural language. The input for this step is the text data of resource names and customer preference patterns, and the output is the generated suggestion text.

[0122] Step 5:

[0123] The server sends the generated suggestion text to the terminal. The terminal's display shows information about the suggested products and meal plans. The input is the generated suggestion text, and the output is the information displayed on the terminal's display.

[0124] Step 6:

[0125] The user (store staff) makes product and dish recommendations to customers based on the information displayed on the smart glasses' screen. This enables personalized information delivery to customers. In this step, the user's understanding of what they see on the display is the input, and the explanation given to the customer is the output.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] This invention relates to a food ingredient management and cooking menu suggestion system that takes into account the user's emotional state, and a specific embodiment thereof is shown below.

[0128] The user accesses the system via a device, takes pictures of the food in the refrigerator, and sends them to the server through an application. Along with the image data, the device can also acquire and send additional data to the server, such as audio and facial expressions, to understand the user's emotions.

[0129] The server processes the received image data using image analysis tools and extracts the names of the ingredients as text data. In this analysis process, advanced image recognition algorithms are used to identify the ingredients in the image.

[0130] Next, the server retrieves user preference information from the database and analyzes the user's eating habits using past data. This allows it to infer what kinds of ingredients and dishes the user prefers.

[0131] In addition, the emotion engine processes the transmitted emotion data using emotion analysis algorithms to evaluate the user's current emotional state. For example, it analyzes the tone of voice from audio data to determine whether the user is relaxed or stressed.

[0132] The server further considers image analysis data, preference information, and emotional states obtained from the emotion engine to create an appropriate meal menu using a generation tool. Menu selection also incorporates special offer information based on the user's location and seasonal ingredient information.

[0133] Furthermore, based on the user's emotional state, recipes using ingredients with relaxation effects, or dishes that provide energy, can be selected. This allows for the suggestion of more personalized menus.

[0134] The server then searches for cooking videos related to the suggested menu and sends the necessary access information to the user's terminal. The user can view the suggested menu and video links they receive, and by checking the specific cooking methods, they can confidently proceed with preparing the meal.

[0135] For example, if a user's photo includes chicken and broccoli, and voice analysis indicates the user is experiencing some stress, the server will suggest a stress-relieving dish such as "herb-grilled chicken and broccoli." Along with the recipe, it will provide a link to a video demonstrating the cooking process.

[0136] In this way, the present invention realizes a system that effectively utilizes the user's emotional state, preferences, and ingredients to provide appropriate and personalized cooking suggestions.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user takes photos of the food in the refrigerator and their own facial expression with their device, and sends the image data and additional emotion-related data to the system.

[0140] Step 2:

[0141] The terminal securely transfers food image data and emotion-related data such as voice and facial expressions to the server.

[0142] Step 3:

[0143] The server processes the received image data using image analysis tools to identify ingredients and convert them into corresponding text data.

[0144] Step 4:

[0145] The server retrieves information about the user from a preference database and uses analytical tools to infer the user's eating habits.

[0146] Step 5:

[0147] The server uses an emotion engine to analyze emotion-related data and evaluate the user's current emotional state. This evaluation takes into account factors such as voice tone and facial expressions.

[0148] Step 6:

[0149] The server uses image analysis, preference information, and emotional state data to generate a meal menu optimized for the user.

[0150] Step 7:

[0151] The server retrieves cooking videos and recipe information related to the most suitable menu from the internet and partner databases through search mechanisms.

[0152] Step 8:

[0153] The server organizes the suggested menu and links to related videos and sends them to the user's terminal.

[0154] Step 9:

[0155] The user checks the suggested menu information and video links on their device and begins cooking while referring to the selected recipe and video.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] Conventional ingredient management and menu suggestion systems struggled to provide personalized menu suggestions that took into account the user's emotional state. Furthermore, they were unable to appropriately combine local sale information and user preference data, failing to offer optimal cooking suggestions. Additionally, access to the correct cooking procedures for the suggested menus was limited, resulting in insufficient support for users to cook with confidence.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes an image analysis means for converting image data acquired from a user terminal into text data, an emotion analysis means for evaluating the emotional state based on emotion data acquired from the user, and a generation means for generating an appropriate menu based on preference information and emotional state. This enables personalized menu suggestions that take the user's emotional state into consideration, as well as appropriate access to cooking procedures.

[0161] A "user terminal" is an electronic device used by a user to input or retrieve data.

[0162] "Image data" refers to digital information used to visually represent an object.

[0163] "Text data" refers to digital information expressed as character data.

[0164] "Image analysis means" refers to an algorithm or device for analyzing image data and extracting information.

[0165] "Emotional analysis means" refers to an algorithm or device for processing emotional data such as voice and facial expressions to evaluate the user's emotional state.

[0166] "Preference information" refers to data about a user's preferences and tendencies.

[0167] A "generation method" is a mechanism or algorithm for creating new information or proposals based on specific data.

[0168] "Information provision means" refers to a device or process for efficiently providing users with the information they need.

[0169] "Food name" is a string of characters used to identify a food item.

[0170] "Local information" refers to information related to a specific geographical location.

[0171] This invention is a system for suggesting personalized meal menus based on a user's emotional state and preference information. This system consists of a user terminal, a server, and a network connection environment. An embodiment of this system is described below.

[0172] The user takes pictures of food in the refrigerator using an electronic device they use daily, i.e., a user terminal. The terminal acquires image data of the food and, if necessary, simultaneously collects emotional data such as the user's voice and facial expressions. On the terminal, the camera function for acquiring high-resolution images and the microphone for properly recording audio data play important roles.

[0173] The terminal sends the acquired image data and emotion data to the server. The server analyzes the received image data using "image analysis means" and identifies food items in the image using an image recognition algorithm, such as a general machine learning library. Specifically, the image analysis engine recognizes the contours and shapes of objects and outputs the food names as text data.

[0174] Next, the server uses an emotion analysis engine to analyze the user's emotional data. From the voice data, it analyzes the tone and tempo of the voice to determine whether the user is relaxed or stressed. Specifically, a natural language processing algorithm is implemented to evaluate the emotional state. This process categorizes the user's mental state.

[0175] The server retrieves previously recorded user preference information from a database and performs analysis to predict the user's food preferences. This information plays a crucial role when using a generative AI model to suggest menu items.

[0176] Finally, the server synthesizes these analysis results and uses a generative AI model to create the optimal menu for the user. This process also takes into account local sale information and seasonal ingredient information. The server also searches for cooking videos related to the menu and provides links to them on the user's device. As a result, the user can easily cook based on the suggested menu.

[0177] As a concrete example, if a user has chicken and broccoli in their refrigerator and voice analysis indicates they are feeling stressed, a relaxing menu such as "herb-grilled chicken and broccoli" might be suggested. An example of a prompt in response to this suggestion would be, "Please suggest a stress-reducing dish using the chicken and broccoli in my refrigerator."

[0178] Thus, this invention provides a concrete means for personalizing cooking suggestions for users based on their emotional state and preferences.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The user takes pictures of food items in the refrigerator using their device. To do this, the user activates the camera function and positions the device appropriately to photograph the food items. The input is image data of the food items. Ideally, this image data should be as clear and high-resolution as possible at the time of shooting. The output is the acquired image data saved on the device.

[0182] Step 2:

[0183] The device collects user voice and facial expression data along with captured image data. This involves recording voice data using a microphone and capturing facial expression data with a camera. In addition, with the user's permission, it may also acquire various sensor data and user setting information. The inputs acquired are image data and voice / facial expression data related to emotions. As output, this data is sent to the server as a single package.

[0184] Step 3:

[0185] The server analyzes the image data received from the terminal. Specifically, it uses an image recognition algorithm to identify food items and extract text data of their names. This process involves, for example, the execution of a machine learning model using a specific framework. The input is the transmitted image data, and after its analysis, a list of food names is generated as output.

[0186] Step 4:

[0187] The server analyzes voice and facial expression data to evaluate the user's emotional state. In this process, an emotion analysis algorithm analyzes the tone and tempo of the voice and changes in facial expression to categorize emotions. The input is voice and facial expression data related to emotions, and the output is a classification of the user's emotional state.

[0188] Step 5:

[0189] The server retrieves user preference information from a database and infers the user's preferences based on that information. This allows for analysis of past records to determine what tastes and ingredients the user prefers. The input is past preference data stored in the database, and the output identifies the user's culinary preferences.

[0190] Step 6:

[0191] The server integrates image analysis results, emotional states, and preference information, and uses a generative AI model to generate an appropriate menu. The generated prompt sentences are input into the model, and a personalized meal menu is proposed. The process is executed based on the given conditions, and the proposed recipe is output.

[0192] Step 7:

[0193] The server searches online for relevant cooking videos based on the generated meal menu and provides the user with access information. This operation involves utilizing the API of the video platform. The input is the generated menu information, and the output is a link to the cooking video sent to the user's terminal.

[0194] (Application Example 2)

[0195] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0196] In recent years, there has been growing interest in obtaining more personalized services based on users' psychological states and subjective experiences. However, conventional ingredient management and menu suggestion systems do not take into account users' emotional states, and therefore cannot provide optimal suggestions for users. This makes it difficult to suggest meals that match the user's emotional state, resulting in a challenge in increasing overall satisfaction.

[0197] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0198] In this invention, the server includes: an analysis means that receives image information and emotional state acquired from a user terminal, converts the image information into text information, and analyzes the user's emotional state; an analysis means that analyzes preference information acquired from the user and infers suggestions that match the user's food preferences and emotions based on the preference information and emotional state; a generation means that generates appropriate meal suggestions based on the text information and emotional information from the analysis means and the preference information from the analysis means; and a search means that searches for cooking procedures related to the generated meal suggestions and provides access information to the cooking procedures. This enables more personalized meal suggestions that respond to the user's emotional state.

[0199] A "user terminal" is an electronic device that allows a user to input or receive data through user operation.

[0200] "Image information" refers to visual data acquired from the user's device and is used for recognizing food and other objects.

[0201] "Emotional state" refers to information that indicates the user's psychological mood and emotions, and is analyzed from voice and facial expressions.

[0202] "Textual information" refers to data in text format converted from image information, and is a data format that can be further processed.

[0203] "Analysis means" refers to a technical method or apparatus used to process acquired image information and emotional states.

[0204] "Preference information" refers to data based on a user's preferences and past choices, and is used to infer the user's tastes.

[0205] "Analysis methods" refer to technical techniques and mechanisms that use collected preference information and emotional states to analyze users' preferences and psychological states.

[0206] "Generation means" refers to a method or apparatus for creating meal suggestions tailored to the user based on analysis and interpretation results.

[0207] A "cooking procedure" is a series of instructions that show how to cook using ingredients, and it is provided in an easy-to-understand format.

[0208] A "search tool" refers to a technical system or device for finding and providing to the user information and materials related to the generated meal suggestions.

[0209] The system for carrying out this invention mainly consists of a server, a user terminal, and necessary software components. The user terminal is a device for acquiring image information and emotional states, and is equipped with a camera and a microphone. Input from the terminal is processed by analysis means on the server.

[0210] The server uses advanced image recognition software such as Google® Cloud Vision API and Amazon Rekognition to convert image information into text information and analyze the user's emotional state. The emotional state analysis utilizes Microsoft® Azure® Face API and Google Cloud Speech-to-Text, enabling the evaluation of the user's psychological state from their facial expressions and voice.

[0211] The analyzed data is then processed by an analysis tool on the server and combined with user preference information. This process utilizes a database such as MongoDB to manage historical preference data, and data analysis libraries such as pandas are used to create suggestions that match the user's food preferences and emotions. This generation tool then suggests meals tailored to the user.

[0212] Ultimately, the server searches video platforms such as YouTube for cooking instructions related to the proposed meal and provides the user with the necessary reference videos. This involves using APIs as a search tool to extract relevant content and provide feedback to the user.

[0213] For example, if a user takes a picture of chicken and broccoli using their device and expresses a desire to relax through voice, the server will suggest "herb-grilled chicken and broccoli" and provide a link to a video showing how to prepare this dish.

[0214] Examples of prompts to input into the generating AI model include "Please suggest a meal menu that utilizes my current emotional state to relieve stress" and "Please come up with a relaxing dish based on the ingredients I have in my refrigerator." This allows the user to receive suggestions that are appropriate to their mood at the time.

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

[0216] Step 1:

[0217] The user uses the camera and microphone on their device to collect image and audio data of the food items inside the refrigerator. The input consists of image and audio data. The user's device then transmits this data to the server.

[0218] Step 2:

[0219] The server analyzes the received image data using the Google Cloud Vision API or Amazon Rekognition. Data processing is performed to extract the names of the ingredients from the input images, and the output is text information converted into the names of the ingredients.

[0220] Step 3:

[0221] Next, the server processes the received audio data using Microsoft Azure Face API or Google Cloud Speech-to-Text to analyze the user's emotional state. At this stage, the audio data is used as input, and emotional information such as relaxed or stressed states is output through data calculations.

[0222] Step 4:

[0223] Based on the analysis results, the server retrieves relevant information from a database of user preferences and uses the pandas library as an analysis tool to generate meal menus suitable for the user's preferences and emotions. Past preference information and extracted emotion information are input, and suggested meal menus are output.

[0224] Step 5:

[0225] The server's search mechanism uses the generated meal menu to search for related cooking instruction videos via video service APIs such as YouTube. The input is the generated menu information, and the output is a link to the related video.

[0226] Step 6:

[0227] Finally, the server sends the suggested dish menu and a link to a cooking instruction video to the user's device. This information allows the user to check the specific cooking method in the video.

[0228] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0229] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0230] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0231] [Second Embodiment]

[0232] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0233] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0234] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0235] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0236] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0237] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0238] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0239] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0240] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0241] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0242] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0243] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0244] The present invention relates to a system that streamlines user ingredient management and menu suggestion, and specific embodiments thereof are shown below.

[0245] The user uses a smartphone or other device to take a picture of the food in the refrigerator and sends the image to an account in a designated application or messenger service. The device then transfers the image data to the system's server.

[0246] The server processes the received image data using image analysis tools and extracts specific ingredients as text data. This analysis process applies existing image recognition techniques to recognize objects in the image and identify each ingredient.

[0247] Next, the server refers to a database containing the user's past preferences and uses analytical tools to identify the user's dietary preferences. For example, it can confirm from the user's previously saved recipes and chat history that they frequently choose spicy foods.

[0248] The server integrates ingredient information obtained through image analysis and preference information obtained through analysis, and uses a generation tool to create an optimal meal menu for the user. This generated menu takes into account the selected ingredients and the user's preferences.

[0249] Furthermore, the server uses search mechanisms to find cooking videos related to the generated menu from a database or online platform and provides the search results to the user's terminal. In this way, users can check the details of the suggested recipe on LINE or a dedicated application, and visually learn the specific cooking procedures by playing the cooking videos.

[0250] For example, if a user has chicken and broccoli in their refrigerator, they take pictures of these ingredients and send them to the system. The server analyzes these images to recognize the ingredients and learns from the user's past preferences that they like spicy food. As a result, the server suggests a menu item called "Spicy Chicken and Broccoli Stir-fry" and provides the user with a video link showing how to prepare it. The user accepts this suggestion and can smoothly begin cooking while following the recipe.

[0251] In this way, the present invention provides support that allows users to effectively utilize the ingredients they possess and easily prepare dishes that suit their individual preferences.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] Users take pictures of the food items in their refrigerator using their device and send them to the system. This transmission is done via LINE messages or a dedicated application.

[0255] Step 2:

[0256] The terminal transfers the transmitted image data to the server using a secure protocol. The transmission process includes optimization based on the image data's resolution and format.

[0257] Step 3:

[0258] The server processes the received image data using image analysis tools to identify objects in the image and extract the names of the ingredients as text data. For example, an AI-based image recognition algorithm is applied to obtain information such as "chicken" and "broccoli."

[0259] Step 4:

[0260] The server retrieves user preference information from the database and performs preference analysis based on past data. This analysis utilizes the user's past choices, purchase history, and saved recipes.

[0261] Step 5:

[0262] The server uses a generation mechanism to select the optimal menu based on the analyzed ingredient information and preference data. The generated menu includes options customized to the user's preferences.

[0263] Step 6:

[0264] The server uses search engines to search the internet and affiliated databases for cooking videos related to the generated menu, and retrieves relevant video and recipe URLs.

[0265] Step 7:

[0266] The server organizes the selected recipes and cooking video information and sends it to the device as a suggested menu. This information is then provided to the user via LINE message or in-app notification.

[0267] Step 8:

[0268] Users review the suggested menu received from their device, play the linked video, and visually confirm the specific cooking methods. This clarifies the cooking process and allows them to proceed with cooking quickly.

[0269] (Example 1)

[0270] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0271] In modern households, it's crucial to effectively manage the ingredients in the refrigerator and suggest meal menus that suit the family's preferences. However, traditional methods require users to individually check ingredients, consider preferences, and search for recipes, making it time-consuming and difficult to efficiently create optimal menus.

[0272] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0273] In this invention, the server includes an image processing device that receives digital images acquired from the user's information device and converts the digital images into text data; an evaluation device that evaluates preference data acquired from the user and infers the user's food preferences based on the preference data; a generation device that generates an appropriate meal plan based on the text data from the image processing device and the preference data from the evaluation device; and a search device that searches for cooking videos related to the generated meal plan and provides access information to the cooking videos. This makes it possible to easily generate and provide efficient and optimal meal menus tailored to the ingredients and preferences of the user.

[0274] "User information device" refers to an electronic device used by the user, such as a smartphone, tablet, or personal computer, that has the function of acquiring and transmitting images of food ingredients.

[0275] A "digital image" refers to non-analog image data acquired by a camera or scanner and processed by a computer or other device.

[0276] "Text data" refers to text information stored in digital format, including ingredient names and other text information extracted through image analysis.

[0277] An "image processing device" refers to a hardware or software configuration that receives a digital image as input, analyzes it, and converts it into text data.

[0278] "Preference data" refers to information that indicates a user's preferences and tastes regarding food, and includes past eating history and saved preference information.

[0279] An "evaluation device" is a component of a system that analyzes preference data and performs processing to predict user preferences, and includes a predictive algorithm.

[0280] The "generation device" refers to a device or program that integrates the information obtained by the image processing device and the evaluation device to generate an optimal diet plan for the user.

[0281] The "cooking video" refers to video content that visually shows the cooking method of a specific diet menu and is accessible on an online platform or database.

[0282] The "search device" refers to a device or system that searches for cooking videos related to the provided diet plan and provides access information for the user to watch.

[0283] This invention is a system for providing an optimal diet plan based on the ingredients the user has and personal preferences. Specifically, the user uses an information device (such as a smartphone or tablet) to take pictures of the ingredients in the refrigerator. Thereby, the terminal sends the taken digital image to the server of the system.

[0284] The server receives this digital image via the image processing device and converts it into character data. Existing image recognition technologies such as TensorFlow and OpenCV are used in this process. The ingredient names extracted by image analysis are compared with an existing food database to improve accuracy.

[0285] Furthermore, the server analyzes the user's preference data through the evaluation device. This evaluation device refers to data including past diet history and conversation history to infer the user's preferences. Natural language processing technology is used to analyze the preference trends from the text data.

[0286] After that, the server uses the generation device to integrate the ingredient information from the image processing device and the preference information from the evaluation device, and uses an AI model to generate an optimal diet menu. The generated menu can also be adjusted considering promotional information according to the user's location.

[0287] Finally, the server uses a search device to retrieve cooking videos from online platforms and dedicated databases, and provides relevant video links to the user's device. The user can then review the suggested recipes and videos and easily begin cooking.

[0288] For example, if a user has chicken and broccoli in their refrigerator, they take a picture of them and send it to the system. The server recognizes the ingredients and learns that the user likes spicy food. The server then generates a menu item called "Spicy Chicken and Broccoli Stir-fry" and provides the user with a video link showing how to prepare it.

[0289] An example of a prompt message might be, "Please suggest a recipe for a spicy dish that can be made with chicken and broccoli that I have in my refrigerator. Please also provide specific cooking instructions and a link to a helpful video." In this way, the present invention enables convenient and personalized meal preparation for the user.

[0290] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0291] Step 1:

[0292] The user uses an information device to photograph the food items inside the refrigerator. The terminal sends the captured digital image to the system's server. In this case, the input is a digital image, and the output is the transmission of image data to the server.

[0293] Step 2:

[0294] The server passes the received digital image as input to the image processing unit. The image processing unit analyzes the image using TensorFlow or OpenCV to recognize the food ingredients. The output of this process is text data containing the names of the food ingredients. Specifically, the pixel data in the image is analyzed using an algorithm to identify the outlines and shapes of the food ingredients.

[0295] Step 3:

[0296] The server uses the text data obtained through image processing to refer to the food database and match the objects. This uniquely identifies the names of the ingredients. The output of this step is a list of ingredients.

[0297] Step 4:

[0298] The server retrieves user preference data from a database and inputs it into the evaluation device. The evaluation device uses natural language processing technology to analyze past meal and conversation history to predict the user's food preferences. The input is preference data, and the output is information about the predicted food preferences.

[0299] Step 5:

[0300] The server passes the output of the image processing device and the output of the evaluation device to the generation device. The generation device uses an AI model to integrate this information and generate an optimal meal menu. In this case, the input is a list of ingredients and preference information, and the output is the generated meal menu.

[0301] Step 6:

[0302] The server sends cooking videos related to the generated meal menu to the search device. The search device searches online platforms and finds relevant video links. The input is the meal menu, and the output is the video link.

[0303] Step 7:

[0304] The server sends the found video link to the terminal, and the user reviews the provided recipe and video. The input for this step is the video link, and the output is the provision of visual information to the user. This allows the user to learn the specific cooking steps and begin cooking.

[0305] (Application Example 1)

[0306] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0307] In modern food sales and food service industries, it is required to quickly and accurately respond to diverse customer needs. However, it is difficult to quickly make personalized proposals based on customer preferences and purchase histories by conventional methods. Also, since inventory management and information provision to customers require labor, efficiency improvements are demanded. Therefore, there is a demand for providing an effective system for grasping the usage status of food ingredients and making optimal product proposals and cooking plans for individual customers.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0309] In this invention, the server includes an analysis means, a speculation means, a generation means, a search means, and a presentation means. Thereby, it becomes possible to perform real-time inventory management using smart glasses and present optimal product and cooking configuration plans according to customer preferences.

[0310] The "analysis means" refers to a technology for converting image data acquired from a user terminal into text data.

[0311] The "speculation means" refers to a technology for analyzing and speculating on a user's eating preferences based on preference information acquired from the user.

[0312] The "generation means" is a technology for creating an appropriate meal plan based on the analyzed text data and the speculated preference information.

[0313] The "search means" is a technology for searching for a procedure video related to the generated meal plan and providing access information thereto.

[0314] The "presentation means" refers to a technology for directly presenting the generated plan and search results to a customer through a display device.

[0315] This invention provides a system that uses smart glasses in physical stores to streamline food management and product recommendations to customers. Specifically, it uses smart glasses as a server and user terminal to perform processing according to the following procedure.

[0316] The server uses image recognition software (e.g., OpenCV) as an analysis tool to receive video data of the food shelves transmitted from the smart glasses, analyze it, and convert it into text data. This process makes it possible to understand the types and quantities of resources on the shelves.

[0317] Next, the server uses inference tools to extract customer preference information from the database and uses data analysis software (e.g., Python's Pandas library) to identify the customer's food preferences. For example, it analyzes the products and taste trends the customer has chosen in the past.

[0318] The generation method generates optimal product suggestions and meal plans for the customer based on text data obtained from the analysis method and customer preference information identified by the inference method. Using a generation AI model (e.g., ChatGPT), it creates product configuration proposals in natural language and displays them on the smart glasses display via the presentation method.

[0319] As an example, when a store staff member wearing smart glasses scans potatoes and carrots on a shelf, a message such as "Today's recommendation is a spicy curry made with potatoes and carrots" appears on the display. An example of a prompt in this case would be, "Generate a spicy recipe using potatoes and carrots."

[0320] In this way, the system of the present invention enables real-time food inventory management and personalized product recommendations to improve the customer experience in physical stores.

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The device (smart glasses) photographs the food items on the shelf and acquires image data. The captured image data is automatically sent to a server via the network. The input for this step is the video of the shelf, and the output is the image data sent to the server.

[0324] Step 2:

[0325] The server processes the received image data using analysis tools. Image recognition software (e.g., OpenCV) is used to recognize objects in the image and convert their corresponding resource names into text. The input for this step is the image data sent from the terminal, and the output is the text data of the recognized resource names.

[0326] Step 3:

[0327] The server extracts customer preference information from the database using inference methods. It then uses data analysis software (e.g., Python's Pandas library) to analyze past purchase history and preference patterns. The input is a user ID, and the output is data on the customer's preference patterns.

[0328] Step 4:

[0329] The server uses a generation method to generate optimal product suggestions based on the analyzed text data and inferred preference patterns. It uses a generation AI model (e.g., ChatGPT) to generate suggestion text in natural language. The input for this step is the text data of resource names and customer preference patterns, and the output is the generated suggestion text.

[0330] Step 5:

[0331] The server sends the generated suggestion text to the terminal. The terminal's display shows information about the suggested products and meal plans. The input is the generated suggestion text, and the output is the information displayed on the terminal's display.

[0332] Step 6:

[0333] The user (store staff) makes product and dish recommendations to customers based on the information displayed on the smart glasses' screen. This enables personalized information delivery to customers. In this step, the user's understanding of what they see on the display is the input, and the explanation given to the customer is the output.

[0334] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0335] This invention relates to a food ingredient management and cooking menu suggestion system that takes into account the user's emotional state, and a specific embodiment thereof is shown below.

[0336] The user accesses the system via a device, takes pictures of the food in the refrigerator, and sends them to the server through an application. Along with the image data, the device can also acquire and send additional data to the server, such as audio and facial expressions, to understand the user's emotions.

[0337] The server processes the received image data using image analysis tools and extracts the names of the ingredients as text data. In this analysis process, advanced image recognition algorithms are used to identify the ingredients in the image.

[0338] Next, the server retrieves user preference information from the database and analyzes the user's eating habits using past data. This allows it to infer what kinds of ingredients and dishes the user prefers.

[0339] In addition, the emotion engine processes the transmitted emotion data using emotion analysis algorithms to evaluate the user's current emotional state. For example, it analyzes the tone of voice from audio data to determine whether the user is relaxed or stressed.

[0340] The server further considers image analysis data, preference information, and emotional states obtained from the emotion engine to create an appropriate meal menu using a generation tool. Menu selection also incorporates special offer information based on the user's location and seasonal ingredient information.

[0341] Furthermore, based on the user's emotional state, recipes using ingredients with relaxation effects, or dishes that provide energy, can be selected. This allows for the suggestion of more personalized menus.

[0342] The server then searches for cooking videos related to the suggested menu and sends the necessary access information to the user's terminal. The user can view the suggested menu and video links they receive, and by checking the specific cooking methods, they can confidently proceed with preparing the meal.

[0343] For example, if a user's photo includes chicken and broccoli, and voice analysis indicates the user is experiencing some stress, the server will suggest a stress-relieving dish such as "herb-grilled chicken and broccoli." Along with the recipe, it will provide a link to a video demonstrating the cooking process.

[0344] In this way, the present invention realizes a system that effectively utilizes the user's emotional state, preferences, and ingredients to provide appropriate and personalized cooking suggestions.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] The user takes photos of the food in the refrigerator and their own facial expression with their device, and sends the image data and additional emotion-related data to the system.

[0348] Step 2:

[0349] The terminal securely transfers food image data and emotion-related data such as voice and facial expressions to the server.

[0350] Step 3:

[0351] The server processes the received image data using image analysis tools to identify ingredients and convert them into corresponding text data.

[0352] Step 4:

[0353] The server retrieves information about the user from a preference database and uses analytical tools to infer the user's eating habits.

[0354] Step 5:

[0355] The server uses an emotion engine to analyze emotion-related data and evaluate the user's current emotional state. This evaluation takes into account factors such as voice tone and facial expressions.

[0356] Step 6:

[0357] The server uses image analysis, preference information, and emotional state data to generate a meal menu optimized for the user.

[0358] Step 7:

[0359] The server retrieves cooking videos and recipe information related to the most suitable menu from the internet and partner databases through search mechanisms.

[0360] Step 8:

[0361] The server organizes the suggested menu and links to related videos and sends them to the user's terminal.

[0362] Step 9:

[0363] The user checks the suggested menu information and video links on their device and begins cooking while referring to the selected recipe and video.

[0364] (Example 2)

[0365] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0366] Conventional ingredient management and menu suggestion systems struggled to provide personalized menu suggestions that took into account the user's emotional state. Furthermore, they were unable to appropriately combine local sale information and user preference data, failing to offer optimal cooking suggestions. Additionally, access to the correct cooking procedures for the suggested menus was limited, resulting in insufficient support for users to cook with confidence.

[0367] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0368] In this invention, the server includes an image analysis means for converting image data acquired from a user terminal into text data, an emotion analysis means for evaluating the emotional state based on emotion data acquired from the user, and a generation means for generating an appropriate menu based on preference information and emotional state. This enables personalized menu suggestions that take the user's emotional state into consideration, as well as appropriate access to cooking procedures.

[0369] A "user terminal" is an electronic device used by a user to input or retrieve data.

[0370] "Image data" refers to digital information used to visually represent an object.

[0371] "Text data" refers to digital information expressed as character data.

[0372] "Image analysis means" refers to an algorithm or device for analyzing image data and extracting information.

[0373] "Emotional analysis means" refers to an algorithm or device for processing emotional data such as voice and facial expressions to evaluate the user's emotional state.

[0374] "Preference information" refers to data about a user's preferences and tendencies.

[0375] A "generation method" is a mechanism or algorithm for creating new information or proposals based on specific data.

[0376] "Information provision means" refers to a device or process for efficiently providing users with the information they need.

[0377] "Food name" is a string of characters used to identify a food item.

[0378] "Local information" refers to information related to a specific geographical location.

[0379] This invention is a system for suggesting personalized meal menus based on a user's emotional state and preference information. This system consists of a user terminal, a server, and a network connection environment. An embodiment of this system is described below.

[0380] The user takes pictures of food in the refrigerator using an electronic device they use daily, i.e., a user terminal. The terminal acquires image data of the food and, if necessary, simultaneously collects emotional data such as the user's voice and facial expressions. On the terminal, the camera function for acquiring high-resolution images and the microphone for properly recording audio data play important roles.

[0381] The terminal sends the acquired image data and emotion data to the server. The server analyzes the received image data using "image analysis means" and identifies food items in the image using an image recognition algorithm, such as a general machine learning library. Specifically, the image analysis engine recognizes the contours and shapes of objects and outputs the food names as text data.

[0382] Next, the server uses an emotion analysis engine to analyze the user's emotional data. From the voice data, it analyzes the tone and tempo of the voice to determine whether the user is relaxed or stressed. Specifically, a natural language processing algorithm is implemented to evaluate the emotional state. This process categorizes the user's mental state.

[0383] The server retrieves previously recorded user preference information from a database and performs analysis to predict the user's food preferences. This information plays a crucial role when using a generative AI model to suggest menu items.

[0384] Finally, the server synthesizes these analysis results and uses a generative AI model to create the optimal menu for the user. This process also takes into account local sale information and seasonal ingredient information. The server also searches for cooking videos related to the menu and provides links to them on the user's device. As a result, the user can easily cook based on the suggested menu.

[0385] As a concrete example, if a user has chicken and broccoli in their refrigerator and voice analysis indicates they are feeling stressed, a relaxing menu such as "herb-grilled chicken and broccoli" might be suggested. An example of a prompt in response to this suggestion would be, "Please suggest a stress-reducing dish using the chicken and broccoli in my refrigerator."

[0386] Thus, this invention provides a concrete means for personalizing cooking suggestions for users based on their emotional state and preferences.

[0387] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0388] Step 1:

[0389] The user takes pictures of food items in the refrigerator using their device. To do this, the user activates the camera function and positions the device appropriately to photograph the food items. The input is image data of the food items. Ideally, this image data should be as clear and high-resolution as possible at the time of shooting. The output is the acquired image data saved on the device.

[0390] Step 2:

[0391] The device collects user voice and facial expression data along with captured image data. This involves recording voice data using a microphone and capturing facial expression data with a camera. In addition, with the user's permission, it may also acquire various sensor data and user setting information. The inputs acquired are image data and voice / facial expression data related to emotions. As output, this data is sent to the server as a single package.

[0392] Step 3:

[0393] The server analyzes the image data received from the terminal. Specifically, it uses an image recognition algorithm to identify food items and extract text data of their names. This process involves, for example, the execution of a machine learning model using a specific framework. The input is the transmitted image data, and after its analysis, a list of food names is generated as output.

[0394] Step 4:

[0395] The server analyzes voice and facial expression data to evaluate the user's emotional state. In this process, an emotion analysis algorithm analyzes the tone and tempo of the voice and changes in facial expression to categorize emotions. The input is voice and facial expression data related to emotions, and the output is a classification of the user's emotional state.

[0396] Step 5:

[0397] The server retrieves user preference information from a database and infers the user's preferences based on that information. This allows for analysis of past records to determine what tastes and ingredients the user prefers. The input is past preference data stored in the database, and the output identifies the user's culinary preferences.

[0398] Step 6:

[0399] The server integrates image analysis results, emotional states, and preference information, and uses a generative AI model to generate an appropriate menu. The generated prompt sentences are input into the model, and a personalized meal menu is proposed. The process is executed based on the given conditions, and the proposed recipe is output.

[0400] Step 7:

[0401] The server searches online for relevant cooking videos based on the generated meal menu and provides the user with access information. This operation involves utilizing the API of the video platform. The input is the generated menu information, and the output is a link to the cooking video sent to the user's terminal.

[0402] (Application Example 2)

[0403] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0404] In recent years, there has been growing interest in obtaining more personalized services based on users' psychological states and subjective experiences. However, conventional ingredient management and menu suggestion systems do not take into account users' emotional states, and therefore cannot provide optimal suggestions for users. This makes it difficult to suggest meals that match the user's emotional state, resulting in a challenge in increasing overall satisfaction.

[0405] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0406] In this invention, the server includes: an analysis means that receives image information and emotional state acquired from a user terminal, converts the image information into text information, and analyzes the user's emotional state; an analysis means that analyzes preference information acquired from the user and infers suggestions that match the user's food preferences and emotions based on the preference information and emotional state; a generation means that generates appropriate meal suggestions based on the text information and emotional information from the analysis means and the preference information from the analysis means; and a search means that searches for cooking procedures related to the generated meal suggestions and provides access information to the cooking procedures. This enables more personalized meal suggestions that respond to the user's emotional state.

[0407] A "user terminal" is an electronic device that allows a user to input or receive data through user operation.

[0408] "Image information" refers to visual data acquired from the user's device and is used for recognizing food and other objects.

[0409] "Emotional state" refers to information that indicates the user's psychological mood and emotions, and is analyzed from voice and facial expressions.

[0410] "Textual information" refers to data in text format converted from image information, and is a data format that can be further processed.

[0411] "Analysis means" refers to a technical method or apparatus used to process acquired image information and emotional states.

[0412] "Preference information" refers to data based on a user's preferences and past choices, and is used to infer the user's tastes.

[0413] "Analysis methods" refer to technical techniques and mechanisms that use collected preference information and emotional states to analyze users' preferences and psychological states.

[0414] "Generation means" refers to a method or apparatus for creating meal suggestions tailored to the user based on analysis and interpretation results.

[0415] A "cooking procedure" is a series of instructions that show how to cook using ingredients, and it is provided in an easy-to-understand format.

[0416] A "search tool" refers to a technical system or device for finding and providing to the user information and materials related to the generated meal suggestions.

[0417] The system for carrying out this invention mainly consists of a server, a user terminal, and necessary software components. The user terminal is a device for acquiring image information and emotional states, and is equipped with a camera and a microphone. Input from the terminal is processed by analysis means on the server.

[0418] The server uses advanced image recognition software such as Google Cloud Vision API and Amazon Rekognition to convert image information into text information and analyze the user's emotional state. The emotional state analysis utilizes Microsoft Azure Face API and Google Cloud Speech-to-Text, enabling the system to evaluate the user's psychological state from their facial expressions and voice.

[0419] The analyzed data is then processed by an analysis tool on the server and combined with user preference information. This process utilizes a database such as MongoDB to manage historical preference data, and data analysis libraries such as pandas are used to create suggestions that match the user's food preferences and emotions. This generation tool then suggests meals tailored to the user.

[0420] Ultimately, the server searches video platforms such as YouTube for cooking instructions related to the proposed meal and provides the user with the necessary reference videos. This involves using APIs as a search tool to extract relevant content and provide feedback to the user.

[0421] For example, if a user takes a picture of chicken and broccoli using their device and expresses a desire to relax through voice, the server will suggest "herb-grilled chicken and broccoli" and provide a link to a video showing how to prepare this dish.

[0422] Examples of prompts to input into the generating AI model include "Please suggest a meal menu that utilizes my current emotional state to relieve stress" and "Please come up with a relaxing dish based on the ingredients I have in my refrigerator." This allows the user to receive suggestions that are appropriate to their mood at the time.

[0423] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0424] Step 1:

[0425] The user uses the camera and microphone on their device to collect image and audio data of the food items inside the refrigerator. The input consists of image and audio data. The user's device then transmits this data to the server.

[0426] Step 2:

[0427] The server analyzes the received image data using the Google Cloud Vision API or Amazon Rekognition. Data processing is performed to extract the names of the ingredients from the input images, and the output is text information converted into the names of the ingredients.

[0428] Step 3:

[0429] Next, the server processes the received audio data using Microsoft Azure Face API or Google Cloud Speech-to-Text to analyze the user's emotional state. At this stage, the audio data is used as input, and emotional information such as relaxed or stressed states is output through data calculations.

[0430] Step 4:

[0431] Based on the analysis results, the server retrieves relevant information from a database of user preferences and uses the pandas library as an analysis tool to generate meal menus suitable for the user's preferences and emotions. Past preference information and extracted emotion information are input, and suggested meal menus are output.

[0432] Step 5:

[0433] The server's search mechanism uses the generated meal menu to search for related cooking instruction videos via video service APIs such as YouTube. The input is the generated menu information, and the output is a link to the related video.

[0434] Step 6:

[0435] Finally, the server sends the suggested dish menu and a link to a cooking instruction video to the user's device. This information allows the user to check the specific cooking method in the video.

[0436] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0437] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0438] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0439] [Third Embodiment]

[0440] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0441] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0442] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0443] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0444] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0445] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0446] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0447] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0448] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0449] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0450] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0451] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0452] The present invention relates to a system that streamlines user ingredient management and menu suggestion, and specific embodiments thereof are shown below.

[0453] The user uses a smartphone or other device to take a picture of the food in the refrigerator and sends the image to an account in a designated application or messenger service. The device then transfers the image data to the system's server.

[0454] The server processes the received image data using image analysis tools and extracts specific ingredients as text data. This analysis process applies existing image recognition techniques to recognize objects in the image and identify each ingredient.

[0455] Next, the server refers to a database containing the user's past preferences and uses analytical tools to identify the user's dietary preferences. For example, it can confirm from the user's previously saved recipes and chat history that they frequently choose spicy foods.

[0456] The server integrates ingredient information obtained through image analysis and preference information obtained through analysis, and uses a generation tool to create an optimal meal menu for the user. This generated menu takes into account the selected ingredients and the user's preferences.

[0457] Furthermore, the server uses search mechanisms to find cooking videos related to the generated menu from a database or online platform and provides the search results to the user's terminal. In this way, users can check the details of the suggested recipe on LINE or a dedicated application, and visually learn the specific cooking procedures by playing the cooking videos.

[0458] For example, if a user has chicken and broccoli in their refrigerator, they take pictures of these ingredients and send them to the system. The server analyzes these images to recognize the ingredients and learns from the user's past preferences that they like spicy food. As a result, the server suggests a menu item called "Spicy Chicken and Broccoli Stir-fry" and provides the user with a video link showing how to prepare it. The user accepts this suggestion and can smoothly begin cooking while following the recipe.

[0459] In this way, the present invention provides support that allows users to effectively utilize the ingredients they possess and easily prepare dishes that suit their individual preferences.

[0460] The following describes the processing flow.

[0461] Step 1:

[0462] Users take pictures of the food items in their refrigerator using their device and send them to the system. This transmission is done via LINE messages or a dedicated application.

[0463] Step 2:

[0464] The terminal transfers the transmitted image data to the server using a secure protocol. The transmission process includes optimization based on the image data's resolution and format.

[0465] Step 3:

[0466] The server processes the received image data using image analysis tools to identify objects in the image and extract the names of the ingredients as text data. For example, an AI-based image recognition algorithm is applied to obtain information such as "chicken" and "broccoli."

[0467] Step 4:

[0468] The server retrieves user preference information from the database and performs preference analysis based on past data. This analysis utilizes the user's past choices, purchase history, and saved recipes.

[0469] Step 5:

[0470] The server uses a generation mechanism to select the optimal menu based on the analyzed ingredient information and preference data. The generated menu includes options customized to the user's preferences.

[0471] Step 6:

[0472] The server uses search engines to search the internet and affiliated databases for cooking videos related to the generated menu, and retrieves relevant video and recipe URLs.

[0473] Step 7:

[0474] The server organizes the selected recipes and cooking video information and sends it to the device as a suggested menu. This information is then provided to the user via LINE message or in-app notification.

[0475] Step 8:

[0476] Users review the suggested menu received from their device, play the linked video, and visually confirm the specific cooking methods. This clarifies the cooking process and allows them to proceed with cooking quickly.

[0477] (Example 1)

[0478] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0479] In modern households, it's crucial to effectively manage the ingredients in the refrigerator and suggest meal menus that suit the family's preferences. However, traditional methods require users to individually check ingredients, consider preferences, and search for recipes, making it time-consuming and difficult to efficiently create optimal menus.

[0480] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0481] In this invention, the server includes an image processing device that receives digital images acquired from the user's information device and converts the digital images into text data; an evaluation device that evaluates preference data acquired from the user and infers the user's food preferences based on the preference data; a generation device that generates an appropriate meal plan based on the text data from the image processing device and the preference data from the evaluation device; and a search device that searches for cooking videos related to the generated meal plan and provides access information to the cooking videos. This makes it possible to easily generate and provide efficient and optimal meal menus tailored to the ingredients and preferences of the user.

[0482] "User information device" refers to an electronic device used by the user, such as a smartphone, tablet, or personal computer, that has the function of acquiring and transmitting images of food ingredients.

[0483] A "digital image" refers to non-analog image data acquired by a camera or scanner and processed by a computer or other device.

[0484] "Text data" refers to text information stored in digital format, including ingredient names and other text information extracted through image analysis.

[0485] An "image processing device" refers to a hardware or software configuration that receives a digital image as input, analyzes it, and converts it into text data.

[0486] "Preference data" refers to information that indicates a user's preferences and tastes regarding food, and includes past eating history and saved preference information.

[0487] An "evaluation device" is a component of a system that analyzes preference data and performs processing to predict user preferences, and includes a predictive algorithm.

[0488] A "generation device" refers to a device or program that integrates information obtained from an image processing device and an evaluation device to generate an optimal meal plan for the user.

[0489] "Cooking videos" refer to video content that visually demonstrates how to prepare a specific meal, and are accessible on online platforms or databases.

[0490] A "search device" refers to a device or system that searches for cooking videos related to a provided meal plan and provides users with access information for viewing them.

[0491] This invention is a system for providing an optimal meal plan based on the ingredients a user possesses and their personal preferences. Specifically, the user uses an information device (such as a smartphone or tablet) to photograph the ingredients in their refrigerator. The device then transmits the captured digital image to the system's server.

[0492] The server receives this digital image via an image processing unit and converts it into text data. Existing image recognition technologies such as TensorFlow and OpenCV are used in this process. The names of the ingredients extracted through image analysis are then compared against an existing food database to improve accuracy.

[0493] Furthermore, the server analyzes user preference data through an evaluation device. This evaluation device refers to data including past meal history and conversation history to infer the user's preferences. Natural language processing technology is used to analyze preference trends from text data.

[0494] Subsequently, the server uses a generation device to integrate ingredient information from the image processing device and preference information from the evaluation device, and generates an optimal meal menu using an AI model. The generated menu can also be adjusted to take into account promotional information based on the user's location.

[0495] Finally, the server uses a search device to retrieve cooking videos from online platforms and dedicated databases, and provides relevant video links to the user's device. The user can then review the suggested recipes and videos and easily begin cooking.

[0496] For example, if a user has chicken and broccoli in their refrigerator, they take a picture of them and send it to the system. The server recognizes the ingredients and learns that the user likes spicy food. The server then generates a menu item called "Spicy Chicken and Broccoli Stir-fry" and provides the user with a video link showing how to prepare it.

[0497] An example of a prompt message might be, "Please suggest a recipe for a spicy dish that can be made with chicken and broccoli that I have in my refrigerator. Please also provide specific cooking instructions and a link to a helpful video." In this way, the present invention enables convenient and personalized meal preparation for the user.

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] The user uses an information device to photograph the food items inside the refrigerator. The terminal sends the captured digital image to the system's server. In this case, the input is a digital image, and the output is the transmission of image data to the server.

[0501] Step 2:

[0502] The server passes the received digital image as input to the image processing unit. The image processing unit analyzes the image using TensorFlow or OpenCV to recognize the food ingredients. The output of this process is text data containing the names of the food ingredients. Specifically, the pixel data in the image is analyzed using an algorithm to identify the outlines and shapes of the food ingredients.

[0503] Step 3:

[0504] The server uses the text data obtained through image processing to refer to the food database and match the objects. This uniquely identifies the names of the ingredients. The output of this step is a list of ingredients.

[0505] Step 4:

[0506] The server retrieves user preference data from a database and inputs it into the evaluation device. The evaluation device uses natural language processing technology to analyze past meal and conversation history to predict the user's food preferences. The input is preference data, and the output is information about the predicted food preferences.

[0507] Step 5:

[0508] The server passes the output of the image processing device and the output of the evaluation device to the generation device. The generation device uses an AI model to integrate this information and generate an optimal meal menu. In this case, the input is a list of ingredients and preference information, and the output is the generated meal menu.

[0509] Step 6:

[0510] The server sends cooking videos related to the generated meal menu to the search device. The search device searches online platforms and finds relevant video links. The input is the meal menu, and the output is the video link.

[0511] Step 7:

[0512] The server sends the found video link to the terminal, and the user reviews the provided recipe and video. The input for this step is the video link, and the output is the provision of visual information to the user. This allows the user to learn the specific cooking steps and begin cooking.

[0513] (Application Example 1)

[0514] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0515] In today's food retail and restaurant industries, there is a demand for quick and accurate responses to diverse customer needs. However, providing personalized recommendations based on customer preferences and purchase history is difficult with traditional methods. Furthermore, inventory management and customer information provision are labor-intensive, necessitating increased efficiency. Therefore, there is a need for an effective system that understands ingredient usage and provides optimal product recommendations and meal plans for individual customers.

[0516] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0517] In this invention, the server includes analysis means, prediction means, generation means, search means, and presentation means. This enables real-time inventory management using smart glasses and the presentation of optimal product and meal combinations tailored to customer preferences.

[0518] "Analysis means" refers to technology for converting image data acquired from a user terminal into text data.

[0519] "Inference methods" refer to technologies used to analyze and infer a user's food preferences based on preference information obtained from the user.

[0520] "Generation method" refers to a technology for creating an appropriate meal plan based on analyzed text data and inferred preference information.

[0521] "Search method" refers to technology for searching for instructional videos related to the generated meal plan and providing access information to them.

[0522] "Presentation means" refers to technology for directly presenting generated plans and search results to customers through a display device.

[0523] This invention provides a system that uses smart glasses in physical stores to streamline food management and product recommendations to customers. Specifically, it uses smart glasses as a server and user terminal to perform processing according to the following procedure.

[0524] The server uses image recognition software (e.g., OpenCV) as an analysis tool to receive video data of the food shelves transmitted from the smart glasses, analyze it, and convert it into text data. This process makes it possible to understand the types and quantities of resources on the shelves.

[0525] Next, the server uses inference tools to extract customer preference information from the database and uses data analysis software (e.g., Python's Pandas library) to identify the customer's food preferences. For example, it analyzes the products and taste trends the customer has chosen in the past.

[0526] The generation method generates optimal product suggestions and meal plans for the customer based on text data obtained from the analysis method and customer preference information identified by the inference method. Using a generation AI model (e.g., ChatGPT), it creates product configuration proposals in natural language and displays them on the smart glasses display via the presentation method.

[0527] As an example, when a store staff member wearing smart glasses scans potatoes and carrots on a shelf, a message such as "Today's recommendation is a spicy curry made with potatoes and carrots" appears on the display. An example of a prompt in this case would be, "Generate a spicy recipe using potatoes and carrots."

[0528] In this way, the system of the present invention enables real-time food inventory management and personalized product recommendations to improve the customer experience in physical stores.

[0529] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0530] Step 1:

[0531] The device (smart glasses) photographs the food items on the shelf and acquires image data. The captured image data is automatically sent to a server via the network. The input for this step is the video of the shelf, and the output is the image data sent to the server.

[0532] Step 2:

[0533] The server processes the received image data using analysis tools. Image recognition software (e.g., OpenCV) is used to recognize objects in the image and convert their corresponding resource names into text. The input for this step is the image data sent from the terminal, and the output is the text data of the recognized resource names.

[0534] Step 3:

[0535] The server extracts customer preference information from the database using inference methods. It then uses data analysis software (e.g., Python's Pandas library) to analyze past purchase history and preference patterns. The input is a user ID, and the output is data on the customer's preference patterns.

[0536] Step 4:

[0537] The server uses a generation method to generate optimal product suggestions based on the analyzed text data and inferred preference patterns. It uses a generation AI model (e.g., ChatGPT) to generate suggestion text in natural language. The input for this step is the text data of resource names and customer preference patterns, and the output is the generated suggestion text.

[0538] Step 5:

[0539] The server sends the generated suggestion text to the terminal. The terminal's display shows information about the suggested products and meal plans. The input is the generated suggestion text, and the output is the information displayed on the terminal's display.

[0540] Step 6:

[0541] The user (store staff) makes product and dish recommendations to customers based on the information displayed on the smart glasses' screen. This enables personalized information delivery to customers. In this step, the user's understanding of what they see on the display is the input, and the explanation given to the customer is the output.

[0542] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0543] This invention relates to a food ingredient management and cooking menu suggestion system that takes into account the user's emotional state, and a specific embodiment thereof is shown below.

[0544] The user accesses the system via a device, takes pictures of the food in the refrigerator, and sends them to the server through an application. Along with the image data, the device can also acquire and send additional data to the server, such as audio and facial expressions, to understand the user's emotions.

[0545] The server processes the received image data using image analysis tools and extracts the names of the ingredients as text data. In this analysis process, advanced image recognition algorithms are used to identify the ingredients in the image.

[0546] Next, the server retrieves user preference information from the database and analyzes the user's eating habits using past data. This allows it to infer what kinds of ingredients and dishes the user prefers.

[0547] In addition, the emotion engine processes the transmitted emotion data using emotion analysis algorithms to evaluate the user's current emotional state. For example, it analyzes the tone of voice from audio data to determine whether the user is relaxed or stressed.

[0548] The server further considers image analysis data, preference information, and emotional states obtained from the emotion engine to create an appropriate meal menu using a generation tool. Menu selection also incorporates special offer information based on the user's location and seasonal ingredient information.

[0549] Furthermore, based on the user's emotional state, recipes using ingredients with relaxation effects, or dishes that provide energy, can be selected. This allows for the suggestion of more personalized menus.

[0550] The server then searches for cooking videos related to the suggested menu and sends the necessary access information to the user's terminal. The user can view the suggested menu and video links they receive, and by checking the specific cooking methods, they can confidently proceed with preparing the meal.

[0551] For example, if a user's photo includes chicken and broccoli, and voice analysis indicates the user is experiencing some stress, the server will suggest a stress-relieving dish such as "herb-grilled chicken and broccoli." Along with the recipe, it will provide a link to a video demonstrating the cooking process.

[0552] In this way, the present invention realizes a system that effectively utilizes the user's emotional state, preferences, and ingredients to provide appropriate and personalized cooking suggestions.

[0553] The following describes the processing flow.

[0554] Step 1:

[0555] The user takes photos of the food in the refrigerator and their own facial expression with their device, and sends the image data and additional emotion-related data to the system.

[0556] Step 2:

[0557] The terminal securely transfers food image data and emotion-related data such as voice and facial expressions to the server.

[0558] Step 3:

[0559] The server processes the received image data using image analysis tools to identify ingredients and convert them into corresponding text data.

[0560] Step 4:

[0561] The server retrieves information about the user from a preference database and uses analytical tools to infer the user's eating habits.

[0562] Step 5:

[0563] The server uses an emotion engine to analyze emotion-related data and evaluate the user's current emotional state. This evaluation takes into account factors such as voice tone and facial expressions.

[0564] Step 6:

[0565] The server uses image analysis, preference information, and emotional state data to generate a meal menu optimized for the user.

[0566] Step 7:

[0567] The server retrieves cooking videos and recipe information related to the most suitable menu from the internet and partner databases through search mechanisms.

[0568] Step 8:

[0569] The server organizes the suggested menu and links to related videos and sends them to the user's terminal.

[0570] Step 9:

[0571] The user checks the suggested menu information and video links on their device and begins cooking while referring to the selected recipe and video.

[0572] (Example 2)

[0573] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0574] Conventional ingredient management and menu suggestion systems struggled to provide personalized menu suggestions that took into account the user's emotional state. Furthermore, they were unable to appropriately combine local sale information and user preference data, failing to offer optimal cooking suggestions. Additionally, access to the correct cooking procedures for the suggested menus was limited, resulting in insufficient support for users to cook with confidence.

[0575] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0576] In this invention, the server includes an image analysis means for converting image data acquired from a user terminal into text data, an emotion analysis means for evaluating the emotional state based on emotion data acquired from the user, and a generation means for generating an appropriate menu based on preference information and emotional state. This enables personalized menu suggestions that take the user's emotional state into consideration, as well as appropriate access to cooking procedures.

[0577] A "user terminal" is an electronic device used by a user to input or retrieve data.

[0578] "Image data" refers to digital information used to visually represent an object.

[0579] "Text data" refers to digital information expressed as character data.

[0580] "Image analysis means" refers to an algorithm or device for analyzing image data and extracting information.

[0581] "Emotional analysis means" refers to an algorithm or device for processing emotional data such as voice and facial expressions to evaluate the user's emotional state.

[0582] "Preference information" refers to data about a user's preferences and tendencies.

[0583] A "generation method" is a mechanism or algorithm for creating new information or proposals based on specific data.

[0584] "Information provision means" refers to a device or process for efficiently providing users with the information they need.

[0585] "Food name" is a string of characters used to identify a food item.

[0586] "Local information" refers to information related to a specific geographical location.

[0587] This invention is a system for suggesting personalized meal menus based on a user's emotional state and preference information. This system consists of a user terminal, a server, and a network connection environment. An embodiment of this system is described below.

[0588] The user takes pictures of food in the refrigerator using an electronic device they use daily, i.e., a user terminal. The terminal acquires image data of the food and, if necessary, simultaneously collects emotional data such as the user's voice and facial expressions. On the terminal, the camera function for acquiring high-resolution images and the microphone for properly recording audio data play important roles.

[0589] The terminal sends the acquired image data and emotion data to the server. The server analyzes the received image data using "image analysis means" and identifies food items in the image using an image recognition algorithm, such as a general machine learning library. Specifically, the image analysis engine recognizes the contours and shapes of objects and outputs the food names as text data.

[0590] Next, the server uses an emotion analysis engine to analyze the user's emotional data. From the voice data, it analyzes the tone and tempo of the voice to determine whether the user is relaxed or stressed. Specifically, a natural language processing algorithm is implemented to evaluate the emotional state. This process categorizes the user's mental state.

[0591] The server retrieves previously recorded user preference information from a database and performs analysis to predict the user's food preferences. This information plays a crucial role when using a generative AI model to suggest menu items.

[0592] Finally, the server synthesizes these analysis results and uses a generative AI model to create the optimal menu for the user. This process also takes into account local sale information and seasonal ingredient information. The server also searches for cooking videos related to the menu and provides links to them on the user's device. As a result, the user can easily cook based on the suggested menu.

[0593] As a concrete example, if a user has chicken and broccoli in their refrigerator and voice analysis indicates they are feeling stressed, a relaxing menu such as "herb-grilled chicken and broccoli" might be suggested. An example of a prompt in response to this suggestion would be, "Please suggest a stress-reducing dish using the chicken and broccoli in my refrigerator."

[0594] Thus, this invention provides a concrete means for personalizing cooking suggestions for users based on their emotional state and preferences.

[0595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0596] Step 1:

[0597] The user takes pictures of food items in the refrigerator using their device. To do this, the user activates the camera function and positions the device appropriately to photograph the food items. The input is image data of the food items. Ideally, this image data should be as clear and high-resolution as possible at the time of shooting. The output is the acquired image data saved on the device.

[0598] Step 2:

[0599] The device collects user voice and facial expression data along with captured image data. This involves recording voice data using a microphone and capturing facial expression data with a camera. In addition, with the user's permission, it may also acquire various sensor data and user setting information. The inputs acquired are image data and voice / facial expression data related to emotions. As output, this data is sent to the server as a single package.

[0600] Step 3:

[0601] The server analyzes the image data received from the terminal. Specifically, it uses an image recognition algorithm to identify food items and extract text data of their names. This process involves, for example, the execution of a machine learning model using a specific framework. The input is the transmitted image data, and after its analysis, a list of food names is generated as output.

[0602] Step 4:

[0603] The server analyzes voice and facial expression data to evaluate the user's emotional state. In this process, an emotion analysis algorithm analyzes the tone and tempo of the voice and changes in facial expression to categorize emotions. The input is voice and facial expression data related to emotions, and the output is a classification of the user's emotional state.

[0604] Step 5:

[0605] The server retrieves user preference information from a database and infers the user's preferences based on that information. This allows for analysis of past records to determine what tastes and ingredients the user prefers. The input is past preference data stored in the database, and the output identifies the user's culinary preferences.

[0606] Step 6:

[0607] The server integrates image analysis results, emotional states, and preference information, and uses a generative AI model to generate an appropriate menu. The generated prompt sentences are input into the model, and a personalized meal menu is proposed. The process is executed based on the given conditions, and the proposed recipe is output.

[0608] Step 7:

[0609] The server searches online for relevant cooking videos based on the generated meal menu and provides the user with access information. This operation involves utilizing the API of the video platform. The input is the generated menu information, and the output is a link to the cooking video sent to the user's terminal.

[0610] (Application Example 2)

[0611] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0612] In recent years, there has been growing interest in obtaining more personalized services based on users' psychological states and subjective experiences. However, conventional ingredient management and menu suggestion systems do not take into account users' emotional states, and therefore cannot provide optimal suggestions for users. This makes it difficult to suggest meals that match the user's emotional state, resulting in a challenge in increasing overall satisfaction.

[0613] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0614] In this invention, the server includes: an analysis means that receives image information and emotional state acquired from a user terminal, converts the image information into text information, and analyzes the user's emotional state; an analysis means that analyzes preference information acquired from the user and infers suggestions that match the user's food preferences and emotions based on the preference information and emotional state; a generation means that generates appropriate meal suggestions based on the text information and emotional information from the analysis means and the preference information from the analysis means; and a search means that searches for cooking procedures related to the generated meal suggestions and provides access information to the cooking procedures. This enables more personalized meal suggestions that respond to the user's emotional state.

[0615] A "user terminal" is an electronic device that allows a user to input or receive data through user operation.

[0616] "Image information" refers to visual data acquired from the user's device and is used for recognizing food and other objects.

[0617] "Emotional state" refers to information that indicates the user's psychological mood and emotions, and is analyzed from voice and facial expressions.

[0618] "Textual information" refers to data in text format converted from image information, and is a data format that can be further processed.

[0619] "Analysis means" refers to a technical method or apparatus used to process acquired image information and emotional states.

[0620] "Preference information" refers to data based on a user's preferences and past choices, and is used to infer the user's tastes.

[0621] "Analysis methods" refer to technical techniques and mechanisms that use collected preference information and emotional states to analyze users' preferences and psychological states.

[0622] "Generation means" refers to a method or apparatus for creating meal suggestions tailored to the user based on analysis and interpretation results.

[0623] A "cooking procedure" is a series of instructions that show how to cook using ingredients, and it is provided in an easy-to-understand format.

[0624] A "search tool" refers to a technical system or device for finding and providing to the user information and materials related to the generated meal suggestions.

[0625] The system for carrying out this invention mainly consists of a server, a user terminal, and necessary software components. The user terminal is a device for acquiring image information and emotional states, and is equipped with a camera and a microphone. Input from the terminal is processed by analysis means on the server.

[0626] The server uses advanced image recognition software such as Google Cloud Vision API and Amazon Rekognition to convert image information into text information and analyze the user's emotional state. The emotional state analysis utilizes Microsoft Azure Face API and Google Cloud Speech-to-Text, enabling the system to evaluate the user's psychological state from their facial expressions and voice.

[0627] The analyzed data is then processed by an analysis tool on the server and combined with user preference information. This process utilizes a database such as MongoDB to manage historical preference data, and data analysis libraries such as pandas are used to create suggestions that match the user's food preferences and emotions. This generation tool then suggests meals tailored to the user.

[0628] Ultimately, the server searches video platforms such as YouTube for cooking instructions related to the proposed meal and provides the user with the necessary reference videos. This involves using APIs as a search tool to extract relevant content and provide feedback to the user.

[0629] For example, if a user takes a picture of chicken and broccoli using their device and expresses a desire to relax through voice, the server will suggest "herb-grilled chicken and broccoli" and provide a link to a video showing how to prepare this dish.

[0630] Examples of prompts to input into the generating AI model include "Please suggest a meal menu that utilizes my current emotional state to relieve stress" and "Please come up with a relaxing dish based on the ingredients I have in my refrigerator." This allows the user to receive suggestions that are appropriate to their mood at the time.

[0631] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0632] Step 1:

[0633] The user uses the camera and microphone on their device to collect image and audio data of the food items inside the refrigerator. The input consists of image and audio data. The user's device then transmits this data to the server.

[0634] Step 2:

[0635] The server analyzes the received image data using the Google Cloud Vision API or Amazon Rekognition. Data processing is performed to extract the names of the ingredients from the input images, and the output is text information converted into the names of the ingredients.

[0636] Step 3:

[0637] Next, the server processes the received audio data using Microsoft Azure Face API or Google Cloud Speech-to-Text to analyze the user's emotional state. At this stage, the audio data is used as input, and emotional information such as relaxed or stressed states is output through data calculations.

[0638] Step 4:

[0639] Based on the analysis results, the server retrieves relevant information from a database of user preferences and uses the pandas library as an analysis tool to generate meal menus suitable for the user's preferences and emotions. Past preference information and extracted emotion information are input, and suggested meal menus are output.

[0640] Step 5:

[0641] The server's search mechanism uses the generated meal menu to search for related cooking instruction videos via video service APIs such as YouTube. The input is the generated menu information, and the output is a link to the related video.

[0642] Step 6:

[0643] Finally, the server sends the suggested dish menu and a link to a cooking instruction video to the user's device. This information allows the user to check the specific cooking method in the video.

[0644] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0645] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0646] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0647] [Fourth Embodiment]

[0648] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0649] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0650] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0651] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0652] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0653] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0654] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0655] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0656] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0657] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0658] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0659] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0660] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0661] The present invention relates to a system that streamlines user ingredient management and menu suggestion, and specific embodiments thereof are shown below.

[0662] The user uses a smartphone or other device to take a picture of the food in the refrigerator and sends the image to an account in a designated application or messenger service. The device then transfers the image data to the system's server.

[0663] The server processes the received image data using image analysis tools and extracts specific ingredients as text data. This analysis process applies existing image recognition techniques to recognize objects in the image and identify each ingredient.

[0664] Next, the server refers to a database containing the user's past preferences and uses analytical tools to identify the user's dietary preferences. For example, it can confirm from the user's previously saved recipes and chat history that they frequently choose spicy foods.

[0665] The server integrates ingredient information obtained through image analysis and preference information obtained through analysis, and uses a generation tool to create an optimal meal menu for the user. This generated menu takes into account the selected ingredients and the user's preferences.

[0666] Furthermore, the server uses search mechanisms to find cooking videos related to the generated menu from a database or online platform and provides the search results to the user's terminal. In this way, users can check the details of the suggested recipe on LINE or a dedicated application, and visually learn the specific cooking procedures by playing the cooking videos.

[0667] For example, if a user has chicken and broccoli in their refrigerator, they take pictures of these ingredients and send them to the system. The server analyzes these images to recognize the ingredients and learns from the user's past preferences that they like spicy food. As a result, the server suggests a menu item called "Spicy Chicken and Broccoli Stir-fry" and provides the user with a video link showing how to prepare it. The user accepts this suggestion and can smoothly begin cooking while following the recipe.

[0668] In this way, the present invention provides support that allows users to effectively utilize the ingredients they possess and easily prepare dishes that suit their individual preferences.

[0669] The following describes the processing flow.

[0670] Step 1:

[0671] Users take pictures of the food items in their refrigerator using their device and send them to the system. This transmission is done via LINE messages or a dedicated application.

[0672] Step 2:

[0673] The terminal transfers the transmitted image data to the server using a secure protocol. The transmission process includes optimization based on the image data's resolution and format.

[0674] Step 3:

[0675] The server processes the received image data using image analysis tools to identify objects in the image and extract the names of the ingredients as text data. For example, an AI-based image recognition algorithm is applied to obtain information such as "chicken" and "broccoli."

[0676] Step 4:

[0677] The server retrieves user preference information from the database and performs preference analysis based on past data. This analysis utilizes the user's past choices, purchase history, and saved recipes.

[0678] Step 5:

[0679] The server uses a generation mechanism to select the optimal menu based on the analyzed ingredient information and preference data. The generated menu includes options customized to the user's preferences.

[0680] Step 6:

[0681] The server uses search engines to search the internet and affiliated databases for cooking videos related to the generated menu, and retrieves relevant video and recipe URLs.

[0682] Step 7:

[0683] The server organizes the selected recipes and cooking video information and sends it to the device as a suggested menu. This information is then provided to the user via LINE message or in-app notification.

[0684] Step 8:

[0685] Users review the suggested menu received from their device, play the linked video, and visually confirm the specific cooking methods. This clarifies the cooking process and allows them to proceed with cooking quickly.

[0686] (Example 1)

[0687] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0688] In modern households, it's crucial to effectively manage the ingredients in the refrigerator and suggest meal menus that suit the family's preferences. However, traditional methods require users to individually check ingredients, consider preferences, and search for recipes, making it time-consuming and difficult to efficiently create optimal menus.

[0689] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0690] In this invention, the server includes an image processing device that receives digital images acquired from the user's information device and converts the digital images into text data; an evaluation device that evaluates preference data acquired from the user and infers the user's food preferences based on the preference data; a generation device that generates an appropriate meal plan based on the text data from the image processing device and the preference data from the evaluation device; and a search device that searches for cooking videos related to the generated meal plan and provides access information to the cooking videos. This makes it possible to easily generate and provide efficient and optimal meal menus tailored to the ingredients and preferences of the user.

[0691] "User information device" refers to an electronic device used by the user, such as a smartphone, tablet, or personal computer, that has the function of acquiring and transmitting images of food ingredients.

[0692] A "digital image" refers to non-analog image data acquired by a camera or scanner and processed by a computer or other device.

[0693] "Text data" refers to text information stored in digital format, including ingredient names and other text information extracted through image analysis.

[0694] An "image processing device" refers to a hardware or software configuration that receives a digital image as input, analyzes it, and converts it into text data.

[0695] "Preference data" refers to information that indicates a user's preferences and tastes regarding food, and includes past eating history and saved preference information.

[0696] An "evaluation device" is a component of a system that analyzes preference data and performs processing to predict user preferences, and includes a predictive algorithm.

[0697] A "generation device" refers to a device or program that integrates information obtained from an image processing device and an evaluation device to generate an optimal meal plan for the user.

[0698] "Cooking videos" refer to video content that visually demonstrates how to prepare a specific meal, and are accessible on online platforms or databases.

[0699] A "search device" refers to a device or system that searches for cooking videos related to a provided meal plan and provides users with access information for viewing them.

[0700] This invention is a system for providing an optimal meal plan based on the ingredients a user possesses and their personal preferences. Specifically, the user uses an information device (such as a smartphone or tablet) to photograph the ingredients in their refrigerator. The device then transmits the captured digital image to the system's server.

[0701] The server receives this digital image via an image processing unit and converts it into text data. Existing image recognition technologies such as TensorFlow and OpenCV are used in this process. The names of the ingredients extracted through image analysis are then compared against an existing food database to improve accuracy.

[0702] Furthermore, the server analyzes user preference data through an evaluation device. This evaluation device refers to data including past meal history and conversation history to infer the user's preferences. Natural language processing technology is used to analyze preference trends from text data.

[0703] Subsequently, the server uses a generation device to integrate ingredient information from the image processing device and preference information from the evaluation device, and generates an optimal meal menu using an AI model. The generated menu can also be adjusted to take into account promotional information based on the user's location.

[0704] Finally, the server uses a search device to retrieve cooking videos from online platforms and dedicated databases, and provides relevant video links to the user's device. The user can then review the suggested recipes and videos and easily begin cooking.

[0705] For example, if a user has chicken and broccoli in their refrigerator, they take a picture of them and send it to the system. The server recognizes the ingredients and learns that the user likes spicy food. The server then generates a menu item called "Spicy Chicken and Broccoli Stir-fry" and provides the user with a video link showing how to prepare it.

[0706] An example of a prompt message might be, "Please suggest a recipe for a spicy dish that can be made with chicken and broccoli that I have in my refrigerator. Please also provide specific cooking instructions and a link to a helpful video." In this way, the present invention enables convenient and personalized meal preparation for the user.

[0707] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0708] Step 1:

[0709] The user uses an information device to photograph the food items inside the refrigerator. The terminal sends the captured digital image to the system's server. In this case, the input is a digital image, and the output is the transmission of image data to the server.

[0710] Step 2:

[0711] The server passes the received digital image as input to the image processing unit. The image processing unit analyzes the image using TensorFlow or OpenCV to recognize the food ingredients. The output of this process is text data containing the names of the food ingredients. Specifically, the pixel data in the image is analyzed using an algorithm to identify the outlines and shapes of the food ingredients.

[0712] Step 3:

[0713] The server uses the text data obtained through image processing to refer to the food database and match the objects. This uniquely identifies the names of the ingredients. The output of this step is a list of ingredients.

[0714] Step 4:

[0715] The server retrieves user preference data from a database and inputs it into the evaluation device. The evaluation device uses natural language processing technology to analyze past meal and conversation history to predict the user's food preferences. The input is preference data, and the output is information about the predicted food preferences.

[0716] Step 5:

[0717] The server passes the output of the image processing device and the output of the evaluation device to the generation device. The generation device uses an AI model to integrate this information and generate an optimal meal menu. In this case, the input is a list of ingredients and preference information, and the output is the generated meal menu.

[0718] Step 6:

[0719] The server sends cooking videos related to the generated meal menu to the search device. The search device searches online platforms and finds relevant video links. The input is the meal menu, and the output is the video link.

[0720] Step 7:

[0721] The server sends the found video link to the terminal, and the user reviews the provided recipe and video. The input for this step is the video link, and the output is the provision of visual information to the user. This allows the user to learn the specific cooking steps and begin cooking.

[0722] (Application Example 1)

[0723] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0724] In today's food retail and restaurant industries, there is a demand for quick and accurate responses to diverse customer needs. However, providing personalized recommendations based on customer preferences and purchase history is difficult with traditional methods. Furthermore, inventory management and customer information provision are labor-intensive, necessitating increased efficiency. Therefore, there is a need for an effective system that understands ingredient usage and provides optimal product recommendations and meal plans for individual customers.

[0725] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0726] In this invention, the server includes analysis means, prediction means, generation means, search means, and presentation means. This enables real-time inventory management using smart glasses and the presentation of optimal product and meal combinations tailored to customer preferences.

[0727] "Analysis means" refers to technology for converting image data acquired from a user terminal into text data.

[0728] "Inference methods" refer to technologies used to analyze and infer a user's food preferences based on preference information obtained from the user.

[0729] "Generation method" refers to a technology for creating an appropriate meal plan based on analyzed text data and inferred preference information.

[0730] "Search method" refers to technology for searching for instructional videos related to the generated meal plan and providing access information to them.

[0731] "Presentation means" refers to technology for directly presenting generated plans and search results to customers through a display device.

[0732] This invention provides a system that uses smart glasses in physical stores to streamline food management and product recommendations to customers. Specifically, it uses smart glasses as a server and user terminal to perform processing according to the following procedure.

[0733] The server uses image recognition software (e.g., OpenCV) as an analysis tool to receive video data of the food shelves transmitted from the smart glasses, analyze it, and convert it into text data. This process makes it possible to understand the types and quantities of resources on the shelves.

[0734] Next, the server uses inference tools to extract customer preference information from the database and uses data analysis software (e.g., Python's Pandas library) to identify the customer's food preferences. For example, it analyzes the products and taste trends the customer has chosen in the past.

[0735] The generation method generates optimal product suggestions and meal plans for the customer based on text data obtained from the analysis method and customer preference information identified by the inference method. Using a generation AI model (e.g., ChatGPT), it creates product configuration proposals in natural language and displays them on the smart glasses display via the presentation method.

[0736] As an example, when a store staff member wearing smart glasses scans potatoes and carrots on a shelf, a message such as "Today's recommendation is a spicy curry made with potatoes and carrots" appears on the display. An example of a prompt in this case would be, "Generate a spicy recipe using potatoes and carrots."

[0737] In this way, the system of the present invention enables real-time food inventory management and personalized product recommendations to improve the customer experience in physical stores.

[0738] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0739] Step 1:

[0740] The device (smart glasses) photographs the food items on the shelf and acquires image data. The captured image data is automatically sent to a server via the network. The input for this step is the video of the shelf, and the output is the image data sent to the server.

[0741] Step 2:

[0742] The server processes the received image data using analysis tools. Image recognition software (e.g., OpenCV) is used to recognize objects in the image and convert their corresponding resource names into text. The input for this step is the image data sent from the terminal, and the output is the text data of the recognized resource names.

[0743] Step 3:

[0744] The server extracts customer preference information from the database using inference methods. It then uses data analysis software (e.g., Python's Pandas library) to analyze past purchase history and preference patterns. The input is a user ID, and the output is data on the customer's preference patterns.

[0745] Step 4:

[0746] The server uses a generation method to generate optimal product suggestions based on the analyzed text data and inferred preference patterns. It uses a generation AI model (e.g., ChatGPT) to generate suggestion text in natural language. The input for this step is the text data of resource names and customer preference patterns, and the output is the generated suggestion text.

[0747] Step 5:

[0748] The server sends the generated suggestion text to the terminal. The terminal's display shows information about the suggested products and meal plans. The input is the generated suggestion text, and the output is the information displayed on the terminal's display.

[0749] Step 6:

[0750] The user (store staff) makes product and dish recommendations to customers based on the information displayed on the smart glasses' screen. This enables personalized information delivery to customers. In this step, the user's understanding of what they see on the display is the input, and the explanation given to the customer is the output.

[0751] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0752] This invention relates to a food ingredient management and cooking menu suggestion system that takes into account the user's emotional state, and a specific embodiment thereof is shown below.

[0753] The user accesses the system via a device, takes pictures of the food in the refrigerator, and sends them to the server through an application. Along with the image data, the device can also acquire and send additional data to the server, such as audio and facial expressions, to understand the user's emotions.

[0754] The server processes the received image data using image analysis tools and extracts the names of the ingredients as text data. In this analysis process, advanced image recognition algorithms are used to identify the ingredients in the image.

[0755] Next, the server retrieves user preference information from the database and analyzes the user's eating habits using past data. This allows it to infer what kinds of ingredients and dishes the user prefers.

[0756] In addition, the emotion engine processes the transmitted emotion data using emotion analysis algorithms to evaluate the user's current emotional state. For example, it analyzes the tone of voice from audio data to determine whether the user is relaxed or stressed.

[0757] The server further considers image analysis data, preference information, and emotional states obtained from the emotion engine to create an appropriate meal menu using a generation tool. Menu selection also incorporates special offer information based on the user's location and seasonal ingredient information.

[0758] Furthermore, based on the user's emotional state, recipes using ingredients with relaxation effects, or dishes that provide energy, can be selected. This allows for the suggestion of more personalized menus.

[0759] The server then searches for cooking videos related to the suggested menu and sends the necessary access information to the user's terminal. The user can view the suggested menu and video links they receive, and by checking the specific cooking methods, they can confidently proceed with preparing the meal.

[0760] For example, if a user's photo includes chicken and broccoli, and voice analysis indicates the user is experiencing some stress, the server will suggest a stress-relieving dish such as "herb-grilled chicken and broccoli." Along with the recipe, it will provide a link to a video demonstrating the cooking process.

[0761] In this way, the present invention realizes a system that effectively utilizes the user's emotional state, preferences, and ingredients to provide appropriate and personalized cooking suggestions.

[0762] The following describes the processing flow.

[0763] Step 1:

[0764] The user takes photos of the food in the refrigerator and their own facial expression with their device, and sends the image data and additional emotion-related data to the system.

[0765] Step 2:

[0766] The terminal securely transfers food image data and emotion-related data such as voice and facial expressions to the server.

[0767] Step 3:

[0768] The server processes the received image data using image analysis tools to identify ingredients and convert them into corresponding text data.

[0769] Step 4:

[0770] The server retrieves information about the user from a preference database and uses analytical tools to infer the user's eating habits.

[0771] Step 5:

[0772] The server uses an emotion engine to analyze emotion-related data and evaluate the user's current emotional state. This evaluation takes into account factors such as voice tone and facial expressions.

[0773] Step 6:

[0774] The server uses image analysis, preference information, and emotional state data to generate a meal menu optimized for the user.

[0775] Step 7:

[0776] The server retrieves cooking videos and recipe information related to the most suitable menu from the internet and partner databases through search mechanisms.

[0777] Step 8:

[0778] The server organizes the suggested menu and links to related videos and sends them to the user's terminal.

[0779] Step 9:

[0780] The user checks the suggested menu information and video links on their device and begins cooking while referring to the selected recipe and video.

[0781] (Example 2)

[0782] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0783] Conventional ingredient management and menu suggestion systems struggled to provide personalized menu suggestions that took into account the user's emotional state. Furthermore, they were unable to appropriately combine local sale information and user preference data, failing to offer optimal cooking suggestions. Additionally, access to the correct cooking procedures for the suggested menus was limited, resulting in insufficient support for users to cook with confidence.

[0784] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0785] In this invention, the server includes an image analysis means for converting image data acquired from a user terminal into text data, an emotion analysis means for evaluating the emotional state based on emotion data acquired from the user, and a generation means for generating an appropriate menu based on preference information and emotional state. This enables personalized menu suggestions that take the user's emotional state into consideration, as well as appropriate access to cooking procedures.

[0786] A "user terminal" is an electronic device used by a user to input or retrieve data.

[0787] "Image data" refers to digital information used to visually represent an object.

[0788] "Text data" refers to digital information expressed as character data.

[0789] "Image analysis means" refers to an algorithm or device for analyzing image data and extracting information.

[0790] "Emotional analysis means" refers to an algorithm or device for processing emotional data such as voice and facial expressions to evaluate the user's emotional state.

[0791] "Preference information" refers to data about a user's preferences and tendencies.

[0792] A "generation method" is a mechanism or algorithm for creating new information or proposals based on specific data.

[0793] "Information provision means" refers to a device or process for efficiently providing users with the information they need.

[0794] "Food name" is a string of characters used to identify a food item.

[0795] "Local information" refers to information related to a specific geographical location.

[0796] This invention is a system for suggesting personalized meal menus based on a user's emotional state and preference information. This system consists of a user terminal, a server, and a network connection environment. An embodiment of this system is described below.

[0797] The user takes pictures of food in the refrigerator using an electronic device they use daily, i.e., a user terminal. The terminal acquires image data of the food and, if necessary, simultaneously collects emotional data such as the user's voice and facial expressions. On the terminal, the camera function for acquiring high-resolution images and the microphone for properly recording audio data play important roles.

[0798] The terminal sends the acquired image data and emotion data to the server. The server analyzes the received image data using "image analysis means" and identifies food items in the image using an image recognition algorithm, such as a general machine learning library. Specifically, the image analysis engine recognizes the contours and shapes of objects and outputs the food names as text data.

[0799] Next, the server uses an emotion analysis engine to analyze the user's emotional data. From the voice data, it analyzes the tone and tempo of the voice to determine whether the user is relaxed or stressed. Specifically, a natural language processing algorithm is implemented to evaluate the emotional state. This process categorizes the user's mental state.

[0800] The server retrieves previously recorded user preference information from a database and performs analysis to predict the user's food preferences. This information plays a crucial role when using a generative AI model to suggest menu items.

[0801] Finally, the server synthesizes these analysis results and uses a generative AI model to create the optimal menu for the user. This process also takes into account local sale information and seasonal ingredient information. The server also searches for cooking videos related to the menu and provides links to them on the user's device. As a result, the user can easily cook based on the suggested menu.

[0802] As a concrete example, if a user has chicken and broccoli in their refrigerator and voice analysis indicates they are feeling stressed, a relaxing menu such as "herb-grilled chicken and broccoli" might be suggested. An example of a prompt in response to this suggestion would be, "Please suggest a stress-reducing dish using the chicken and broccoli in my refrigerator."

[0803] Thus, this invention provides a concrete means for personalizing cooking suggestions for users based on their emotional state and preferences.

[0804] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0805] Step 1:

[0806] The user takes pictures of food items in the refrigerator using their device. To do this, the user activates the camera function and positions the device appropriately to photograph the food items. The input is image data of the food items. Ideally, this image data should be as clear and high-resolution as possible at the time of shooting. The output is the acquired image data saved on the device.

[0807] Step 2:

[0808] The device collects user voice and facial expression data along with captured image data. This involves recording voice data using a microphone and capturing facial expression data with a camera. In addition, with the user's permission, it may also acquire various sensor data and user setting information. The inputs acquired are image data and voice / facial expression data related to emotions. As output, this data is sent to the server as a single package.

[0809] Step 3:

[0810] The server analyzes the image data received from the terminal. Specifically, it uses an image recognition algorithm to identify food items and extract text data of their names. This process involves, for example, the execution of a machine learning model using a specific framework. The input is the transmitted image data, and after its analysis, a list of food names is generated as output.

[0811] Step 4:

[0812] The server analyzes voice and facial expression data to evaluate the user's emotional state. In this process, an emotion analysis algorithm analyzes the tone and tempo of the voice and changes in facial expression to categorize emotions. The input is voice and facial expression data related to emotions, and the output is a classification of the user's emotional state.

[0813] Step 5:

[0814] The server retrieves user preference information from a database and infers the user's preferences based on that information. This allows for analysis of past records to determine what tastes and ingredients the user prefers. The input is past preference data stored in the database, and the output identifies the user's culinary preferences.

[0815] Step 6:

[0816] The server integrates image analysis results, emotional states, and preference information, and uses a generative AI model to generate an appropriate menu. The generated prompt sentences are input into the model, and a personalized meal menu is proposed. The process is executed based on the given conditions, and the proposed recipe is output.

[0817] Step 7:

[0818] The server searches online for relevant cooking videos based on the generated meal menu and provides the user with access information. This operation involves utilizing the API of the video platform. The input is the generated menu information, and the output is a link to the cooking video sent to the user's terminal.

[0819] (Application Example 2)

[0820] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0821] In recent years, there has been growing interest in obtaining more personalized services based on users' psychological states and subjective experiences. However, conventional ingredient management and menu suggestion systems do not take into account users' emotional states, and therefore cannot provide optimal suggestions for users. This makes it difficult to suggest meals that match the user's emotional state, resulting in a challenge in increasing overall satisfaction.

[0822] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0823] In this invention, the server includes: an analysis means that receives image information and emotional state acquired from a user terminal, converts the image information into text information, and analyzes the user's emotional state; an analysis means that analyzes preference information acquired from the user and infers suggestions that match the user's food preferences and emotions based on the preference information and emotional state; a generation means that generates appropriate meal suggestions based on the text information and emotional information from the analysis means and the preference information from the analysis means; and a search means that searches for cooking procedures related to the generated meal suggestions and provides access information to the cooking procedures. This enables more personalized meal suggestions that respond to the user's emotional state.

[0824] A "user terminal" is an electronic device that allows a user to input or receive data through user operation.

[0825] "Image information" refers to visual data acquired from the user's device and is used for recognizing food and other objects.

[0826] "Emotional state" refers to information that indicates the user's psychological mood and emotions, and is analyzed from voice and facial expressions.

[0827] "Textual information" refers to data in text format converted from image information, and is a data format that can be further processed.

[0828] "Analysis means" refers to a technical method or apparatus used to process acquired image information and emotional states.

[0829] "Preference information" refers to data based on a user's preferences and past choices, and is used to infer the user's tastes.

[0830] "Analysis methods" refer to technical techniques and mechanisms that use collected preference information and emotional states to analyze users' preferences and psychological states.

[0831] "Generation means" refers to a method or apparatus for creating meal suggestions tailored to the user based on analysis and interpretation results.

[0832] A "cooking procedure" is a series of instructions that show how to cook using ingredients, and it is provided in an easy-to-understand format.

[0833] A "search tool" refers to a technical system or device for finding and providing to the user information and materials related to the generated meal suggestions.

[0834] The system for carrying out this invention mainly consists of a server, a user terminal, and necessary software components. The user terminal is a device for acquiring image information and emotional states, and is equipped with a camera and a microphone. Input from the terminal is processed by analysis means on the server.

[0835] The server uses advanced image recognition software such as Google Cloud Vision API and Amazon Rekognition to convert image information into text information and analyze the user's emotional state. The emotional state analysis utilizes Microsoft Azure Face API and Google Cloud Speech-to-Text, enabling the system to evaluate the user's psychological state from their facial expressions and voice.

[0836] The analyzed data is then processed by an analysis tool on the server and combined with user preference information. This process utilizes a database such as MongoDB to manage historical preference data, and data analysis libraries such as pandas are used to create suggestions that match the user's food preferences and emotions. This generation tool then suggests meals tailored to the user.

[0837] Ultimately, the server searches video platforms such as YouTube for cooking instructions related to the proposed meal and provides the user with the necessary reference videos. This involves using APIs as a search tool to extract relevant content and provide feedback to the user.

[0838] For example, if a user takes a picture of chicken and broccoli using their device and expresses a desire to relax through voice, the server will suggest "herb-grilled chicken and broccoli" and provide a link to a video showing how to prepare this dish.

[0839] Examples of prompts to input into the generating AI model include "Please suggest a meal menu that utilizes my current emotional state to relieve stress" and "Please come up with a relaxing dish based on the ingredients I have in my refrigerator." This allows the user to receive suggestions that are appropriate to their mood at the time.

[0840] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0841] Step 1:

[0842] The user uses the camera and microphone on their device to collect image and audio data of the food items inside the refrigerator. The input consists of image and audio data. The user's device then transmits this data to the server.

[0843] Step 2:

[0844] The server analyzes the received image data using the Google Cloud Vision API or Amazon Rekognition. Data processing is performed to extract the names of the ingredients from the input images, and the output is text information converted into the names of the ingredients.

[0845] Step 3:

[0846] Next, the server processes the received audio data using Microsoft Azure Face API or Google Cloud Speech-to-Text to analyze the user's emotional state. At this stage, the audio data is used as input, and emotional information such as relaxed or stressed states is output through data calculations.

[0847] Step 4:

[0848] Based on the analysis results, the server retrieves relevant information from a database of user preferences and uses the pandas library as an analysis tool to generate meal menus suitable for the user's preferences and emotions. Past preference information and extracted emotion information are input, and suggested meal menus are output.

[0849] Step 5:

[0850] The server's search mechanism uses the generated meal menu to search for related cooking instruction videos via video service APIs such as YouTube. The input is the generated menu information, and the output is a link to the related video.

[0851] Step 6:

[0852] Finally, the server sends the suggested dish menu and a link to a cooking instruction video to the user's device. This information allows the user to check the specific cooking method in the video.

[0853] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0854] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0855] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0856] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0857] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0858] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0859] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0860] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0861] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0862] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0863] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0864] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0865] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0866] 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.

[0867] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0868] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0869] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0870] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0871] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0872] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0873] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0874] The following is further disclosed regarding the embodiments described above.

[0875] (Claim 1)

[0876] Image analysis means that receives image data acquired from a user terminal and converts said image data into text data,

[0877] An analytical means for analyzing preference information obtained from users and inferring the user's food preferences based on said preference information,

[0878] A generation means that generates an appropriate meal menu based on text data obtained by the image analysis means and preference information obtained by the analysis means,

[0879] A system including a search means for searching for cooking videos related to the generated meal menu and providing information on how to access said cooking videos.

[0880] (Claim 2)

[0881] The system according to claim 1, characterized in that the image analysis means includes a process of recognizing multiple objects in image data and outputting the names of the food ingredients corresponding to those objects as text.

[0882] (Claim 3)

[0883] The system according to claim 1, characterized in that the generation means includes multiple recommended recipes in the generated menu that take into account special offer information based on the user's location.

[0884] "Example 1"

[0885] (Claim 1)

[0886] An image processing device that receives a digital image acquired from a user's information device and converts the digital image into text data,

[0887] An evaluation device that evaluates preference data obtained from a user and infers the user's food preferences based on said preference data,

[0888] A generation device that generates an appropriate meal plan based on character data from the image processing device and preference data from the evaluation device,

[0889] A system including a search device that searches for cooking videos related to the generated meal plan and provides information on how to access the cooking videos.

[0890] (Claim 2)

[0891] The system according to claim 1, characterized in that the image processing device includes a process of recognizing multiple objects in a digital image and outputting the names of the food ingredients corresponding to those objects in text.

[0892] (Claim 3)

[0893] The system according to claim 1, characterized in that the generating device includes multiple recommended plans that take into account promotional information based on the user's location in the generated plan.

[0894] "Application Example 1"

[0895] (Claim 1)

[0896] An analysis means that receives image data acquired from a user terminal and converts the image data into text data,

[0897] An estimation means that analyzes preference information obtained from the user and infers the user's food preferences based on said preference information,

[0898] A generation means that generates an appropriate meal plan based on text data obtained by the analysis means and preference information obtained by the estimation means,

[0899] A search means for searching for instructional videos related to the generated meal plan and providing information on how to access such instructional videos,

[0900] A means of presenting information directly to the customer using a display device,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, characterized in that the analysis means includes a process of recognizing multiple objects in video data and outputting the resource names corresponding to those objects as text.

[0904] (Claim 3)

[0905] The system according to claim 1, characterized in that the generation means includes a plurality of recommended steps that take into account special sale information based on the user's location in the generated plan.

[0906] "Example 2 of combining an emotion engine"

[0907] (Claim 1)

[0908] Image analysis means that receives image data acquired from a user terminal and converts said image data into text data,

[0909] An emotion analysis means that analyzes emotion data obtained from a user and evaluates the user's emotional state based on said emotion data,

[0910] A generation means for generating an appropriate meal menu based on the user's preference information and emotional state,

[0911] A system including an information-providing means that obtains cooking procedures related to a generated meal menu and provides information on how to access said cooking procedures.

[0912] (Claim 2)

[0913] The system according to claim 1, characterized in that the image analysis means includes a process of recognizing multiple objects in image data and outputting the names of the food items corresponding to those objects as text.

[0914] (Claim 3)

[0915] The system according to claim 1, characterized in that the generation means includes multiple recommended recipes that take into account local information based on the user's location and ingredients that contribute to the user's emotional state.

[0916] "Application example 2 when combining with an emotional engine"

[0917] (Claim 1)

[0918] An analysis means that receives image information and emotional state acquired from a user terminal, converts the image information into text information, and analyzes the user's emotional state,

[0919] An analytical means that analyzes preference information obtained from users and infers suggestions that match the user's food preferences and emotions based on said preference information and emotional state,

[0920] A generation means that generates appropriate meal suggestions based on textual information and emotional information obtained by the analysis means and preference information obtained by the analysis means,

[0921] A system including a search means for searching for cooking procedures related to the generated meal suggestions and providing information on how to access those cooking procedures.

[0922] (Claim 2)

[0923] The system according to claim 1, characterized in that the analysis means includes a process of recognizing multiple objects in image information and outputting the element names corresponding to those objects and the user's emotional state in text.

[0924] (Claim 3)

[0925] The system according to claim 1, characterized in that the generation means includes special offer information based on the user's location and recommended recipes adjusted according to the user's emotional state in the generated suggestions. [Explanation of symbols]

[0926] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Image analysis means that receives image data acquired from a user terminal and converts said image data into text data, An analytical means for analyzing preference information obtained from users and inferring the user's food preferences based on said preference information, A generation means that generates an appropriate meal menu based on text data obtained by the image analysis means and preference information obtained by the analysis means, A system including a search means for searching for cooking videos related to the generated meal menu and providing information on how to access said cooking videos.

2. The system according to claim 1, characterized in that the image analysis means includes a process of recognizing multiple objects in image data and outputting the names of the food ingredients corresponding to those objects as text.

3. The system according to claim 1, characterized in that the generation means includes a plurality of recommended recipes in the generated menu that take into account special sale information based on the user's location.

Images