system

Abstract

We provide the system. [Solution] Means for receiving user information, A means of obtaining dietary history data from multiple external sources, A means of analyzing collected data and generating a user's dietary profile, A means for generating suggested candidates based on the user's profile, A means of notifying the user terminal of suggested candidates, A means of collecting user feedback and improving the system, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 modern society, many people tend to have a bias towards limited choices of dishes in their daily diet. As a result, there is a possibility of missing out on new taste experiences. Also, when meal choices become fixed, there is a risk of an unbalanced diet. Therefore, it is required to provide users with opportunities to encounter new dishes they have never experienced and expand the enjoyment of food.

Means for Solving the Problems

[0005] This invention constructs a system that generates a food profile based on a user's eating history and preference data, and then proposes new foods and serving locations based on that profile. Specifically, it receives user information, acquires data from multiple external sources, and creates a user profile through AI analysis. Based on this profile, it proposes foods that the user has not yet tried but is likely to like, and notifies the user's terminal, thereby encouraging new food experiences. Through this series of processes, it is possible to provide food diversity and contribute to improving the user's eating habits.

[0006] "User information" refers to data necessary for the system to make suggestions, such as the user's personal preferences, allergy information, and past eating history.

[0007] "External sources" refer to external databases or services that are connected to in order to obtain a user's meal history.

[0008] "Meal history data" refers to information about the dishes a user has selected and the facilities they have visited in the past, and is used to understand the user's eating habits.

[0009] "Analysis" is the process of organizing and evaluating collected data and extracting useful information, and it commonly involves the use of AI technology.

[0010] A "food profile" is an individualized model created based on the user's preferences and habits, and serves as the foundation for providing meal suggestions.

[0011] "Possible suggestions" are a list of unknown foods and establishments that users might be interested in, derived through analysis.

[0012] A "user terminal" is a device used by a user to receive information or communicate, and includes smartphones and computers.

[0013] "Feedback" refers to the evaluations and opinions that users provide after trying out a suggestion, and it is important data for improving the system.

[0014] A "serving establishment" is a place that serves a specific type of food, and this includes restaurants and eateries. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the 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, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] This invention describes an embodiment of a system that proposes new foods and serving locations to users in order to broaden their dining experience. The system primarily functions through a flow of data collection, analysis, proposal, and feedback between a server, terminals, and users.

[0037] 1. Collection of user information

[0038] Users input personal information such as dietary preferences, allergy information, and lifestyle habits into a terminal using a dedicated application or web interface. The terminal transmits this information to a server. Furthermore, the server collaborates with external sources to obtain the user's dietary history data.

[0039] 2. Data Analysis and Profile Generation

[0040] The server uses an AI algorithm to analyze received user information and meal history data collected from external sources. This analysis takes into account the user's taste preferences, eating patterns, and meal frequency to generate an individualized meal profile. This narrows down the list of optimal suggestions for each user.

[0041] 3. Proposal generation and notification

[0042] Based on the generated profile, the server creates a list of suggested foods that the user has not yet tried but is likely to enjoy. These suggestions include information about the characteristics of each dish and the establishments that serve them. The server then notifies the user of these suggestions on their device.

[0043] 4. Gathering feedback and improving the system

[0044] Users who receive a suggestion try the suggested food and send feedback from their device. This feedback includes opinions on the taste of the dish, satisfaction level, and whether it was a new discovery. The server collects this feedback and updates the system's AI algorithm to improve the accuracy of future suggestions.

[0045] Specific example

[0046] For example, let's assume a user primarily eats Japanese food. This user registers with the app and enters their food preferences. The server generates a profile based on past meal history and suggests "sauerkraut and sausage," a German dish. Although this dish is different from the user's usual Japanese food, the server's analysis determines that it is likely to suit the user's preferences. The user follows this suggestion, tries the suggested recipe, or orders it at a restaurant, thereby gaining a new taste experience.

[0047] In this way, users can discover unfamiliar foods through the system and expand their culinary horizons. This invention not only suggests foods but also provides suggestions tailored to the user's preferences and evolves the system based on feedback, thereby offering a more effective dining experience.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] Users access the application through their device and enter personal information, dietary preferences, allergy information, etc. The device then sends this information to the server.

[0051] Step 2:

[0052] The server connects to external sources via APIs to retrieve the user's past meal history data. The retrieved data is stored in a database.

[0053] Step 3:

[0054] The server uses an AI algorithm to analyze the received user information and meal history data to generate a user's food profile. This profile reflects the user's preferred types of food and taste preferences.

[0055] Step 4:

[0056] Based on the analysis results, the server generates suggested food items and establishments that the user has not yet experienced and is likely to enjoy.

[0057] Step 5:

[0058] The server notifies the user's terminal of the generated suggestions. The user can review the suggestions through their terminal and, if interested, obtain information on how to try the suggested dishes.

[0059] Step 6:

[0060] After trying the suggested dish, the user sends feedback to the server using their device. This feedback includes an evaluation of the experience.

[0061] Step 7:

[0062] The server analyzes the collected feedback and updates its AI algorithm to improve the accuracy of future suggestions.

[0063] (Example 1)

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

[0065] The challenge lies in providing a system that accurately understands individual food preferences and eating patterns, and proposes new dining experiences to users. Conventional systems have struggled to effectively utilize user feedback to improve the accuracy of their suggestions.

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

[0067] In this invention, the server includes means for receiving user attributes, means for acquiring dining history information from multiple sources, means for analyzing the collected data and generating a user's food profile, and means for adaptively improving the accuracy of suggestions using a generation AI model. This makes it possible to suggest foods that are suitable for each individual user and to improve the accuracy of suggestions for the next time by utilizing feedback.

[0068] "User attributes" refer to personalized information such as individual user preferences, allergy information, and lifestyle habits.

[0069] "Dining history information" refers to records of past meals and order history obtained from external data sources.

[0070] A "food profile" is a data profile used to analyze a user's preferences and eating patterns, and to provide personalized recommendations.

[0071] "Information sources" refer to various systems and databases that provide information on dining history from external sources.

[0072] An "analysis algorithm" is a set of calculation procedures that use collected data to understand user preferences and eating patterns, and then use that information to generate suggestions.

[0073] A "generative AI model" is a model that applies machine learning and artificial intelligence technologies to improve the accuracy of suggestions based on user feedback.

[0074] "Recommendation accuracy" is an indicator that shows the accuracy and suitability of food recommendations tailored to the user's preferences.

[0075] This system aims to improve users' dining experiences by suggesting new foods and serving locations. The system is primarily based on the exchange of information between servers, terminals, and users, establishing a flow of data collection, analysis, suggestion, and feedback.

[0076] Users input attributes such as their dietary preferences, allergy information, and lifestyle into a terminal using a dedicated application or web interface. This data is then transmitted from the terminal to the server.

[0077] The server organizes the received user attributes and retrieves dining history information in conjunction with external sources. These external sources include restaurant reservation systems and online ordering platforms. This allows the server to understand the user's past dining history.

[0078] The collected data is analyzed on the server. The analysis utilizes analytical algorithms equipped with generative AI models. For example, machine learning libraries such as TENSORFLOW® and sclearn are used to analyze user preferences and eating patterns, generating food profiles. Based on these profiles, suggestions for foods the user has not yet tried but is likely to enjoy are generated.

[0079] The server notifies the user's terminal of the generated suggestions. The suggestions include information about the characteristics of the suggested dishes and the establishments that serve them. Based on this information, the user can try new foods.

[0080] For example, if a user typically eats mainly Japanese food, the server will suggest German dishes such as "sauerkraut and sausage" based on that profile. This suggestion encourages a new experience beyond their usual eating habits. Another example of a prompt for a generative AI model would be, "Create an algorithm for the AI ​​to suggest foreign dishes to a user who likes Japanese food."

[0081] User feedback is sent back to the server from the device and used to readjust the generated AI model. This improves the accuracy of suggestions and maximizes user satisfaction. In this way, the system provides an effective dining experience through continuous improvement and adaptation.

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

[0083] Step 1:

[0084] Users input attributes such as their dietary preferences, allergy information, and lifestyle into their device using a dedicated application or web interface. This input data is encoded in JSON format and sent from the device to the server. Upon receiving this data, the server receives the user attribute data.

[0085] Step 2:

[0086] The server organizes the received user attributes and stores them in a database. This storage process uses the user ID as a key to ensure data consistency and enable quick retrieval. Based on this information, the server collaborates with external sources to retrieve dining history information. The server connects to these external sources via an Application Programming Interface (API). The retrieved dining history information is then added to the database.

[0087] Step 3:

[0088] The server inputs user attributes and dining history information stored in the database into an AI algorithm. Using a generative AI model, it analyzes the user's preferences and eating patterns to generate a food profile. This profile includes foods the user is likely to like and their eating tendencies. The generated food profile is obtained as output.

[0089] Step 4:

[0090] The server creates personalized suggestions for the user based on the generated food profile. These suggestions include information on foods the user may not have tried but is likely to enjoy, as well as information on establishments that serve them. This includes a list of foods selected using a recommendation algorithm. The generated suggestions are then sent to the terminal.

[0091] Step 5:

[0092] Users can review the suggestions received on their device and try foods that interest them. After trying the food, users input their results as feedback on their device. This feedback includes taste evaluations and comments on any new discoveries. This data is then sent back to the server in JSON format and treated as input data.

[0093] Step 6:

[0094] The server stores the received feedback in a database and retrains the generating AI model. This retraining process improves the accuracy of subsequent suggestions. By leveraging this feedback loop, the server can provide more appropriate suggestions to the user.

[0095] (Application Example 1)

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

[0097] In today's increasingly diverse food landscape, it's not easy for users to efficiently discover new dining experiences that match their preferences. Furthermore, traditional food delivery services tend to be biased towards foods and establishments that users have already experienced, making it difficult to broaden their dining horizons. Against this backdrop, there is a need for a system that suggests foods that users might like, even if they haven't tried them before, based on their preferences and past dining habits, thereby providing new dining experiences.

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

[0099] In this invention, the server includes means for receiving user information, means for acquiring meal history data from multiple external sources, means for analyzing the collected data and generating a user's food profile, means for generating suggested dishes based on the user's profile, means for notifying the user terminal of the suggested dishes, means for collecting user feedback and improving the system, and means for analyzing the user's preferences and taking orders to provide previously unexperienced meals. This enables users to efficiently discover new dining experiences that align with their preferences.

[0100] "Means of receiving user information" refers to methods by which the system acquires personal data such as preferences, allergy information, and lifestyle habits entered by the user.

[0101] "Methods for obtaining meal history data from external sources" refers to methods of integrating with third-party services or databases to obtain a user's past meal history.

[0102] "Methods for analyzing data and generating user dietary profiles" refers to methods that use acquired user information and meal history data to analyze users' taste preferences and eating patterns, thereby revealing individual dietary preferences.

[0103] "Methods for generating suggested items" refers to methods that suggest foods and facilities that the user has not yet experienced but are likely to match their preferences, based on the user's food profile.

[0104] "Means for notifying user terminals of proposed suggestions" refers to a method of sending generated suggestions to the information device used by the user to inform the user.

[0105] "Methods for collecting feedback and improving the system" refers to methods of collecting opinions and evaluations from users and using those results to improve the accuracy of suggestions and the overall performance of the system.

[0106] "An order-taking method that analyzes user preferences and provides previously unexperienced meals" refers to a method of providing new foods that users have not yet experienced as food delivery, based on a detailed analysis of their preferences.

[0107] This invention consists of a system designed to enable users to efficiently obtain new dining experiences through food delivery services. The system primarily utilizes smartphones, cloud servers, and AI algorithms.

[0108] The server is responsible for receiving user information. Users input personal data such as their food preferences, allergy information, and lifestyle habits using an application on their smartphone, and this information is sent to the server. The server also collects dietary history data from external sources and uses this to record the user's past eating behavior.

[0109] Next, the server analyzes this data. Specifically, it uses AI algorithms (e.g., TensorFlow or PyTorch) to analyze the user's taste preferences and eating patterns, and generates an individual food profile. Based on this profile, it generates a list of foods and establishments that the user has not yet experienced but are likely to match their preferences.

[0110] The generated suggestions are notified to the user via smartphone notification features (such as Firebase Cloud Messaging). The user orders the suggested food items through the application and submits feedback about the experience.

[0111] The feedback is returned to the server, and the feedback data is used via an AI algorithm to improve the accuracy of future suggestions. This allows the suggestion process to continuously improve, resulting in more personalized suggestions.

[0112] For example, if it is detected that the user usually prefers vegetarian food, a unique menu plan from a vegan restaurant can be suggested. An example of a prompt message might be, "Please recommend the following vegetarian dishes. The user usually tends to prefer XX."

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

[0114] Step 1:

[0115] Users use their smartphones to input personal information such as their food preferences, allergy information, and lifestyle habits. This data is then transmitted from the device to the server. The input includes information in text and selection formats, and the server receives user information as output.

[0116] Step 2:

[0117] The server retrieves user meal history data from an external source. This retrieval process involves accessing a third-party service's database via an API and downloading data such as the user's past order history and ratings. The input is API data from an external source, and the output is meal history data stored on the server.

[0118] Step 3:

[0119] The server analyzes collected user information and meal history data. Specifically, it runs AI algorithms (using TensorFlow or PyTorch) to analyze the user's taste preferences and eating patterns. As a result of the analysis, a user's food profile is generated. The input is personal information and history data, and the output is the user's profile.

[0120] Step 4:

[0121] The server generates suggested options based on the generated user profile. In this process, the AI ​​selects foods and establishments that the user may have not experienced and might enjoy. The output is a list of suggested options.

[0122] Step 5:

[0123] Potential proposals are notified from the server to the user's device. Services such as Firebase Cloud Messaging are used for notifications, ensuring that proposals are communicated to the user in real time. The output is the proposed content displayed on the user's device.

[0124] Step 6:

[0125] Users try the suggested food items and send feedback about their experience from their device to the server. This feedback includes opinions on satisfaction with the meal and any new discoveries. The input is user feedback data.

[0126] Step 7:

[0127] The server collects user feedback and uses AI algorithms to improve the entire system. It analyzes the feedback data and learns to improve the accuracy of future suggestions. The output is the suggested algorithm with specific improvements.

[0128] 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.

[0129] This invention describes a system that provides more accurate meal recommendations by utilizing user emotional data. This system aims to improve the quality of recommendations by processing information between the server, terminal, and user.

[0130] 1. User information collection and sentiment recognition

[0131] Users access the application through their device and enter personal information such as their dietary preferences, allergy information, and lifestyle. Simultaneously, the emotion engine captures the user's facial expressions and voice data in real time to determine their emotional state. The device then transmits this information to the server.

[0132] 2. Data Analysis and Profile Generation

[0133] The server uses an AI algorithm to analyze collected user information, past meal history, and emotional data acquired by the engine. The analysis generates a food profile that takes into account the user's preferences, eating patterns, and emotional responses. This enables multifaceted suggestions that include the user's emotional satisfaction.

[0134] 3. Generating candidate proposals

[0135] Based on the generated profile, the server lists foods and establishments that the user has not yet experienced but are likely to provide emotional satisfaction. Suggestions include information about the cuisine, the establishments that serve it, and the emotional target audience.

[0136] 4. Notification of proposals and collection of feedback

[0137] The server notifies the user's device of suggested dishes. After trying the suggested dishes, the user uses their device to provide feedback and sends it to the server. This feedback, including emotional reactions to the dishes tried, is reflected in future suggestions.

[0138] Specific example

[0139] For example, consider a user who generally avoids spicy food but is seeking new stimuli. After this user accesses the app and enters their allergy information, an emotion engine measures the user's level of excitement and interest. The server analyzes this data and suggests ethnic dishes with a moderate level of spiciness. These dishes are designed to satisfy the user's curiosity while also providing emotional satisfaction. Through these suggestions, users can enjoy new culinary experiences and broaden their culinary horizons with the system's recommendations.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The user launches a dedicated application on their device and enters their dietary preferences and allergy information. The device then uses an emotion engine to capture the user's voice and facial expression data and analyze their emotional state.

[0143] Step 2:

[0144] The terminal transmits collected preference and emotional data to the server. The server, in cooperation with an external source, retrieves the user's past meal history data and stores it in a database.

[0145] Step 3:

[0146] The server analyzes acquired meal history data, preference data, and emotional data using an AI algorithm. This analysis generates a user's food profile, including taste preferences, eating patterns, and emotional analysis information.

[0147] Step 4:

[0148] Based on the profile, the server generates suggested dishes and restaurants that are suitable for the user and that they may not have tried before. The suggested dishes include an overview of each dish and elements that take into account emotional satisfaction.

[0149] Step 5:

[0150] The server sends suggested proposals as notifications to the user's device. The user reviews the proposals on their device and tries out any that interest them.

[0151] Step 6:

[0152] Users send feedback to the server via their device, expressing their thoughts and emotional reactions to the dishes they try.

[0153] Step 7:

[0154] The server analyzes the feedback received and updates its AI algorithms to improve the accuracy of future suggestions and user satisfaction.

[0155] (Example 2)

[0156] 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".

[0157] Conventional food recommendation systems make suggestions based on user preference data, but the results do not necessarily guarantee user emotional satisfaction. Therefore, there is a need for more personalized recommendations that take into account the user's emotional state.

[0158] 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.

[0159] In this invention, the server includes means for receiving user information, means for capturing emotional data in real time and determining the emotional state, and means for generating suggested products based on a profile that includes the emotional data. This enables more accurate food recommendations that meet the user's emotional and preference needs.

[0160] "User information" refers to data about the user's personal preferences, allergy information, and lifestyle.

[0161] "External sources" refer to external databases or services that provide information about food.

[0162] A "food profile" refers to a record of food preferences generated based on a user's taste preferences, eating patterns, frequency, and emotional responses.

[0163] "Emotional data" refers to information about a user's emotional state obtained by analyzing their facial expressions, voice, and other data.

[0164] "Recommended items" refers to a list of food products and suppliers recommended to the user based on their profile.

[0165] "Feedback" refers to information about the evaluations and emotional responses that users provide after trying a suggested food product.

[0166] "Analysis method" refers to the computational methods and algorithms used to generate user profiles based on collected data.

[0167] In this invention, a food recommendation system achieves highly accurate suggestions based on the user's emotions and preferences by coordinating between a server, terminal, and user. A specific embodiment is shown below.

[0168] The user accesses the application using a device. The device is equipped with sensors, a camera, and a microphone, which collect the user's facial expressions and voice data in real time. The device analyzes this data using software called an emotion engine to determine the user's emotional state. The determined emotional data is then sent to a server.

[0169] The server receives emotional data and user information, including food preferences and meal history, transmitted from the terminal. This data is analyzed using AI algorithms to generate the user's food profile. Commonly used data analysis software and machine learning libraries can be applied to the analysis.

[0170] A concrete example would be a user who likes sweets but also values ​​health. The emotion engine captures the user's facial expression when they see images of sweets and sends this emotion information to the server if they show interest. Based on this, the server suggests establishments that offer low-sugar desserts and notifies the user's device. In this case, the prompt used for input to the generating AI model is, "Please tell us what flavors you usually prefer and what healthy alternatives you would like to try."

[0171] After the server notifies the user of a suggestion, it collects feedback from the user when they actually try the suggested food. This feedback includes their impressions of the dish and changes in their emotional state. The collected feedback is further analyzed by an AI algorithm and used to improve the overall accuracy of the system. This makes it possible to continuously improve the quality of the user experience.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] Users access the application using their device and enter personal information such as dietary preferences, allergy information, and lifestyle. This information is sent from the device to the server. The entered information is treated as user-specific initial data. The device uses a protocol to format the data and send it to the server efficiently.

[0175] Step 2:

[0176] The device uses its camera and microphone to collect the user's facial expressions and voice in real time. This emotional data is analyzed using an emotion engine. Specifically, it uses image recognition and voice analysis to extract the user's emotional state from their smile and voice tone. The device then sends these analysis results to a server.

[0177] Step 3:

[0178] The server receives user information and sentiment data transmitted from the terminal. Based on the received data, it uses an AI algorithm to generate a user's food profile. This profile is a complex model that takes into account the user's preferences and emotional satisfaction. The server then trains the AI ​​model to identify the user's preferred trends.

[0179] Step 4:

[0180] The server creates a list of food items to suggest to the user based on the generated profile. Specifically, it uses a generative AI model to select food items and dining establishments that are likely to emotionally satisfy the user. The output is a list of suggested options for the user, based on the results of algorithmic calculations using the input emotional data and profile.

[0181] Step 5:

[0182] The server notifies the user's device of a list of food suggestions. The information is visually organized so that it can be easily viewed on the user's screen. The user can browse this list and select suggestions that interest them.

[0183] Step 6:

[0184] Users try the suggested food items and provide feedback on their experience. They input specific levels of satisfaction and changes in emotions as feedback. The device uses this feedback and sends the data to the server.

[0185] Step 7:

[0186] The server analyzes the collected feedback to improve the accuracy of future suggestions. The AI ​​algorithm integrates the new feedback data as training data to generate a more refined predictive model. This continuous learning process improves the user experience.

[0187] (Application Example 2)

[0188] 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".

[0189] In modern society, consumer food needs have diversified, and when choosing meals, not only nutritional value and taste are considered, but emotional satisfaction is also important. However, conventional systems do not take emotional states into account when suggesting meals, and have not been able to sufficiently improve the satisfaction users experience with meals. Therefore, there is a need for a system that improves the user experience by utilizing user emotional data and providing optimal meal suggestions tailored to individual circumstances.

[0190] 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.

[0191] In this invention, the server includes means for receiving user information, means for acquiring meal history data from multiple external sources, means for acquiring emotion recognition data for determining the user's emotional state, means for analyzing the collected data to generate the user's eating profile, and means for making meal suggestions that take emotional satisfaction into account based on the user's profile. This makes it possible to suggest the optimal meal according to the user's emotional state and improve the user's dining experience.

[0192] "User information" refers to data about the user that the system uses, including information about dietary preferences, allergies, and lifestyle.

[0193] "Dietary history data" refers to data about the food that a user has selected or consumed in the past, and is used to analyze preferences and eating patterns.

[0194] "Emotion recognition data" refers to data obtained from the user's facial expressions and voice, and is used to determine the user's emotional state.

[0195] An "analysis algorithm" is a mathematical method used to generate a user's food profile based on collected data, enabling analysis that takes into account the user's preferences and emotional state.

[0196] A "food profile" is a collection of information that reflects a user's food preferences, patterns, and emotional satisfaction, and serves as the basis for generating suggested options.

[0197] "Suggested options" are lists of food products and establishments generated based on the user's food profile, and include choices that are likely to provide emotional satisfaction even if the user has not experienced them before.

[0198] "Feedback" refers to the response information provided by users after trying a suggested meal, and is used to improve the accuracy of the system's suggestions.

[0199] The system in this invention mainly consists of the interaction between a server, a terminal, and a user. First, the user terminal functions as an input interface for user information, receiving data such as the user's dietary preferences, allergy information, and lifestyle. The terminal also uses a camera and microphone to acquire real-time facial expressions and voice data of the user and transmits emotion recognition data to the server.

[0200] The server analyzes user information and emotion recognition data received from the terminal using AI algorithms. This analysis utilizes generative AI models such as TensorFlow to determine the user's emotional state. Furthermore, the server generates a profile based on the user's past meal history data, constructing a multifaceted food profile that incorporates the user's preferences and emotional satisfaction.

[0201] Next, based on the generated profile, the server suggests foods and establishments that the user has not experienced before but that are likely to be emotionally satisfying. These suggested options are then notified to the user's device via an API using Flask.

[0202] After a user tries a suggested food item, their feedback is collected via their device and sent to a server. This feedback includes the user's emotional response, which is used to continuously improve the system's recommendation accuracy.

[0203] This system allows users to receive meal suggestions optimized for their emotional state, resulting in a more satisfying dining experience.

[0204] For example, if a user is feeling the need to relax, the system may recognize that emotion from the user's facial expressions and voice data and suggest a herbal tea that is expected to have a relaxing effect.

[0205] An example of a prompt message is: "Determine the user's current emotional state based on their facial expressions and voice data, and suggest a meal that is expected to have a relaxing effect."

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] Users access the application using their smartphones and input user information such as dietary preferences, allergy information, and lifestyle. This input is done through the application's interface, and the information is transmitted to the server via the device. As output, the user information is provided to the server as formalized digital data.

[0209] Step 2:

[0210] The device uses a camera and microphone to acquire the user's facial expressions and voice data in real time. This provides input data for emotion recognition. The acquired data is sent from the device to the server and becomes basic data for identifying the user's emotional state. As output, analyzable data of facial expressions and voice is transferred to the server.

[0211] Step 3:

[0212] The server analyzes received user information and emotion recognition data using a generating AI model to create a user's eating profile. Input data also includes past meal history. The analysis results in a comprehensive eating profile that reflects the user's preferences, eating patterns, and emotional state.

[0213] Step 4:

[0214] The server creates a list of suggested foods and establishments based on the generated food profile. The input is a food profile, and based on this, options that the user has not yet experienced but is likely to like are determined. The suggested options are output as text data and sent to the terminal via the API.

[0215] Step 5:

[0216] The user terminal notifies the server of suggested options, and the user makes a selection from the suggested menu. Input data is generated based on the user's selection, and the delivery order process proceeds.

[0217] Step 6:

[0218] Users provide feedback on the meals they try via their device. This feedback includes emotional responses and is sent from the device to the server. The input is feedback data, which is used as output to improve the accuracy of the system's recommendations.

[0219] Step 7:

[0220] The server stores the received feedback and uses it to improve new analysis algorithms. The input is feedback data, and the analysis results are reflected in the generation of future proposal candidates. This results in proposals that are more tailored to individual users.

[0221] 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.

[0222] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] This invention describes an embodiment of a system that proposes new foods and serving locations to users in order to broaden their dining experience. The system primarily functions through a flow of data collection, analysis, proposal, and feedback between a server, terminals, and users.

[0238] 1. Collection of user information

[0239] Users input personal information such as dietary preferences, allergy information, and lifestyle habits into a terminal using a dedicated application or web interface. The terminal transmits this information to a server. Furthermore, the server collaborates with external sources to obtain the user's dietary history data.

[0240] 2. Data Analysis and Profile Generation

[0241] The server uses an AI algorithm to analyze received user information and meal history data collected from external sources. This analysis takes into account the user's taste preferences, eating patterns, and meal frequency to generate an individualized meal profile. This narrows down the list of optimal suggestions for each user.

[0242] 3. Proposal generation and notification

[0243] Based on the generated profile, the server creates a list of suggested foods that the user has not yet tried but is likely to enjoy. These suggestions include information about the characteristics of each dish and the establishments that serve them. The server then notifies the user of these suggestions on their device.

[0244] 4. Gathering feedback and improving the system

[0245] Users who receive a suggestion try the suggested food and send feedback from their device. This feedback includes opinions on the taste of the dish, satisfaction level, and whether it was a new discovery. The server collects this feedback and updates the system's AI algorithm to improve the accuracy of future suggestions.

[0246] Specific example

[0247] For example, let's assume a user primarily eats Japanese food. This user registers with the app and enters their food preferences. The server generates a profile based on past meal history and suggests "sauerkraut and sausage," a German dish. Although this dish is different from the user's usual Japanese food, the server's analysis determines that it is likely to suit the user's preferences. The user follows this suggestion, tries the suggested recipe, or orders it at a restaurant, thereby gaining a new taste experience.

[0248] In this way, users can discover unfamiliar foods through the system and expand their culinary horizons. This invention not only suggests foods but also provides suggestions tailored to the user's preferences and evolves the system based on feedback, thereby offering a more effective dining experience.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] Users access the application through their device and enter personal information, dietary preferences, allergy information, etc. The device then sends this information to the server.

[0252] Step 2:

[0253] The server connects to external sources via APIs to retrieve the user's past meal history data. The retrieved data is stored in a database.

[0254] Step 3:

[0255] The server uses an AI algorithm to analyze the received user information and meal history data to generate a user's food profile. This profile reflects the user's preferred types of food and taste preferences.

[0256] Step 4:

[0257] Based on the analysis results, the server generates suggested food items and establishments that the user has not yet experienced and is likely to enjoy.

[0258] Step 5:

[0259] The server notifies the user's terminal of the generated suggestions. The user can review the suggestions through their terminal and, if interested, obtain information on how to try the suggested dishes.

[0260] Step 6:

[0261] After trying the suggested dish, the user sends feedback to the server using their device. This feedback includes an evaluation of the experience.

[0262] Step 7:

[0263] The server analyzes the collected feedback and updates its AI algorithm to improve the accuracy of future suggestions.

[0264] (Example 1)

[0265] 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."

[0266] The challenge lies in providing a system that accurately understands individual food preferences and eating patterns, and proposes new dining experiences to users. Conventional systems have struggled to effectively utilize user feedback to improve the accuracy of their suggestions.

[0267] 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.

[0268] In this invention, the server includes means for receiving user attributes, means for acquiring dining history information from multiple sources, means for analyzing the collected data and generating a user's food profile, and means for adaptively improving the accuracy of suggestions using a generation AI model. This makes it possible to suggest foods that are suitable for each individual user and to improve the accuracy of suggestions for the next time by utilizing feedback.

[0269] "User attributes" refer to personalized information such as individual user preferences, allergy information, and lifestyle habits.

[0270] "Dining history information" refers to records of past meals and order history obtained from external data sources.

[0271] A "food profile" is a data profile used to analyze a user's preferences and eating patterns, and to provide personalized recommendations.

[0272] "Information sources" refer to various systems and databases that provide information on dining history from external sources.

[0273] An "analysis algorithm" is a set of calculation procedures that use collected data to understand user preferences and eating patterns, and then use that information to generate suggestions.

[0274] A "generative AI model" is a model that applies machine learning and artificial intelligence technologies to improve the accuracy of suggestions based on user feedback.

[0275] "Recommendation accuracy" is an indicator that shows the accuracy and suitability of food recommendations tailored to the user's preferences.

[0276] This system aims to improve users' dining experiences by suggesting new foods and serving locations. The system is primarily based on the exchange of information between servers, terminals, and users, establishing a flow of data collection, analysis, suggestion, and feedback.

[0277] Users input attributes such as their dietary preferences, allergy information, and lifestyle into a terminal using a dedicated application or web interface. This data is then transmitted from the terminal to the server.

[0278] The server organizes the received user attributes and retrieves dining history information in conjunction with external sources. These external sources include restaurant reservation systems and online ordering platforms. This allows the server to understand the user's past dining history.

[0279] The collected data is analyzed on the server. The analysis utilizes analytical algorithms equipped with generative AI models. For example, machine learning libraries such as TensorFlow and sclearn are used to analyze user preferences and eating patterns, generating food profiles. Based on these profiles, suggestions for foods the user has not yet tried but is likely to enjoy are generated.

[0280] The server notifies the user's terminal of the generated suggestions. The suggestions include information about the characteristics of the suggested dishes and the establishments that serve them. Based on this information, the user can try new foods.

[0281] For example, if a user typically eats mainly Japanese food, the server will suggest German dishes such as "sauerkraut and sausage" based on that profile. This suggestion encourages a new experience beyond their usual eating habits. Another example of a prompt for a generative AI model would be, "Create an algorithm for the AI ​​to suggest foreign dishes to a user who likes Japanese food."

[0282] User feedback is sent back to the server from the device and used to readjust the generated AI model. This improves the accuracy of suggestions and maximizes user satisfaction. In this way, the system provides an effective dining experience through continuous improvement and adaptation.

[0283] The process of a specific treatment in Example 1 will be described with reference to FIG. 11.

[0284] Step 1:

[0285] The user uses a dedicated application or web interface to input attributes such as their dietary preferences, allergy information, and lifestyle habits into the terminal. This input data is encoded in JSON format and sent from the terminal to the server. When the server receives it, user attribute data is input.

[0286] Step 2:

[0287] The server organizes the received user attributes and saves them in the database. In this saving process, the user ID is used as the key to enable data consistency and rapid retrieval. Based on this information, the server cooperates with external information sources to obtain dietary history information. The external information sources are connected through an application programming interface (API). The obtained dietary history information is added to the database.

[0288] Step 3:

[0289] The server inputs the user attributes and dietary history information saved in the database into the AI algorithm. Using the generated AI model, it analyzes the user's preferences and eating patterns and generates a food profile. This profile includes foods and eating trends that the user is likely to like. As output, the generated food profile is obtained.

[0290] Step 4:

[0291] The server creates proposals suitable for the user based on the generated food profile. The proposals include information on foods that the user has not experienced but is likely to like and information on the providing facilities. This includes a list of foods selected using a recommendation algorithm. The generated proposals are sent to the terminal.

[0292] Step 5:

[0293] Users can review the suggestions received on their device and try foods that interest them. After trying the food, users input their results as feedback on their device. This feedback includes taste evaluations and comments on any new discoveries. This data is then sent back to the server in JSON format and treated as input data.

[0294] Step 6:

[0295] The server stores the received feedback in a database and retrains the generating AI model. This retraining process improves the accuracy of subsequent suggestions. By leveraging this feedback loop, the server can provide more appropriate suggestions to the user.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] In today's increasingly diverse food landscape, it's not easy for users to efficiently discover new dining experiences that match their preferences. Furthermore, traditional food delivery services tend to be biased towards foods and establishments that users have already experienced, making it difficult to broaden their dining horizons. Against this backdrop, there is a need for a system that suggests foods that users might like, even if they haven't tried them before, based on their preferences and past dining habits, thereby providing new dining experiences.

[0299] 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.

[0300] In this invention, the server includes means for receiving user information, means for acquiring meal history data from multiple external sources, means for analyzing the collected data and generating a user's food profile, means for generating suggested dishes based on the user's profile, means for notifying the user terminal of the suggested dishes, means for collecting user feedback and improving the system, and means for analyzing the user's preferences and taking orders to provide previously unexperienced meals. This enables users to efficiently discover new dining experiences that align with their preferences.

[0301] "Means of receiving user information" refers to methods by which the system acquires personal data such as preferences, allergy information, and lifestyle habits entered by the user.

[0302] "Methods for obtaining meal history data from external sources" refers to methods of integrating with third-party services or databases to obtain a user's past meal history.

[0303] "Methods for analyzing data and generating user dietary profiles" refers to methods that use acquired user information and meal history data to analyze users' taste preferences and eating patterns, thereby revealing individual dietary preferences.

[0304] "Methods for generating suggested items" refers to methods that suggest foods and facilities that the user has not yet experienced but are likely to match their preferences, based on the user's food profile.

[0305] "Means for notifying user terminals of proposed suggestions" refers to a method of sending generated suggestions to the information device used by the user to inform the user.

[0306] "Methods for collecting feedback and improving the system" refers to methods of collecting opinions and evaluations from users and using those results to improve the accuracy of suggestions and the overall performance of the system.

[0307] The means of "ordering means for analyzing the user's orientation and providing unexperienced meals" is a method for analyzing the user's preferences in detail and providing new foods that the user has not yet experienced as food delivery.

[0308] This invention is composed of a system aimed at enabling users to efficiently obtain new food experiences through a food delivery service. The system mainly uses a smartphone, a cloud server, and AI algorithms.

[0309] The server is responsible for receiving user information. The user inputs personal data such as their food preferences, allergy information, and lifestyle habits using an application on their smartphone, and this information is sent to the server. The server also collects meal history data from external sources and records the user's past food behaviors based on this.

[0310] Next, the server analyzes this data. Specifically, using AI algorithms (such as TensorFlow or PyTorch), it analyzes the user's taste preferences and meal patterns to generate individual food profiles. Based on this profile, a list of foods and providing facilities that the user has not experienced but are likely to match their preferences is generated.

[0311] The generated proposal candidates are notified to the user via the notification function of the smartphone (such as Firebase Cloud Messaging). The user orders the proposed foods through the application and sends feedback on this experience. [[ID=1十八]]

[0312] The feedback returns to the server, and the feedback data is used via the AI algorithm to improve the accuracy of the next proposal. As a result, the proposal process is continuously improved, and more personalized proposals are made.

[0313] For example, if it is detected that the user usually prefers vegetarian food, a unique menu plan from a vegan restaurant can be suggested. An example of a prompt message might be, "Please recommend the following vegetarian dishes. The user usually tends to prefer XX."

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1:

[0316] Users use their smartphones to input personal information such as their food preferences, allergy information, and lifestyle habits. This data is then transmitted from the device to the server. The input includes information in text and selection formats, and the server receives user information as output.

[0317] Step 2:

[0318] The server retrieves user meal history data from an external source. This retrieval process involves accessing a third-party service's database via an API and downloading data such as the user's past order history and ratings. The input is API data from an external source, and the output is meal history data stored on the server.

[0319] Step 3:

[0320] The server analyzes collected user information and meal history data. Specifically, it runs AI algorithms (using TensorFlow or PyTorch) to analyze the user's taste preferences and eating patterns. As a result of the analysis, a user's food profile is generated. The input is personal information and history data, and the output is the user's profile.

[0321] Step 4:

[0322] The server generates suggested options based on the generated user profile. In this process, the AI ​​selects foods and establishments that the user may have not experienced and might enjoy. The output is a list of suggested options.

[0323] Step 5:

[0324] Potential proposals are notified from the server to the user's device. Services such as Firebase Cloud Messaging are used for notifications, ensuring that proposals are communicated to the user in real time. The output is the proposed content displayed on the user's device.

[0325] Step 6:

[0326] Users try the suggested food items and send feedback about their experience from their device to the server. This feedback includes opinions on satisfaction with the meal and any new discoveries. The input is user feedback data.

[0327] Step 7:

[0328] The server collects user feedback and uses AI algorithms to improve the entire system. It analyzes the feedback data and learns to improve the accuracy of future suggestions. The output is the suggested algorithm with specific improvements.

[0329] 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.

[0330] This invention describes a system that provides more accurate meal recommendations by utilizing user emotional data. This system aims to improve the quality of recommendations by processing information between the server, terminal, and user.

[0331] 1. User information collection and sentiment recognition

[0332] Users access the application through their device and enter personal information such as their dietary preferences, allergy information, and lifestyle. Simultaneously, the emotion engine captures the user's facial expressions and voice data in real time to determine their emotional state. The device then transmits this information to the server.

[0333] 2. Data Analysis and Profile Generation

[0334] The server uses an AI algorithm to analyze collected user information, past meal history, and emotional data acquired by the engine. The analysis generates a food profile that takes into account the user's preferences, eating patterns, and emotional responses. This enables multifaceted suggestions that include the user's emotional satisfaction.

[0335] 3. Generating candidate proposals

[0336] Based on the generated profile, the server lists foods and establishments that the user has not yet experienced but are likely to provide emotional satisfaction. Suggestions include information about the cuisine, the establishments that serve it, and the emotional target audience.

[0337] 4. Notification of proposals and collection of feedback

[0338] The server notifies the user's device of suggested dishes. After trying the suggested dishes, the user uses their device to provide feedback and sends it to the server. This feedback, including emotional reactions to the dishes tried, is reflected in future suggestions.

[0339] Specific example

[0340] For example, consider a user who generally avoids spicy food but is seeking new stimuli. After this user accesses the app and enters their allergy information, an emotion engine measures the user's level of excitement and interest. The server analyzes this data and suggests ethnic dishes with a moderate level of spiciness. These dishes are designed to satisfy the user's curiosity while also providing emotional satisfaction. Through these suggestions, users can enjoy new culinary experiences and broaden their culinary horizons with the system's recommendations.

[0341] The following describes the processing flow.

[0342] Step 1:

[0343] The user launches a dedicated application on their device and enters their dietary preferences and allergy information. The device then uses an emotion engine to capture the user's voice and facial expression data and analyze their emotional state.

[0344] Step 2:

[0345] The terminal transmits collected preference and emotional data to the server. The server, in cooperation with an external source, retrieves the user's past meal history data and stores it in a database.

[0346] Step 3:

[0347] The server analyzes acquired meal history data, preference data, and emotional data using an AI algorithm. This analysis generates a user's food profile, including taste preferences, eating patterns, and emotional analysis information.

[0348] Step 4:

[0349] Based on the profile, the server generates suggested dishes and restaurants that are suitable for the user and that they may not have tried before. The suggested dishes include an overview of each dish and elements that take into account emotional satisfaction.

[0350] Step 5:

[0351] The server sends suggested proposals as notifications to the user's device. The user reviews the proposals on their device and tries out any that interest them.

[0352] Step 6:

[0353] Users send feedback to the server via their device, expressing their thoughts and emotional reactions to the dishes they try.

[0354] Step 7:

[0355] The server analyzes the feedback received and updates its AI algorithms to improve the accuracy of future suggestions and user satisfaction.

[0356] (Example 2)

[0357] 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".

[0358] Conventional food recommendation systems make suggestions based on user preference data, but the results do not necessarily guarantee user emotional satisfaction. Therefore, there is a need for more personalized recommendations that take into account the user's emotional state.

[0359] 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.

[0360] In this invention, the server includes means for receiving user information, means for capturing emotional data in real time and determining the emotional state, and means for generating suggested products based on a profile that includes the emotional data. This enables more accurate food recommendations that meet the user's emotional and preference needs.

[0361] "User information" refers to data about the user's personal preferences, allergy information, and lifestyle.

[0362] "External sources" refer to external databases or services that provide information about food.

[0363] A "food profile" refers to a record of food preferences generated based on a user's taste preferences, eating patterns, frequency, and emotional responses.

[0364] "Emotional data" refers to information about a user's emotional state obtained by analyzing their facial expressions, voice, and other data.

[0365] "Recommended items" refers to a list of food products and suppliers recommended to the user based on their profile.

[0366] "Feedback" refers to information about the evaluations and emotional responses that users provide after trying a suggested food product.

[0367] "Analysis method" refers to the computational methods and algorithms used to generate user profiles based on collected data.

[0368] In this invention, a food recommendation system achieves highly accurate suggestions based on the user's emotions and preferences by coordinating between a server, terminal, and user. A specific embodiment is shown below.

[0369] The user accesses the application using a device. The device is equipped with sensors, a camera, and a microphone, which collect the user's facial expressions and voice data in real time. The device analyzes this data using software called an emotion engine to determine the user's emotional state. The determined emotional data is then sent to a server.

[0370] The server receives emotional data and user information, including food preferences and meal history, transmitted from the terminal. This data is analyzed using AI algorithms to generate the user's food profile. Commonly used data analysis software and machine learning libraries can be applied to the analysis.

[0371] A concrete example would be a user who likes sweets but also values ​​health. The emotion engine captures the user's facial expression when they see images of sweets and sends this emotion information to the server if they show interest. Based on this, the server suggests establishments that offer low-sugar desserts and notifies the user's device. In this case, the prompt used for input to the generating AI model is, "Please tell us what flavors you usually prefer and what healthy alternatives you would like to try."

[0372] After the server notifies the user of a suggestion, it collects feedback from the user when they actually try the suggested food. This feedback includes their impressions of the dish and changes in their emotional state. The collected feedback is further analyzed by an AI algorithm and used to improve the overall accuracy of the system. This makes it possible to continuously improve the quality of the user experience.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] Users access the application using their device and enter personal information such as dietary preferences, allergy information, and lifestyle. This information is sent from the device to the server. The entered information is treated as user-specific initial data. The device uses a protocol to format the data and send it to the server efficiently.

[0376] Step 2:

[0377] The device uses its camera and microphone to collect the user's facial expressions and voice in real time. This emotional data is analyzed using an emotion engine. Specifically, it uses image recognition and voice analysis to extract the user's emotional state from their smile and voice tone. The device then sends these analysis results to a server.

[0378] Step 3:

[0379] The server receives user information and sentiment data transmitted from the terminal. Based on the received data, it uses an AI algorithm to generate a user's food profile. This profile is a complex model that takes into account the user's preferences and emotional satisfaction. The server then trains the AI ​​model to identify the user's preferred trends.

[0380] Step 4:

[0381] The server creates a list of food items to suggest to the user based on the generated profile. Specifically, it uses a generative AI model to select food items and dining establishments that are likely to emotionally satisfy the user. The output is a list of suggested options for the user, based on the results of algorithmic calculations using the input emotional data and profile.

[0382] Step 5:

[0383] The server notifies the user's device of a list of food suggestions. The information is visually organized so that it can be easily viewed on the user's screen. The user can browse this list and select suggestions that interest them.

[0384] Step 6:

[0385] Users try the suggested food items and provide feedback on their experience. They input specific levels of satisfaction and changes in emotions as feedback. The device uses this feedback and sends the data to the server.

[0386] Step 7:

[0387] The server analyzes the collected feedback to improve the accuracy of future suggestions. The AI ​​algorithm integrates the new feedback data as training data to generate a more refined predictive model. This continuous learning process improves the user experience.

[0388] (Application Example 2)

[0389] 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."

[0390] In modern society, consumer food needs have diversified, and when choosing meals, not only nutritional value and taste are considered, but emotional satisfaction is also important. However, conventional systems do not take emotional states into account when suggesting meals, and have not been able to sufficiently improve the satisfaction users experience with meals. Therefore, there is a need for a system that improves the user experience by utilizing user emotional data and providing optimal meal suggestions tailored to individual circumstances.

[0391] 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.

[0392] In this invention, the server includes means for receiving user information, means for acquiring meal history data from multiple external sources, means for acquiring emotion recognition data for determining the user's emotional state, means for analyzing the collected data to generate the user's eating profile, and means for making meal suggestions that take emotional satisfaction into account based on the user's profile. This makes it possible to suggest the optimal meal according to the user's emotional state and improve the user's dining experience.

[0393] "User information" refers to data about the user that the system uses, including information about dietary preferences, allergies, and lifestyle.

[0394] "Dietary history data" refers to data about the food that a user has selected or consumed in the past, and is used to analyze preferences and eating patterns.

[0395] "Emotion recognition data" refers to data obtained from the user's facial expressions and voice, and is used to determine the user's emotional state.

[0396] An "analysis algorithm" is a mathematical method used to generate a user's food profile based on collected data, enabling analysis that takes into account the user's preferences and emotional state.

[0397] A "food profile" is a collection of information that reflects a user's food preferences, patterns, and emotional satisfaction, and serves as the basis for generating suggested options.

[0398] "Suggested options" are lists of food products and establishments generated based on the user's food profile, and include choices that are likely to provide emotional satisfaction even if the user has not experienced them before.

[0399] "Feedback" refers to the response information provided by users after trying a suggested meal, and is used to improve the accuracy of the system's suggestions.

[0400] The system in this invention mainly consists of the interaction between a server, a terminal, and a user. First, the user terminal functions as an input interface for user information, receiving data such as the user's dietary preferences, allergy information, and lifestyle. The terminal also uses a camera and microphone to acquire real-time facial expressions and voice data of the user and transmits emotion recognition data to the server.

[0401] The server analyzes user information and emotion recognition data received from the terminal using AI algorithms. This analysis utilizes generative AI models such as TensorFlow to determine the user's emotional state. Furthermore, the server generates a profile based on the user's past meal history data, constructing a multifaceted food profile that incorporates the user's preferences and emotional satisfaction.

[0402] Next, based on the generated profile, the server suggests foods and establishments that the user has not experienced before but that are likely to be emotionally satisfying. These suggested options are then notified to the user's device via an API using Flask.

[0403] After a user tries a suggested food item, their feedback is collected via their device and sent to a server. This feedback includes the user's emotional response, which is used to continuously improve the system's recommendation accuracy.

[0404] This system allows users to receive meal suggestions optimized for their emotional state, resulting in a more satisfying dining experience.

[0405] For example, if a user is feeling the need to relax, the system may recognize that emotion from the user's facial expressions and voice data and suggest a herbal tea that is expected to have a relaxing effect.

[0406] An example of a prompt message is: "Determine the user's current emotional state based on their facial expressions and voice data, and suggest a meal that is expected to have a relaxing effect."

[0407] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0408] Step 1:

[0409] Users access the application using their smartphones and input user information such as dietary preferences, allergy information, and lifestyle. This input is done through the application's interface, and the information is transmitted to the server via the device. As output, the user information is provided to the server as formalized digital data.

[0410] Step 2:

[0411] The device uses a camera and microphone to acquire the user's facial expressions and voice data in real time. This provides input data for emotion recognition. The acquired data is sent from the device to the server and becomes basic data for identifying the user's emotional state. As output, analyzable data of facial expressions and voice is transferred to the server.

[0412] Step 3:

[0413] The server analyzes received user information and emotion recognition data using a generating AI model to create a user's eating profile. Input data also includes past meal history. The analysis results in a comprehensive eating profile that reflects the user's preferences, eating patterns, and emotional state.

[0414] Step 4:

[0415] The server creates a list of suggested foods and establishments based on the generated food profile. The input is a food profile, and based on this, options that the user has not yet experienced but is likely to like are determined. The suggested options are output as text data and sent to the terminal via the API.

[0416] Step 5:

[0417] The user terminal notifies the server of suggested options, and the user makes a selection from the suggested menu. Input data is generated based on the user's selection, and the delivery order process proceeds.

[0418] Step 6:

[0419] Users provide feedback on the meals they try via their device. This feedback includes emotional responses and is sent from the device to the server. The input is feedback data, which is used as output to improve the accuracy of the system's recommendations.

[0420] Step 7:

[0421] The server stores the received feedback and uses it to improve new analysis algorithms. The input is feedback data, and the analysis results are reflected in the generation of future proposal candidates. This results in proposals that are more tailored to individual users.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] [Third Embodiment]

[0426] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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).

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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".

[0438] This invention describes an embodiment of a system that proposes new foods and serving locations to users in order to broaden their dining experience. The system primarily functions through a flow of data collection, analysis, proposal, and feedback between a server, terminals, and users.

[0439] 1. Collection of user information

[0440] Users input personal information such as dietary preferences, allergy information, and lifestyle habits into a terminal using a dedicated application or web interface. The terminal transmits this information to a server. Furthermore, the server collaborates with external sources to obtain the user's dietary history data.

[0441] 2. Data Analysis and Profile Generation

[0442] The server uses an AI algorithm to analyze received user information and meal history data collected from external sources. This analysis takes into account the user's taste preferences, eating patterns, and meal frequency to generate an individualized meal profile. This narrows down the list of optimal suggestions for each user.

[0443] 3. Proposal generation and notification

[0444] Based on the generated profile, the server creates a list of suggested foods that the user has not yet tried but is likely to enjoy. These suggestions include information about the characteristics of each dish and the establishments that serve them. The server then notifies the user of these suggestions on their device.

[0445] 4. Gathering feedback and improving the system

[0446] Users who receive a suggestion try the suggested food and send feedback from their device. This feedback includes opinions on the taste of the dish, satisfaction level, and whether it was a new discovery. The server collects this feedback and updates the system's AI algorithm to improve the accuracy of future suggestions.

[0447] Specific example

[0448] For example, let's assume a user primarily eats Japanese food. This user registers with the app and enters their food preferences. The server generates a profile based on past meal history and suggests "sauerkraut and sausage," a German dish. Although this dish is different from the user's usual Japanese food, the server's analysis determines that it is likely to suit the user's preferences. The user follows this suggestion, tries the suggested recipe, or orders it at a restaurant, thereby gaining a new taste experience.

[0449] In this way, users can discover unfamiliar foods through the system and expand their culinary horizons. This invention not only suggests foods but also provides suggestions tailored to the user's preferences and evolves the system based on feedback, thereby offering a more effective dining experience.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] Users access the application through their device and enter personal information, dietary preferences, allergy information, etc. The device then sends this information to the server.

[0453] Step 2:

[0454] The server connects to external sources via APIs to retrieve the user's past meal history data. The retrieved data is stored in a database.

[0455] Step 3:

[0456] The server uses an AI algorithm to analyze the received user information and meal history data to generate a user's food profile. This profile reflects the user's preferred types of food and taste preferences.

[0457] Step 4:

[0458] Based on the analysis results, the server generates suggested food items and establishments that the user has not yet experienced and is likely to enjoy.

[0459] Step 5:

[0460] The server notifies the user's terminal of the generated suggestions. The user can review the suggestions through their terminal and, if interested, obtain information on how to try the suggested dishes.

[0461] Step 6:

[0462] After trying the suggested dish, the user sends feedback to the server using their device. This feedback includes an evaluation of the experience.

[0463] Step 7:

[0464] The server analyzes the collected feedback and updates its AI algorithm to improve the accuracy of future suggestions.

[0465] (Example 1)

[0466] 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."

[0467] The challenge lies in providing a system that accurately understands individual food preferences and eating patterns, and proposes new dining experiences to users. Conventional systems have struggled to effectively utilize user feedback to improve the accuracy of their suggestions.

[0468] 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.

[0469] In this invention, the server includes means for receiving user attributes, means for acquiring dining history information from multiple sources, means for analyzing the collected data and generating a user's food profile, and means for adaptively improving the accuracy of suggestions using a generation AI model. This makes it possible to suggest foods that are suitable for each individual user and to improve the accuracy of suggestions for the next time by utilizing feedback.

[0470] "User attributes" refer to personalized information such as individual user preferences, allergy information, and lifestyle habits.

[0471] "Dining history information" refers to records of past meals and order history obtained from external data sources.

[0472] A "food profile" is a data profile used to analyze a user's preferences and eating patterns, and to provide personalized recommendations.

[0473] "Information sources" refer to various systems and databases that provide information on dining history from external sources.

[0474] An "analysis algorithm" is a set of calculation procedures that use collected data to understand user preferences and eating patterns, and then use that information to generate suggestions.

[0475] A "generative AI model" is a model that applies machine learning and artificial intelligence technologies to improve the accuracy of suggestions based on user feedback.

[0476] "Recommendation accuracy" is an indicator that shows the accuracy and suitability of food recommendations tailored to the user's preferences.

[0477] This system aims to improve users' dining experiences by suggesting new foods and serving locations. The system is primarily based on the exchange of information between servers, terminals, and users, establishing a flow of data collection, analysis, suggestion, and feedback.

[0478] Users input attributes such as their dietary preferences, allergy information, and lifestyle into a terminal using a dedicated application or web interface. This data is then transmitted from the terminal to the server.

[0479] The server organizes the received user attributes and retrieves dining history information in conjunction with external sources. These external sources include restaurant reservation systems and online ordering platforms. This allows the server to understand the user's past dining history.

[0480] The collected data is analyzed on the server. The analysis utilizes analytical algorithms equipped with generative AI models. For example, machine learning libraries such as TensorFlow and sclearn are used to analyze user preferences and eating patterns, generating food profiles. Based on these profiles, suggestions for foods the user has not yet tried but is likely to enjoy are generated.

[0481] The server notifies the user's terminal of the generated suggestions. The suggestions include information about the characteristics of the suggested dishes and the establishments that serve them. Based on this information, the user can try new foods.

[0482] For example, if a user typically eats mainly Japanese food, the server will suggest German dishes such as "sauerkraut and sausage" based on that profile. This suggestion encourages a new experience beyond their usual eating habits. Another example of a prompt for a generative AI model would be, "Create an algorithm for the AI ​​to suggest foreign dishes to a user who likes Japanese food."

[0483] User feedback is sent back to the server from the device and used to readjust the generated AI model. This improves the accuracy of suggestions and maximizes user satisfaction. In this way, the system provides an effective dining experience through continuous improvement and adaptation.

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] Users input attributes such as their dietary preferences, allergy information, and lifestyle into their device using a dedicated application or web interface. This input data is encoded in JSON format and sent from the device to the server. Upon receiving this data, the server receives the user attribute data.

[0487] Step 2:

[0488] The server organizes the received user attributes and stores them in a database. This storage process uses the user ID as a key to ensure data consistency and enable quick retrieval. Based on this information, the server collaborates with external sources to retrieve dining history information. The server connects to these external sources via an Application Programming Interface (API). The retrieved dining history information is then added to the database.

[0489] Step 3:

[0490] The server inputs user attributes and dining history information stored in the database into an AI algorithm. Using a generative AI model, it analyzes the user's preferences and eating patterns to generate a food profile. This profile includes foods the user is likely to like and their eating tendencies. The generated food profile is obtained as output.

[0491] Step 4:

[0492] The server creates personalized suggestions for the user based on the generated food profile. These suggestions include information on foods the user may not have tried but is likely to enjoy, as well as information on establishments that serve them. This includes a list of foods selected using a recommendation algorithm. The generated suggestions are then sent to the terminal.

[0493] Step 5:

[0494] Users can review the suggestions received on their device and try foods that interest them. After trying the food, users input their results as feedback on their device. This feedback includes taste evaluations and comments on any new discoveries. This data is then sent back to the server in JSON format and treated as input data.

[0495] Step 6:

[0496] The server stores the received feedback in a database and retrains the generating AI model. This retraining process improves the accuracy of subsequent suggestions. By leveraging this feedback loop, the server can provide more appropriate suggestions to the user.

[0497] (Application Example 1)

[0498] 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."

[0499] In today's increasingly diverse food landscape, it's not easy for users to efficiently discover new dining experiences that match their preferences. Furthermore, traditional food delivery services tend to be biased towards foods and establishments that users have already experienced, making it difficult to broaden their dining horizons. Against this backdrop, there is a need for a system that suggests foods that users might like, even if they haven't tried them before, based on their preferences and past dining habits, thereby providing new dining experiences.

[0500] 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.

[0501] In this invention, the server includes means for receiving user information, means for acquiring meal history data from multiple external sources, means for analyzing the collected data and generating a user's food profile, means for generating suggested dishes based on the user's profile, means for notifying the user terminal of the suggested dishes, means for collecting user feedback and improving the system, and means for analyzing the user's preferences and taking orders to provide previously unexperienced meals. This enables users to efficiently discover new dining experiences that align with their preferences.

[0502] "Means of receiving user information" refers to methods by which the system acquires personal data such as preferences, allergy information, and lifestyle habits entered by the user.

[0503] "Methods for obtaining meal history data from external sources" refers to methods of integrating with third-party services or databases to obtain a user's past meal history.

[0504] "Methods for analyzing data and generating user dietary profiles" refers to methods that use acquired user information and meal history data to analyze users' taste preferences and eating patterns, thereby revealing individual dietary preferences.

[0505] "Methods for generating suggested items" refers to methods that suggest foods and facilities that the user has not yet experienced but are likely to match their preferences, based on the user's food profile.

[0506] "Means for notifying user terminals of proposed suggestions" refers to a method of sending generated suggestions to the information device used by the user to inform the user.

[0507] "Methods for collecting feedback and improving the system" refers to methods of collecting opinions and evaluations from users and using those results to improve the accuracy of suggestions and the overall performance of the system.

[0508] "An order-taking method that analyzes user preferences and provides previously unexperienced meals" refers to a method of providing new foods that users have not yet experienced as food delivery, based on a detailed analysis of their preferences.

[0509] This invention consists of a system designed to enable users to efficiently obtain new dining experiences through food delivery services. The system primarily utilizes smartphones, cloud servers, and AI algorithms.

[0510] The server is responsible for receiving user information. Users input personal data such as their food preferences, allergy information, and lifestyle habits using an application on their smartphone, and this information is sent to the server. The server also collects dietary history data from external sources and uses this to record the user's past eating behavior.

[0511] Next, the server analyzes this data. Specifically, it uses AI algorithms (e.g., TensorFlow or PyTorch) to analyze the user's taste preferences and eating patterns, and generates an individual food profile. Based on this profile, it generates a list of foods and establishments that the user has not yet experienced but are likely to match their preferences.

[0512] The generated suggestions are notified to the user via smartphone notification features (such as Firebase Cloud Messaging). The user orders the suggested food items through the application and submits feedback about the experience.

[0513] The feedback is returned to the server, and the feedback data is used via an AI algorithm to improve the accuracy of future suggestions. This allows the suggestion process to continuously improve, resulting in more personalized suggestions.

[0514] For example, if it is detected that the user usually prefers vegetarian food, a unique menu plan from a vegan restaurant can be suggested. An example of a prompt message might be, "Please recommend the following vegetarian dishes. The user usually tends to prefer XX."

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] Users use their smartphones to input personal information such as their food preferences, allergy information, and lifestyle habits. This data is then transmitted from the device to the server. The input includes information in text and selection formats, and the server receives user information as output.

[0518] Step 2:

[0519] The server retrieves user meal history data from an external source. This retrieval process involves accessing a third-party service's database via an API and downloading data such as the user's past order history and ratings. The input is API data from an external source, and the output is meal history data stored on the server.

[0520] Step 3:

[0521] The server analyzes collected user information and meal history data. Specifically, it runs AI algorithms (using TensorFlow or PyTorch) to analyze the user's taste preferences and eating patterns. As a result of the analysis, a user's food profile is generated. The input is personal information and history data, and the output is the user's profile.

[0522] Step 4:

[0523] The server generates suggested options based on the generated user profile. In this process, the AI ​​selects foods and establishments that the user may have not experienced and might enjoy. The output is a list of suggested options.

[0524] Step 5:

[0525] Potential proposals are notified from the server to the user's device. Services such as Firebase Cloud Messaging are used for notifications, ensuring that proposals are communicated to the user in real time. The output is the proposed content displayed on the user's device.

[0526] Step 6:

[0527] Users try the suggested food items and send feedback about their experience from their device to the server. This feedback includes opinions on satisfaction with the meal and any new discoveries. The input is user feedback data.

[0528] Step 7:

[0529] The server collects user feedback and uses AI algorithms to improve the entire system. It analyzes the feedback data and learns to improve the accuracy of future suggestions. The output is the suggested algorithm with specific improvements.

[0530] 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.

[0531] This invention describes a system that provides more accurate meal recommendations by utilizing user emotional data. This system aims to improve the quality of recommendations by processing information between the server, terminal, and user.

[0532] 1. User information collection and sentiment recognition

[0533] Users access the application through their device and enter personal information such as their dietary preferences, allergy information, and lifestyle. Simultaneously, the emotion engine captures the user's facial expressions and voice data in real time to determine their emotional state. The device then transmits this information to the server.

[0534] 2. Data Analysis and Profile Generation

[0535] The server uses an AI algorithm to analyze collected user information, past meal history, and emotional data acquired by the engine. The analysis generates a food profile that takes into account the user's preferences, eating patterns, and emotional responses. This enables multifaceted suggestions that include the user's emotional satisfaction.

[0536] 3. Generating candidate proposals

[0537] Based on the generated profile, the server lists foods and establishments that the user has not yet experienced but are likely to provide emotional satisfaction. Suggestions include information about the cuisine, the establishments that serve it, and the emotional target audience.

[0538] 4. Notification of proposals and collection of feedback

[0539] The server notifies the user's device of suggested dishes. After trying the suggested dishes, the user uses their device to provide feedback and sends it to the server. This feedback, including emotional reactions to the dishes tried, is reflected in future suggestions.

[0540] Specific example

[0541] For example, consider a user who generally avoids spicy food but is seeking new stimuli. After this user accesses the app and enters their allergy information, an emotion engine measures the user's level of excitement and interest. The server analyzes this data and suggests ethnic dishes with a moderate level of spiciness. These dishes are designed to satisfy the user's curiosity while also providing emotional satisfaction. Through these suggestions, users can enjoy new culinary experiences and broaden their culinary horizons with the system's recommendations.

[0542] The following describes the processing flow.

[0543] Step 1:

[0544] The user launches a dedicated application on their device and enters their dietary preferences and allergy information. The device then uses an emotion engine to capture the user's voice and facial expression data and analyze their emotional state.

[0545] Step 2:

[0546] The terminal transmits collected preference and emotional data to the server. The server, in cooperation with an external source, retrieves the user's past meal history data and stores it in a database.

[0547] Step 3:

[0548] The server analyzes acquired meal history data, preference data, and emotional data using an AI algorithm. This analysis generates a user's food profile, including taste preferences, eating patterns, and emotional analysis information.

[0549] Step 4:

[0550] Based on the profile, the server generates suggested dishes and restaurants that are suitable for the user and that they may not have tried before. The suggested dishes include an overview of each dish and elements that take into account emotional satisfaction.

[0551] Step 5:

[0552] The server sends suggested proposals as notifications to the user's device. The user reviews the proposals on their device and tries out any that interest them.

[0553] Step 6:

[0554] Users send feedback to the server via their device, expressing their thoughts and emotional reactions to the dishes they try.

[0555] Step 7:

[0556] The server analyzes the feedback received and updates its AI algorithms to improve the accuracy of future suggestions and user satisfaction.

[0557] (Example 2)

[0558] 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."

[0559] Conventional food recommendation systems make suggestions based on user preference data, but the results do not necessarily guarantee user emotional satisfaction. Therefore, there is a need for more personalized recommendations that take into account the user's emotional state.

[0560] 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.

[0561] In this invention, the server includes means for receiving user information, means for capturing emotional data in real time and determining the emotional state, and means for generating suggested products based on a profile that includes the emotional data. This enables more accurate food recommendations that meet the user's emotional and preference needs.

[0562] "User information" refers to data about the user's personal preferences, allergy information, and lifestyle.

[0563] "External sources" refer to external databases or services that provide information about food.

[0564] A "food profile" refers to a record of food preferences generated based on a user's taste preferences, eating patterns, frequency, and emotional responses.

[0565] "Emotional data" refers to information about a user's emotional state obtained by analyzing their facial expressions, voice, and other data.

[0566] "Recommended items" refers to a list of food products and suppliers recommended to the user based on their profile.

[0567] "Feedback" refers to information about the evaluations and emotional responses that users provide after trying a suggested food product.

[0568] "Analysis method" refers to the computational methods and algorithms used to generate user profiles based on collected data.

[0569] In this invention, a food recommendation system achieves highly accurate suggestions based on the user's emotions and preferences by coordinating between a server, terminal, and user. A specific embodiment is shown below.

[0570] The user accesses the application using a device. The device is equipped with sensors, a camera, and a microphone, which collect the user's facial expressions and voice data in real time. The device analyzes this data using software called an emotion engine to determine the user's emotional state. The determined emotional data is then sent to a server.

[0571] The server receives emotional data and user information, including food preferences and meal history, transmitted from the terminal. This data is analyzed using AI algorithms to generate the user's food profile. Commonly used data analysis software and machine learning libraries can be applied to the analysis.

[0572] A concrete example would be a user who likes sweets but also values ​​health. The emotion engine captures the user's facial expression when they see images of sweets and sends this emotion information to the server if they show interest. Based on this, the server suggests establishments that offer low-sugar desserts and notifies the user's device. In this case, the prompt used for input to the generating AI model is, "Please tell us what flavors you usually prefer and what healthy alternatives you would like to try."

[0573] After the server notifies the user of a suggestion, it collects feedback from the user when they actually try the suggested food. This feedback includes their impressions of the dish and changes in their emotional state. The collected feedback is further analyzed by an AI algorithm and used to improve the overall accuracy of the system. This makes it possible to continuously improve the quality of the user experience.

[0574] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0575] Step 1:

[0576] Users access the application using their device and enter personal information such as dietary preferences, allergy information, and lifestyle. This information is sent from the device to the server. The entered information is treated as user-specific initial data. The device uses a protocol to format the data and send it to the server efficiently.

[0577] Step 2:

[0578] The device uses its camera and microphone to collect the user's facial expressions and voice in real time. This emotional data is analyzed using an emotion engine. Specifically, it uses image recognition and voice analysis to extract the user's emotional state from their smile and voice tone. The device then sends these analysis results to a server.

[0579] Step 3:

[0580] The server receives user information and sentiment data transmitted from the terminal. Based on the received data, it uses an AI algorithm to generate a user's food profile. This profile is a complex model that takes into account the user's preferences and emotional satisfaction. The server then trains the AI ​​model to identify the user's preferred trends.

[0581] Step 4:

[0582] The server creates a list of food items to suggest to the user based on the generated profile. Specifically, it uses a generative AI model to select food items and dining establishments that are likely to emotionally satisfy the user. The output is a list of suggested options for the user, based on the results of algorithmic calculations using the input emotional data and profile.

[0583] Step 5:

[0584] The server notifies the user's device of a list of food suggestions. The information is visually organized so that it can be easily viewed on the user's screen. The user can browse this list and select suggestions that interest them.

[0585] Step 6:

[0586] Users try the suggested food items and provide feedback on their experience. They input specific levels of satisfaction and changes in emotions as feedback. The device uses this feedback and sends the data to the server.

[0587] Step 7:

[0588] The server analyzes the collected feedback to improve the accuracy of future suggestions. The AI ​​algorithm integrates the new feedback data as training data to generate a more refined predictive model. This continuous learning process improves the user experience.

[0589] (Application Example 2)

[0590] 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."

[0591] In modern society, consumer food needs have diversified, and when choosing meals, not only nutritional value and taste are considered, but emotional satisfaction is also important. However, conventional systems do not take emotional states into account when suggesting meals, and have not been able to sufficiently improve the satisfaction users experience with meals. Therefore, there is a need for a system that improves the user experience by utilizing user emotional data and providing optimal meal suggestions tailored to individual circumstances.

[0592] 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.

[0593] In this invention, the server includes means for receiving user information, means for acquiring meal history data from multiple external sources, means for acquiring emotion recognition data for determining the user's emotional state, means for analyzing the collected data to generate the user's eating profile, and means for making meal suggestions that take emotional satisfaction into account based on the user's profile. This makes it possible to suggest the optimal meal according to the user's emotional state and improve the user's dining experience.

[0594] "User information" refers to data about the user that the system uses, including information about dietary preferences, allergies, and lifestyle.

[0595] "Dietary history data" refers to data about the food that a user has selected or consumed in the past, and is used to analyze preferences and eating patterns.

[0596] "Emotion recognition data" refers to data obtained from the user's facial expressions and voice, and is used to determine the user's emotional state.

[0597] An "analysis algorithm" is a mathematical method used to generate a user's food profile based on collected data, enabling analysis that takes into account the user's preferences and emotional state.

[0598] A "food profile" is a collection of information that reflects a user's food preferences, patterns, and emotional satisfaction, and serves as the basis for generating suggested options.

[0599] "Suggested options" are lists of food products and establishments generated based on the user's food profile, and include choices that are likely to provide emotional satisfaction even if the user has not experienced them before.

[0600] "Feedback" refers to the response information provided by users after trying a suggested meal, and is used to improve the accuracy of the system's suggestions.

[0601] The system in this invention mainly consists of the interaction between a server, a terminal, and a user. First, the user terminal functions as an input interface for user information, receiving data such as the user's dietary preferences, allergy information, and lifestyle. The terminal also uses a camera and microphone to acquire real-time facial expressions and voice data of the user and transmits emotion recognition data to the server.

[0602] The server analyzes user information and emotion recognition data received from the terminal using AI algorithms. This analysis utilizes generative AI models such as TensorFlow to determine the user's emotional state. Furthermore, the server generates a profile based on the user's past meal history data, constructing a multifaceted food profile that incorporates the user's preferences and emotional satisfaction.

[0603] Next, based on the generated profile, the server suggests foods and establishments that the user has not yet experienced but that are likely to be emotionally satisfying. These suggested options are then communicated to the user's device via an API using Flask.

[0604] After a user tries a suggested food item, their feedback is collected via their device and sent to a server. This feedback includes the user's emotional response, which is used to continuously improve the system's recommendation accuracy.

[0605] This system allows users to receive meal suggestions optimized for their emotional state, resulting in a more satisfying dining experience.

[0606] For example, if a user is feeling the need to relax, the system may recognize that emotion from the user's facial expressions and voice data and suggest a herbal tea that is expected to have a relaxing effect.

[0607] An example of a prompt message is: "Determine the user's current emotional state based on their facial expressions and voice data, and suggest a meal that is expected to have a relaxing effect."

[0608] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0609] Step 1:

[0610] Users access the application using their smartphones and input user information such as dietary preferences, allergy information, and lifestyle. This input is done through the application's interface, and the information is transmitted to the server via the device. As output, the user information is provided to the server as formalized digital data.

[0611] Step 2:

[0612] The device uses a camera and microphone to acquire the user's facial expressions and voice data in real time. This provides input data for emotion recognition. The acquired data is sent from the device to the server and becomes basic data for identifying the user's emotional state. As output, analyzable data of facial expressions and voice is transferred to the server.

[0613] Step 3:

[0614] The server analyzes received user information and emotion recognition data using a generating AI model to create a user's eating profile. Input data also includes past meal history. The analysis results in a comprehensive eating profile that reflects the user's preferences, eating patterns, and emotional state.

[0615] Step 4:

[0616] The server creates a list of suggested foods and establishments based on the generated food profile. The input is a food profile, and based on this, options that the user has not yet experienced but is likely to like are determined. The suggested options are output as text data and sent to the terminal via the API.

[0617] Step 5:

[0618] The user terminal notifies the server of suggested options, and the user makes a selection from the suggested menu. Input data is generated based on the user's selection, and the delivery order process proceeds.

[0619] Step 6:

[0620] Users provide feedback on the meals they try via their device. This feedback includes emotional responses and is sent from the device to the server. The input is feedback data, which is used as output to improve the accuracy of the system's recommendations.

[0621] Step 7:

[0622] The server stores the received feedback and uses it to improve new analysis algorithms. The input is feedback data, and the analysis results are reflected in the generation of future proposal candidates. This results in proposals that are more tailored to individual users.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] [Fourth Embodiment]

[0627] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0628] 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.

[0629] 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).

[0630] 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.

[0631] 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.

[0632] 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).

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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".

[0640] This invention describes an embodiment of a system that proposes new foods and serving locations to users in order to broaden their dining experience. The system primarily functions through a flow of data collection, analysis, proposal, and feedback between a server, terminals, and users.

[0641] 1. Collection of user information

[0642] Users input personal information such as dietary preferences, allergy information, and lifestyle habits into a terminal using a dedicated application or web interface. The terminal transmits this information to a server. Furthermore, the server collaborates with external sources to obtain the user's dietary history data.

[0643] 2. Data Analysis and Profile Generation

[0644] The server uses an AI algorithm to analyze received user information and meal history data collected from external sources. This analysis takes into account the user's taste preferences, eating patterns, and meal frequency to generate an individualized meal profile. This narrows down the list of optimal suggestions for each user.

[0645] 3. Proposal generation and notification

[0646] Based on the generated profile, the server creates a list of suggested foods that the user has not yet tried but is likely to enjoy. These suggestions include information about the characteristics of each dish and the establishments that serve them. The server then notifies the user of these suggestions on their device.

[0647] 4. Gathering feedback and improving the system

[0648] Users who receive a suggestion try the suggested food and send feedback from their device. This feedback includes opinions on the taste of the dish, satisfaction level, and whether it was a new discovery. The server collects this feedback and updates the system's AI algorithm to improve the accuracy of future suggestions.

[0649] Specific example

[0650] For example, let's assume a user primarily eats Japanese food. This user registers with the app and enters their food preferences. The server generates a profile based on past meal history and suggests "sauerkraut and sausage," a German dish. Although this dish is different from the user's usual Japanese food, the server's analysis determines that it is likely to suit the user's preferences. The user follows this suggestion, tries the suggested recipe, or orders it at a restaurant, thereby gaining a new taste experience.

[0651] In this way, users can discover unfamiliar foods through the system and expand their culinary horizons. This invention not only suggests foods but also provides suggestions tailored to the user's preferences and evolves the system based on feedback, thereby offering a more effective dining experience.

[0652] The following describes the processing flow.

[0653] Step 1:

[0654] Users access the application through their device and enter personal information, dietary preferences, allergy information, etc. The device then sends this information to the server.

[0655] Step 2:

[0656] The server connects to external sources via APIs to retrieve the user's past meal history data. The retrieved data is stored in a database.

[0657] Step 3:

[0658] The server uses an AI algorithm to analyze the received user information and meal history data to generate a user's food profile. This profile reflects the user's preferred types of food and taste preferences.

[0659] Step 4:

[0660] Based on the analysis results, the server generates suggested food items and establishments that the user has not yet experienced and is likely to enjoy.

[0661] Step 5:

[0662] The server notifies the user's terminal of the generated suggestions. The user can review the suggestions through their terminal and, if interested, obtain information on how to try the suggested dishes.

[0663] Step 6:

[0664] After trying the suggested dish, the user sends feedback to the server using their device. This feedback includes an evaluation of the experience.

[0665] Step 7:

[0666] The server analyzes the collected feedback and updates its AI algorithm to improve the accuracy of future suggestions.

[0667] (Example 1)

[0668] 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".

[0669] The challenge lies in providing a system that accurately understands individual food preferences and eating patterns, and proposes new dining experiences to users. Conventional systems have struggled to effectively utilize user feedback to improve the accuracy of their suggestions.

[0670] 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.

[0671] In this invention, the server includes means for receiving user attributes, means for acquiring dining history information from multiple sources, means for analyzing the collected data and generating a user's food profile, and means for adaptively improving the accuracy of suggestions using a generation AI model. This makes it possible to suggest foods that are suitable for each individual user and to improve the accuracy of suggestions for the next time by utilizing feedback.

[0672] "User attributes" refer to personalized information such as individual user preferences, allergy information, and lifestyle habits.

[0673] "Dining history information" refers to records of past meals and order history obtained from external data sources.

[0674] A "food profile" is a data profile used to analyze a user's preferences and eating patterns, and to provide personalized recommendations.

[0675] "Information sources" refer to various systems and databases that provide information on dining history from external sources.

[0676] An "analysis algorithm" is a set of calculation procedures that use collected data to understand user preferences and eating patterns, and then use that information to generate suggestions.

[0677] A "generative AI model" is a model that applies machine learning and artificial intelligence technologies to improve the accuracy of suggestions based on user feedback.

[0678] "Recommendation accuracy" is an indicator that shows the accuracy and suitability of food recommendations tailored to the user's preferences.

[0679] This system aims to improve users' dining experiences by suggesting new foods and serving locations. The system is primarily based on the exchange of information between servers, terminals, and users, establishing a flow of data collection, analysis, suggestion, and feedback.

[0680] Users input attributes such as their dietary preferences, allergy information, and lifestyle into a terminal using a dedicated application or web interface. This data is then transmitted from the terminal to the server.

[0681] The server organizes the received user attributes and retrieves dining history information in conjunction with external sources. These external sources include restaurant reservation systems and online ordering platforms. This allows the server to understand the user's past dining history.

[0682] The collected data is analyzed on the server. The analysis utilizes analytical algorithms equipped with generative AI models. For example, machine learning libraries such as TensorFlow and sclearn are used to analyze user preferences and eating patterns, generating food profiles. Based on these profiles, suggestions for foods the user has not yet tried but is likely to enjoy are generated.

[0683] The server notifies the user's terminal of the generated suggestions. The suggestions include information about the characteristics of the suggested dishes and the establishments that serve them. Based on this information, the user can try new foods.

[0684] For example, if a user typically eats mainly Japanese food, the server will suggest German dishes such as "sauerkraut and sausage" based on that profile. This suggestion encourages a new experience beyond their usual eating habits. Another example of a prompt for a generative AI model would be, "Create an algorithm for the AI ​​to suggest foreign dishes to a user who likes Japanese food."

[0685] User feedback is sent back to the server from the device and used to readjust the generated AI model. This improves the accuracy of suggestions and maximizes user satisfaction. In this way, the system provides an effective dining experience through continuous improvement and adaptation.

[0686] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0687] Step 1:

[0688] Users input attributes such as their dietary preferences, allergy information, and lifestyle into their device using a dedicated application or web interface. This input data is encoded in JSON format and sent from the device to the server. Upon receiving this data, the server receives the user attribute data.

[0689] Step 2:

[0690] The server organizes the received user attributes and stores them in a database. This storage process uses the user ID as a key to ensure data consistency and enable quick retrieval. Based on this information, the server collaborates with external sources to retrieve dining history information. The server connects to these external sources via an Application Programming Interface (API). The retrieved dining history information is then added to the database.

[0691] Step 3:

[0692] The server inputs user attributes and dining history information stored in the database into an AI algorithm. Using a generative AI model, it analyzes the user's preferences and eating patterns to generate a food profile. This profile includes foods the user is likely to like and their eating tendencies. The generated food profile is obtained as output.

[0693] Step 4:

[0694] The server creates personalized suggestions for the user based on the generated food profile. These suggestions include information on foods the user may not have tried but is likely to enjoy, as well as information on establishments that serve them. This includes a list of foods selected using a recommendation algorithm. The generated suggestions are then sent to the terminal.

[0695] Step 5:

[0696] Users can review the suggestions received on their device and try foods that interest them. After trying the food, users input their results as feedback on their device. This feedback includes taste evaluations and comments on any new discoveries. This data is then sent back to the server in JSON format and treated as input data.

[0697] Step 6:

[0698] The server stores the received feedback in a database and retrains the generating AI model. This retraining process improves the accuracy of subsequent suggestions. By leveraging this feedback loop, the server can provide more appropriate suggestions to the user.

[0699] (Application Example 1)

[0700] 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".

[0701] In today's increasingly diverse food landscape, it's not easy for users to efficiently discover new dining experiences that match their preferences. Furthermore, traditional food delivery services tend to be biased towards foods and establishments that users have already experienced, making it difficult to broaden their dining horizons. Against this backdrop, there is a need for a system that suggests foods that users might like, even if they haven't tried them before, based on their preferences and past dining habits, thereby providing new dining experiences.

[0702] 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.

[0703] In this invention, the server includes means for receiving user information, means for acquiring meal history data from multiple external sources, means for analyzing the collected data and generating a user's food profile, means for generating suggested dishes based on the user's profile, means for notifying the user terminal of the suggested dishes, means for collecting user feedback and improving the system, and means for analyzing the user's preferences and taking orders to provide previously unexperienced meals. This enables users to efficiently discover new dining experiences that align with their preferences.

[0704] "Means of receiving user information" refers to methods by which the system acquires personal data such as preferences, allergy information, and lifestyle habits entered by the user.

[0705] "Methods for obtaining meal history data from external sources" refers to methods of integrating with third-party services or databases to obtain a user's past meal history.

[0706] "Methods for analyzing data and generating user dietary profiles" refers to methods that use acquired user information and meal history data to analyze users' taste preferences and eating patterns, thereby revealing individual dietary preferences.

[0707] "Methods for generating suggested items" refers to methods that suggest foods and facilities that the user has not yet experienced but are likely to match their preferences, based on the user's food profile.

[0708] "Means for notifying user terminals of proposed suggestions" refers to a method of sending generated suggestions to the information device used by the user to inform the user.

[0709] "Methods for collecting feedback and improving the system" refers to methods of collecting opinions and evaluations from users and using those results to improve the accuracy of suggestions and the overall performance of the system.

[0710] "An order-taking method that analyzes user preferences and provides previously unexperienced meals" refers to a method of providing new foods that users have not yet experienced as food delivery, based on a detailed analysis of their preferences.

[0711] This invention consists of a system designed to enable users to efficiently obtain new dining experiences through food delivery services. The system primarily utilizes smartphones, cloud servers, and AI algorithms.

[0712] The server is responsible for receiving user information. Users input personal data such as their food preferences, allergy information, and lifestyle habits using an application on their smartphone, and this information is sent to the server. The server also collects dietary history data from external sources and uses this to record the user's past eating behavior.

[0713] Next, the server analyzes this data. Specifically, it uses AI algorithms (e.g., TensorFlow or PyTorch) to analyze the user's taste preferences and eating patterns, and generates an individual food profile. Based on this profile, it generates a list of foods and establishments that the user has not yet experienced but are likely to match their preferences.

[0714] The generated suggestions are notified to the user via smartphone notification features (such as Firebase Cloud Messaging). The user orders the suggested food items through the application and submits feedback about the experience.

[0715] The feedback is returned to the server, and the feedback data is used via an AI algorithm to improve the accuracy of future suggestions. This allows the suggestion process to continuously improve, resulting in more personalized suggestions.

[0716] For example, if it is detected that the user usually prefers vegetarian food, a unique menu plan from a vegan restaurant can be suggested. An example of a prompt message might be, "Please recommend the following vegetarian dishes. The user usually tends to prefer XX."

[0717] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0718] Step 1:

[0719] Users use their smartphones to input personal information such as their food preferences, allergy information, and lifestyle habits. This data is then transmitted from the device to the server. The input includes information in text and selection formats, and the server receives user information as output.

[0720] Step 2:

[0721] The server retrieves user meal history data from an external source. This retrieval process involves accessing a third-party service's database via an API and downloading data such as the user's past order history and ratings. The input is API data from an external source, and the output is meal history data stored on the server.

[0722] Step 3:

[0723] The server analyzes collected user information and meal history data. Specifically, it runs AI algorithms (using TensorFlow or PyTorch) to analyze the user's taste preferences and eating patterns. As a result of the analysis, a user's food profile is generated. The input is personal information and history data, and the output is the user's profile.

[0724] Step 4:

[0725] The server generates suggested options based on the generated user profile. In this process, the AI ​​selects foods and establishments that the user may have not experienced and might enjoy. The output is a list of suggested options.

[0726] Step 5:

[0727] Potential proposals are notified from the server to the user's device. Services such as Firebase Cloud Messaging are used for notifications, ensuring that proposals are communicated to the user in real time. The output is the proposed content displayed on the user's device.

[0728] Step 6:

[0729] Users try the suggested food items and send feedback about their experience from their device to the server. This feedback includes opinions on satisfaction with the meal and any new discoveries. The input is user feedback data.

[0730] Step 7:

[0731] The server collects user feedback and uses AI algorithms to improve the entire system. It analyzes the feedback data and learns to improve the accuracy of future suggestions. The output is the suggested algorithm with specific improvements.

[0732] 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.

[0733] This invention describes a system that provides more accurate meal recommendations by utilizing user emotional data. This system aims to improve the quality of recommendations by processing information between the server, terminal, and user.

[0734] 1. User information collection and sentiment recognition

[0735] Users access the application through their device and enter personal information such as their dietary preferences, allergy information, and lifestyle. Simultaneously, the emotion engine captures the user's facial expressions and voice data in real time to determine their emotional state. The device then transmits this information to the server.

[0736] 2. Data Analysis and Profile Generation

[0737] The server uses an AI algorithm to analyze collected user information, past meal history, and emotional data acquired by the engine. The analysis generates a food profile that takes into account the user's preferences, eating patterns, and emotional responses. This enables multifaceted suggestions that include the user's emotional satisfaction.

[0738] 3. Generating candidate proposals

[0739] Based on the generated profile, the server lists foods and establishments that the user has not yet experienced but are likely to provide emotional satisfaction. Suggestions include information about the cuisine, the establishments that serve it, and the emotional target audience.

[0740] 4. Notification of proposals and collection of feedback

[0741] The server notifies the user's device of suggested dishes. After trying the suggested dishes, the user uses their device to provide feedback and sends it to the server. This feedback, including emotional reactions to the dishes tried, is reflected in future suggestions.

[0742] Specific example

[0743] For example, consider a user who generally avoids spicy food but is seeking new stimuli. After this user accesses the app and enters their allergy information, an emotion engine measures the user's level of excitement and interest. The server analyzes this data and suggests ethnic dishes with a moderate level of spiciness. These dishes are designed to satisfy the user's curiosity while also providing emotional satisfaction. Through these suggestions, users can enjoy new culinary experiences and broaden their culinary horizons with the system's recommendations.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The user launches a dedicated application on their device and enters their dietary preferences and allergy information. The device then uses an emotion engine to capture the user's voice and facial expression data and analyze their emotional state.

[0747] Step 2:

[0748] The terminal transmits collected preference and emotional data to the server. The server, in cooperation with an external source, retrieves the user's past meal history data and stores it in a database.

[0749] Step 3:

[0750] The server analyzes acquired meal history data, preference data, and emotional data using an AI algorithm. This analysis generates a user's food profile, including taste preferences, eating patterns, and emotional analysis information.

[0751] Step 4:

[0752] Based on the profile, the server generates suggested dishes and restaurants that are suitable for the user and that they may not have tried before. The suggested dishes include an overview of each dish and elements that take into account emotional satisfaction.

[0753] Step 5:

[0754] The server sends suggested proposals as notifications to the user's device. The user reviews the proposals on their device and tries out any that interest them.

[0755] Step 6:

[0756] Users send feedback to the server via their device, expressing their thoughts and emotional reactions to the dishes they try.

[0757] Step 7:

[0758] The server analyzes the feedback received and updates its AI algorithms to improve the accuracy of future suggestions and user satisfaction.

[0759] (Example 2)

[0760] 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".

[0761] Conventional food recommendation systems make suggestions based on user preference data, but the results do not necessarily guarantee user emotional satisfaction. Therefore, there is a need for more personalized recommendations that take into account the user's emotional state.

[0762] 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.

[0763] In this invention, the server includes means for receiving user information, means for capturing emotional data in real time and determining the emotional state, and means for generating suggested products based on a profile that includes the emotional data. This enables more accurate food recommendations that meet the user's emotional and preference needs.

[0764] "User information" refers to data about the user's personal preferences, allergy information, and lifestyle.

[0765] "External sources" refer to external databases or services that provide information about food.

[0766] A "food profile" refers to a record of food preferences generated based on a user's taste preferences, eating patterns, frequency, and emotional responses.

[0767] "Emotional data" refers to information about a user's emotional state obtained by analyzing their facial expressions, voice, and other data.

[0768] "Recommended items" refers to a list of food products and suppliers recommended to the user based on their profile.

[0769] "Feedback" refers to information about the evaluations and emotional responses that users provide after trying a suggested food product.

[0770] "Analysis method" refers to the computational methods and algorithms used to generate user profiles based on collected data.

[0771] In this invention, a food recommendation system achieves highly accurate suggestions based on the user's emotions and preferences by coordinating between a server, terminal, and user. A specific embodiment is shown below.

[0772] The user accesses the application using a device. The device is equipped with sensors, a camera, and a microphone, which collect the user's facial expressions and voice data in real time. The device analyzes this data using software called an emotion engine to determine the user's emotional state. The determined emotional data is then sent to a server.

[0773] The server receives emotional data and user information, including food preferences and meal history, transmitted from the terminal. This data is analyzed using AI algorithms to generate the user's food profile. Commonly used data analysis software and machine learning libraries can be applied to the analysis.

[0774] A concrete example would be a user who likes sweets but also values ​​health. The emotion engine captures the user's facial expression when they see images of sweets and sends this emotion information to the server if they show interest. Based on this, the server suggests establishments that offer low-sugar desserts and notifies the user's device. In this case, the prompt used for input to the generating AI model is, "Please tell us what flavors you usually prefer and what healthy alternatives you would like to try."

[0775] After the server notifies the user of a suggestion, it collects feedback from the user when they actually try the suggested food. This feedback includes their impressions of the dish and changes in their emotional state. The collected feedback is further analyzed by an AI algorithm and used to improve the overall accuracy of the system. This makes it possible to continuously improve the quality of the user experience.

[0776] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0777] Step 1:

[0778] Users access the application using their device and enter personal information such as dietary preferences, allergy information, and lifestyle. This information is sent from the device to the server. The entered information is treated as user-specific initial data. The device uses a protocol to format the data and send it to the server efficiently.

[0779] Step 2:

[0780] The device uses its camera and microphone to collect the user's facial expressions and voice in real time. This emotional data is analyzed using an emotion engine. Specifically, it uses image recognition and voice analysis to extract the user's emotional state from their smile and voice tone. The device then sends these analysis results to a server.

[0781] Step 3:

[0782] The server receives user information and sentiment data transmitted from the terminal. Based on the received data, it uses an AI algorithm to generate a user's food profile. This profile is a complex model that takes into account the user's preferences and emotional satisfaction. The server then trains the AI ​​model to identify the user's preferred trends.

[0783] Step 4:

[0784] The server creates a list of food items to suggest to the user based on the generated profile. Specifically, it uses a generative AI model to select food items and dining establishments that are likely to emotionally satisfy the user. The output is a list of suggested options for the user, based on the results of algorithmic calculations using the input emotional data and profile.

[0785] Step 5:

[0786] The server notifies the user's device of a list of food suggestions. The information is visually organized so that it can be easily viewed on the user's screen. The user can browse this list and select suggestions that interest them.

[0787] Step 6:

[0788] Users try the suggested food items and provide feedback on their experience. They input specific levels of satisfaction and changes in emotions as feedback. The device uses this feedback and sends the data to the server.

[0789] Step 7:

[0790] The server analyzes the collected feedback to improve the accuracy of future suggestions. The AI ​​algorithm integrates the new feedback data as training data to generate a more refined predictive model. This continuous learning process improves the user experience.

[0791] (Application Example 2)

[0792] 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".

[0793] In modern society, consumer food needs have diversified, and when choosing meals, not only nutritional value and taste are considered, but emotional satisfaction is also important. However, conventional systems do not take emotional states into account when suggesting meals, and have not been able to sufficiently improve the satisfaction users experience with meals. Therefore, there is a need for a system that improves the user experience by utilizing user emotional data and providing optimal meal suggestions tailored to individual circumstances.

[0794] 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.

[0795] In this invention, the server includes means for receiving user information, means for acquiring meal history data from multiple external sources, means for acquiring emotion recognition data for determining the user's emotional state, means for analyzing the collected data to generate the user's eating profile, and means for making meal suggestions that take emotional satisfaction into account based on the user's profile. This makes it possible to suggest the optimal meal according to the user's emotional state and improve the user's dining experience.

[0796] "User information" refers to data about the user that the system uses, including information about dietary preferences, allergies, and lifestyle.

[0797] "Dietary history data" refers to data about the food that a user has selected or consumed in the past, and is used to analyze preferences and eating patterns.

[0798] "Emotion recognition data" refers to data obtained from the user's facial expressions and voice, and is used to determine the user's emotional state.

[0799] An "analysis algorithm" is a mathematical method used to generate a user's food profile based on collected data, enabling analysis that takes into account the user's preferences and emotional state.

[0800] A "food profile" is a collection of information that reflects a user's food preferences, patterns, and emotional satisfaction, and serves as the basis for generating suggested options.

[0801] "Suggested options" are lists of food products and establishments generated based on the user's food profile, and include choices that are likely to provide emotional satisfaction even if the user has not experienced them before.

[0802] "Feedback" refers to the response information provided by users after trying a suggested meal, and is used to improve the accuracy of the system's suggestions.

[0803] The system in this invention mainly consists of the interaction between a server, a terminal, and a user. First, the user terminal functions as an input interface for user information, receiving data such as the user's dietary preferences, allergy information, and lifestyle. The terminal also uses a camera and microphone to acquire real-time facial expressions and voice data of the user and transmits emotion recognition data to the server.

[0804] The server analyzes user information and emotion recognition data received from the terminal using AI algorithms. This analysis utilizes generative AI models such as TensorFlow to determine the user's emotional state. Furthermore, the server generates a profile based on the user's past meal history data, constructing a multifaceted food profile that incorporates the user's preferences and emotional satisfaction.

[0805] Next, based on the generated profile, the server suggests foods and establishments that the user has not experienced before but that are likely to be emotionally satisfying. These suggested options are then notified to the user's device via an API using Flask.

[0806] After a user tries a suggested food item, their feedback is collected via their device and sent to a server. This feedback includes the user's emotional response, which is used to continuously improve the system's recommendation accuracy.

[0807] This system allows users to receive meal suggestions optimized for their emotional state, resulting in a more satisfying dining experience.

[0808] For example, if a user is feeling the need to relax, the system may recognize that emotion from the user's facial expressions and voice data and suggest a herbal tea that is expected to have a relaxing effect.

[0809] An example of a prompt message is: "Determine the user's current emotional state based on their facial expressions and voice data, and suggest a meal that is expected to have a relaxing effect."

[0810] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0811] Step 1:

[0812] Users access the application using their smartphones and input user information such as dietary preferences, allergy information, and lifestyle. This input is done through the application's interface, and the information is transmitted to the server via the device. As output, the user information is provided to the server as formalized digital data.

[0813] Step 2:

[0814] The device uses a camera and microphone to acquire the user's facial expressions and voice data in real time. This provides input data for emotion recognition. The acquired data is sent from the device to the server and becomes basic data for identifying the user's emotional state. As output, analyzable data of facial expressions and voice is transferred to the server.

[0815] Step 3:

[0816] The server analyzes received user information and emotion recognition data using a generating AI model to create a user's eating profile. Input data also includes past meal history. The analysis results in a comprehensive eating profile that reflects the user's preferences, eating patterns, and emotional state.

[0817] Step 4:

[0818] The server creates a list of suggested foods and establishments based on the generated food profile. The input is a food profile, and based on this, options that the user has not yet experienced but is likely to like are determined. The suggested options are output as text data and sent to the terminal via the API.

[0819] Step 5:

[0820] The user terminal notifies the server of suggested options, and the user makes a selection from the suggested menu. Input data is generated based on the user's selection, and the delivery order process proceeds.

[0821] Step 6:

[0822] Users provide feedback on the meals they try via their device. This feedback includes emotional responses and is sent from the device to the server. The input is feedback data, which is used as output to improve the accuracy of the system's recommendations.

[0823] Step 7:

[0824] The server stores the received feedback and uses it to improve new analysis algorithms. The input is feedback data, and the analysis results are reflected in the generation of future proposal candidates. This results in proposals that are more tailored to individual users.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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."

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0846] The following is further disclosed regarding the embodiments described above.

[0847] (Claim 1)

[0848] Means for receiving user information,

[0849] A means of obtaining dietary history data from multiple external sources,

[0850] A means of analyzing collected data and generating a user's dietary profile,

[0851] A means for generating suggested candidates based on the user's profile,

[0852] A means of notifying the user terminal of suggested candidates,

[0853] A means of collecting user feedback and improving the system,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The proposed system according to claim 1 includes information on food products and serving establishments that users have not yet experienced but are likely to like.

[0857] (Claim 3)

[0858] The system according to claim 1, wherein the user profile is created using an analytical algorithm that takes into account taste preferences, eating patterns, and meal frequency.

[0859] "Example 1"

[0860] (Claim 1)

[0861] Means for receiving user attributes,

[0862] A means of obtaining dining history information from multiple sources,

[0863] A means of analyzing collected data and generating a user's food profile,

[0864] A means for generating suggested candidates based on the user's profile,

[0865] A means of notifying the user device of proposed candidates,

[0866] A means of collecting user feedback and improving the system,

[0867] A means of adaptively improving the accuracy of proposals using a generative AI model,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The proposed system according to claim 1 includes information on foods that users have not yet experienced but are likely to like, and places where they can be served.

[0871] (Claim 3)

[0872] The system according to claim 1, wherein the profile creation uses an analytical algorithm that takes into account preferences, eating patterns, and meal frequency.

[0873] "Application Example 1"

[0874] (Claim 1)

[0875] Means for receiving user information,

[0876] A means of obtaining dietary history data from multiple external sources,

[0877] A means of analyzing collected data and generating a user's dietary profile,

[0878] A means for generating suggested candidates based on the user's profile,

[0879] A means of notifying the user terminal of suggested candidates,

[0880] A means of collecting user feedback and improving the system,

[0881] A method of taking orders that analyzes user preferences and provides unprecedented dining experiences,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The proposed system according to claim 1 includes information on food products and serving locations that users have not yet experienced but are likely to like, as well as a delivery method for providing such food products.

[0885] (Claim 3)

[0886] The system according to claim 1, wherein the user profile is created using an analytical algorithm that takes into account taste preferences, eating patterns, and eating frequency, and an artificial intelligence algorithm that predicts future preferences based on the user's order history.

[0887] "Example 2 of combining an emotion engine"

[0888] (Claim 1)

[0889] Means for receiving user information,

[0890] A means of obtaining historical data on food from multiple external sources,

[0891] A means for analyzing collected data and generating a user's food profile,

[0892] A means for capturing user emotion data in real time and determining their emotional state,

[0893] A means for generating suggested candidates based on a profile that includes emotional data,

[0894] A means of notifying the user's device of suggested candidates,

[0895] A means of collecting user feedback and improving the system,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The proposed system according to claim 1 includes information on food products and suppliers that the user has not yet experienced but which are likely to provide emotional and tactile satisfaction.

[0899] (Claim 3)

[0900] The system according to claim 1, wherein the creation of a user profile uses an analytical method that takes into account taste preferences, food patterns, food frequency, and emotional responses.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] Means for receiving user information,

[0904] A means of obtaining dietary history data from multiple external sources,

[0905] A means of analyzing collected data and generating a user's dietary profile,

[0906] A means for generating suggested candidates based on the user's profile,

[0907] A means of notifying the user terminal of suggested candidates,

[0908] A means of collecting user feedback and improving the system,

[0909] A means of obtaining emotion recognition data from the user to determine the emotional state,

[0910] A method for providing meal suggestions that take emotional satisfaction into consideration, based on emotion recognition data,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The proposed system according to claim 1 includes, in addition to information on foods and establishments that the user has not yet experienced but is likely to like, as well as dining characteristics that correspond to the user's emotional state.

[0914] (Claim 3)

[0915] The system according to claim 1, wherein, in addition to an analytical algorithm that considers taste preferences, eating patterns, and eating frequency, an analytical algorithm based on emotional state is used to create a user profile. [Explanation of Symbols]

[0916] 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. Means for receiving user information, A means of obtaining dietary history data from multiple external sources, A means of analyzing collected data and generating a user's dietary profile, A means for generating suggested candidates based on the user's profile, A means of notifying the user terminal of suggested candidates, A means of collecting user feedback and improving the system, A system that includes this.

2. The proposed system according to claim 1 includes information on food products and serving establishments that users have not yet experienced but are likely to like.

3. The system according to claim 1, wherein the user profile is created using an analytical algorithm that takes into account taste preferences, eating patterns, and meal frequency.

Images