system

Abstract

The system according to this embodiment aims to suggest the optimal menu based on the user's preferences and health condition. [Solution] The system according to the embodiment comprises a hearing unit, a setting unit, a reading unit, a calculation unit, and a generation unit. The hearing unit hears the user's preferences. The setting unit sets the importance of taste, price, and health based on the information obtained by the hearing unit. The reading unit takes pictures of the restaurant's menu with a camera and reads it. The calculation unit calculates the calories and nutrients of each menu item based on the menu items read by the reading unit. The generation unit generates a recommended menu list based on the information calculated by the calculation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that menu selection in restaurants is not optimized for the user's preferences and health condition.

[0005] The system according to the embodiment aims to propose an optimal menu based on the user's preferences and health condition.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a listening unit, a setting unit, a reading unit, a calculation unit, and a generation unit. The listening unit listens to the user's preferences. The setting unit sets the importance of taste, price, and health based on the information obtained by the listening unit. The reading unit takes pictures of the restaurant's menu with a camera and reads it. The calculation unit calculates the calories and nutrients of each menu item based on the menu items read by the reading unit. The generation unit generates a list of recommended menu items based on the information calculated by the calculation unit. [Effects of the Invention]

[0007] The system according to this embodiment can suggest an optimal menu based on the user's preferences and health condition. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The menu selection suggestion system according to an embodiment of the present invention is a system that suggests menu choices at a restaurant. This system first interviews and analyzes the user's favorite foods and past dining history. Next, the user sets their priorities regarding taste, price, and health. Then, the user takes a picture of the restaurant's menu with a camera, and the app reads the menu. Based on the read menu, the app calculates the general calories and nutrients of each menu item. Finally, the generating AI automatically generates an optimal recommended menu order list for the user. Furthermore, the system interviews the user about their satisfaction with each menu item after they have eaten it, and incorporates this into their next order. For example, the system first interviews and analyzes the user's favorite foods and past dining history. At this time, it collects information about dishes the user has eaten in the past and their evaluations, and the generating AI analyzes this information. For example, it can identify dishes that the user found particularly delicious or healthy among those they have eaten in the past. Next, the user sets their priorities regarding taste, price, and health. For example, if taste is prioritized, the system can be set to prioritize suggesting delicious dishes over price or health. Conversely, if health is prioritized, the system can be set to suggest menus that take calories and nutrients into consideration. Next, the user takes a picture of the restaurant's menu with their camera, and the app reads the menu. For example, when a user takes a picture of the menu with their camera device, the app can analyze the image and read the menu contents as digital data. Based on the read menu, the app calculates the general calories and nutrients of each menu item. For example, based on the name and ingredients of the dish listed on the menu, the generating AI can estimate the calories and nutrients of that dish. This allows the user to make health-conscious choices for each menu item. Finally, the generating AI automatically generates a list of recommended menu items that are best suited to the user. For example, based on the user's preferences and settings, the generating AI can select the best menu items and display them as a list. This makes it easy for the user to choose a menu that suits them. Furthermore, the app gathers feedback on the user's satisfaction with each menu item after they've eaten it, and incorporates this into their next order. For example, if the user enters a rating for the dishes they ate, the generating AI can use that rating to improve its suggestions for the next time.This allows for continuous suggestions tailored to the user's preferences. As a result, the menu selection suggestion system can propose the optimal menu based on the user's preferences and health condition.

[0029] The menu selection suggestion system according to the embodiment comprises a hearing unit, a setting unit, a reading unit, a calculation unit, and a generation unit. The hearing unit hears the user's preferences. User preferences include, but are not limited to, taste preferences, ingredient preferences, and cooking method preferences. The hearing unit identifies the user's preferences by, for example, analyzing the user's past eating and drinking history. The hearing unit can also customize the content of the hearing to take into account the user's current health condition and dietary restrictions. For example, if the user is on a diet, it will ask questions about low-calorie dishes. The setting unit sets the importance of taste, price, and health based on the information obtained by the hearing unit. The importance of taste, price, and health can be set by, for example, the user. For example, if taste is important, the system can be set to prioritize suggesting delicious dishes over price or health. The reading unit photographs and reads the restaurant's menu with a camera. The reading unit can read menus photographed with a camera device, for example. For example, when a user takes a picture of a menu with a camera device, the reading unit analyzes the image and reads the menu contents as digital data. The calculation unit calculates the calories and nutrients of each menu item based on the menu read by the reading unit. The calculation unit can estimate calories and nutrients based on, for example, the names and ingredients of the dishes listed on the menu. The generation unit generates a recommended menu order list based on the information calculated by the calculation unit. The generation unit can select the optimal menu items based on, for example, the user's preferences and settings and display them as a list. As a result, the menu selection suggestion system according to this embodiment can suggest the optimal menu items based on the user's preferences and health condition.

[0030] The interviewing department gathers information about the user's preferences. These preferences include, but are not limited to, taste preferences, ingredient preferences, and cooking method preferences. For example, the interviewing department analyzes the user's past eating history to identify their preferences. Specifically, it stores the dishes the user has ordered and their ratings in a database and analyzes this data to understand the user's tastes. The interviewing department can also customize the interview content considering the user's current health status and dietary restrictions. For example, if the user is on a diet, it will ask questions about low-calorie dishes. Furthermore, the interviewing department also considers the user's allergy information and preferences for specific ingredients. For example, if the user has an allergy to a particular ingredient, it will prioritize suggesting menus that do not contain that ingredient. The interviewing department also collects information about the user's meal frequency and timing and uses this to suggest the most suitable menu. For example, if the user tends to eat a light breakfast, it will suggest a light breakfast menu. In this way, the interviewing department can support the user in selecting the optimal menu while considering their diverse needs and constraints.

[0031] The settings unit sets the importance of taste, price, and health based on the information obtained by the hearing unit. The importance of taste, price, and health can be set by the user, for example. Specifically, the user can adjust the importance of each item using sliders or checkboxes through the application interface. For example, if taste is prioritized, the system can be set to prioritize delicious dishes over price or health. Users can change these settings at any time, allowing for flexible adaptation to different situations. For example, the setting can be changed to prioritize taste for special events or anniversaries, and health for everyday meals. The settings unit can also automatically adjust the importance based on the user's past selection history and feedback. For example, if a user has frequently selected health-focused menus in the past, the system will automatically suggest a setting that increases the importance of health. This allows the settings unit to provide flexible menu suggestions tailored to the user's preferences and needs.

[0032] The reading unit reads the restaurant's menu by taking a picture of it with a camera. For example, the reading unit can read a menu that has been photographed with a camera device. Specifically, when a user takes a picture of a menu with a camera device, the reading unit can analyze the image and read the menu contents as digital data. For image analysis, OCR (Optical Character Recognition) technology is used to extract the text information written on the menu. Furthermore, using image recognition technology, it can analyze the photos and icons of the dishes listed on the menu to identify the type and characteristics of the dishes. For example, it can determine whether a dish is a meat dish or a fish dish from the photo of the dish listed on the menu. In addition, the reading unit can accurately read various types of menus, regardless of the menu's layout or format. This allows users to easily import menus of any format into the system. Furthermore, the reading unit can save the read menu information to a cloud server and share it with other devices and systems. This allows users to access consistent menu information from different devices.

[0033] The calculation unit calculates the calories and nutrients of each menu item based on the menu items read by the reading unit. For example, the calculation unit can estimate calories and nutrients based on the name and ingredients of the dishes listed on the menu. Specifically, it compares the name and ingredients of the dishes with a database and obtains calorie and nutrient information for each ingredient. For example, if the menu item is listed as "chicken curry," it obtains ingredient information such as chicken, curry sauce, and vegetables from the database, and calculates the total calories by adding up the calories and nutrients of each ingredient. The calculation unit can also calculate calories and nutrients more accurately by considering the cooking method and portion size of the dishes. For example, since fried and grilled foods have different calorie counts, it performs calorie calculations according to the cooking method. Furthermore, the calculation unit can perform calculations that emphasize specific nutrients according to the user's individual needs and constraints. For example, if a user wants to consume a lot of protein, it performs calculations that emphasize the protein content. In this way, the calculation unit can support the user in selecting the optimal menu item according to their health condition and dietary restrictions.

[0034] The generation unit generates a recommended menu order list based on information calculated by the calculation unit. For example, the generation unit can select the most suitable menu items based on the user's preferences and settings and display them as a list. Specifically, it uses an algorithm to select the most suitable menu items, taking into account the user's preferences, health status, budget, and other settings. For example, if the user desires low-calorie dishes, low-calorie menu items will be prioritized and included in the list. The generation unit also displays detailed information and nutritional information for the selected menu items to make it easier for the user to choose. Furthermore, the generation unit can continuously improve its suggestions based on the user's past selection history and feedback. For example, it can prioritize suggesting menu items that the user has previously given high ratings to. In addition, the generation unit can provide the latest suggestions based on menu information that is updated in real time. As a result, the generation unit can provide optimal menu suggestions that meet the diverse needs and circumstances of the user, thereby improving user satisfaction.

[0035] The system includes a satisfaction feedback unit that gathers feedback from users about their satisfaction with each menu item after they have eaten. For example, the satisfaction feedback unit can input the user's evaluation of the dishes they ate. For instance, the satisfaction feedback unit can input the user's evaluation of the dishes on a five-point scale. The satisfaction feedback unit can also input specific feedback from the user about the dishes they ate. For example, the satisfaction feedback unit can input feedback about the taste and texture of the dishes. This allows the system to gather user satisfaction and reflect it in future suggestions. Some or all of the above processing in the satisfaction feedback unit may be performed using AI, or not. For example, the satisfaction feedback unit can input user feedback into a generating AI and have the generating AI process the data to reflect it in future suggestions.

[0036] The satisfaction feedback unit may include a reflection unit that incorporates the feedback into the next order. For example, the satisfaction feedback unit can adjust the next order based on the user's evaluation of the dishes they ate. For example, the satisfaction feedback unit can incorporate dishes that the user gave a high rating to the next order. The satisfaction feedback unit can also exclude dishes that the user gave a low rating to the next order. For example, the satisfaction feedback unit can incorporate information about ingredients that the user should avoid into the next order. This allows the user's satisfaction to be reflected in the next order. Some or all of the above processing in the satisfaction feedback unit may be performed using AI, for example, or without AI. For example, the satisfaction feedback unit can input user feedback into a generating AI and have the generating AI process the data to be incorporated into the next order.

[0037] The interviewing unit can analyze the user's past eating and drinking history. For example, the interviewing unit can identify the user's preferences based on their past eating and drinking history. For instance, it can identify dishes the user has eaten in the past that they found particularly delicious or healthy. The interviewing unit can also identify ingredients the user should avoid based on their past eating and drinking history. For example, it can identify dishes the user has eaten in the past that caused allergic reactions or that they disliked. By analyzing the user's past eating and drinking history, more appropriate suggestions can be made. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input the user's past eating and drinking history into a generating AI and have the generating AI generate data to identify the user's preferences.

[0038] The settings unit allows users to set their priorities regarding taste, price, and health. For example, if taste is prioritized, the settings unit can be configured to suggest delicious dishes as a priority over price or health. For example, the settings unit can be configured to prioritize taste. If health is prioritized, the settings unit can be configured to suggest menus that take calories and nutrients into consideration. For example, the settings unit can be configured to prioritize health. Furthermore, if price is prioritized, the settings unit can be configured to suggest the best menu within the budget. For example, the settings unit can be configured to prioritize price. This allows for settings tailored to the user's preferences. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input the user's settings information into a generating AI and have the generating AI execute the optimal settings.

[0039] The reading unit can read menus captured by a camera device. For example, the reading unit can capture a menu using a smartphone camera, analyze the image, and read the menu contents as digital data. The reading unit can also read menus using a dedicated scanner. For example, the reading unit can scan a menu with a dedicated scanner, analyze the image, and read the menu contents as digital data. Furthermore, the reading unit can read printed menus using OCR technology. For example, the reading unit can use OCR technology to recognize printed menus with high accuracy and convert them into digital text. This allows menu information to be digitized by reading menus captured by a camera device. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input image data of a menu captured by a camera device into a generating AI, and have the generating AI perform the conversion from image data to text data.

[0040] The calculation unit can calculate calories and nutrients based on the names and ingredients of the dishes listed on the menu. For example, the calculation unit can calculate calories and nutrients based on the names and ingredients of the dishes listed on the menu. The calculation unit can also calculate calories and nutrients considering the cooking method of the dishes. Furthermore, the calculation unit can calculate calories and nutrients considering the origin and quality of the ingredients. This allows for health-conscious suggestions by estimating calories and nutrients based on the information provided on the menu. Some or all of the above processing in the calculation unit may be performed using AI, or without AI. For example, the calculation unit can input data on the names and ingredients of the dishes listed on the menu into a generating AI and have the generating AI perform the calculation of calories and nutrients.

[0041] The generation unit can select appropriate menus based on the user's preferences and settings and display them as a list. For example, the generation unit can select the optimal menu based on the user's preferences and settings and display it as a list. For example, the generation unit can select the optimal menu based on the user's preferences and settings and display it as a list. The generation unit can also analyze the user's past order history and suggest the optimal menu. For example, the generation unit suggests the optimal menu based on the user's past order history. Furthermore, the generation unit can generate menus while considering the user's current health condition and dietary restrictions. For example, the generation unit generates menus while considering the user's current health condition and dietary restrictions. This allows the generation unit to suggest the optimal menu based on the user's preferences and settings. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input data on the user's preferences and settings into a generation AI and have the generation AI generate the optimal menu.

[0042] The interviewing unit can analyze the user's past eating and drinking history and select the optimal interviewing method. For example, the interviewing unit can ask relevant questions based on the dishes the user has enjoyed eating in the past. For example, the interviewing unit can ask relevant questions based on the dishes the user has enjoyed eating in the past. The interviewing unit can also ask about ingredients to avoid based on the dishes the user has avoided in the past. For example, the interviewing unit can ask about ingredients to avoid based on the dishes the user has avoided in the past. Furthermore, the interviewing unit can estimate the user's preferences for specific dishes from their past eating and drinking history and customize the interview content. For example, the interviewing unit can estimate the user's preferences for specific dishes from their past eating and drinking history and customize the interview content. This allows the optimal interviewing method to be selected by analyzing the user's past eating and drinking history. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without using AI. For example, the interviewing unit can input the user's past dining history into a generating AI and have the AI ​​process the data to select the optimal interviewing method.

[0043] The interview function can customize the interview content to take into account the user's current health condition and dietary restrictions. For example, if the user is on a diet, the interview function can ask questions about low-calorie dishes. Furthermore, if the user has allergies, the interview function can ask questions about dishes that do not contain allergens. Additionally, if the user needs to consume specific nutrients, the interview function can ask questions about dishes that contain those nutrients. This enables interviews tailored to the user's health condition and dietary restrictions. Some or all of the above processing in the interview function may be performed using AI, or not. For example, the interview function can input data on the user's health condition and dietary restrictions into a generating AI and have the generating AI process data to customize the interview content.

[0044] The interviewing unit can conduct interviews about regionally specific ingredients and dishes, taking into account the user's geographical location. For example, if the user is traveling, the interviewing unit can ask questions about local specialties. The interviewing unit can also ask questions about popular local dishes if the user is in their hometown. Furthermore, if the user is interested in a particular region, the interviewing unit can ask questions about the cuisine of that region. This makes it possible to conduct interviews about regionally specific ingredients and dishes based on the user's geographical location. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input the user's geographical location information into a generating AI and have the generating AI generate data for conducting interviews about regionally specific ingredients and dishes.

[0045] The interviewing unit can analyze the user's social media activity and reflect relevant dining history in the interview. For example, the interviewing unit can estimate preferences based on photos of food shared by the user on social media. For example, the interviewing unit can estimate preferences based on photos of food shared by the user on social media. The interviewing unit can also estimate the types of food the user is interested in based on the food-related accounts the user follows on social media. For example, the interviewing unit can estimate the types of food the user is interested in based on the food-related accounts the user follows on social media. Furthermore, the interviewing unit can ask questions about relevant food based on events the user has participated in on social media. For example, the interviewing unit can ask questions about relevant food based on events the user has participated in on social media. This allows relevant dining history to be reflected in the interview based on the user's social media activity. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input data on the user's social media activity into a generating AI, and then have the AI ​​generate data to reflect related dining history in the interview.

[0046] The settings unit can analyze the user's past settings history and suggest the optimal settings method. For example, the settings unit can suggest the optimal settings based on the user's past priorities regarding taste, price, and health. The settings unit can also suggest customized settings based on setting options the user has changed in the past. Furthermore, the settings unit can suggest settings suitable for specific time periods based on the user's past settings history. In this way, by analyzing the user's past settings history, the optimal settings method can be suggested. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input the user's past settings history into a generating AI and have the generating AI generate data to suggest the optimal settings method.

[0047] The settings unit can customize the settings considering the user's current lifestyle and health condition. For example, if the user is on a diet, the settings unit can suggest health-focused settings. The settings unit can also suggest settings that prioritize specific nutrients if the user needs to consume those nutrients. Furthermore, if the user has specific dietary restrictions, the settings unit can suggest settings that take those restrictions into account. This makes it possible to customize settings according to the user's lifestyle and health condition. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input data on the user's lifestyle and health condition into a generating AI and have the generating AI process data to customize the settings.

[0048] The settings unit can take the user's geographical location into consideration and configure settings related to region-specific ingredients and cuisine. For example, if the user is traveling, the settings unit can suggest settings that prioritize the local specialties of that region. For example, if the user is traveling, the settings unit can suggest settings that prioritize the local specialties of that region. For example, if the user is in their hometown, the settings unit can suggest settings that prioritize the popular local dishes. For example, if the user is in their hometown, the settings unit can suggest settings that prioritize the popular local dishes. Furthermore, if the user is interested in a particular region, the settings unit can suggest settings that prioritize the cuisine of that region. For example, if the user is interested in a particular region, the settings unit can suggest settings that prioritize the cuisine of that region. This makes it possible to configure settings related to region-specific ingredients and cuisine based on the user's geographical location. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input the user's geographical location into a generating AI and have the generating AI generate data to configure settings related to region-specific ingredients and cuisine.

[0049] The settings unit can analyze the user's social media activity and suggest relevant settings. For example, the settings unit can suggest settings that prioritize taste based on photos of food the user has shared on social media. The settings unit can also suggest settings that prioritize dishes the user is interested in, based on food-related accounts the user follows on social media. Furthermore, the settings unit can suggest settings that prioritize dishes related to events the user has participated in on social media. In this way, relevant settings can be suggested based on the user's social media activity. Some or all of the above processing in the settings unit may be performed using AI, for example, or not. For example, the settings unit can input data on the user's social media activity into a generating AI and have the generating AI generate data to suggest relevant settings.

[0050] The reading unit can support shooting under different lighting conditions to improve the accuracy of character recognition in menus. For example, the reading unit can recommend shooting under bright lighting to improve character recognition accuracy. The reading unit can also use a flash to improve character recognition accuracy when shooting under dim lighting. Furthermore, the reading unit can recommend shooting under natural light to improve character recognition accuracy. In this way, character recognition accuracy is improved by supporting shooting under different lighting conditions. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input image data of menus taken under different lighting conditions into a generating AI and have the generating AI execute data to improve character recognition accuracy.

[0051] The reading unit can apply the most suitable reading algorithm depending on the menu layout and font. For example, if the menu is written vertically, the reading unit can apply a reading algorithm that supports vertical writing. The reading unit can also apply a handwriting recognition algorithm if the menu is handwritten. Furthermore, if the menu is written in multiple languages, the reading unit can apply a multilingual reading algorithm. This enables optimal reading according to the menu layout and font. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input menu layout and font data into a generating AI and have the generating AI execute data to apply the most suitable reading algorithm.

[0052] The reading unit can prioritize reading region-specific dish names and ingredients, taking into account the geographical location information of the menu. For example, if the user is traveling, the reading unit can prioritize reading local specialties of that region. For example, if the user is traveling, the reading unit can prioritize reading local specialties of that region. For example, if the user is in their hometown, the reading unit can prioritize reading popular local dishes. For example, if the user is in their hometown, the reading unit can prioritize reading popular local dishes. Furthermore, if the user is interested in a particular region, the reading unit can prioritize reading dish names and ingredients of that region. For example, if the user is interested in a particular region, the reading unit can prioritize reading dish names and ingredients of that region. By prioritizing the reading of region-specific dish names and ingredients, it becomes possible to make optimal suggestions tailored to the region. Some or all of the above processing in the reading unit may be performed using AI, for example, or not using AI. For example, the reading unit can input the geographical location information of the menu into a generating AI and cause the generating AI to execute data to prioritize the reading of region-specific dish names and ingredients.

[0053] The reading unit can improve its reading accuracy by referring to related literature for the menu. For example, the reading unit can improve its reading accuracy by referring to related literature for the names of dishes listed in the menu. The reading unit can also improve its reading accuracy by referring to related literature for the ingredients listed in the menu. For example, the reading unit can improve its reading accuracy by referring to related literature for the ingredients listed in the menu. Furthermore, the reading unit can also improve its reading accuracy by referring to related literature for the cooking methods listed in the menu. For example, the reading unit can improve its reading accuracy by referring to related literature for the cooking methods listed in the menu. In this way, reading accuracy is improved by referring to related literature. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input data on related literature for the menu into a generating AI and have the generating AI execute data to improve reading accuracy.

[0054] The calculation unit can perform more detailed calorie and nutrient calculations based on the ingredients and cooking methods of the menu. For example, the calculation unit can perform detailed calorie calculations based on the types and quantities of ingredients listed in the menu. The calculation unit can also calculate changes in nutrients by considering the cooking methods listed in the menu. Furthermore, the calculation unit can perform more accurate nutrient calculations by considering the origin and quality of the ingredients listed in the menu. This makes it possible to perform detailed calorie and nutrient calculations based on ingredients and cooking methods. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input data on the ingredients and cooking methods of the menu into a generating AI and have the generating AI perform detailed calorie and nutrient calculations.

[0055] The calculation unit can optimize the calculation algorithm by referring to past calculation data. For example, the calculation unit can improve the accuracy of calorie calculations based on past calculation data. The calculation unit can also improve the accuracy of nutrient calculations based on past calculation data. Furthermore, the calculation unit can improve the efficiency of the calculation algorithm based on past calculation data. This makes it possible to optimize the calculation algorithm by referring to past calculation data. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input past calculation data into a generating AI and have the generating AI execute data to optimize the calculation algorithm.

[0056] The calculation unit can calculate the calories and nutrients of regionally specific ingredients and dishes, taking into account the geographical location information of the menu. For example, the calculation unit can calculate the calories of dishes using regionally specific ingredients. The calculation unit can also calculate changes in nutrients, taking into account regionally specific cooking methods. Furthermore, the calculation unit can perform more accurate nutrient calculations by taking into account the origin and quality of regionally specific ingredients. By calculating the calories and nutrients of regionally specific ingredients and dishes, it becomes possible to make optimal suggestions tailored to each region. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input the geographical location information of the menu into a generating AI and have the generating AI process data to calculate the calories and nutrients of regionally specific ingredients and dishes.

[0057] The calculation unit can improve its calculation accuracy by referring to relevant literature for the menu. For example, the calculation unit can improve its calculation accuracy by referring to relevant literature for the names of dishes listed in the menu. The calculation unit can also improve its calculation accuracy by referring to relevant literature for the ingredients listed in the menu. For example, the calculation unit can improve its calculation accuracy by referring to relevant literature for the ingredients listed in the menu. Furthermore, the calculation unit can also improve its calculation accuracy by referring to relevant literature for the cooking methods listed in the menu. For example, the calculation unit can improve its calculation accuracy by referring to relevant literature for the cooking methods listed in the menu. In this way, calculation accuracy is improved by referring to relevant literature. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input data on relevant literature for the menu into a generating AI and have the generating AI execute data to improve calculation accuracy.

[0058] The generation unit can analyze the user's past order history and suggest the optimal menu. For example, the generation unit can suggest the optimal menu based on dishes the user has previously ordered and enjoyed. The generation unit can also suggest dishes to avoid based on dishes the user has previously avoided. Furthermore, the generation unit can estimate the user's preferences for specific dishes from their past order history and suggest the optimal menu. In this way, the optimal menu can be suggested by analyzing the user's past order history. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the user's past order history into a generation AI and have the generation AI process the data to suggest the optimal menu.

[0059] The generation unit can generate menus that take into account the user's current health condition and dietary restrictions. For example, if the user is on a diet, the generation unit can suggest low-calorie menus. The generation unit can also suggest menus that do not contain allergens if the user has allergies. Furthermore, if the user needs to consume specific nutrients, the generation unit can suggest menus that contain those nutrients. This makes it possible to generate menus that are tailored to the user's health condition and dietary restrictions. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input data on the user's health condition and dietary restrictions into a generation AI and have the generation AI process the data to generate the menus.

[0060] The generation unit can prioritize suggesting region-specific dishes by considering the geographical location information of the menu. For example, if the user is traveling, the generation unit can prioritize suggesting local specialties. The generation unit can also prioritize suggesting popular local dishes if the user is in their hometown. Furthermore, if the user is interested in a particular region, the generation unit can prioritize suggesting dishes from that region. This allows for optimal suggestions tailored to the region by prioritizing region-specific dishes. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the geographical location information of the menu into the generation AI and have the generation AI process data to prioritize suggesting region-specific dishes.

[0061] The generation unit can improve the accuracy of its suggestions by referring to relevant literature for the menu. For example, the generation unit can improve the accuracy of its suggestions by referring to relevant literature for the names of the dishes listed in the menu. The generation unit can also improve the accuracy of its suggestions by referring to relevant literature for the ingredients listed in the menu. For example, the generation unit can improve the accuracy of its suggestions by referring to relevant literature for the ingredients listed in the menu. Furthermore, the generation unit can also improve the accuracy of its suggestions by referring to relevant literature for the cooking methods listed in the menu. For example, the generation unit can improve the accuracy of its suggestions by referring to relevant literature for the cooking methods listed in the menu. In this way, the accuracy of suggestions is improved by referring to relevant literature. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input data on relevant literature for the menu into the generation AI and have the generation AI execute data to improve the accuracy of suggestions.

[0062] The satisfaction assessment department can analyze a user's past satisfaction ratings and select the optimal assessment method. For example, the satisfaction assessment department can ask relevant questions based on dishes that the user has previously given high ratings to. For example, the satisfaction assessment department can ask relevant questions based on dishes that the user has previously given high ratings to. The satisfaction assessment department can also ask about ingredients to avoid based on dishes that the user has previously given low ratings to. For example, the satisfaction assessment department can ask about ingredients to avoid based on dishes that the user has previously given low ratings to. Furthermore, the satisfaction assessment department can estimate a user's preferences for specific dishes from their past satisfaction ratings and customize the assessment content. For example, the satisfaction assessment department can estimate a user's preferences for specific dishes from their past satisfaction ratings and customize the assessment content. This allows for the selection of the optimal assessment method by analyzing a user's past satisfaction ratings. Some or all of the above-described processes in the satisfaction assessment department may be performed using AI, for example, or without AI. For example, the satisfaction assessment unit can input users' past satisfaction ratings into a generating AI and have the AI ​​process the data to select the optimal assessment method.

[0063] The satisfaction assessment unit can assess user satisfaction with regional cuisine, taking into account the user's geographical location. For example, if the user is traveling, the satisfaction assessment unit can assess satisfaction with local specialties. The satisfaction assessment unit can also assess user satisfaction with popular local cuisine if the user is in their hometown. Furthermore, if the user is interested in a particular region, the satisfaction assessment unit can assess satisfaction with the cuisine of that region. This allows for optimal recommendations tailored to each region by assessing satisfaction with regional cuisine. Some or all of the above-described processes in the satisfaction assessment unit may be performed using AI, for example, or without AI. For example, the satisfaction hearing unit can input the user's geographical location information into a generating AI and have the AI ​​generate data to gather information on satisfaction levels regarding local cuisine.

[0064] The reflection unit can analyze the user's past satisfaction ratings and select the optimal reflection method. For example, the reflection unit can adjust the next order based on dishes the user has given high ratings to in the past. The reflection unit can also suggest menu items to avoid based on dishes the user has given low ratings to in the past. Furthermore, the reflection unit can estimate the user's preference for specific dishes from their past satisfaction ratings and adjust the next order accordingly. In this way, the optimal reflection method can be selected by analyzing the user's past satisfaction ratings. Some or all of the above processing in the reflection unit may be performed using AI, for example, or without AI. For example, the reflection unit can input the user's past satisfaction ratings into a generating AI and have the generating AI process the data to select the optimal reflection method.

[0065] The reflection unit can reflect the user's geographical location information and make recommendations based on region-specific cuisine. For example, if the user is traveling, the reflection unit can adjust the next order based on feedback about local specialties. The reflection unit can also adjust the next order based on feedback about popular local dishes if the user is in their hometown. Furthermore, if the user is interested in a particular region, the reflection unit can adjust the next order based on feedback about the cuisine of that region. This allows for optimal suggestions tailored to the region by reflecting on region-specific cuisine. Some or all of the above processing in the reflection unit may be performed using AI, for example, or without AI. For example, the reflection unit can input the user's geographical location information into a generating AI and have the generating AI generate data to reflect on region-specific cuisine.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The menu selection suggestion system can also make suggestions considering the user's meal timing. For example, it can suggest different menus depending on whether it's breakfast, lunch, or dinner. For breakfast, it can suggest menus that prioritize energy replenishment; for lunch, it can suggest menus containing balanced nutrients; and for dinner, it can suggest lighter, easily digestible menus. This makes it possible to suggest the optimal menu according to the user's meal timing.

[0068] The settings unit can make suggestions considering the user's meal frequency. For example, if a user frequently eats out, it can suggest menus containing balanced nutrients. If a user only eats out once a week, it can suggest a high-end menu to make that one meal special. Furthermore, if a user is on a diet, it can suggest low-calorie menus. This allows for optimal menu suggestions tailored to the user's meal frequency.

[0069] The reading unit can make suggestions considering the user's dining location. For example, if the user is eating at home, it can suggest easy-to-prepare menus. If the user is dining at a restaurant, it can suggest the restaurant's specialty dishes. Furthermore, if the user is dining outdoors, such as on a picnic, it can suggest menus that are easy to carry. This enables optimal menu suggestions tailored to the user's dining location.

[0070] The calculation unit can calculate calories and nutrients while considering the user's meal times. For example, for breakfast, it can perform calorie calculations that prioritize energy replenishment. For lunch, it can perform calorie calculations that include a balanced range of nutrients. Furthermore, for dinner, it can perform lighter calorie calculations that are easy to digest. This makes it possible to calculate optimal calories and nutrients according to the user's meal times.

[0071] The generation unit can make suggestions considering the user's dietary goals. For example, if the user's goal is weight loss, it can suggest low-calorie menus. If the user's goal is muscle building, it can suggest high-protein menus. Furthermore, if the user's goal is relaxation, it can suggest menus that include ingredients with relaxing effects. This makes it possible to suggest optimal menus tailored to the user's dietary goals.

[0072] The interviewing department can make suggestions while considering the user's eating habits. For example, if a user has a habit of eating at the same time every day, the department can suggest a menu that suits that time. Also, if a user has a habit of having a special meal on weekends, the department can suggest a special menu that suits that habit. Furthermore, if a user has a habit of eating a specific dish on a specific day of the week, the department can suggest a menu that suits that day. This makes it possible to suggest the most suitable menu according to the user's eating habits.

[0073] The following briefly describes the processing flow for example form 1.

[0074] Step 1: The interview team interviews the user to understand their preferences. These preferences include, for example, taste preferences, ingredient preferences, and cooking method preferences. The interview team analyzes the user's past eating and drinking history to identify their preferences. They can also customize the interview content to take into account the user's current health condition and dietary restrictions. Step 2: The settings unit sets the importance of taste, price, and health based on the information obtained by the interviewing unit. For example, if taste is prioritized, the unit can be set to prioritize suggesting delicious dishes over price or health. Step 3: The reading unit takes a picture of the store's menu with a camera and reads it. For example, when a user takes a picture of the menu with a camera device, the reading unit can analyze the image and read the menu contents as digital data. Step 4: The calculation unit calculates the calories and nutrients for each menu item based on the menu items read by the reading unit. For example, it can estimate calories and nutrients based on the names and ingredients of the dishes listed in the menu. Step 5: The generation unit generates a recommended menu list based on the information calculated by the calculation unit. For example, it can select the optimal menu based on the user's preferences and settings and display it as a list.

[0075] (Example of form 2)The menu selection suggestion system according to an embodiment of the present invention is a system that suggests menu choices at a restaurant. This system first interviews and analyzes the user's favorite foods and past dining history. Next, the user sets their priorities regarding taste, price, and health. Then, the user takes a picture of the restaurant's menu with a camera, and the app reads the menu. Based on the read menu, the app calculates the general calories and nutrients of each menu item. Finally, the generating AI automatically generates an optimal recommended menu order list for the user. Furthermore, the system interviews the user about their satisfaction with each menu item after they have eaten it, and incorporates this into their next order. For example, the system first interviews and analyzes the user's favorite foods and past dining history. At this time, it collects information about dishes the user has eaten in the past and their evaluations, and the generating AI analyzes this information. For example, it can identify dishes that the user found particularly delicious or healthy among those they have eaten in the past. Next, the user sets their priorities regarding taste, price, and health. For example, if taste is prioritized, the system can be set to prioritize suggesting delicious dishes over price or health. Conversely, if health is prioritized, the system can be set to suggest menus that take calories and nutrients into consideration. Next, the user takes a picture of the restaurant's menu with their camera, and the app reads the menu. For example, when a user takes a picture of the menu with their camera device, the app can analyze the image and read the menu contents as digital data. Based on the read menu, the app calculates the general calories and nutrients of each menu item. For example, based on the name and ingredients of the dish listed on the menu, the generating AI can estimate the calories and nutrients of that dish. This allows the user to make health-conscious choices for each menu item. Finally, the generating AI automatically generates a list of recommended menu items that are best suited to the user. For example, based on the user's preferences and settings, the generating AI can select the best menu items and display them as a list. This makes it easy for the user to choose a menu that suits them. Furthermore, the app gathers feedback on the user's satisfaction with each menu item after they've eaten it, and incorporates this into their next order. For example, if the user enters a rating for the dishes they ate, the generating AI can use that rating to improve its suggestions for the next time.This allows for continuous suggestions tailored to the user's preferences. As a result, the menu selection suggestion system can propose the optimal menu based on the user's preferences and health condition.

[0076] The menu selection suggestion system according to the embodiment comprises a hearing unit, a setting unit, a reading unit, a calculation unit, and a generation unit. The hearing unit hears the user's preferences. User preferences include, but are not limited to, taste preferences, ingredient preferences, and cooking method preferences. The hearing unit identifies the user's preferences by, for example, analyzing the user's past eating and drinking history. The hearing unit can also customize the content of the hearing to take into account the user's current health condition and dietary restrictions. For example, if the user is on a diet, it will ask questions about low-calorie dishes. The setting unit sets the importance of taste, price, and health based on the information obtained by the hearing unit. The importance of taste, price, and health can be set by, for example, the user. For example, if taste is important, the system can be set to prioritize suggesting delicious dishes over price or health. The reading unit photographs and reads the restaurant's menu with a camera. The reading unit can read menus photographed with a camera device, for example. For example, when a user takes a picture of a menu with a camera device, the reading unit analyzes the image and reads the menu contents as digital data. The calculation unit calculates the calories and nutrients of each menu item based on the menu read by the reading unit. The calculation unit can estimate calories and nutrients based on, for example, the names and ingredients of the dishes listed on the menu. The generation unit generates a recommended menu order list based on the information calculated by the calculation unit. The generation unit can select the optimal menu items based on, for example, the user's preferences and settings and display them as a list. As a result, the menu selection suggestion system according to this embodiment can suggest the optimal menu items based on the user's preferences and health condition.

[0077] The interviewing department gathers information about the user's preferences. These preferences include, but are not limited to, taste preferences, ingredient preferences, and cooking method preferences. For example, the interviewing department analyzes the user's past eating history to identify their preferences. Specifically, it stores the dishes the user has ordered and their ratings in a database and analyzes this data to understand the user's tastes. The interviewing department can also customize the interview content considering the user's current health status and dietary restrictions. For example, if the user is on a diet, it will ask questions about low-calorie dishes. Furthermore, the interviewing department also considers the user's allergy information and preferences for specific ingredients. For example, if the user has an allergy to a particular ingredient, it will prioritize suggesting menus that do not contain that ingredient. The interviewing department also collects information about the user's meal frequency and timing and uses this to suggest the most suitable menu. For example, if the user tends to eat a light breakfast, it will suggest a light breakfast menu. In this way, the interviewing department can support the user in selecting the optimal menu while considering their diverse needs and constraints.

[0078] The settings unit sets the importance of taste, price, and health based on the information obtained by the hearing unit. The importance of taste, price, and health can be set by the user, for example. Specifically, the user can adjust the importance of each item using sliders or checkboxes through the application interface. For example, if taste is prioritized, the system can be set to prioritize delicious dishes over price or health. Users can change these settings at any time, allowing for flexible adaptation to different situations. For example, the setting can be changed to prioritize taste for special events or anniversaries, and health for everyday meals. The settings unit can also automatically adjust the importance based on the user's past selection history and feedback. For example, if a user has frequently selected health-focused menus in the past, the system will automatically suggest a setting that increases the importance of health. This allows the settings unit to provide flexible menu suggestions tailored to the user's preferences and needs.

[0079] The reading unit reads the restaurant's menu by taking a picture of it with a camera. For example, the reading unit can read a menu that has been photographed with a camera device. Specifically, when a user takes a picture of a menu with a camera device, the reading unit can analyze the image and read the menu contents as digital data. For image analysis, OCR (Optical Character Recognition) technology is used to extract the text information written on the menu. Furthermore, using image recognition technology, it can analyze the photos and icons of the dishes listed on the menu to identify the type and characteristics of the dishes. For example, it can determine whether a dish is a meat dish or a fish dish from the photo of the dish listed on the menu. In addition, the reading unit can accurately read various types of menus, regardless of the menu's layout or format. This allows users to easily import menus of any format into the system. Furthermore, the reading unit can save the read menu information to a cloud server and share it with other devices and systems. This allows users to access consistent menu information from different devices.

[0080] The calculation unit calculates the calories and nutrients of each menu item based on the menu items read by the reading unit. For example, the calculation unit can estimate calories and nutrients based on the name and ingredients of the dishes listed on the menu. Specifically, it compares the name and ingredients of the dishes with a database and obtains calorie and nutrient information for each ingredient. For example, if the menu item is listed as "chicken curry," it obtains ingredient information such as chicken, curry sauce, and vegetables from the database, and calculates the total calories by adding up the calories and nutrients of each ingredient. The calculation unit can also calculate calories and nutrients more accurately by considering the cooking method and portion size of the dishes. For example, since fried and grilled foods have different calorie counts, it performs calorie calculations according to the cooking method. Furthermore, the calculation unit can perform calculations that emphasize specific nutrients according to the user's individual needs and constraints. For example, if a user wants to consume a lot of protein, it performs calculations that emphasize the protein content. In this way, the calculation unit can support the user in selecting the optimal menu item according to their health condition and dietary restrictions.

[0081] The generation unit generates a recommended menu order list based on information calculated by the calculation unit. For example, the generation unit can select the most suitable menu items based on the user's preferences and settings and display them as a list. Specifically, it uses an algorithm to select the most suitable menu items, taking into account the user's preferences, health status, budget, and other settings. For example, if the user desires low-calorie dishes, low-calorie menu items will be prioritized and included in the list. The generation unit also displays detailed information and nutritional information for the selected menu items to make it easier for the user to choose. Furthermore, the generation unit can continuously improve its suggestions based on the user's past selection history and feedback. For example, it can prioritize suggesting menu items that the user has previously given high ratings to. In addition, the generation unit can provide the latest suggestions based on menu information that is updated in real time. As a result, the generation unit can provide optimal menu suggestions that meet the diverse needs and circumstances of the user, thereby improving user satisfaction.

[0082] The system includes a satisfaction feedback unit that gathers feedback from users about their satisfaction with each menu item after they have eaten. For example, the satisfaction feedback unit can input the user's evaluation of the dishes they ate. For instance, the satisfaction feedback unit can input the user's evaluation of the dishes on a five-point scale. The satisfaction feedback unit can also input specific feedback from the user about the dishes they ate. For example, the satisfaction feedback unit can input feedback about the taste and texture of the dishes. This allows the system to gather user satisfaction and reflect it in future suggestions. Some or all of the above processing in the satisfaction feedback unit may be performed using AI, or not. For example, the satisfaction feedback unit can input user feedback into a generating AI and have the generating AI process the data to reflect it in future suggestions.

[0083] The satisfaction feedback unit may include a reflection unit that incorporates the feedback into the next order. For example, the satisfaction feedback unit can adjust the next order based on the user's evaluation of the dishes they ate. For example, the satisfaction feedback unit can incorporate dishes that the user gave a high rating to the next order. The satisfaction feedback unit can also exclude dishes that the user gave a low rating to the next order. For example, the satisfaction feedback unit can incorporate information about ingredients that the user should avoid into the next order. This allows the user's satisfaction to be reflected in the next order. Some or all of the above processing in the satisfaction feedback unit may be performed using AI, for example, or without AI. For example, the satisfaction feedback unit can input user feedback into a generating AI and have the generating AI process the data to be incorporated into the next order.

[0084] The interviewing unit can analyze the user's past eating and drinking history. For example, the interviewing unit can identify the user's preferences based on their past eating and drinking history. For instance, it can identify dishes the user has eaten in the past that they found particularly delicious or healthy. The interviewing unit can also identify ingredients the user should avoid based on their past eating and drinking history. For example, it can identify dishes the user has eaten in the past that caused allergic reactions or that they disliked. By analyzing the user's past eating and drinking history, more appropriate suggestions can be made. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input the user's past eating and drinking history into a generating AI and have the generating AI generate data to identify the user's preferences.

[0085] The settings unit allows users to set their priorities regarding taste, price, and health. For example, if taste is prioritized, the settings unit can be configured to suggest delicious dishes as a priority over price or health. For example, the settings unit can be configured to prioritize taste. If health is prioritized, the settings unit can be configured to suggest menus that take calories and nutrients into consideration. For example, the settings unit can be configured to prioritize health. Furthermore, if price is prioritized, the settings unit can be configured to suggest the best menu within the budget. For example, the settings unit can be configured to prioritize price. This allows for settings tailored to the user's preferences. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input the user's settings information into a generating AI and have the generating AI execute the optimal settings.

[0086] The reading unit can read menus captured by a camera device. For example, the reading unit can capture a menu using a smartphone camera, analyze the image, and read the menu contents as digital data. The reading unit can also read menus using a dedicated scanner. For example, the reading unit can scan a menu with a dedicated scanner, analyze the image, and read the menu contents as digital data. Furthermore, the reading unit can read printed menus using OCR technology. For example, the reading unit can use OCR technology to recognize printed menus with high accuracy and convert them into digital text. This allows menu information to be digitized by reading menus captured by a camera device. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input image data of a menu captured by a camera device into a generating AI, and have the generating AI perform the conversion from image data to text data.

[0087] The calculation unit can calculate calories and nutrients based on the names and ingredients of the dishes listed on the menu. For example, the calculation unit can calculate calories and nutrients based on the names and ingredients of the dishes listed on the menu. The calculation unit can also calculate calories and nutrients considering the cooking method of the dishes. Furthermore, the calculation unit can calculate calories and nutrients considering the origin and quality of the ingredients. This allows for health-conscious suggestions by estimating calories and nutrients based on the information provided on the menu. Some or all of the above processing in the calculation unit may be performed using AI, or without AI. For example, the calculation unit can input data on the names and ingredients of the dishes listed on the menu into a generating AI and have the generating AI perform the calculation of calories and nutrients.

[0088] The generation unit can select appropriate menus based on the user's preferences and settings and display them as a list. For example, the generation unit can select the optimal menu based on the user's preferences and settings and display it as a list. For example, the generation unit can select the optimal menu based on the user's preferences and settings and display it as a list. The generation unit can also analyze the user's past order history and suggest the optimal menu. For example, the generation unit suggests the optimal menu based on the user's past order history. Furthermore, the generation unit can generate menus while considering the user's current health condition and dietary restrictions. For example, the generation unit generates menus while considering the user's current health condition and dietary restrictions. This allows the generation unit to suggest the optimal menu based on the user's preferences and settings. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input data on the user's preferences and settings into a generation AI and have the generation AI generate the optimal menu.

[0089] The interviewing unit can estimate the user's emotions and adjust the timing of the interview based on the estimated emotions. For example, if the user is relaxed, the interviewing unit can conduct the interview before the meal to collect detailed preferences. For example, if the user is relaxed, the interviewing unit can conduct the interview before the meal. For example, if the user is busy, the interviewing unit can conduct the interview after the meal in the form of a simple questionnaire. For example, if the user is busy, the interviewing unit can conduct the interview after the meal in the form of a simple questionnaire. Furthermore, if the user is stressed, the interviewing unit can conduct the interview during the meal in a relaxed atmosphere. For example, if the user is stressed, the interviewing unit can conduct the interview during the meal in a relaxed atmosphere. In this way, by adjusting the timing of the interview according to the user's emotions, more appropriate interviews become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processes in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input user emotion data into a generating AI and have the generating AI generate data to adjust the timing of the interview.

[0090] The interviewing unit can analyze the user's past eating and drinking history and select the optimal interviewing method. For example, the interviewing unit can ask relevant questions based on the dishes the user has enjoyed eating in the past. For example, the interviewing unit can ask relevant questions based on the dishes the user has enjoyed eating in the past. The interviewing unit can also ask about ingredients to avoid based on the dishes the user has avoided in the past. For example, the interviewing unit can ask about ingredients to avoid based on the dishes the user has avoided in the past. Furthermore, the interviewing unit can estimate the user's preferences for specific dishes from their past eating and drinking history and customize the interview content. For example, the interviewing unit can estimate the user's preferences for specific dishes from their past eating and drinking history and customize the interview content. This allows the optimal interviewing method to be selected by analyzing the user's past eating and drinking history. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without using AI. For example, the interviewing unit can input the user's past dining history into a generating AI and have the AI ​​process the data to select the optimal interviewing method.

[0091] The interview function can customize the interview content to take into account the user's current health condition and dietary restrictions. For example, if the user is on a diet, the interview function can ask questions about low-calorie dishes. Furthermore, if the user has allergies, the interview function can ask questions about dishes that do not contain allergens. Additionally, if the user needs to consume specific nutrients, the interview function can ask questions about dishes that contain those nutrients. This enables interviews tailored to the user's health condition and dietary restrictions. Some or all of the above processing in the interview function may be performed using AI, or not. For example, the interview function can input data on the user's health condition and dietary restrictions into a generating AI and have the generating AI process data to customize the interview content.

[0092] The interviewing unit can estimate the user's emotions and determine the priority of the interview based on the estimated emotions. For example, if the user is excited, the interviewing unit can immediately begin the interview and collect detailed information. For example, if the user is excited, the interviewing unit can immediately begin the interview and collect detailed information. For example, if the user is tired, the interviewing unit can postpone the interview and start with simple questions. For example, if the user is tired, the interviewing unit can postpone the interview and start with simple questions. Furthermore, if the user is relaxed, the interviewing unit can conduct the interview before a meal to collect detailed preferences. For example, if the user is relaxed, the interviewing unit can conduct the interview before a meal to collect detailed preferences. This allows for more effective interviews by determining the priority of the interview according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the hearing unit may be performed using AI, or not using AI. For example, the hearing unit may input user emotion data into the generative AI and have the generative AI process data to determine the priority of the hearing.

[0093] The interviewing unit can conduct interviews about regionally specific ingredients and dishes, taking into account the user's geographical location. For example, if the user is traveling, the interviewing unit can ask questions about local specialties. The interviewing unit can also ask questions about popular local dishes if the user is in their hometown. Furthermore, if the user is interested in a particular region, the interviewing unit can ask questions about the cuisine of that region. This makes it possible to conduct interviews about regionally specific ingredients and dishes based on the user's geographical location. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input the user's geographical location information into a generating AI and have the generating AI generate data for conducting interviews about regionally specific ingredients and dishes.

[0094] The interviewing unit can analyze the user's social media activity and reflect relevant dining history in the interview. For example, the interviewing unit can estimate preferences based on photos of food shared by the user on social media. For example, the interviewing unit can estimate preferences based on photos of food shared by the user on social media. The interviewing unit can also estimate the types of food the user is interested in based on the food-related accounts the user follows on social media. For example, the interviewing unit can estimate the types of food the user is interested in based on the food-related accounts the user follows on social media. Furthermore, the interviewing unit can ask questions about relevant food based on events the user has participated in on social media. For example, the interviewing unit can ask questions about relevant food based on events the user has participated in on social media. This allows relevant dining history to be reflected in the interview based on the user's social media activity. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input data on the user's social media activity into a generating AI, and then have the AI ​​generate data to reflect related dining history in the interview.

[0095] The settings unit can estimate the user's emotions and adjust the way the settings are presented based on the estimated emotions. For example, if the user is relaxed, the settings unit can provide detailed settings options. For example, if the user is relaxed, the settings unit can provide detailed settings options. For example, if the user is in a hurry, the settings unit can provide simple settings options. For example, if the user is in a hurry, the settings unit can provide simple settings options. Furthermore, if the user is stressed, the settings unit can provide a simple and intuitive settings interface. For example, if the user is stressed, the settings unit can provide a simple and intuitive settings interface. This allows for more appropriate settings by adjusting the way the settings are presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input user emotion data into a generating AI and have the generating AI process data to adjust how the settings are expressed.

[0096] The settings unit can analyze the user's past settings history and suggest the optimal settings method. For example, the settings unit can suggest the optimal settings based on the user's past priorities regarding taste, price, and health. The settings unit can also suggest customized settings based on setting options the user has changed in the past. Furthermore, the settings unit can suggest settings suitable for specific time periods based on the user's past settings history. In this way, by analyzing the user's past settings history, the optimal settings method can be suggested. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input the user's past settings history into a generating AI and have the generating AI generate data to suggest the optimal settings method.

[0097] The settings unit can customize the settings considering the user's current lifestyle and health condition. For example, if the user is on a diet, the settings unit can suggest health-focused settings. The settings unit can also suggest settings that prioritize specific nutrients if the user needs to consume those nutrients. Furthermore, if the user has specific dietary restrictions, the settings unit can suggest settings that take those restrictions into account. This makes it possible to customize settings according to the user's lifestyle and health condition. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input data on the user's lifestyle and health condition into a generating AI and have the generating AI process data to customize the settings.

[0098] The settings unit can estimate the user's emotions and determine the priority of settings based on the estimated emotions. For example, if the user is relaxed, the settings unit can suggest settings that prioritize taste. For example, if the user is relaxed, the settings unit can suggest settings that prioritize taste. For example, if the user is in a hurry, the settings unit can suggest settings that prioritize price. For example, if the user is in a hurry, the settings unit can suggest settings that prioritize price. Furthermore, if the user is stressed, the settings unit can suggest settings that prioritize health. For example, if the user is stressed, the settings unit can suggest settings that prioritize health. This allows for more effective settings by determining the priority of settings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input user emotion data into a generating AI and have the AI ​​generate data to determine the priority of settings.

[0099] The settings unit can take the user's geographical location into consideration and configure settings related to region-specific ingredients and cuisine. For example, if the user is traveling, the settings unit can suggest settings that prioritize the local specialties of that region. For example, if the user is traveling, the settings unit can suggest settings that prioritize the local specialties of that region. For example, if the user is in their hometown, the settings unit can suggest settings that prioritize the popular local dishes. For example, if the user is in their hometown, the settings unit can suggest settings that prioritize the popular local dishes. Furthermore, if the user is interested in a particular region, the settings unit can suggest settings that prioritize the cuisine of that region. For example, if the user is interested in a particular region, the settings unit can suggest settings that prioritize the cuisine of that region. This makes it possible to configure settings related to region-specific ingredients and cuisine based on the user's geographical location. Some or all of the above processing in the settings unit may be performed using AI, for example, or without AI. For example, the settings unit can input the user's geographical location into a generating AI and have the generating AI generate data to configure settings related to region-specific ingredients and cuisine.

[0100] The settings unit can analyze the user's social media activity and suggest relevant settings. For example, the settings unit can suggest settings that prioritize taste based on photos of food the user has shared on social media. The settings unit can also suggest settings that prioritize dishes the user is interested in, based on food-related accounts the user follows on social media. Furthermore, the settings unit can suggest settings that prioritize dishes related to events the user has participated in on social media. In this way, relevant settings can be suggested based on the user's social media activity. Some or all of the above processing in the settings unit may be performed using AI, for example, or not. For example, the settings unit can input data on the user's social media activity into a generating AI and have the generating AI generate data to suggest relevant settings.

[0101] The loading unit can estimate the user's emotions and adjust the loading timing based on the estimated emotions. For example, if the user is relaxed, the loading unit can load the menu before the meal. For example, if the user is relaxed, the loading unit can load the menu before the meal. Also, if the user is busy, the loading unit can load the menu after the meal. For example, if the user is busy, the loading unit can load the menu after the meal. Furthermore, if the user is stressed, the loading unit can load the menu during the meal in a relaxed atmosphere. For example, if the user is stressed, the loading unit can load the menu during the meal in a relaxed atmosphere. By adjusting the loading timing according to the user's emotions, more appropriate loading becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the loading unit may be performed using AI, for example, or without AI. For example, the reading unit can input user emotion data into a generating AI and have the generating AI execute data to adjust the timing of the reading process.

[0102] The reading unit can support shooting under different lighting conditions to improve the accuracy of character recognition in menus. For example, the reading unit can recommend shooting under bright lighting to improve character recognition accuracy. The reading unit can also use a flash to improve character recognition accuracy when shooting under dim lighting. Furthermore, the reading unit can recommend shooting under natural light to improve character recognition accuracy. In this way, character recognition accuracy is improved by supporting shooting under different lighting conditions. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input image data of menus taken under different lighting conditions into a generating AI and have the generating AI execute data to improve character recognition accuracy.

[0103] The reading unit can apply the most suitable reading algorithm depending on the menu layout and font. For example, if the menu is written vertically, the reading unit can apply a reading algorithm that supports vertical writing. The reading unit can also apply a handwriting recognition algorithm if the menu is handwritten. Furthermore, if the menu is written in multiple languages, the reading unit can apply a multilingual reading algorithm. This enables optimal reading according to the menu layout and font. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input menu layout and font data into a generating AI and have the generating AI execute data to apply the most suitable reading algorithm.

[0104] The reading unit can estimate the user's emotions and determine the reading priority based on the estimated emotions. For example, if the user is relaxed, the reading unit can prioritize reading the menu before the meal. For example, if the user is relaxed, the reading unit can prioritize reading the menu before the meal. For example, if the user is busy, the reading unit can prioritize reading the menu after the meal. For example, if the user is busy, the reading unit can prioritize reading the menu after the meal. Furthermore, if the user is stressed, the reading unit can prioritize reading the menu in a relaxed atmosphere during the meal. For example, if the user is stressed, the reading unit can prioritize reading the menu in a relaxed atmosphere during the meal. This allows for more effective reading by determining the reading priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input user emotion data into a generating AI and have the generating AI process data to determine the priority of the reading process.

[0105] The reading unit can prioritize reading region-specific dish names and ingredients, taking into account the geographical location information of the menu. For example, if the user is traveling, the reading unit can prioritize reading local specialties of that region. For example, if the user is traveling, the reading unit can prioritize reading local specialties of that region. For example, if the user is in their hometown, the reading unit can prioritize reading popular local dishes. For example, if the user is in their hometown, the reading unit can prioritize reading popular local dishes. Furthermore, if the user is interested in a particular region, the reading unit can prioritize reading dish names and ingredients of that region. For example, if the user is interested in a particular region, the reading unit can prioritize reading dish names and ingredients of that region. By prioritizing the reading of region-specific dish names and ingredients, it becomes possible to make optimal suggestions tailored to the region. Some or all of the above processing in the reading unit may be performed using AI, for example, or not using AI. For example, the reading unit can input the geographical location information of the menu into a generating AI and cause the generating AI to execute data to prioritize the reading of region-specific dish names and ingredients.

[0106] The reading unit can improve its reading accuracy by referring to related literature for the menu. For example, the reading unit can improve its reading accuracy by referring to related literature for the names of dishes listed in the menu. The reading unit can also improve its reading accuracy by referring to related literature for the ingredients listed in the menu. For example, the reading unit can improve its reading accuracy by referring to related literature for the ingredients listed in the menu. Furthermore, the reading unit can also improve its reading accuracy by referring to related literature for the cooking methods listed in the menu. For example, the reading unit can improve its reading accuracy by referring to related literature for the cooking methods listed in the menu. In this way, reading accuracy is improved by referring to related literature. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input data on related literature for the menu into a generating AI and have the generating AI execute data to improve reading accuracy.

[0107] The calculation unit can estimate the user's emotions and adjust the calorie and nutrient calculation method based on the estimated emotions. For example, if the user is relaxed, the calculation unit can perform a detailed calculation of calories and nutrients. For example, if the user is relaxed, the calculation unit can perform a simplified calculation of calories and nutrients. For example, if the user is in a hurry, the calculation unit can perform a simplified calculation of calories and nutrients. For example, if the user is stressed, the calculation unit can perform a simple calculation of calories and nutrients. For example, if the user is stressed, the calculation unit can perform a simple calculation of calories and nutrients. By adjusting the calorie and nutrient calculation method according to the user's emotions, more appropriate calculations become possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input user emotion data into the generating AI and have the generating AI execute data to adjust the calculation method for calories and nutrients.

[0108] The calculation unit can perform more detailed calorie and nutrient calculations based on the ingredients and cooking methods of the menu. For example, the calculation unit can perform detailed calorie calculations based on the types and quantities of ingredients listed in the menu. The calculation unit can also calculate changes in nutrients by considering the cooking methods listed in the menu. Furthermore, the calculation unit can perform more accurate nutrient calculations by considering the origin and quality of the ingredients listed in the menu. This makes it possible to perform detailed calorie and nutrient calculations based on ingredients and cooking methods. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input data on the ingredients and cooking methods of the menu into a generating AI and have the generating AI perform detailed calorie and nutrient calculations.

[0109] The calculation unit can optimize the calculation algorithm by referring to past calculation data. For example, the calculation unit can improve the accuracy of calorie calculations based on past calculation data. The calculation unit can also improve the accuracy of nutrient calculations based on past calculation data. Furthermore, the calculation unit can improve the efficiency of the calculation algorithm based on past calculation data. This makes it possible to optimize the calculation algorithm by referring to past calculation data. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input past calculation data into a generating AI and have the generating AI execute data to optimize the calculation algorithm.

[0110] The calculation unit can estimate the user's emotions and adjust how the calculation results are displayed based on the estimated emotions. For example, if the user is relaxed, the calculation unit can display detailed calculation results. For example, if the user is relaxed, the calculation unit can display detailed calculation results. The calculation unit can also display simplified calculation results if the user is in a hurry. For example, if the user is in a hurry, the calculation unit can display simplified calculation results. Furthermore, if the user is stressed, the calculation unit can display simple calculation results. For example, if the user is stressed, the calculation unit can display simple calculation results. By adjusting how the calculation results are displayed according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input user emotion data into the generating AI and have the generating AI process data to adjust how the calculation results are displayed.

[0111] The calculation unit can calculate the calories and nutrients of regionally specific ingredients and dishes, taking into account the geographical location information of the menu. For example, the calculation unit can calculate the calories of dishes using regionally specific ingredients. The calculation unit can also calculate changes in nutrients, taking into account regionally specific cooking methods. Furthermore, the calculation unit can perform more accurate nutrient calculations by taking into account the origin and quality of regionally specific ingredients. By calculating the calories and nutrients of regionally specific ingredients and dishes, it becomes possible to make optimal suggestions tailored to each region. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input the geographical location information of the menu into a generating AI and have the generating AI process data to calculate the calories and nutrients of regionally specific ingredients and dishes.

[0112] The calculation unit can improve its calculation accuracy by referring to relevant literature for the menu. For example, the calculation unit can improve its calculation accuracy by referring to relevant literature for the names of dishes listed in the menu. The calculation unit can also improve its calculation accuracy by referring to relevant literature for the ingredients listed in the menu. For example, the calculation unit can improve its calculation accuracy by referring to relevant literature for the ingredients listed in the menu. Furthermore, the calculation unit can also improve its calculation accuracy by referring to relevant literature for the cooking methods listed in the menu. For example, the calculation unit can improve its calculation accuracy by referring to relevant literature for the cooking methods listed in the menu. In this way, calculation accuracy is improved by referring to relevant literature. Some or all of the above processing in the calculation unit may be performed using AI, for example, or without AI. For example, the calculation unit can input data on relevant literature for the menu into a generating AI and have the generating AI execute data to improve calculation accuracy.

[0113] The generation unit can estimate the user's emotions and adjust the method of generating the recommended menu order list based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate a recommended menu order list that includes detailed descriptions. For example, if the user is relaxed, the generation unit can generate a recommended menu order list that includes detailed descriptions. For example, if the user is in a hurry, the generation unit can generate a concise recommended menu order list. For example, if the user is in a hurry, the generation unit can generate a concise recommended menu order list. Furthermore, if the user is stressed, the generation unit can generate a simple and intuitive recommended menu order list. For example, if the user is stressed, the generation unit can generate a simple and intuitive recommended menu order list. By adjusting the method of generating the recommended menu order list according to the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processes in the generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the generation unit can input user emotion data into the generation AI and cause the generation AI to execute data to adjust the method for generating the recommended menu order list.

[0114] The generation unit can analyze the user's past order history and suggest the optimal menu. For example, the generation unit can suggest the optimal menu based on dishes the user has previously ordered and enjoyed. The generation unit can also suggest dishes to avoid based on dishes the user has previously avoided. Furthermore, the generation unit can estimate the user's preferences for specific dishes from their past order history and suggest the optimal menu. In this way, the optimal menu can be suggested by analyzing the user's past order history. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the user's past order history into a generation AI and have the generation AI process the data to suggest the optimal menu.

[0115] The generation unit can generate menus that take into account the user's current health condition and dietary restrictions. For example, if the user is on a diet, the generation unit can suggest low-calorie menus. The generation unit can also suggest menus that do not contain allergens if the user has allergies. Furthermore, if the user needs to consume specific nutrients, the generation unit can suggest menus that contain those nutrients. This makes it possible to generate menus that are tailored to the user's health condition and dietary restrictions. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input data on the user's health condition and dietary restrictions into a generation AI and have the generation AI process the data to generate the menus.

[0116] The generation unit can estimate the user's emotions and adjust the display method of the recommended menu order list based on the estimated user emotions. For example, if the user is relaxed, the generation unit can provide a display method that includes detailed explanations. For example, if the user is relaxed, the generation unit can provide a display method that includes detailed explanations. For example, if the user is in a hurry, the generation unit can provide a concise display method. For example, if the user is in a hurry, the generation unit can provide a concise display method. Furthermore, if the user is stressed, the generation unit can provide a simple and intuitive display method. For example, if the user is stressed, the generation unit can provide a simple and intuitive display method. This allows for a more appropriate display by adjusting the display method of the recommended menu order list according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI process data to adjust how the recommended menu order list is displayed.

[0117] The generation unit can prioritize suggesting region-specific dishes by considering the geographical location information of the menu. For example, if the user is traveling, the generation unit can prioritize suggesting local specialties. The generation unit can also prioritize suggesting popular local dishes if the user is in their hometown. Furthermore, if the user is interested in a particular region, the generation unit can prioritize suggesting dishes from that region. This allows for optimal suggestions tailored to the region by prioritizing region-specific dishes. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the geographical location information of the menu into the generation AI and have the generation AI process data to prioritize suggesting region-specific dishes.

[0118] The generation unit can improve the accuracy of its suggestions by referring to relevant literature for the menu. For example, the generation unit can improve the accuracy of its suggestions by referring to relevant literature for the names of the dishes listed in the menu. The generation unit can also improve the accuracy of its suggestions by referring to relevant literature for the ingredients listed in the menu. For example, the generation unit can improve the accuracy of its suggestions by referring to relevant literature for the ingredients listed in the menu. Furthermore, the generation unit can also improve the accuracy of its suggestions by referring to relevant literature for the cooking methods listed in the menu. For example, the generation unit can improve the accuracy of its suggestions by referring to relevant literature for the cooking methods listed in the menu. In this way, the accuracy of suggestions is improved by referring to relevant literature. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input data on relevant literature for the menu into the generation AI and have the generation AI execute data to improve the accuracy of suggestions.

[0119] The satisfaction assessment unit can estimate the user's emotions and adjust the timing of satisfaction assessments based on those emotions. For example, if the user is relaxed, the satisfaction assessment unit can conduct a detailed satisfaction assessment after the meal. Furthermore, if the user is busy, the satisfaction assessment unit can conduct a simple questionnaire-style satisfaction assessment after the meal. Additionally, if the user is stressed, the satisfaction assessment unit can conduct a relaxed atmosphere during the meal. This allows for more appropriate assessments by adjusting the timing of satisfaction assessments according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the satisfaction hearing unit may be performed using AI, or not using AI. For example, the satisfaction hearing unit may input user emotion data into the generation AI and have the generation AI process data to adjust the timing of the satisfaction hearing.

[0120] The satisfaction assessment department can analyze a user's past satisfaction ratings and select the optimal assessment method. For example, the satisfaction assessment department can ask relevant questions based on dishes that the user has previously given high ratings to. For example, the satisfaction assessment department can ask relevant questions based on dishes that the user has previously given high ratings to. The satisfaction assessment department can also ask about ingredients to avoid based on dishes that the user has previously given low ratings to. For example, the satisfaction assessment department can ask about ingredients to avoid based on dishes that the user has previously given low ratings to. Furthermore, the satisfaction assessment department can estimate a user's preferences for specific dishes from their past satisfaction ratings and customize the assessment content. For example, the satisfaction assessment department can estimate a user's preferences for specific dishes from their past satisfaction ratings and customize the assessment content. This allows for the selection of the optimal assessment method by analyzing a user's past satisfaction ratings. Some or all of the above-described processes in the satisfaction assessment department may be performed using AI, for example, or without AI. For example, the satisfaction assessment unit can input users' past satisfaction ratings into a generating AI and have the AI ​​process the data to select the optimal assessment method.

[0121] The satisfaction assessment unit can estimate the user's emotions and determine the priority of satisfaction assessments based on those emotions. For example, if the user is relaxed, the satisfaction assessment unit can prioritize conducting the satisfaction assessment after the meal. Similarly, if the user is busy, the satisfaction assessment unit can prioritize conducting a simple questionnaire after the meal. Furthermore, if the user is stressed, the satisfaction assessment unit can prioritize conducting the satisfaction assessment in a relaxed atmosphere during the meal. This allows for more effective assessments by prioritizing satisfaction assessments according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the satisfaction hearing unit may be performed using AI, or not using AI. For example, the satisfaction hearing unit may input user emotion data into the generation AI and have the generation AI process data to determine the priority of satisfaction hearings.

[0122] The satisfaction assessment unit can assess user satisfaction with regional cuisine, taking into account the user's geographical location. For example, if the user is traveling, the satisfaction assessment unit can assess satisfaction with local specialties. The satisfaction assessment unit can also assess user satisfaction with popular local cuisine if the user is in their hometown. Furthermore, if the user is interested in a particular region, the satisfaction assessment unit can assess satisfaction with the cuisine of that region. This allows for optimal recommendations tailored to each region by assessing satisfaction with regional cuisine. Some or all of the above-described processes in the satisfaction assessment unit may be performed using AI, for example, or without AI. For example, the satisfaction hearing unit can input the user's geographical location information into a generating AI and have the AI ​​generate data to gather information on satisfaction levels regarding local cuisine.

[0123] The reflection unit can estimate the user's emotions and adjust how it reflects those emotions in the next order. For example, if the user is relaxed, the reflection unit can adjust the next order based on detailed feedback. For example, if the user is relaxed, the reflection unit can adjust the next order based on detailed feedback. For example, if the user is in a hurry, the reflection unit can adjust the next order based on concise feedback. For example, if the user is in a hurry, the reflection unit can adjust the next order based on concise feedback. Furthermore, if the user is stressed, the reflection unit can adjust the next order based on simple feedback. For example, if the user is stressed, the reflection unit can adjust the next order based on simple feedback. By adjusting how it reflects the user's emotions in the next order, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reflection unit may be performed using AI, for example, or without AI. For example, the reflection unit can input user emotion data into the generating AI and have the generating AI execute data to adjust how to reflect that in the next order.

[0124] The reflection unit can analyze the user's past satisfaction ratings and select the optimal reflection method. For example, the reflection unit can adjust the next order based on dishes the user has given high ratings to in the past. The reflection unit can also suggest menu items to avoid based on dishes the user has given low ratings to in the past. Furthermore, the reflection unit can estimate the user's preference for specific dishes from their past satisfaction ratings and adjust the next order accordingly. In this way, the optimal reflection method can be selected by analyzing the user's past satisfaction ratings. Some or all of the above processing in the reflection unit may be performed using AI, for example, or without AI. For example, the reflection unit can input the user's past satisfaction ratings into a generating AI and have the generating AI process the data to select the optimal reflection method.

[0125] The reflection unit can estimate the user's emotions and determine priorities for reflecting those emotions in the next order based on the estimated emotions. For example, if the user is relaxed, the reflection unit can prioritize the next order based on detailed feedback. For example, if the user is relaxed, the reflection unit can prioritize the next order based on detailed feedback. For example, if the user is in a hurry, the reflection unit can prioritize the next order based on concise feedback. For example, if the user is in a hurry, the reflection unit can prioritize the next order based on concise feedback. Furthermore, if the user is stressed, the reflection unit can prioritize the next order based on simple feedback. For example, if the user is stressed, the reflection unit can prioritize the next order based on simple feedback. This allows for more effective suggestions by determining priorities for reflecting the user's emotions in the next order. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the reflection unit may be performed using AI, for example, or without AI. For example, the reflection unit can input user emotion data into a generating AI and cause the generating AI to generate data to determine the priority of which data to reflect in the next order.

[0126] The reflection unit can reflect the user's geographical location information and make recommendations based on region-specific cuisine. For example, if the user is traveling, the reflection unit can adjust the next order based on feedback about local specialties. The reflection unit can also adjust the next order based on feedback about popular local dishes if the user is in their hometown. Furthermore, if the user is interested in a particular region, the reflection unit can adjust the next order based on feedback about the cuisine of that region. This allows for optimal suggestions tailored to the region by reflecting on region-specific cuisine. Some or all of the above processing in the reflection unit may be performed using AI, for example, or without AI. For example, the reflection unit can input the user's geographical location information into a generating AI and have the generating AI generate data to reflect on region-specific cuisine.

[0127] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0128] The menu selection suggestion system can also make suggestions considering the user's meal timing. For example, it can suggest different menus depending on whether it's breakfast, lunch, or dinner. For breakfast, it can suggest menus that prioritize energy replenishment; for lunch, it can suggest menus containing balanced nutrients; and for dinner, it can suggest lighter, easily digestible menus. This makes it possible to suggest the optimal menu according to the user's meal timing.

[0129] The satisfaction feedback department can analyze the content of users' conversations during meals and incorporate it into future recommendations. For example, if a user talks about a particular dish during a meal, the department can gather feedback on their satisfaction with that dish. If a user mentions wanting to try a new dish, that dish can be included in future recommendations. Furthermore, if a user talks about a specific ingredient during a meal, menu items containing that ingredient can be included in future recommendations. This allows for recommendations based on the user's conversations during meals.

[0130] The satisfaction assessment department can analyze users' facial expressions during meals and reflect this in future recommendations. For example, if a user smiles during a meal, it can be estimated that they are highly satisfied with the dish and this can be reflected in future recommendations. Conversely, if a user shows a confused expression during a meal, it can be estimated that they are not highly satisfied with the dish and can be excluded from future recommendations. Furthermore, if a user shows a surprised expression during a meal, it can be estimated that they found the dish novel and can be included in future recommendations. This makes it possible to make recommendations based on user expressions.

[0131] The listening department can analyze users' voices while they are eating and incorporate this into future recommendations. For example, if a user says "delicious" during a meal, it can be estimated that they were highly satisfied with the dish and this can be reflected in future recommendations. Similarly, if a user says "spicy," it can be estimated that they found the dish too spicy and can be excluded from future recommendations. Furthermore, if a user says "I want to eat this again," that dish can be included in future recommendations. This enables recommendations based on user voices.

[0132] The settings unit can make suggestions considering the user's meal frequency. For example, if a user frequently eats out, it can suggest menus containing balanced nutrients. If a user only eats out once a week, it can suggest a high-end menu to make that one meal special. Furthermore, if a user is on a diet, it can suggest low-calorie menus. This allows for optimal menu suggestions tailored to the user's meal frequency.

[0133] The reading unit can make suggestions considering the user's dining location. For example, if the user is eating at home, it can suggest easy-to-prepare menus. If the user is dining at a restaurant, it can suggest the restaurant's specialty dishes. Furthermore, if the user is dining outdoors, such as on a picnic, it can suggest menus that are easy to carry. This enables optimal menu suggestions tailored to the user's dining location.

[0134] The calculation unit can calculate calories and nutrients while considering the user's meal times. For example, for breakfast, it can perform calorie calculations that prioritize energy replenishment. For lunch, it can perform calorie calculations that include a balanced range of nutrients. Furthermore, for dinner, it can perform lighter calorie calculations that are easy to digest. This makes it possible to calculate optimal calories and nutrients according to the user's meal times.

[0135] The generation unit can make suggestions considering the user's dietary goals. For example, if the user's goal is weight loss, it can suggest low-calorie menus. If the user's goal is muscle building, it can suggest high-protein menus. Furthermore, if the user's goal is relaxation, it can suggest menus that include ingredients with relaxing effects. This makes it possible to suggest optimal menus tailored to the user's dietary goals.

[0136] The interviewing department can make suggestions while considering the user's eating habits. For example, if a user has a habit of eating at the same time every day, the department can suggest a menu that suits that time. Also, if a user has a habit of having a special meal on weekends, the department can suggest a special menu that suits that habit. Furthermore, if a user has a habit of eating a specific dish on a specific day of the week, the department can suggest a menu that suits that day. This makes it possible to suggest the most suitable menu according to the user's eating habits.

[0137] The interview function can estimate the user's emotions and adjust the interview content based on those estimations. For example, if the user is relaxed, detailed questions can be asked to gain a deeper understanding of their preferences. If the user is in a hurry, concise questions can be asked to gather necessary information quickly. Furthermore, if the user is stressed, the interview can be conducted in a relaxed atmosphere to reduce their burden. This enables optimal interviews tailored to the user's emotions.

[0138] The following briefly describes the processing flow for example form 2.

[0139] Step 1: The interview team interviews the user to understand their preferences. These preferences include, for example, taste preferences, ingredient preferences, and cooking method preferences. The interview team analyzes the user's past eating and drinking history to identify their preferences. They can also customize the interview content to take into account the user's current health condition and dietary restrictions. Step 2: The settings unit sets the importance of taste, price, and health based on the information obtained by the interviewing unit. For example, if taste is prioritized, the unit can be set to prioritize suggesting delicious dishes over price or health. Step 3: The reading unit takes a picture of the store's menu with a camera and reads it. For example, when a user takes a picture of the menu with a camera device, the reading unit can analyze the image and read the menu contents as digital data. Step 4: The calculation unit calculates the calories and nutrients for each menu item based on the menu items read by the reading unit. For example, it can estimate calories and nutrients based on the names and ingredients of the dishes listed in the menu. Step 5: The generation unit generates a recommended menu list based on the information calculated by the calculation unit. For example, it can select the optimal menu based on the user's preferences and settings and display it as a list.

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0141] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0142] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0143] For example, the hearing unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the setting unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the reading unit is implemented by the camera 42 and control unit 46A of the smart device 14. For example, the calculation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the satisfaction hearing unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0144] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0145] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0147] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0150] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0151] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0152] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0153] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0154] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0155] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0156] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0158] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0159] For example, the hearing unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the setting unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the reading unit is implemented by the camera 42 and control unit 46A of the smart glasses 214. For example, the calculation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the satisfaction hearing unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0160] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0161] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0162] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0163] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0164] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0166] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0167] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] For example, the hearing unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the setting unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the reading unit is implemented by the camera 42 and control unit 46A of the headset terminal 314. For example, the calculation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the satisfaction hearing unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0176] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0177] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0178] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0179] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0180] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0181] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0182] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0183] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0184] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0185] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0186] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0187] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0188] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0189] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0190] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0191] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0192] For example, the hearing unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the setting unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the reading unit is implemented by the camera 42 and control unit 46A of the robot 414. For example, the calculation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the satisfaction hearing unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0193] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0194] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0195] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0196] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0197] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0198] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0199] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0200] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0201] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0202] 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.

[0203] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0204] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0205] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0206] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0207] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0208] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0209] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0210] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0211] (Note 1) A section for gathering user preferences, Based on the information obtained by the aforementioned hearing unit, a setting unit sets the importance of taste, price, and health, A reading unit that takes a picture of the store's menu with a camera and reads it, A calculation unit calculates the calories and nutrients of each menu item based on the menu items read by the aforementioned reading unit, The system comprises a generation unit that generates a recommended menu list based on the information calculated by the calculation unit. A system characterized by the following features. (Note 2) It includes a satisfaction assessment section that gathers feedback from users about their satisfaction with each menu item after they've eaten. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned satisfaction hearing department, Includes a section to reflect changes in the next order. The system described in Appendix 2, characterized by the features described herein. (Note 4) The aforementioned hearing section is, Analyze the user's past dining history. The system described in Appendix 1, characterized by the features described herein. (Note 5) The setting unit is, Users can set their priorities regarding taste, price, and health. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reading unit, Read menus captured by a camera device. The system described in Appendix 1, characterized by the features described herein. (Note 7) The calculation unit, Calculate calories and nutrients based on the names and ingredients of the dishes listed on the menu. The system described in Appendix 1, characterized by the features described herein. (Note 8) The generating unit is Based on the user's preferences and settings, the system selects the appropriate menu and displays it as a list. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned hearing section is, The system estimates the user's emotions and adjusts the timing of interviews based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned hearing section is, We analyze the user's past dining history and select the most suitable interview method. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned hearing section is, Customize the interview content to take into account the user's current health status and dietary restrictions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned hearing section is, The system estimates the user's emotions and determines the priority of interviews based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned hearing section is, Taking into account the user's geographical location, we conduct interviews about local ingredients and dishes. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned hearing section is, Analyze users' social media activity and incorporate their relevant dining history into interviews. The system described in Appendix 1, characterized by the features described herein. (Note 15) The setting unit is, It estimates the user's emotions and adjusts how settings are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The setting unit is, It analyzes the user's past settings history and suggests the optimal settings. The system described in Appendix 1, characterized by the features described herein. (Note 17) The setting unit is, Customize settings to take into account the user's current lifestyle and health condition. The system described in Appendix 1, characterized by the features described herein. (Note 18) The setting unit is, It estimates the user's emotions and determines the priority of settings based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The setting unit is, The settings for local ingredients and dishes are configured taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 20) The setting unit is, Analyzes users' social media activity and suggests relevant settings. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned reading unit, It estimates the user's emotions and adjusts the loading timing based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned reading unit, To improve the accuracy of menu character recognition, support for shooting under different lighting conditions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned reading unit, The optimal loading algorithm is applied depending on the menu layout and font. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned reading unit, It estimates the user's emotions and determines the loading priority based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned reading unit, The system prioritizes loading regionally specific dish names and ingredients, taking into account the geographical location of the menu. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned reading unit, Refer to related literature in the menu to improve reading accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 27) The calculation unit, It estimates the user's emotions and adjusts the calorie and nutrient calculation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The calculation unit, Based on the ingredients and cooking methods of the menu, more detailed calorie and nutrient calculations are performed. The system described in Appendix 1, characterized by the features described herein. (Note 29) The calculation unit, Optimize the calculation algorithm by referring to past calculation data. The system described in Appendix 1, characterized by the features described herein. (Note 30) The calculation unit, It estimates the user's emotions and adjusts how the calculation results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The calculation unit, The menu's geographical location information is taken into consideration when calculating the calories and nutrients of regionally specific ingredients and dishes. The system described in Appendix 1, characterized by the features described herein. (Note 32) The calculation unit, Refer to the related literature in the menu to improve calculation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 33) The generating unit is We estimate the user's emotions and adjust the method of generating the recommended menu order list based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The generating unit is We analyze the user's past order history and suggest the most suitable menu. The system described in Appendix 1, characterized by the features described herein. (Note 35) The generating unit is The system generates menus that take into account the user's current health status and dietary restrictions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The generating unit is The system estimates the user's emotions and adjusts how the recommended menu order list is displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The generating unit is The menu prioritizes suggesting regionally specific dishes, taking into account the geographical location of the menu. The system described in Appendix 1, characterized by the features described herein. (Note 38) The generating unit is Refer to related literature in the menu to improve the accuracy of your suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned satisfaction hearing department, We estimate the user's emotions and adjust the timing of satisfaction assessments based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 40) The aforementioned satisfaction hearing department, We analyze past user satisfaction ratings and select the most suitable interview method. The system described in Appendix 2, characterized by the features described herein. (Note 41) The aforementioned satisfaction hearing department, The system estimates user emotions and prioritizes satisfaction interviews based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 42) The aforementioned satisfaction hearing department, We will take into account the user's geographical location and gather feedback on their satisfaction with local cuisine. The system described in Appendix 2, characterized by the features described herein. (Note 43) The aforementioned reflection unit is, We estimate the user's emotions and adjust how those emotions are reflected in the next order. The system described in Appendix 3, characterized by the features described herein. (Note 44) The aforementioned reflection unit is, We analyze past user satisfaction ratings and select the most appropriate method for reflecting them. The system described in Appendix 3, characterized by the features described herein. (Note 45) The aforementioned reflection unit is, It estimates the user's emotions and determines priorities to reflect those emotions in the next order. The system described in Appendix 3, characterized by the features described herein. (Note 46) The aforementioned reflection unit is, The system takes the user's geographical location into account to reflect regionally specific cuisines. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0212] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A section for gathering user preferences, Based on the information obtained by the aforementioned hearing unit, a setting unit sets the importance of taste, price, and health, A reading unit that takes a picture of the store's menu with a camera and reads it, A calculation unit calculates the calories and nutrients of each menu item based on the menu items read by the aforementioned reading unit, The system comprises a generation unit that generates a recommended menu list based on the information calculated by the calculation unit. A system characterized by the following features.

2. It includes a satisfaction assessment section that gathers feedback from users about their satisfaction with each menu item after they've eaten. The system according to feature 1.

3. The aforementioned satisfaction hearing department, Includes a section to reflect changes in the next order. The system according to feature 2.

4. The aforementioned hearing section is, Analyze the user's past dining history. The system according to feature 1.

5. The setting unit is, Users can set their priorities regarding taste, price, and health. The system according to feature 1.

6. The aforementioned reading unit, Read menus captured by a camera device. The system according to feature 1.

7. The calculation unit, Calculate calories and nutrients based on the names and ingredients of the dishes listed on the menu. The system according to feature 1.

8. The generating unit is Based on the user's preferences and settings, the system selects the appropriate menu and displays it as a list. The system according to feature 1.

9. The aforementioned hearing section is, The system estimates the user's emotions and adjusts the timing of interviews based on those estimated emotions. The system according to feature 1.

Images