System

Abstract

An object of a system according to an embodiment is to recommend an optimal menu item based on individual information of a customer.SOLUTION: A system includes a data collection unit, an analysis unit, and a recommendation unit. The data collection part collects the sex, age, exercise quantity and allergy information of the customer. The analysis unit analyzes the customer data collected by the data collection unit. The recommendation unit recommends an optimum menu on the basis of a result analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult to provide optimal menus based on individual customer information, and there is room for improvement in improving service and reducing food waste.

[0005] The system according to the embodiment aims to recommend the most suitable menu based on individual information of the customer. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, an analysis unit, and a recommendation unit. The data collection unit collects information on the gender, age, amount of exercise, and allergies of customers. The analysis unit analyzes the customer data collected by the data collection unit. The recommendation unit recommends an optimal menu based on the results of the analysis by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can recommend the most suitable menu based on the individual information of the customer. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A recommendation system according to an embodiment of the present invention is a system that recommends optimal menu items based on a customer's gender, age, the amount of exercise that day, and allergy information. By selecting optimal menu items based on individual customer data, the recommendation system can contribute to improving service and reducing food waste.

[0029] A recommendation system according to an embodiment includes a data collection unit, an analysis unit, and a recommendation unit. The data collection unit collects information on a customer's gender, age, amount of exercise, and allergies. For example, the customer can input this information via a smartphone app. The data collection unit can also collect information on the customer's exercise level and facial expressions using sensors and cameras in the store. The analysis unit analyzes the customer data collected by the data collection unit. For example, a generation AI understands the customer's health condition and preferences based on the customer's gender, age, amount of exercise, and allergy information. The generation AI analyzes the customer data using a text generation AI (e.g., LLM) or a multimodal generation AI. The recommendation unit recommends optimal menu items based on the results of the analysis by the analysis unit. For example, the generation AI may suggest a higher-calorie menu item on a day when the customer exercises a lot, or a menu item that does not include specific ingredients based on the customer's allergy information. The generation AI selects a menu item that is optimal for the customer's health condition and preferences. As a result, the recommendation system can recommend optimal menu items based on the customer's individual data, contributing to improved service and reduced food waste.

[0030] The data collection unit can perform analysis based on prompts containing customer data. For example, the data collection unit uses a smartphone app to input a customer's emotional state in real time. For example, the customer may record their current mood and stress level by answering simple questions in the app. The data collection unit also uses cameras and sensors in the store to analyze the customer's facial expressions and body movements to grasp the customer's emotional state in real time. For example, facial recognition technology is used to estimate the customer's emotions from their facial expressions. The data collection unit also analyzes the voice data that the customer uses to input their voice when placing an order to grasp the customer's emotional state. For example, the stress level is estimated from the tone and speed of the voice. This enables more accurate recommendations to be made by analyzing customer data as prompts.

[0031] The analysis unit can recommend menus based on prompts containing instructions about health status or preferences, based on customer data. For example, the analysis unit collects data on menus previously ordered by customers and integrates it with health checkup data. For example, it analyzes nutritional balance based on past meal history and compares it with health checkup results. The analysis unit also allows customers to input health checkup data into the app, and based on that data, suggests menus that take long-term health management into consideration. For example, it selects appropriate ingredients based on blood pressure and blood sugar data. The analysis unit also manages customers' meal history and health checkup data on the cloud, and the generation AI analyzes this data to suggest optimal menus. For example, it accesses a database on the cloud to reflect the latest health information. This makes it possible to meet individual needs by recommending menus based on customers' health status and preferences.

[0032] The recommendation unit can customize menus based on prompts including customization requests based on customer data. The recommendation unit, for example, uses an in-store camera to analyze the facial expressions of customers while they are eating in real time and evaluate their satisfaction. For example, it detects smiling or surprised expressions and scores their satisfaction. The recommendation unit also analyzes the sounds made by customers while they are eating and evaluates their satisfaction. For example, it analyzes conversations and exclamations made during the meal to estimate their satisfaction. The recommendation unit also evaluates their satisfaction based on feedback provided by customers through an app after their meal. For example, it allows customers to enter their satisfaction in a simple questionnaire format. This improves customer satisfaction by providing menus that meet the customers' customization requests.

[0033] The analysis unit performs analysis based on prompts containing feedback based on customer data and can reflect this in the next recommendation. For example, if a customer uses a fitness tracker or smartwatch, the analysis unit links that data with the app. For example, it collects data on exercise volume and heart rate in real time. The analysis unit also uses the fitness tracker or smartwatch's API to automatically obtain the customer's exercise data. For example, it imports data on the number of steps taken and calories burned into the app. The analysis unit also allows customers to manually input their exercise data and suggests menus based on that data. For example, it prompts them to input the number of calories burned after exercise. This allows customer feedback to be reflected in the next recommendation, improving the quality of service.

[0034] The analysis unit analyzes prompts based on customer data, including their eating history, and can suggest appropriate portions. For example, the analysis unit uses microphones in the restaurant to analyze conversations customers make while they eat and automatically updates their preference and allergy information. For example, it detects conversations about specific ingredients and updates allergy information. The analysis unit also allows customers to voice-input their impressions of their meal through the app, analyzes that data, and updates their preference and allergy information. For example, it analyzes comments such as "This dish is delicious." Furthermore, if a customer talks about allergies while eating, the analysis unit automatically updates the database. For example, it analyzes conversations such as "I have a nut allergy." This reduces food waste by suggesting appropriate portions based on the customer's eating history.

[0035] The data collection unit can integrate past meal history and health checkup data based on customer data to propose menus that take long-term health management into consideration. For example, the data collection unit collects data on menus that customers have ordered in the past and integrates it with health checkup data. For example, it analyzes nutritional balance from past meal history and compares it with health checkup results. The data collection unit also allows customers to enter their health checkup data into the app, and based on that data, proposes menus that take long-term health management into consideration. For example, it selects appropriate ingredients based on blood pressure and blood sugar data. The data collection unit also manages customers' meal history and health checkup data on the cloud, and the generation AI analyzes the data to propose optimal menus. For example, it accesses a database on the cloud to reflect the latest health information. This contributes to maintaining health by proposing menus that take long-term health management into consideration.

[0036] The data collection unit can link with a fitness tracker or smartwatch to collect exercise data based on customer data. For example, if a customer uses a fitness tracker or smartwatch, the data collection unit links that data with the app. For example, it collects data on the amount of exercise and heart rate in real time. The data collection unit also uses the fitness tracker's or smartwatch's API to automatically obtain the customer's exercise data. For example, it imports data on the number of steps taken and calories burned into the app. The data collection unit also allows the customer to manually input exercise data and suggests menus based on that data. For example, it prompts the customer to input the amount of calories burned after exercise. In this way, collecting the customer's exercise data enables more accurate menu suggestions.

[0037] The data collection unit can analyze conversations during meals based on customer data and automatically update preference or allergy information. For example, the data collection unit uses microphones in the restaurant to analyze conversations between customers while they are eating and automatically update preference and allergy information. For example, it detects conversations about specific ingredients and updates allergy information. The data collection unit also allows customers to voice-input their impressions of the meal through an app, analyzes that data, and updates preference and allergy information. For example, it analyzes comments such as "This dish is delicious." Furthermore, if a customer talks about allergies during a meal, the data collection unit automatically updates the database. For example, it analyzes conversations such as "I have a nut allergy." This allows for more personalized service to be provided by analyzing customer conversations and automatically updating preference and allergy information.

[0038] The recommendation unit can propose nutritionally balanced menus based on customer data, such as dietary history and exercise data. For example, the recommendation unit analyzes a customer's past dietary history and exercise data to propose nutritionally balanced menus. For example, on days when the customer exercises a lot, it proposes menus high in protein. The recommendation unit also proposes nutritionally balanced menus based on the exercise data the customer enters into the app. For example, it selects ingredients high in vitamins and minerals for a post-exercise recovery menu. The recommendation unit also manages the customer's dietary history and exercise data on the cloud, and the generation AI analyzes this data to propose optimal menus. For example, it accesses a database on the cloud to reflect the latest health information. This contributes to maintaining health by proposing nutritionally balanced menus based on the customer's dietary history and exercise data.

[0039] The recommendation unit can suggest menus according to the season or weather based on customer data, and support health management. The recommendation unit, for example, takes into account seasonal ingredients and suggests menus according to the season. For example, in summer, it suggests menus that emphasize cold dishes and hydration. The recommendation unit also suggests menus that support health management based on weather data. For example, it suggests hot soups and stews on cold days. The recommendation unit also suggests menus that support health management, taking into account nutritional balance according to the season and weather. For example, it selects ingredients that boost immunity at the change of seasons. In this way, it supports customers' health management by suggesting menus according to the season and weather.

[0040] The recommendation unit can automatically update ingredient preferences or allergy information based on customer data and dietary history, and reflect this in the next recommendation. For example, the recommendation unit collects data on menu items a customer has previously ordered and automatically updates ingredient preferences and allergy information. For example, if a customer frequently orders a particular ingredient, it records that ingredient as a preference. The recommendation unit also allows customers to enter allergy information through the app, and reflects this data in the next recommendation. For example, if a customer has a nut allergy, it will suggest a nut-free menu. The recommendation unit also manages customers' dietary history on the cloud, and the generation AI analyzes this data to automatically update ingredient preferences and allergy information. For example, it accesses a cloud-based database to reflect the latest information. This allows preference and allergy information to be automatically updated based on the customer's dietary history and reflected in the next recommendation, enabling a more personalized service to be provided.

[0041] The recommendation unit can suggest menus based on customer data in accordance with health goals. For example, a customer may input their health goals through an app, and the recommendation unit will suggest menus based on that data. For example, if the goal is to lose weight, the recommendation unit will suggest low-calorie, nutritionally balanced menus. The recommendation unit also considers the nutritional balance of the customer's health goals and suggests the optimal menu. For example, if the goal is to increase muscle strength, the recommendation unit will suggest a menu high in protein. The recommendation unit also manages customers' health goals on the cloud, and the generation AI analyzes that data to suggest the optimal menu. For example, it accesses a database on the cloud to reflect the latest health information. This allows the recommendation unit to suggest menus in accordance with the customer's health goals, contributing to maintaining health and achieving those goals.

[0042] The recommendation unit can customize menus in real time based on customer data, such as food preferences or allergy information. For example, a customer can enter their food preferences and allergy information through an app, and the recommendation unit customizes the menu in real time based on that data. For example, if a customer has a nut allergy, the recommendation unit can suggest a menu that excludes nuts. The recommendation unit also allows customers to enter their food preferences and allergy information using a tablet device in the store, and customizes the menu based on that data. For example, it can exclude certain ingredients or adjust the amount. The recommendation unit also manages customer food preferences and allergy information on the cloud, and the generation AI analyzes that data to suggest customized menus in real time. For example, it accesses a cloud-based database to reflect the latest information. This improves customer satisfaction by customizing menus in real time based on customers' food preferences and allergy information.

[0043] The recommendation unit can propose customized menus with optimized nutritional balance based on customer data, dietary history, and health data. For example, the recommendation unit analyzes a customer's past dietary history and health data to propose customized menus with optimized nutritional balance. For example, it might propose a menu high in protein on days when the customer exercises a lot. The recommendation unit also proposes customized menus that take nutritional balance into consideration based on health data entered by the customer into the app. For example, it might propose a menu high in specific nutrients based on health checkup results. The recommendation unit also manages customers' dietary history and health data on the cloud, and the generation AI analyzes this data to propose the optimal customized menu. For example, it accesses a database on the cloud to reflect the latest health information. This contributes to maintaining health by proposing customized menus with optimized nutritional balance based on the customer's dietary history and health data.

[0044] The recommendation unit can propose customized menus based on customer data in accordance with health goals. For example, a customer inputs their health goals through an app, and the recommendation unit proposes customized menus based on that data. For example, if the goal is weight loss, the recommendation unit will propose a low-calorie, nutritionally balanced menu. The recommendation unit also considers the nutritional balance of the customer's health goals and proposes the optimal customized menu. For example, if the goal is to increase muscle strength, the recommendation unit will propose a menu high in protein. The recommendation unit also manages customers' health goals on the cloud, and the generation AI analyzes that data to propose the optimal customized menu. For example, it accesses a database on the cloud to reflect the latest health information. This allows the recommendation unit to propose customized menus based on the customer's health goals, contributing to maintaining health and achieving those goals.

[0045] The analysis unit can analyze feedback based on customer data in real time and reflect it in the next recommendation. For example, after a meal, a customer provides feedback through an app, and the analysis unit analyzes that data in real time to reflect it in the next recommendation. For example, customers enter their satisfaction level and areas for improvement in a simple questionnaire format. The analysis unit also allows customers to enter feedback after a meal using a tablet device in the restaurant, analyzes the data, and reflects it in the next recommendation. For example, it collects opinions about the taste of the food and the service. The analysis unit also manages customer feedback on the cloud, and the generation AI analyzes that data and reflects it in the next recommendation. For example, it accesses a database on the cloud to reflect the latest feedback information. This allows customer feedback to be analyzed in real time and reflected in the next recommendation, improving the quality of service.

[0046] The analysis unit can continuously improve menus or services based on feedback from customer data. For example, customers provide feedback through an app after their meal, and the analysis unit continuously improves menus and services based on that data. For example, customers are asked to enter their satisfaction and areas for improvement in a simple questionnaire format. The analysis unit also uses tablet devices in the restaurant to allow customers to enter feedback after their meal, and analyzes the data to improve menus and services. For example, it collects opinions about the taste of food and service. The analysis unit also manages customer feedback on the cloud, and the generation AI analyzes the data to continuously improve menus and services. For example, it accesses a database on the cloud and reflects the latest feedback information. This allows for continuous improvement of menus and services based on customer feedback, thereby improving the quality of service.

[0047] The analysis unit can provide services tailored to health goals based on customer data. For example, a customer inputs their health goals through an app, and the analysis unit provides services based on that data. For example, if the goal is to lose weight, the analysis unit will suggest a low-calorie, nutritionally balanced menu. The analysis unit also takes into account the nutritional balance of the customer's health goals and provides optimal services. For example, if the goal is to increase muscle strength, the analysis unit will suggest a menu high in protein. The analysis unit also manages customers' health goals on the cloud, and the generation AI analyzes that data to provide optimal services. For example, it accesses a database on the cloud to reflect the latest health information. This allows the analysis unit to provide services tailored to the customer's health goals, contributing to maintaining health and achieving those goals.

[0048] The analysis unit analyzes meal history based on customer data and suggests appropriate portions, thereby reducing food waste. For example, the analysis unit analyzes a customer's past meal history and suggests appropriate portions. For example, it may suggest reducing the portion size of a menu item that has resulted in a lot of leftover food in the past. The analysis unit also has customers input their meal history through the app, and the analysis unit suggests appropriate portions based on that data. For example, it suggests appropriate portion sizes based on past meal amounts. The analysis unit also manages customers' meal history on the cloud, and the generation AI analyzes that data to suggest appropriate portions. For example, it accesses a database on the cloud and reflects the latest meal history. This allows the analysis of customers' meal history and suggests appropriate portions, thereby reducing food waste.

[0049] The analysis unit can suggest appropriate portions based on customer data in accordance with health goals. For example, a customer inputs their health goals through an app, and the analysis unit suggests appropriate portions based on that data. For example, if the goal is to lose weight, the analysis unit suggests a menu with small portions and a balanced nutritional profile. The analysis unit also considers the nutritional balance of the customer's health goals and suggests appropriate portions. For example, if the goal is to build muscle, the analysis unit suggests a menu with an appropriate amount of protein. The analysis unit also manages customers' health goals on the cloud, and the generation AI analyzes that data to suggest appropriate portions. For example, it accesses a database on the cloud to reflect the latest health information. This reduces food waste by suggesting appropriate portions in accordance with the customer's health goals.

[0050] The analysis unit can automatically update ingredient preferences or allergy information based on customer data and meal history, and suggest appropriate portions. For example, the analysis unit collects data on menu items a customer has previously ordered and automatically updates ingredient preferences and allergy information. For example, if a customer frequently orders a particular ingredient, it records that ingredient as a preference and suggests an appropriate portion. The analysis unit also allows customers to enter allergy information through the app, and reflects that data in the next recommendation. For example, if a customer has a nut allergy, it will suggest a nut-free menu and an appropriate portion. The analysis unit also manages customers' meal history on the cloud, and the generation AI analyzes that data to automatically update ingredient preferences and allergy information and suggest appropriate portions. For example, it accesses a cloud-based database to reflect the latest information. This automatically updates preference and allergy information based on the customer's meal history and suggests appropriate portions, reducing food waste.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The recommendation system may further include a purchase history analysis unit that analyzes a customer's purchase history. The purchase history analysis unit, for example, collects data on products and services purchased by the customer in the past and analyzes the customer's preferences and purchasing patterns. For example, if a customer tends to frequently purchase a particular brand or product, it proposes a menu that includes that brand or product. The purchase history analysis unit also analyzes reviews and ratings of products purchased by the customer in the past to understand the customer's satisfaction level. For example, it proposes a menu that includes highly rated products. The purchase history analysis unit also analyzes the seasonality and trends of products purchased by the customer in the past and proposes a menu that matches the season or trend. For example, it proposes a menu that includes seasonal products or trendy products. This makes it possible to improve customer satisfaction by proposing optimal menus based on the customer's purchase history.

[0053] The recommendation system can further include a behavior analysis unit that analyzes customer behavior while eating. The behavior analysis unit, for example, analyzes what behavior a customer exhibits while eating. For example, it analyzes the frequency and duration of smartphone use while eating to grasp the level of concentration while eating. The behavior analysis unit also analyzes the posture of a customer while eating to evaluate the comfort of the meal. For example, if the customer's posture is poor, it suggests a comfortable dining environment. The behavior analysis unit also analyzes the pace at which a customer eats while eating to evaluate the customer's satisfaction with the meal. For example, if the customer eats at a fast pace, it suggests a menu that allows the customer to enjoy a leisurely meal. This makes it possible to improve customer satisfaction by suggesting the optimal menu based on the customer's behavior while eating.

[0054] The recommendation system can further include a behavior analysis unit that analyzes the customer's behavior after eating. The behavior analysis unit, for example, analyzes what behavior the customer will take after eating. For example, it analyzes whether or not the customer will exercise after eating, and suggests a menu suitable for after exercise. The behavior analysis unit also analyzes how the customer feels after eating, and suggests a menu that suits the mood. For example, if the customer wants to relax after eating, it suggests a menu that has a relaxing effect. The behavior analysis unit also analyzes what activities the customer will do after eating, and suggests a menu that suits the activity. For example, if the customer works after eating, it suggests a menu that will help improve concentration. In this way, customer satisfaction can be improved by suggesting the optimal menu based on the customer's behavior after eating.

[0055] The recommendation system can further include a behavior analysis unit that analyzes the customer's behavior before a meal. The behavior analysis unit, for example, analyzes what behavior the customer takes before a meal. For example, it analyzes what activities the customer engages in before a meal and suggests a menu according to the activity. For example, if the customer exercises before a meal, it suggests a menu suitable for after exercise. The behavior analysis unit also analyzes how the customer feels before a meal and suggests a menu according to the mood. For example, if the customer wants to relax before a meal, it suggests a menu that has a relaxing effect. The behavior analysis unit also analyzes how the customer prepares before a meal and suggests a menu according to the preparations. For example, if the customer prepares specific ingredients before a meal, it suggests a menu using those ingredients. In this way, customer satisfaction can be improved by suggesting the optimal menu based on the customer's behavior before a meal.

[0056] The recommendation system can further include a conversation analysis unit that analyzes the content of conversations customers have while eating. The conversation analysis unit, for example, analyzes the types of conversations customers have while eating. For example, it can ascertain customer preferences and interests from conversations during the meal and suggest menus accordingly. For example, if there is a lot of conversation about a particular dish, it can suggest a menu that includes that dish. The conversation analysis unit can also analyze the emotions customers express while eating and suggest a menu that matches their emotions. For example, if there is a lot of happy conversation during the meal, it can suggest a menu that will further enhance the happy mood. The conversation analysis unit can also analyze the topics customers talk about while eating and suggest a menu that matches the topic. For example, if there is a lot of conversation about health, it can suggest a health-conscious menu. In this way, customer satisfaction can be improved by suggesting optimal menus based on the content of conversations customers have while eating.

[0057] The recommendation system can further include a health analysis unit that analyzes the health condition of a customer. The health analysis unit, for example, analyzes the health condition of a customer while eating. For example, it estimates the customer's health condition from facial expressions and voice while eating and suggests a menu according to the health condition. For example, if the health condition is good, it suggests a menu that will maintain health. The health analysis unit also analyzes the health condition of a customer while eating and provides a service according to the health condition. For example, if the health condition is good, it provides a service that will maintain health. The health analysis unit also analyzes the health condition of a customer while eating and provides an environment according to the health condition. For example, if the health condition is good, it provides an environment that will maintain health. This makes it possible to improve customer satisfaction by providing optimal menus and services based on the customer's health condition.

[0058] The recommendation system can further include a posture analysis unit that analyzes a customer's posture while eating. The posture analysis unit, for example, analyzes the posture a customer uses while eating. For example, it evaluates the customer's comfort from their posture while eating and suggests a menu that suits their comfort. For example, if their posture is good, it suggests a menu that will make their meal even more enjoyable. The posture analysis unit also analyzes the posture a customer uses while eating and provides a service that suits their posture. For example, if their posture is good, it provides a service that will make their meal even more enjoyable. The posture analysis unit also analyzes the posture a customer uses while eating and provides an environment that suits their posture. For example, if their posture is good, it provides an environment that will make their meal even more enjoyable. This makes it possible to improve customer satisfaction by providing optimal menus and services based on the customer's posture.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The data collection unit collects information on the customer's gender, age, amount of exercise, and allergies. For example, the customer can enter this information through a smartphone app. The data collection unit can also collect the customer's amount of exercise and facial expressions using sensors and cameras in the store. Step 2: The analysis unit analyzes the customer data collected by the data collection unit. For example, the generation AI understands the customer's health condition and preferences based on the customer's gender, age, amount of exercise, and allergy information. The generation AI analyzes the customer data using text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The recommendation unit recommends the optimal menu based on the results of the analysis by the analysis unit. For example, the generation AI might suggest a higher-calorie menu for a day when you exercise a lot, or a menu that does not include certain ingredients based on allergy information. The generation AI selects the menu that is best suited to the customer's health condition and preferences.

[0061] (Example 2) A recommendation system according to an embodiment of the present invention is a system that recommends optimal menu items based on a customer's gender, age, the amount of exercise that day, and allergy information. By selecting optimal menu items based on individual customer data, the recommendation system can contribute to improving service and reducing food waste.

[0062] A recommendation system according to an embodiment includes a data collection unit, an analysis unit, and a recommendation unit. The data collection unit collects information on a customer's gender, age, amount of exercise, and allergies. For example, the customer can input this information via a smartphone app. The data collection unit can also collect information on the customer's exercise level and facial expressions using sensors and cameras in the store. The analysis unit analyzes the customer data collected by the data collection unit. For example, a generation AI understands the customer's health condition and preferences based on the customer's gender, age, amount of exercise, and allergy information. The generation AI analyzes the customer data using a text generation AI (e.g., LLM) or a multimodal generation AI. The recommendation unit recommends optimal menu items based on the results of the analysis by the analysis unit. For example, the generation AI may suggest a higher-calorie menu item on a day when the customer exercises a lot, or a menu item that does not include specific ingredients based on the customer's allergy information. The generation AI selects a menu item that is optimal for the customer's health condition and preferences. As a result, the recommendation system can recommend optimal menu items based on the customer's individual data, contributing to improved service and reduced food waste.

[0063] The data collection unit can perform analysis based on prompts containing customer data. For example, the data collection unit uses a smartphone app to input a customer's emotional state in real time. For example, the customer may record their current mood and stress level by answering simple questions in the app. The data collection unit also uses cameras and sensors in the store to analyze the customer's facial expressions and body movements to grasp the customer's emotional state in real time. For example, facial recognition technology is used to estimate the customer's emotions from their facial expressions. The data collection unit also analyzes the voice data that the customer uses to input their voice when placing an order to grasp the customer's emotional state. For example, the stress level is estimated from the tone and speed of the voice. This enables more accurate recommendations to be made by analyzing customer data as prompts.

[0064] The analysis unit can recommend menus based on prompts containing instructions about health status or preferences, based on customer data. For example, the analysis unit collects data on menus previously ordered by customers and integrates it with health checkup data. For example, it analyzes nutritional balance based on past meal history and compares it with health checkup results. The analysis unit also allows customers to input health checkup data into the app, and based on that data, suggests menus that take long-term health management into consideration. For example, it selects appropriate ingredients based on blood pressure and blood sugar data. The analysis unit also manages customers' meal history and health checkup data on the cloud, and the generation AI analyzes this data to suggest optimal menus. For example, it accesses a database on the cloud to reflect the latest health information. This makes it possible to meet individual needs by recommending menus based on customers' health status and preferences.

[0065] The recommendation unit can customize menus based on prompts including customization requests based on customer data. The recommendation unit, for example, uses an in-store camera to analyze the facial expressions of customers while they are eating in real time and evaluate their satisfaction. For example, it detects smiling or surprised expressions and scores their satisfaction. The recommendation unit also analyzes the sounds made by customers while they are eating and evaluates their satisfaction. For example, it analyzes conversations and exclamations made during the meal to estimate their satisfaction. The recommendation unit also evaluates their satisfaction based on feedback provided by customers through an app after their meal. For example, it allows customers to enter their satisfaction in a simple questionnaire format. This improves customer satisfaction by providing menus that meet the customers' customization requests.

[0066] The analysis unit performs analysis based on prompts containing feedback based on customer data and can reflect this in the next recommendation. For example, if a customer uses a fitness tracker or smartwatch, the analysis unit links that data with the app. For example, it collects data on exercise volume and heart rate in real time. The analysis unit also uses the fitness tracker or smartwatch's API to automatically obtain the customer's exercise data. For example, it imports data on the number of steps taken and calories burned into the app. The analysis unit also allows customers to manually input their exercise data and suggests menus based on that data. For example, it prompts them to input the number of calories burned after exercise. This allows customer feedback to be reflected in the next recommendation, improving the quality of service.

[0067] The analysis unit analyzes prompts based on customer data, including their eating history, and can suggest appropriate portions. For example, the analysis unit uses microphones in the restaurant to analyze conversations customers make while they eat and automatically updates their preference and allergy information. For example, it detects conversations about specific ingredients and updates allergy information. The analysis unit also allows customers to voice-input their impressions of their meal through the app, analyzes that data, and updates their preference and allergy information. For example, it analyzes comments such as "This dish is delicious." Furthermore, if a customer talks about allergies while eating, the analysis unit automatically updates the database. For example, it analyzes conversations such as "I have a nut allergy." This reduces food waste by suggesting appropriate portions based on the customer's eating history.

[0068] The data collection unit can analyze the emotional state based on customer data in real time and suggest a menu item according to the customer's stress level or mood. For example, the customer inputs their emotional state in real time using a smartphone app. For example, the customer records their current mood and stress level by answering simple questions in the app. The data collection unit also analyzes the customer's facial expressions and body movements using cameras and sensors in the store to grasp the customer's emotional state in real time. For example, facial recognition technology is used to estimate the customer's emotions from their facial expressions. The data collection unit also grasps the customer's emotional state by analyzing the voice data when the customer uses voice input when ordering. For example, the data collection unit estimates the stress level from the tone and speed of the voice. This improves customer satisfaction by suggesting a menu item according to the customer's emotional state.

[0069] The data collection unit can integrate past meal history and health checkup data based on customer data to propose menus that take long-term health management into consideration. For example, the data collection unit collects data on menus that customers have ordered in the past and integrates it with health checkup data. For example, it analyzes nutritional balance from past meal history and compares it with health checkup results. The data collection unit also allows customers to enter their health checkup data into the app, and based on that data, proposes menus that take long-term health management into consideration. For example, it selects appropriate ingredients based on blood pressure and blood sugar data. The data collection unit also manages customers' meal history and health checkup data on the cloud, and the generation AI analyzes the data to propose optimal menus. For example, it accesses a database on the cloud to reflect the latest health information. This contributes to maintaining health by proposing menus that take long-term health management into consideration.

[0070] The data collection unit analyzes facial expressions or voices made during meals based on customer data, evaluates meal satisfaction in real time, and can reflect this in next recommendations. The data collection unit, for example, uses an in-store camera to analyze customers' facial expressions while they eat in real time and evaluates their satisfaction. For example, it detects smiling or surprised expressions and scores their satisfaction. The data collection unit also analyzes the voices made by customers while they eat and evaluates their satisfaction. For example, it analyzes conversations and exclamations made during meals to estimate their satisfaction. The data collection unit also allows customers to provide feedback through an app after their meals, and evaluates their satisfaction based on that feedback. For example, it allows customers to enter their satisfaction in a simple questionnaire format. This allows the system to evaluate customers' satisfaction during their meals in real time and reflect this in next recommendations, thereby improving the quality of service.

[0071] The data collection unit can link with a fitness tracker or smartwatch to collect exercise data based on customer data. For example, if a customer uses a fitness tracker or smartwatch, the data collection unit links that data with the app. For example, it collects data on the amount of exercise and heart rate in real time. The data collection unit also uses the fitness tracker's or smartwatch's API to automatically obtain the customer's exercise data. For example, it imports data on the number of steps taken and calories burned into the app. The data collection unit also allows the customer to manually input exercise data and suggests menus based on that data. For example, it prompts the customer to input the amount of calories burned after exercise. In this way, collecting the customer's exercise data enables more accurate menu suggestions.

[0072] The data collection unit can analyze conversations during meals based on customer data and automatically update preference or allergy information. For example, the data collection unit uses microphones in the restaurant to analyze conversations between customers while they are eating and automatically update preference and allergy information. For example, it detects conversations about specific ingredients and updates allergy information. The data collection unit also allows customers to voice-input their impressions of the meal through an app, analyzes that data, and updates preference and allergy information. For example, it analyzes comments such as "This dish is delicious." Furthermore, if a customer talks about allergies during a meal, the data collection unit automatically updates the database. For example, it analyzes conversations such as "I have a nut allergy." This allows for more personalized service to be provided by analyzing customer conversations and automatically updating preference and allergy information.

[0073] The data collection unit uses an emotion estimation function based on customer data to analyze the emotions of customers when selecting a menu and suggest a menu that elicits positive emotions. For example, when a customer selects a menu, the data collection unit uses a camera to analyze their facial expressions and estimate their emotional state. For example, it detects smiling or excited facial expressions and suggests a menu that elicits positive emotions. The data collection unit also uses voice input when a customer selects a menu and analyzes the voice data to understand their emotional state. For example, it estimates emotions from the tone and speed of their voice. The data collection unit also has customers input their emotional state when selecting a menu through an app and suggests a menu that elicits positive emotions based on that data. For example, it has customers answer simple questions and record their emotional state. This allows the data collection unit to analyze customers' emotions and suggest menus that elicit positive emotions, thereby improving customer satisfaction.

[0074] The recommendation unit can propose nutritionally balanced menus based on customer data, such as dietary history and exercise data. For example, the recommendation unit analyzes a customer's past dietary history and exercise data to propose nutritionally balanced menus. For example, on days when the customer exercises a lot, it proposes menus high in protein. The recommendation unit also proposes nutritionally balanced menus based on the exercise data the customer enters into the app. For example, it selects ingredients high in vitamins and minerals for a post-exercise recovery menu. The recommendation unit also manages the customer's dietary history and exercise data on the cloud, and the generation AI analyzes this data to propose optimal menus. For example, it accesses a database on the cloud to reflect the latest health information. This contributes to maintaining health by proposing nutritionally balanced menus based on the customer's dietary history and exercise data.

[0075] The recommendation unit can suggest menus according to the season or weather based on customer data, and support health management. The recommendation unit, for example, takes into account seasonal ingredients and suggests menus according to the season. For example, in summer, it suggests menus that emphasize cold dishes and hydration. The recommendation unit also suggests menus that support health management based on weather data. For example, it suggests hot soups and stews on cold days. The recommendation unit also suggests menus that support health management, taking into account nutritional balance according to the season and weather. For example, it selects ingredients that boost immunity at the change of seasons. In this way, it supports customers' health management by suggesting menus according to the season and weather.

[0076] The recommendation unit can analyze a customer's emotional state based on data and suggest menus that match their mood. For example, a customer inputs their emotional state through an app, and the recommendation unit suggests menus that match their mood based on that data. For example, on a stressful day, the recommendation unit suggests a menu using ingredients that have a relaxing effect. The recommendation unit also uses cameras in the store to analyze customers' facial expressions and grasp their emotional state in real time. For example, on a day when customers smile a lot, the recommendation unit suggests a menu that will further enhance their happy mood. The recommendation unit also uses voice input when ordering, and analyzes the voice data to grasp their emotional state. For example, the recommendation unit can infer their mood from the tone and speed of their voice and suggest a menu that matches that. In this way, customer satisfaction can be improved by suggesting menus that match their mood based on their emotional state.

[0077] The recommendation unit can automatically update ingredient preferences or allergy information based on customer data and dietary history, and reflect this in the next recommendation. For example, the recommendation unit collects data on menu items a customer has previously ordered and automatically updates ingredient preferences and allergy information. For example, if a customer frequently orders a particular ingredient, it records that ingredient as a preference. The recommendation unit also allows customers to enter allergy information through the app, and reflects this data in the next recommendation. For example, if a customer has a nut allergy, it will suggest a nut-free menu. The recommendation unit also manages customers' dietary history on the cloud, and the generation AI analyzes this data to automatically update ingredient preferences and allergy information. For example, it accesses a cloud-based database to reflect the latest information. This allows preference and allergy information to be automatically updated based on the customer's dietary history and reflected in the next recommendation, enabling a more personalized service to be provided.

[0078] The recommendation unit can suggest menus based on customer data in accordance with health goals. For example, a customer may input their health goals through an app, and the recommendation unit will suggest menus based on that data. For example, if the goal is to lose weight, the recommendation unit will suggest low-calorie, nutritionally balanced menus. The recommendation unit also considers the nutritional balance of the customer's health goals and suggests the optimal menu. For example, if the goal is to increase muscle strength, the recommendation unit will suggest a menu high in protein. The recommendation unit also manages customers' health goals on the cloud, and the generation AI analyzes that data to suggest the optimal menu. For example, it accesses a database on the cloud to reflect the latest health information. This allows the recommendation unit to suggest menus in accordance with the customer's health goals, contributing to maintaining health and achieving those goals.

[0079] The recommendation unit uses an emotion estimation function based on customer data to analyze the emotions of customers when selecting a menu and suggest menus that elicit positive emotions. For example, when a customer is selecting a menu, the recommendation unit uses a camera to analyze their facial expressions and estimate their emotional state. For example, it detects smiling or excited facial expressions and suggests menus that elicit positive emotions. The recommendation unit also uses voice input when a customer is selecting a menu and analyzes the voice data to understand their emotional state. For example, it estimates emotions from the tone and speed of the voice. The recommendation unit also has customers input their emotional state when selecting a menu through the app and suggests menus that elicit positive emotions based on that data. For example, it has the customer answer simple questions and record their emotional state. This allows the recommendation unit to analyze the customer's emotions and suggest menus that elicit positive emotions, thereby improving customer satisfaction.

[0080] The recommendation unit can customize menus in real time based on customer data, such as food preferences or allergy information. For example, a customer can enter their food preferences and allergy information through an app, and the recommendation unit customizes the menu in real time based on that data. For example, if a customer has a nut allergy, the recommendation unit can suggest a menu that excludes nuts. The recommendation unit also allows customers to enter their food preferences and allergy information using a tablet device in the store, and customizes the menu based on that data. For example, it can exclude certain ingredients or adjust the amount. The recommendation unit also manages customer food preferences and allergy information on the cloud, and the generation AI analyzes that data to suggest customized menus in real time. For example, it accesses a cloud-based database to reflect the latest information. This improves customer satisfaction by customizing menus in real time based on customers' food preferences and allergy information.

[0081] The recommendation unit can propose customized menus with optimized nutritional balance based on customer data, dietary history, and health data. For example, the recommendation unit analyzes a customer's past dietary history and health data to propose customized menus with optimized nutritional balance. For example, it might propose a menu high in protein on days when the customer exercises a lot. The recommendation unit also proposes customized menus that take nutritional balance into consideration based on health data entered by the customer into the app. For example, it might propose a menu high in specific nutrients based on health checkup results. The recommendation unit also manages customers' dietary history and health data on the cloud, and the generation AI analyzes this data to propose the optimal customized menu. For example, it accesses a database on the cloud to reflect the latest health information. This contributes to maintaining health by proposing customized menus with optimized nutritional balance based on the customer's dietary history and health data.

[0082] The recommendation unit can analyze the emotional state based on customer data and suggest a customized menu that matches the mood. For example, the customer inputs their emotional state through an app, and the recommendation unit suggests a customized menu that matches their mood based on that data. For example, on a stressful day, the recommendation unit suggests a menu that uses ingredients that have a relaxing effect. The recommendation unit also uses cameras in the store to analyze customers' facial expressions and grasp their emotional state in real time. For example, on a day when there are a lot of smiles, the recommendation unit suggests a menu that will further enhance their happy mood. The recommendation unit also uses voice input when customers order, and analyzes the voice data to grasp their emotional state. For example, the recommendation unit can infer their mood from the tone and speed of their voice and suggest a menu that matches that. In this way, customer satisfaction can be improved by suggesting a customized menu that matches the mood based on the customer's emotional state.

[0083] The recommendation unit analyzes facial expressions or voices made during meals based on customer data, evaluates meal satisfaction in real time, and reflects this in next customization. The recommendation unit, for example, uses an in-store camera to analyze the facial expressions of customers while they are eating in real time and evaluates their satisfaction. For example, it detects smiling or surprised expressions and scores their satisfaction. The recommendation unit also analyzes the voices made by customers while they are eating and evaluates their satisfaction. For example, it analyzes conversations and exclamations made during meals to estimate their satisfaction. The recommendation unit also evaluates their satisfaction based on feedback provided by customers through an app after their meal. For example, it has customers enter their satisfaction in a simple questionnaire format. This allows the customer's satisfaction during their meal to be evaluated in real time and reflected in next customization, thereby improving the quality of service.

[0084] The recommendation unit can propose customized menus based on customer data in accordance with health goals. For example, a customer inputs their health goals through an app, and the recommendation unit proposes customized menus based on that data. For example, if the goal is weight loss, the recommendation unit will propose a low-calorie, nutritionally balanced menu. The recommendation unit also considers the nutritional balance of the customer's health goals and proposes the optimal customized menu. For example, if the goal is to increase muscle strength, the recommendation unit will propose a menu high in protein. The recommendation unit also manages customers' health goals on the cloud, and the generation AI analyzes that data to propose the optimal customized menu. For example, it accesses a database on the cloud to reflect the latest health information. This allows the recommendation unit to propose customized menus based on the customer's health goals, contributing to maintaining health and achieving those goals.

[0085] The recommendation unit uses an emotion estimation function based on customer data to analyze the emotions of customers when selecting a menu and propose a customized menu that elicits positive emotions. For example, when a customer selects a menu, the recommendation unit uses a camera to analyze their facial expressions and estimate their emotional state. For example, it detects smiling or excited expressions and proposes a customized menu that elicits positive emotions. The recommendation unit also uses voice input when a customer selects a menu and analyzes the voice data to understand their emotional state. For example, it estimates emotions from the tone and speed of the voice. The recommendation unit also has customers input their emotional state when selecting a menu through the app and proposes a customized menu that elicits positive emotions based on that data. For example, it has the customer answer simple questions and record their emotional state. This allows the recommendation unit to analyze the customer's emotions and propose a customized menu that elicits positive emotions, thereby improving customer satisfaction.

[0086] The analysis unit can analyze feedback based on customer data in real time and reflect it in the next recommendation. For example, after a meal, a customer provides feedback through an app, and the analysis unit analyzes that data in real time to reflect it in the next recommendation. For example, customers enter their satisfaction level and areas for improvement in a simple questionnaire format. The analysis unit also allows customers to enter feedback after a meal using a tablet device in the restaurant, analyzes the data, and reflects it in the next recommendation. For example, it collects opinions about the taste of the food and the service. The analysis unit also manages customer feedback on the cloud, and the generation AI analyzes that data and reflects it in the next recommendation. For example, it accesses a database on the cloud to reflect the latest feedback information. This allows customer feedback to be analyzed in real time and reflected in the next recommendation, improving the quality of service.

[0087] The analysis unit analyzes facial expressions or voices made during meals based on customer data, evaluates meal satisfaction in real time, and identifies areas for improvement in service. The analysis unit, for example, uses an in-store camera to analyze facial expressions made by customers while they are eating in real time and evaluates their satisfaction. For example, it detects smiling or surprised expressions and scores their satisfaction. The analysis unit also analyzes the voices made by customers while they are eating and evaluates their satisfaction. For example, it analyzes conversations and exclamations made during meals to estimate their satisfaction. The analysis unit also evaluates their satisfaction based on feedback provided by customers through an app after their meals. For example, it has customers enter their satisfaction in a simple questionnaire format. This allows the system to evaluate customers' satisfaction in real time during their meals and identify areas for improvement in service, thereby improving the quality of service.

[0088] The analysis unit can analyze the emotional state based on customer data and provide services tailored to the mood. For example, the analysis unit receives input of the customer's emotional state through an app, and provides services tailored to the mood based on that data. For example, on days when stress is high, the analysis unit provides services with a relaxing effect. The analysis unit also uses cameras in the store to analyze the customer's facial expressions and grasp the emotional state in real time. For example, on days when there are many smiles, the analysis unit provides services that further enhance the customer's happy mood. The analysis unit also grasps the emotional state of customers who use voice input when ordering by analyzing the voice data. For example, the analysis unit infers the customer's mood from the tone and speed of the voice and provides services tailored to that. This improves customer satisfaction by providing services tailored to the customer's mood based on their emotional state.

[0089] The analysis unit can continuously improve menus or services based on feedback from customer data. For example, customers provide feedback through an app after their meal, and the analysis unit continuously improves menus and services based on that data. For example, customers are asked to enter their satisfaction and areas for improvement in a simple questionnaire format. The analysis unit also uses tablet devices in the restaurant to allow customers to enter feedback after their meal, and analyzes the data to improve menus and services. For example, it collects opinions about the taste of food and service. The analysis unit also manages customer feedback on the cloud, and the generation AI analyzes the data to continuously improve menus and services. For example, it accesses a database on the cloud and reflects the latest feedback information. This allows for continuous improvement of menus and services based on customer feedback, thereby improving the quality of service.

[0090] The analysis unit can provide services tailored to health goals based on customer data. For example, a customer inputs their health goals through an app, and the analysis unit provides services based on that data. For example, if the goal is to lose weight, the analysis unit will suggest a low-calorie, nutritionally balanced menu. The analysis unit also takes into account the nutritional balance of the customer's health goals and provides optimal services. For example, if the goal is to increase muscle strength, the analysis unit will suggest a menu high in protein. The analysis unit also manages customers' health goals on the cloud, and the generation AI analyzes that data to provide optimal services. For example, it accesses a database on the cloud to reflect the latest health information. This allows the analysis unit to provide services tailored to the customer's health goals, contributing to maintaining health and achieving those goals.

[0091] The analysis unit can use an emotion estimation function based on customer data to analyze the emotions of customers when they select a menu and provide a service that elicits positive emotions. For example, the analysis unit uses a camera to analyze facial expressions when a customer selects a menu and estimates their emotional state. For example, a service that elicits positive emotions by detecting smiling or excited facial expressions is provided. The analysis unit also uses voice input when a customer selects a menu and analyzes the voice data to understand their emotional state. For example, it estimates emotions from the tone and speed of voice. The analysis unit also has customers input their emotional state when selecting a menu through an app and provides a service that elicits positive emotions based on that data. For example, it has the customer answer simple questions and record their emotional state. This allows for a service that analyzes customers' emotions and elicits positive emotions to improve customer satisfaction.

[0092] The analysis unit analyzes meal history based on customer data and suggests appropriate portions, thereby reducing food waste. For example, the analysis unit analyzes a customer's past meal history and suggests appropriate portions. For example, it may suggest reducing the portion size of a menu item that has resulted in a lot of leftover food in the past. The analysis unit also has customers input their meal history through the app, and the analysis unit suggests appropriate portions based on that data. For example, it suggests appropriate portion sizes based on past meal amounts. The analysis unit also manages customers' meal history on the cloud, and the generation AI analyzes that data to suggest appropriate portions. For example, it accesses a database on the cloud and reflects the latest meal history. This allows the analysis of customers' meal history and suggests appropriate portions, thereby reducing food waste.

[0093] The analysis unit analyzes facial expressions or voices made during meals based on customer data, evaluates meal satisfaction in real time, and suggests appropriate portions. The analysis unit, for example, uses an in-store camera to analyze customers' facial expressions while they eat in real time to evaluate their satisfaction. For example, it detects smiling or surprised expressions, scores their satisfaction, and suggests appropriate portions. The analysis unit also analyzes the voices made by customers while they eat to evaluate their satisfaction. For example, it analyzes conversations and exclamations made during meals to estimate their satisfaction and suggest appropriate portions. The analysis unit also allows customers to provide feedback through an app after their meal, evaluates their satisfaction based on that feedback, and adjusts their next meal portion. For example, the analysis unit allows customers to enter their satisfaction in a simple questionnaire format. This allows the system to evaluate customers' satisfaction in real time during their meal and suggest appropriate portions, thereby reducing food waste.

[0094] The analysis unit can analyze the emotional state of customers based on data and suggest portions appropriate to their mood. For example, customers input their emotional state through an app, and the analysis unit suggests portions appropriate to their mood based on that data. For example, on days when they are under a lot of stress, it suggests a small portion. The analysis unit also uses cameras in the store to analyze customers' facial expressions and grasp their emotional state in real time. For example, on days when they smile a lot, it suggests a normal portion, and on days when they are under a lot of stress, it suggests a small portion. The analysis unit also uses voice input when customers order, and analyzes the voice data to grasp their emotional state. For example, it can infer their mood from the tone and speed of their voice and suggest an appropriate portion to match. This reduces food waste by suggesting portions appropriate to their mood based on their emotional state.

[0095] The analysis unit can suggest appropriate portions based on customer data in accordance with health goals. For example, a customer inputs their health goals through an app, and the analysis unit suggests appropriate portions based on that data. For example, if the goal is to lose weight, the analysis unit suggests a menu with small portions and a balanced nutritional profile. The analysis unit also considers the nutritional balance of the customer's health goals and suggests appropriate portions. For example, if the goal is to build muscle, the analysis unit suggests a menu with an appropriate amount of protein. The analysis unit also manages customers' health goals on the cloud, and the generation AI analyzes that data to suggest appropriate portions. For example, it accesses a database on the cloud to reflect the latest health information. This reduces food waste by suggesting appropriate portions in accordance with the customer's health goals.

[0096] The analysis unit can automatically update ingredient preferences or allergy information based on customer data and meal history, and suggest appropriate portions. For example, the analysis unit collects data on menu items a customer has previously ordered and automatically updates ingredient preferences and allergy information. For example, if a customer frequently orders a particular ingredient, it records that ingredient as a preference and suggests an appropriate portion. The analysis unit also allows customers to enter allergy information through the app, and reflects that data in the next recommendation. For example, if a customer has a nut allergy, it will suggest a nut-free menu and an appropriate portion. The analysis unit also manages customers' meal history on the cloud, and the generation AI analyzes that data to automatically update ingredient preferences and allergy information and suggest appropriate portions. For example, it accesses a cloud-based database to reflect the latest information. This automatically updates preference and allergy information based on the customer's meal history and suggests appropriate portions, reducing food waste.

[0097] The analysis unit uses an emotion estimation function based on customer data to analyze the emotions of customers when selecting a menu item and suggest appropriate portions to elicit positive emotions. For example, when a customer selects a menu item, the analysis unit uses a camera to analyze their facial expressions and estimate their emotional state. For example, it detects smiling or excited expressions and suggests appropriate portions to elicit positive emotions. The analysis unit also uses voice input when a customer selects a menu item, and analyzes the voice data to understand their emotional state. For example, it estimates emotions from the tone and speed of voice and suggests appropriate portions based on that. The analysis unit also has customers input their emotional state when selecting a menu item through the app, and suggests appropriate portions to elicit positive emotions based on that data. For example, it has them answer simple questions and record their emotional state. This allows the analysis of customer emotions and suggests appropriate portions to elicit positive emotions, thereby reducing food waste.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The recommendation system may further include a purchase history analysis unit that analyzes a customer's purchase history. The purchase history analysis unit, for example, collects data on products and services purchased by the customer in the past and analyzes the customer's preferences and purchasing patterns. For example, if a customer tends to frequently purchase a particular brand or product, it proposes a menu that includes that brand or product. The purchase history analysis unit also analyzes reviews and ratings of products purchased by the customer in the past to understand the customer's satisfaction level. For example, it proposes a menu that includes highly rated products. The purchase history analysis unit also analyzes the seasonality and trends of products purchased by the customer in the past and proposes a menu that matches the season or trend. For example, it proposes a menu that includes seasonal products or trendy products. This makes it possible to improve customer satisfaction by proposing optimal menus based on the customer's purchase history.

[0100] The recommendation system can further include a behavior analysis unit that analyzes customer behavior while eating. The behavior analysis unit, for example, analyzes what behavior a customer exhibits while eating. For example, it analyzes the frequency and duration of smartphone use while eating to grasp the level of concentration while eating. The behavior analysis unit also analyzes the posture of a customer while eating to evaluate the comfort of the meal. For example, if the customer's posture is poor, it suggests a comfortable dining environment. The behavior analysis unit also analyzes the pace at which a customer eats while eating to evaluate the customer's satisfaction with the meal. For example, if the customer eats at a fast pace, it suggests a menu that allows the customer to enjoy a leisurely meal. This makes it possible to improve customer satisfaction by suggesting the optimal menu based on the customer's behavior while eating.

[0101] The recommendation system can further include a behavior analysis unit that analyzes the customer's behavior after eating. The behavior analysis unit, for example, analyzes what behavior the customer will take after eating. For example, it analyzes whether or not the customer will exercise after eating, and suggests a menu suitable for after exercise. The behavior analysis unit also analyzes how the customer feels after eating, and suggests a menu that suits the mood. For example, if the customer wants to relax after eating, it suggests a menu that has a relaxing effect. The behavior analysis unit also analyzes what activities the customer will do after eating, and suggests a menu that suits the activity. For example, if the customer works after eating, it suggests a menu that will help improve concentration. In this way, customer satisfaction can be improved by suggesting the optimal menu based on the customer's behavior after eating.

[0102] The recommendation system can further include a behavior analysis unit that analyzes the customer's behavior before a meal. The behavior analysis unit, for example, analyzes what behavior the customer takes before a meal. For example, it analyzes what activities the customer engages in before a meal and suggests a menu according to the activity. For example, if the customer exercises before a meal, it suggests a menu suitable for after exercise. The behavior analysis unit also analyzes how the customer feels before a meal and suggests a menu according to the mood. For example, if the customer wants to relax before a meal, it suggests a menu that has a relaxing effect. The behavior analysis unit also analyzes how the customer prepares before a meal and suggests a menu according to the preparations. For example, if the customer prepares specific ingredients before a meal, it suggests a menu using those ingredients. In this way, customer satisfaction can be improved by suggesting the optimal menu based on the customer's behavior before a meal.

[0103] The recommendation system can further include a conversation analysis unit that analyzes the content of conversations customers have while eating. The conversation analysis unit, for example, analyzes the types of conversations customers have while eating. For example, it can ascertain customer preferences and interests from conversations during the meal and suggest menus accordingly. For example, if there is a lot of conversation about a particular dish, it can suggest a menu that includes that dish. The conversation analysis unit can also analyze the emotions customers express while eating and suggest a menu that matches their emotions. For example, if there is a lot of happy conversation during the meal, it can suggest a menu that will further enhance the happy mood. The conversation analysis unit can also analyze the topics customers talk about while eating and suggest a menu that matches the topic. For example, if there is a lot of conversation about health, it can suggest a health-conscious menu. In this way, customer satisfaction can be improved by suggesting optimal menus based on the content of conversations customers have while eating.

[0104] The recommendation system can further include an emotion analysis unit that analyzes the emotional state of a customer. The emotion analysis unit, for example, analyzes what emotions a customer is expressing while eating. For example, it estimates the customer's emotions from their facial expressions and voice while eating and suggests a menu that matches their emotions. For example, if the customer smiles a lot while eating, it suggests a menu that will further enhance their happy mood. The emotion analysis unit also analyzes what emotions a customer has while eating and provides a service that matches their emotions. For example, if a customer wants to relax while eating, it provides a service that has a relaxing effect. The emotion analysis unit also analyzes what emotions a customer has while eating and provides an environment that matches their emotions. For example, if a customer wants to relax while eating, it provides a relaxing environment. This makes it possible to improve customer satisfaction by providing optimal menus and services based on the customer's emotional state.

[0105] The recommendation system can further include a stress analysis unit that analyzes the stress level of a customer. The stress analysis unit, for example, analyzes the level of stress a customer is feeling while eating. For example, it estimates the customer's stress level from facial expressions and voice while eating and suggests a menu according to the customer's stress. For example, if stress is high, it suggests a menu that has a relaxing effect. The stress analysis unit also analyzes the level of stress a customer is feeling while eating and provides a service according to the stress. For example, if stress is high, it provides a service that has a relaxing effect. The stress analysis unit also analyzes the level of stress a customer is feeling while eating and provides an environment according to the stress. For example, if stress is high, it provides a relaxing environment. This makes it possible to improve customer satisfaction by providing optimal menus and services based on the customer's stress level.

[0106] The recommendation system can further include a mood analysis unit that analyzes the mood of the customer. The mood analysis unit, for example, analyzes the mood of the customer while eating. For example, it estimates the customer's mood from facial expressions and voice while eating and suggests a menu that matches the mood. For example, if the customer is in a good mood, it suggests a menu that will further enhance the enjoyment. The mood analysis unit also analyzes the mood of the customer while eating and provides a service that matches the mood. For example, if the customer is in a good mood, it provides a service that will further enhance the enjoyment. The mood analysis unit also analyzes the mood of the customer while eating and provides an environment that matches the mood. For example, if the customer is in a good mood, it provides an environment that will further enhance the enjoyment. This makes it possible to improve customer satisfaction by providing optimal menus and services based on the customer's mood.

[0107] The recommendation system can further include a health analysis unit that analyzes the health condition of a customer. The health analysis unit, for example, analyzes the health condition of a customer while eating. For example, it estimates the customer's health condition from facial expressions and voice while eating and suggests a menu according to the health condition. For example, if the health condition is good, it suggests a menu that will maintain health. The health analysis unit also analyzes the health condition of a customer while eating and provides a service according to the health condition. For example, if the health condition is good, it provides a service that will maintain health. The health analysis unit also analyzes the health condition of a customer while eating and provides an environment according to the health condition. For example, if the health condition is good, it provides an environment that will maintain health. This makes it possible to improve customer satisfaction by providing optimal menus and services based on the customer's health condition.

[0108] The recommendation system can further include a posture analysis unit that analyzes a customer's posture while eating. The posture analysis unit, for example, analyzes the posture a customer uses while eating. For example, it evaluates the customer's comfort from their posture while eating and suggests a menu that suits their comfort. For example, if their posture is good, it suggests a menu that will make their meal even more enjoyable. The posture analysis unit also analyzes the posture a customer uses while eating and provides a service that suits their posture. For example, if their posture is good, it provides a service that will make their meal even more enjoyable. The posture analysis unit also analyzes the posture a customer uses while eating and provides an environment that suits their posture. For example, if their posture is good, it provides an environment that will make their meal even more enjoyable. This makes it possible to improve customer satisfaction by providing optimal menus and services based on the customer's posture.

[0109] The processing flow of the second embodiment will be briefly explained below.

[0110] Step 1: The data collection unit collects information on the customer's gender, age, amount of exercise, and allergies. For example, the customer can enter this information through a smartphone app. The data collection unit can also collect the customer's amount of exercise and facial expressions using sensors and cameras in the store. Step 2: The analysis unit analyzes the customer data collected by the data collection unit. For example, the generation AI understands the customer's health condition and preferences based on the customer's gender, age, amount of exercise, and allergy information. The generation AI analyzes the customer data using text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The recommendation unit recommends the optimal menu based on the results of the analysis by the analysis unit. For example, the generation AI might suggest a higher-calorie menu for a day when you exercise a lot, or a menu that does not include certain ingredients based on allergy information. The generation AI selects the menu that is best suited to the customer's health condition and preferences.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0113] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0121] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] 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.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0129] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0130] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0133] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0136] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0137] 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.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0139] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0144] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0145] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0147] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0148] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0150] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0151] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0152] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0153] 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.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0155] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0157] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0159] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0160] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0161] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0162] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0163] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0164] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0165] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0167] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0168] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0169] 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.

[0170] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0171] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0172] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0173] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0174] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0175] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0176] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0177] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A data collection department that collects information on customers' gender, age, exercise level, and allergies; an analysis unit that analyzes the customer data collected by the data collection unit; a recommendation unit that recommends an optimal menu based on the results of the analysis by the analysis unit. A system characterized by:

2. The data collection unit Conduct analysis based on prompts containing the customer data 2. The system of claim 1.

3. The analysis unit Recommending menu items based on prompts including instructions regarding health conditions or preferences based on the customer data.

2. The system of claim 1.

4. The recommendation unit Customize the menu based on a prompt containing a customization request based on the customer data.

2. The system of claim 1.

5. The analysis unit Based on the customer data, analysis is performed based on prompts containing feedback, and the results are reflected in the next recommendation.

2. The system of claim 1.

Images