System

Abstract

To provide a system capable of proposing the optimal menu in consideration of food allergies and preferences of a customer.SOLUTION: A system according to an embodiment comprises a collection unit, a proposal unit, an acquisition unit, an introduction unit, and a processing unit. The collection unit collects information about food allergy and preferences of a customer. The proposal unit proposes a menu to the customer on the basis of the information collected by the collection unit. The acquisition unit acquires the past order history and trends. The introduction unit introduces a new menu and promotion to the customer on the basis of the information acquired by the acquisition unit. The processing unit processes the order and payment of the customer.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately consider customers' food allergies and preferences when making menu suggestions, and there is room for improvement.

[0005] The system according to the embodiment aims to propose an optimal menu, taking into consideration a customer's food allergies and preferences. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a suggestion unit, an acquisition unit, an introduction unit, and a processing unit. The collection unit collects information on food allergies and preferences of customers. The suggestion unit suggests menus to customers based on the information collected by the collection unit. The acquisition unit acquires past order history and trends. The introduction unit introduces new menus and promotions to customers based on the information acquired by the acquisition unit. The processing unit processes customer orders and payments. Effect of the Invention

[0007] The system according to the embodiment can propose the most suitable menu in consideration of the food allergies and preferences of the customer. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The order support AI assistant system according to the embodiment of the present invention is a system that proposes a menu in consideration of a customer's food allergies and preferences, and introduces new menus and promotions by analyzing past order history and trends. The system collects information on the customer's food allergies and preferences, and proposes a menu based on the information. Furthermore, the system acquires past order history and trends, and introduces new menus and promotions based on the information. Finally, the system processes the customer's order and payment. For example, when collecting information on a customer's food allergies and preferences, the information can be collected through the customer's smartphone application or SNS account. When the customer inputs information on food allergies and preferences into a smartphone application, the collection unit acquires the information. Furthermore, information on the customer's food allergies and preferences can be collected from SNS accounts. Next, a menu is proposed based on the collected information. The suggestion unit can propose a menu using a generation AI. For example, the generation AI proposes an optimal menu based on information on the customer's food allergies and preferences. In addition, a menu can be proposed while interacting with the customer using an AI chatbot. Furthermore, it is also possible to estimate the customer's current health and psychological state, and propose a menu based on the estimated information. Furthermore, the system acquires past order history and trends, and introduces new menus and promotions based on the acquired information. The acquisition unit acquires past order history and trends, and the introduction unit introduces new menus and promotions based on the acquired information. For example, a customer's past order history can be analyzed and new menu items can be suggested based on trends. It is also possible to introduce new menu items based on the customer's geographic location information. Finally, the customer's order and payment are processed. The processing unit accepts customer orders and processes payments. For example, payments can be processed using blockchain technology. It is also possible to prepare customer orders in advance using predictive models. This can reduce waiting times and improve customer convenience.In this way, the ordering support AI assistant system can reduce waiting times and improve customer convenience by taking into account customers' food allergies and preferences, analyzing past order history and trends to introduce new menu items and promotions, and automatically processing orders and payments.

[0029] The order support AI assistant system according to the embodiment includes a collection unit, a suggestion unit, an acquisition unit, an introduction unit, and a processing unit. The collection unit collects information on the customer's food allergies and preferences. The information on the customer's food allergies and preferences includes, but is not limited to, specific ingredients, cooking methods, and taste preferences. The collection unit can collect information, for example, through the customer's smartphone application. The customer inputs information on food allergies and preferences into the smartphone application, and the collection unit acquires the information. The collection unit can also collect information on the customer's food allergies and preferences from SNS accounts. The suggestion unit uses a generation AI to suggest a menu based on the information collected by the collection unit. The generation AI can suggest a menu using, for example, a text generation AI (e.g., LLM). The generation AI suggests an optimal menu based on the information on the customer's food allergies and preferences. The suggestion unit can also suggest a menu while interacting with the customer using an AI chatbot. Furthermore, the suggestion unit can estimate the customer's current health and psychological states and suggest a menu based on them. The acquisition unit acquires past order histories and trends. The acquisition unit can acquire the customer's past order history and trends, for example, by using a database access or an API call. The introduction unit introduces new menus and promotions to the customer based on the information acquired by the acquisition unit. The introduction unit can introduce the new menus and promotions to the customer, for example, by using a notification method or a display format. The processing unit processes the customer's order and payment. The processing unit can process the payment, for example, by using a blockchain technology. Blockchain technology includes, for example, Ethereum and Hyperledger, but is not limited to such examples. The processing unit can also prepare the customer's order in advance using a predictive model. Predictive models include, for example, regression models and time series predictive models, but are not limited to such examples.As a result, the order support AI assistant system of the embodiment can reduce waiting times and improve customer convenience by taking into account customers' food allergies and preferences, analyzing past order history and trends to introduce new menus and promotions, and automatically processing orders and payments.

[0030] The collection unit collects information on the customer's food allergies and preferences. The information on the customer's food allergies and preferences includes, but is not limited to, specific ingredients, cooking methods, and taste preferences. The collection unit can collect information, for example, through the customer's smartphone application. The customer inputs the information on food allergies and preferences into the smartphone application, and the collection unit acquires the information. The collection unit can also collect information on the customer's food allergies and preferences from SNS accounts. Specifically, the smartphone application is designed to provide a user-friendly interface and allow the customer to easily input information. For example, a check box or a drop-down menu can be used to select specific ingredients or cooking methods. In addition, detailed preferences and allergy information can be freely described using a text input field. Furthermore, in collecting information from SNS accounts, the collection unit analyzes the customer's posting content and activities such as "likes" to grasp trends in food allergies and preferences. For example, if a customer frequently presses "like" on a specific dish or restaurant, the preference can be estimated based on that information. This allows the collection unit to collect information on the customer's food allergies and preferences from multiple angles and provide more accurate data. The information collected is stored in a secure database and encrypted for privacy purposes, minimizing the risk of unauthorized access to customers' personal information.

[0031] The suggestion unit uses the generation AI to suggest a menu based on the information collected by the collection unit. The generation AI can suggest a menu using, for example, a text generation AI (e.g., LLM). The generation AI suggests an optimal menu based on the customer's food allergies and preferences. The suggestion unit can also suggest a menu while interacting with the customer using an AI chatbot. Furthermore, the suggestion unit can estimate the customer's current health and psychological state and suggest a menu based on that. Specifically, the generation AI receives the customer's food allergies and preferences as input, and generates an optimal menu while referring to past data and a recipe database. For example, if the customer has a dairy allergy, the generation AI suggests a menu that does not contain dairy products. Also, if the customer likes spicy food, the generation AI preferentially suggests spicy dishes. The AI ​​chatbot uses natural language processing technology to interact with the customer and suggest menus in real time. For example, if the customer inputs, "I want to have a light meal today," the AI ​​chatbot suggests menus such as light meals and salads. Furthermore, the suggestion unit utilizes sensor data from wearable devices and smartphones to estimate the health and psychological state of the customer. For example, it can monitor the heart rate and stress level and suggest a menu that includes ingredients that have a relaxing effect based on the monitoring. This allows the suggestion unit to provide the optimal menu according to the individual needs of the customer and improve customer satisfaction.

[0032] The acquisition unit acquires past order history and trends. The acquisition unit can acquire the customer's past order history and trends, for example, by using database access or API call. Specifically, the acquisition unit collects detailed data such as the menus that the customer has ordered in the past, the frequency of ordering, and the circumstances at the time of ordering. This allows the customer's preferences and behavioral patterns to be understood and more personalized suggestions to be made. For example, if a customer frequently orders a specific dish, the dish can be preferentially suggested. The acquisition unit also collects trend information according to seasons and events. For example, cold drinks and light meals are often popular in the summer, so menus can be suggested based on such trends. Furthermore, the acquisition unit also utilizes the order history and trend information of other customers to understand popular menus and new trends. This allows new menus and promotions to be effectively introduced to customers. The acquired data is updated in real time, and suggestions are always made based on the latest information. This allows the acquisition unit to accurately understand the customer's past behavior and current trends and provide a foundation for making optimal suggestions.

[0033] The introduction unit introduces new menus and promotions to customers based on the information acquired by the acquisition unit. The introduction unit can introduce new menus and promotions to customers using, for example, a notification method or a display format. Specifically, new menu and promotion information can be quickly conveyed to customers using push notifications, emails, SMS, and the like of a smartphone application. For example, when a new seasonal menu is released, the customer can be notified through push notifications. In addition, it is also possible to visually appeal to the customer using banner advertisements and pop-up messages within the application. Furthermore, the introduction unit can make personalized suggestions based on the customer's past order history and preferences. For example, for a customer who has preferred to order a particular dish in the past, new menus and promotions related to that dish can be preferentially introduced. This allows the customer to enjoy new menus and advantageous promotions that suit their preferences without missing them. The introduction unit can also collect customer feedback and continuously improve the accuracy and effectiveness of the introduction content. For example, it can track whether the customer actually ordered the introduced menu and adjust the next introduction content based on the result. This allows the introduction unit to always provide optimal information to customers and improve customer satisfaction.

[0034] The processing unit processes customer orders and payments. The processing unit can process payments using, for example, blockchain technology. Examples of blockchain technology include, but are not limited to, Ethereum and Hyperledger. The processing unit can also prepare customer orders in advance using a predictive model. Examples of predictive models include, but are not limited to, regression models and time series predictive models. Specifically, after a customer confirms an order, the processing unit encrypts payment information using blockchain technology and safely processes the information. This can prevent tampering with or unauthorized access to payment information and protect customer privacy. Furthermore, the processing unit can use the predictive model to analyze customer order patterns and prepare necessary ingredients and cooking procedures in advance. For example, based on past order history and trend information, it can predict an increase in orders during a specific time period or day of the week, and ensure inventory of ingredients accordingly. This can improve the efficiency of order processing and reduce customer waiting time. Furthermore, the processing unit can flexibly respond to cases where a customer cancels or changes an order. For example, when the order content is changed, the processing unit can recalculate the predictive model and adjust the cooking procedure and preparation of ingredients based on the new order content. This enables the processing unit to efficiently and securely process customer orders and payments, improving customer satisfaction.

[0035] The collection unit can collect information on food allergies and preferences through a smartphone application of the customer. For example, the collection unit can acquire information by the customer inputting the information on food allergies and preferences into the smartphone application. Examples of smartphone applications include, but are not limited to, iOS apps, Android apps, and Web apps. This allows more accurate information to be acquired by collecting information through the smartphone application of the customer. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the information acquired from the smartphone application into AI and have the AI ​​analyze the information.

[0036] The suggestion unit can suggest an appropriate menu using the generation AI. The suggestion unit can suggest a menu based on information about a customer's food allergies and preferences, for example, using the generation AI. The generation AI suggests an optimal menu based on information about a customer's food allergies and preferences. For example, the generation AI receives information about a customer's food allergies and preferences as input, and generates a menu based on that information. In this way, by using the generation AI, it is possible to suggest an optimal menu to a customer. Some or all of the above-mentioned processing in the suggestion unit is performed using the generation AI.

[0037] The estimation unit estimates the health and psychological state of the customer, and the suggestion unit can suggest a menu based on the information. The estimation unit can estimate the health and psychological state of the customer using indicators such as the customer's heart rate, stress level, and emotion analysis. The suggestion unit suggests a menu based on the health and psychological state of the customer estimated by the estimation unit. For example, the estimation unit can collect heart rate data of the customer and estimate the stress level of the customer based on the data. The estimation unit can also analyze facial expression data of the customer and estimate the customer's emotion using an emotion analysis algorithm. This enables a more personalized suggestion by suggesting a menu based on the customer's health and psychological state. A part or all of the above-mentioned processing in the estimation unit and the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input the customer's heart rate data to AI and cause the AI ​​to execute stress level estimation.

[0038] The processing unit can process the payment using the blockchain technology. The processing unit can process the customer's payment using the blockchain technology, for example. Blockchain technology includes, but is not limited to, Ethereum and Hyperledger. By using the blockchain technology, the security and transparency of the payment are improved. For example, the processing unit can record the customer's payment information in the blockchain to prevent tampering with the transaction. The processing unit can also automatically process the payment using a smart contract. As a result, the security and transparency of the payment are improved by using the blockchain technology. A part or all of the above-mentioned processing in the processing unit may be performed using, for example, AI, or may be performed without using AI. For example, the processing unit can input the payment information into the AI ​​and cause the AI ​​to execute the payment processing.

[0039] The introduction unit can introduce a new menu based on the customer's location information. The introduction unit can acquire the customer's location information, for example, by using the customer's GPS information or Wi-Fi location information. Based on the location information, the introduction unit introduces a new menu to the customer. For example, when the customer is in a specific area, the introduction unit can introduce a new menu using ingredients from that area. Also, when the customer is traveling, the introduction unit can introduce a new menu using ingredients from the travel destination. This allows for more appropriate suggestions by introducing a new menu based on the customer's geographic location information. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input the location information into AI and cause the AI ​​to select the optimal menu.

[0040] The collection unit can collect information on food allergies and preferences from the customer's SNS account. Examples of SNS accounts include, but are not limited to, Facebook, Twitter, Instagram, and the like. The collection unit can analyze the information on food allergies and preferences of the customer based on the information acquired from the SNS account. This allows more information to be acquired by collecting information from the SNS account. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the information acquired from the SNS account into AI and have the AI ​​analyze the information.

[0041] The suggestion unit can suggest a menu while interacting with the customer using an AI chatbot. Examples of AI chatbots include, but are not limited to, Dialogflow and Rasa. The AI ​​chatbot collects information on the customer's food allergies and preferences through interaction with the customer, and suggests a menu based on that information. For example, the AI ​​chatbot may ask the customer, "What kind of ingredients do you like?" and suggest a menu based on the customer's answer. In this way, by using the AI ​​chatbot, a more appropriate menu can be suggested through interaction with the customer. A part or all of the above-mentioned processing in the suggestion unit is performed using a generation AI.

[0042] The collection unit can infer information on food allergies and preferences based on the purchase history of the customer. The collection unit can, for example, analyze the purchase history of the customer and infer information on the customer's food allergies and preferences based on the information. The purchase history includes, for example, online shopping history and POS data, but is not limited to such examples. The collection unit analyzes products purchased in the past and products avoided by the customer based on the purchase history, and infers information on food allergies and preferences. For example, the collection unit can infer information on the customer's preferences based on products frequently purchased by the customer in the past. The collection unit can also infer information on food allergies based on products avoided by the customer in the past. This makes it possible to obtain more accurate information by inferring information based on the purchase history. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input purchase history data into AI and have the AI ​​execute analysis of the information.

[0043] The collection unit can infer information on food allergies and preferences based on the past health check results of the customer. The collection unit can, for example, analyze the past health check results of the customer and infer information on food allergies and preferences of the customer based on the information. The health check results include, for example, blood test results and body measurement data, but are not limited to such examples. The collection unit infers the health condition and allergy information of the customer based on the health check results. For example, the collection unit can infer allergy information for a specific food ingredient based on the blood test results of the customer. The collection unit can also infer preference information based on the body measurement data of the customer. This makes it possible to obtain more accurate information by inferring information based on the health check results. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input health check result data to AI and have AI execute analysis of the information.

[0044] The processing unit can prepare customer orders in advance using a predictive model. Predictive models include, but are not limited to, for example, regression models and time series predictive models. The predictive model predicts future orders based on the customer's past order history and trends. For example, the processing unit can receive the customer's past order history as input and predict future orders using the predictive model. In this way, the customer's orders can be processed quickly by using the predictive model. Some or all of the above-mentioned processing in the processing unit may be performed using, for example, AI, or may be performed without using AI. For example, the processing unit can input order history data to AI and cause the AI ​​to execute order prediction.

[0045] The collection unit can analyze the customer's past meal history and select an appropriate collection method. Meal history includes, for example, a meal diary and a restaurant order history, but is not limited to such examples. The collection unit analyzes the menus that the customer frequently ordered and the menus that the customer avoided based on the past meal history and selects an appropriate collection method. For example, the collection unit can collect information on food allergies and preferences based on the menus that the customer frequently ordered in the past. The collection unit can also collect information on food allergies based on the menus that the customer avoided in the past. In this way, by analyzing the past meal history, information can be collected in a more appropriate manner. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input meal history data into AI and have AI execute analysis of the information.

[0046] The collection unit can filter the information on food allergies and preferences based on the customer's current health condition and lifestyle habits when collecting the information on food allergies and preferences. The collection unit can filter the information on food allergies and preferences based on, for example, the results of a health check and information on lifestyle habits of the customer. The health condition and lifestyle habits include, for example, the amount of exercise, sleep patterns, and dietary content, but are not limited to such examples. The collection unit filters the information on food allergies and preferences based on the results of a health check. For example, if a customer is on a specific diet, the information on food allergies and preferences can be filtered based on that information. In addition, if a customer has a specific exercise habit, the information on food allergies and preferences can also be filtered based on that information. In this way, more accurate information can be obtained by filtering information based on the health condition and lifestyle habits. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input health check result data to AI and have the AI ​​execute filtering of information.

[0047] When collecting information on food allergies and preferences, the collection unit can preferentially collect information that is highly relevant to the customer, taking into account the customer's geographical location information. The collection unit can obtain the customer's geographical location information, for example, by using the customer's GPS information or Wi-Fi location information. Based on the location information, the collection unit preferentially collects information that is highly relevant to the customer. For example, if the customer is in a specific area, allergy information on ingredients in that area can be preferentially collected. Also, if the customer is traveling, allergy information on ingredients at the travel destination can be preferentially collected. In this way, more relevant information can be collected by taking the geographical location information into consideration. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input location information to AI and cause AI to select highly relevant information.

[0048] The collection unit can analyze the social media activity of the customer when collecting the information on food allergies and preferences, and collect related information. The collection unit can, for example, analyze the social media activity of the customer and collect the information on food allergies and preferences based on the information. Social media activity includes, for example, the content of posts, the number of likes, comments, and the like, but is not limited to such examples. The collection unit analyzes photos of meals shared by the customer on social media to collect the information on food allergies and preferences. For example, the allergy information can be collected based on ingredients mentioned by the customer on social media. In addition, the food-related accounts that the customer follows on social media can be analyzed to collect the information on preferences. In this way, more information can be collected by analyzing the social media activity. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input social media data into AI and have the AI ​​perform analysis of the information.

[0049] When proposing a menu, the suggestion unit can adjust the level of detail of the suggestion based on the customer's meal history. The meal history includes, but is not limited to, for example, a restaurant order history and a meal diary. The suggestion unit can make a detailed suggestion based on a menu previously ordered by the customer. In addition, when the customer visits for the first time, a basic suggestion can be made. This allows a more appropriate suggestion to be made by adjusting the level of detail of the suggestion based on the meal history. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input meal history data into AI and cause the AI ​​to adjust the level of detail of the suggestion.

[0050] When proposing a menu, the suggestion unit can apply different suggestion algorithms depending on the food category of the customer. The suggestion algorithms include, but are not limited to, collaborative filtering and content-based filtering. If the customer is a vegetarian, the suggestion unit can apply a suggestion algorithm specialized for vegetarian menus. If the customer prefers gluten-free food, the suggestion unit can apply a suggestion algorithm specialized for gluten-free menus. This enables optimal suggestions according to food categories. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input food category data to AI and cause AI to apply the suggestion algorithm.

[0051] When proposing a menu, the suggestion unit can determine the priority of the suggestions based on the time of meal submission of the customer. The priority of the suggestions includes, for example, importance score and urgency, but is not limited to such examples. When the customer orders breakfast, the suggestion unit can preferentially suggest a breakfast menu. Also, when the customer orders at lunchtime, the suggestion unit can preferentially suggest a lunch menu. This allows more appropriate suggestions to be made by determining the priority of the suggestions based on the time of meal submission. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input meal submission time data to AI and cause AI to execute the determination of the priority of the suggestions.

[0052] The suggestion unit can adjust the order of suggestions based on the relevance of the customer's meals when suggesting a menu. The suggestion unit can, for example, analyze the customer's past order history and meal relevance, and adjust the order of suggestions based on the information. The order of suggestions includes, for example, relevance scores and chronological order, but is not limited to such examples. The suggestion unit can preferentially suggest new menus related to menus that the customer has ordered in the past. In addition, if the customer likes a specific ingredient, it can preferentially suggest menus that include the ingredient. This allows more appropriate suggestions to be made by adjusting the order of suggestions based on the relevance of meals. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input order history data to AI and cause AI to adjust the order of suggestions.

[0053] The acquisition unit can analyze the customer's past order history and select an appropriate acquisition method. The acquisition method includes, but is not limited to, for example, an API call or a database query. The acquisition unit analyzes the menu items frequently ordered and avoided by the customer based on the past order history and selects an appropriate acquisition method. For example, the acquisition unit can acquire the order history based on the menu items frequently ordered by the customer in the past. The acquisition unit can also acquire the order history based on the menu items avoided by the customer in the past. This allows information to be acquired in a more appropriate manner by analyzing the past order history. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input the order history data into an AI and have the AI ​​execute the analysis of the information.

[0054] The acquisition unit can filter the order history and trends based on the customer's current living situation and areas of interest when acquiring the order history and trends. The acquisition unit can filter the order history and trends based on, for example, the customer's health check results and information on lifestyle habits. Filtering includes, for example, keyword filtering and attribute filtering, but is not limited to such examples. The acquisition unit filters the order history and trends based on the customer's health check results. For example, if the customer is on a specific diet, the order history and trends can be filtered based on that information. In addition, if the customer has a specific exercise habit, the order history and trends can also be filtered based on that information. This makes it possible to obtain more accurate information by filtering information based on the living situation and areas of interest. Part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input health check result data to AI and have AI execute filtering of information.

[0055] When acquiring order history and trends, the acquisition unit can preferentially acquire history with high relevance in consideration of geographical location information of the customer. The acquisition unit can acquire geographical location information of the customer, for example, by using GPS information or Wi-Fi location information of the customer. Based on the location information, the acquisition unit preferentially acquires history with high relevance to the customer. For example, when the customer is in a specific area, the order history and trends of that area can be preferentially acquired. In addition, when the customer is traveling, the order history and trends of the travel destination can also be preferentially acquired. In this way, by considering the geographical location information, more relevant information can be acquired. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input location information to AI and cause AI to select history with high relevance.

[0056] The acquisition unit can analyze the social media activities of the customer when acquiring the order history and trends, and acquire related history. The acquisition unit can, for example, analyze the social media activities of the customer and acquire the order history and trends based on the information. The social media activities include, for example, the content of the post, the number of likes, comments, etc., but are not limited to such examples. The acquisition unit analyzes the photos of the meal shared by the customer on social media to acquire the order history and trends. For example, the order history can be acquired based on the ingredients mentioned by the customer on social media. In addition, food-related accounts that the customer follows on social media can be analyzed to acquire trends. In this way, more information can be acquired by analyzing the social media activities. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input social media data into AI and have the AI ​​execute analysis of the information.

[0057] The introduction unit can select an appropriate introduction method when introducing a new menu or promotion by analyzing the customer's past order history. The introduction unit can, for example, analyze the customer's past order history and select a method for introducing the new menu or promotion based on the information. The introduction method includes, for example, email, push notification, in-app notification, etc., but is not limited to such examples. The introduction unit can preferentially introduce new menus related to menus ordered by the customer in the past. In addition, if the customer likes a specific ingredient, the introduction unit can preferentially introduce new menus containing that ingredient. In this way, by analyzing the past order history, the new menus and promotions can be introduced in a more appropriate manner. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input order history data into AI and cause the AI ​​to select the introduction method.

[0058] The introduction unit can customize the means of introduction based on the customer's current living situation when introducing a new menu or promotion. The introduction unit can customize the means of introduction of the new menu or promotion based on, for example, the customer's health check result or information on the lifestyle habits. The introduction means include, for example, text, image, and sound, but are not limited to such examples. When the customer provides the health check result, the introduction unit can customize and introduce the new menu or promotion based on the information. Also, when the customer is on a specific diet, the introduction unit can customize and introduce the new menu or promotion based on the information. This allows more appropriate introduction by customizing the means of introduction based on the living situation. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input the health check result data into AI and have the AI ​​execute customization of the introduction means.

[0059] The introduction unit can select an appropriate introduction method in consideration of the geographical location information of the customer when introducing a new menu or promotion. The introduction unit can acquire the geographical location information of the customer, for example, by using the customer's GPS information or Wi-Fi location information. Based on the location information, the introduction unit selects an appropriate introduction method for the customer. For example, when the customer is in a specific area, new menus and promotions using ingredients from that area can be preferentially introduced. In addition, when the customer is traveling, new menus and promotions using ingredients from the travel destination can be preferentially introduced. In this way, by taking the geographical location information into consideration, new menus and promotions can be introduced in a more appropriate manner. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input the location information into AI and cause the AI ​​to select the introduction method.

[0060] The introduction unit can analyze the social media activity of the customer and propose a means of introduction when introducing a new menu or promotion. The introduction unit can, for example, analyze the social media activity of the customer and propose a means of introducing the new menu or promotion based on the information. Social media activity includes, for example, the content of the post, the number of likes, comments, etc., but is not limited to such examples. The introduction unit analyzes photos of meals shared by the customer on social media and proposes new menus and promotions. For example, the introduction unit can propose new menus and promotions based on ingredients mentioned by the customer on social media. In addition, the introduction unit can analyze food-related accounts that the customer follows on social media and propose new menus and promotions. In this way, by analyzing social media activity, it is possible to propose new menus and promotions based on more information. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input social media data into AI and have the AI ​​perform analysis of the information.

[0061] The processing unit can select an optimal processing method by analyzing the customer's past payment history at the time of order and payment processing. Processing methods include, but are not limited to, payment methods and security measures, for example. The processing unit can perform optimal payment processing based on payment methods used by the customer in the past. Also, the processing unit can perform optimal payment processing based on payment methods avoided by the customer in the past. In this way, by analyzing the past payment history, payment processing can be performed in a more appropriate manner. A part or all of the above-mentioned processing in the processing unit may be performed using, for example, AI, or may be performed without using AI. For example, the processing unit can input payment history data into AI and have AI analyze the information.

[0062] The processing unit can customize the processing means based on the customer's current living situation at the time of order and payment processing. The processing unit can customize the processing means for order and payment based on, for example, the customer's medical checkup results and information on living habits. The processing means include, for example, but are not limited to, payment methods and security measures. When the customer provides a medical checkup result, the processing unit can customize the order and payment processing based on the information. Also, when the customer is on a specific diet, the processing unit can customize the order and payment processing based on the information. This enables more appropriate processing by customizing the processing means based on the living situation. Part or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can input medical checkup result data to AI and have AI execute customization of the processing means.

[0063] The processing unit can select the optimal processing method in consideration of the geographical location information of the customer when processing the order and payment. The processing unit can acquire the geographical location information of the customer, for example, by using the customer's GPS information or Wi-Fi location information. Based on the location information, the processing unit selects the optimal processing method for the customer. For example, if the customer is in a specific area, the processing unit can preferentially suggest a payment method for that area. Also, if the customer is traveling, the processing unit can preferentially suggest a payment method for the travel destination. In this way, by taking the geographical location information into consideration, the payment processing can be performed in a more appropriate manner. Part or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can input the location information into AI and have the AI ​​select the processing method.

[0064] The processing unit can analyze the social media activity of the customer and suggest a processing method at the time of order and payment processing. The processing unit can, for example, analyze the social media activity of the customer and suggest the optimal payment processing based on the information. Social media activity includes, for example, the content of posts, the number of likes, comments, etc., but is not limited to such examples. The processing unit analyzes the payment method shared by the customer on social media and suggests the optimal payment processing. For example, the processing unit can suggest the optimal payment processing based on the payment method mentioned by the customer on social media. In addition, the processing unit can analyze the payment-related accounts that the customer follows on social media and suggest the optimal payment processing. In this way, by analyzing the social media activity, the optimal payment processing can be suggested based on more information. Part or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can input social media data into AI and have the AI ​​perform analysis of the information.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The order support AI assistant system can further include a nutritional evaluation unit that evaluates the nutritional balance of a customer's meal. The nutritional evaluation unit evaluates the nutritional balance based on the customer's meal history and health check results, and provides the information to the proposal unit. For example, if a customer has not eaten many vegetables in the past, the nutritional evaluation unit can provide that information to the proposal unit, and the proposal unit can suggest a menu that contains a lot of vegetables. In addition, if a customer has been consuming excessive amounts of a particular nutrient, a balanced menu can be suggested based on that information. This makes it possible to suggest menus that take the customer's health into consideration.

[0067] The order support AI assistant system can further include a satisfaction evaluation unit that evaluates the customer's satisfaction with the meal. The satisfaction evaluation unit analyzes the customer's past feedback and reviews and provides the information to the suggestion unit. For example, it can suggest similar menu items based on menu items that the customer has given high ratings in the past. It can also suggest that the customer avoid menu items that the customer has given low ratings. This makes it possible to suggest menu items that will improve customer satisfaction.

[0068] The order support AI assistant system can further include an environmental evaluation unit that evaluates the environmental impact of the customer's meal. The environmental evaluation unit evaluates the production process and transportation distance of the ingredients of the menu to be proposed, and provides environmentally friendly menus to the proposal unit. For example, it can preferentially propose menus that use locally produced ingredients. In addition, it is also possible to reduce the environmental impact by proposing menus that use seasonal ingredients. This makes it possible to propose environmentally friendly menus.

[0069] The order support AI assistant system can further include a cultural evaluation unit that considers the cultural background of the customer's meal. The cultural evaluation unit considers the customer's cultural background and religious restrictions and provides the information to the suggestion unit. For example, it can suggest menus that take into account dietary restrictions based on a particular religion. It can also improve cultural satisfaction by suggesting traditional dishes from the customer's hometown. This makes it possible to suggest menus that take into account the customer's cultural background.

[0070] The order support AI assistant system can further include an economic evaluation unit that considers the economic background of the customer's meal. The economic evaluation unit analyzes the customer's budget and spending history and provides the information to the suggestion unit. For example, it can suggest the optimal menu within the customer's budget. It can also reduce the financial burden by suggesting a menu that takes into account certain promotions and discounts. This makes it possible to suggest menus that take into account the customer's economic background.

[0071] The process flow of the first embodiment will be briefly described below.

[0072] Step 1: The collection department collects information on the customer's food allergies and preferences. The customer's food allergy and preference information includes specific ingredients, cooking methods, taste preferences, etc. The collection department collects information through the customer's smartphone application and SNS account. Step 2: The suggestion unit proposes a menu based on the information collected by the collection unit. Using a generation AI (e.g., a text generation AI or an AI chatbot), the unit proposes the optimal menu based on the customer's food allergies and preferences. It is also possible to estimate the customer's current health and psychological state and propose a menu based on that. Step 3: The acquisition unit acquires past order history and trends. The acquisition unit acquires the customer's past order history and trends using database access or API calls. Step 4: The introduction unit introduces new menus and promotions to the customer based on the information acquired by the acquisition unit. The introduction unit introduces the new menus and promotions to the customer using a notification method and a display format. Step 5: The processor processes customer orders and payments. The processor processes payments using blockchain technology (e.g., Ethereum or Hyperledger). It can also prepare customer orders in advance using predictive models (e.g., regression models or time series forecasting models).

[0073] (Example 2) The order support AI assistant system according to the embodiment of the present invention is a system that proposes a menu in consideration of a customer's food allergies and preferences, and introduces new menus and promotions by analyzing past order history and trends. The system collects information on the customer's food allergies and preferences, and proposes a menu based on the information. Furthermore, the system acquires past order history and trends, and introduces new menus and promotions based on the information. Finally, the system processes the customer's order and payment. For example, when collecting information on a customer's food allergies and preferences, the information can be collected through the customer's smartphone application or SNS account. When the customer inputs information on food allergies and preferences into a smartphone application, the collection unit acquires the information. Furthermore, information on the customer's food allergies and preferences can be collected from SNS accounts. Next, a menu is proposed based on the collected information. The suggestion unit can propose a menu using a generation AI. For example, the generation AI proposes an optimal menu based on information on the customer's food allergies and preferences. In addition, a menu can be proposed while interacting with the customer using an AI chatbot. Furthermore, it is also possible to estimate the customer's current health and psychological state, and propose a menu based on the estimated information. Furthermore, the system acquires past order history and trends, and introduces new menus and promotions based on the acquired information. The acquisition unit acquires past order history and trends, and the introduction unit introduces new menus and promotions based on the acquired information. For example, a customer's past order history can be analyzed and new menu items can be suggested based on trends. It is also possible to introduce new menu items based on the customer's geographic location information. Finally, the customer's order and payment are processed. The processing unit accepts customer orders and processes payments. For example, payments can be processed using blockchain technology. It is also possible to prepare customer orders in advance using predictive models. This can reduce waiting times and improve customer convenience.In this way, the ordering support AI assistant system can reduce waiting times and improve customer convenience by taking into account customers' food allergies and preferences, analyzing past order history and trends to introduce new menu items and promotions, and automatically processing orders and payments.

[0074] The order support AI assistant system according to the embodiment includes a collection unit, a suggestion unit, an acquisition unit, an introduction unit, and a processing unit. The collection unit collects information on the customer's food allergies and preferences. The information on the customer's food allergies and preferences includes, but is not limited to, specific ingredients, cooking methods, and taste preferences. The collection unit can collect information, for example, through the customer's smartphone application. The customer inputs information on food allergies and preferences into the smartphone application, and the collection unit acquires the information. The collection unit can also collect information on the customer's food allergies and preferences from SNS accounts. The suggestion unit uses a generation AI to suggest a menu based on the information collected by the collection unit. The generation AI can suggest a menu using, for example, a text generation AI (e.g., LLM). The generation AI suggests an optimal menu based on the information on the customer's food allergies and preferences. The suggestion unit can also suggest a menu while interacting with the customer using an AI chatbot. Furthermore, the suggestion unit can estimate the customer's current health and psychological states and suggest a menu based on them. The acquisition unit acquires past order histories and trends. The acquisition unit can acquire the customer's past order history and trends, for example, by using a database access or an API call. The introduction unit introduces new menus and promotions to the customer based on the information acquired by the acquisition unit. The introduction unit can introduce the new menus and promotions to the customer, for example, by using a notification method or a display format. The processing unit processes the customer's order and payment. The processing unit can process the payment, for example, by using a blockchain technology. Blockchain technology includes, for example, Ethereum and Hyperledger, but is not limited to such examples. The processing unit can also prepare the customer's order in advance using a predictive model. Predictive models include, for example, regression models and time series predictive models, but are not limited to such examples.As a result, the order support AI assistant system of the embodiment can reduce waiting times and improve customer convenience by taking into account customers' food allergies and preferences, analyzing past order history and trends to introduce new menus and promotions, and automatically processing orders and payments.

[0075] The collection unit collects information on the customer's food allergies and preferences. The information on the customer's food allergies and preferences includes, but is not limited to, specific ingredients, cooking methods, and taste preferences. The collection unit can collect information, for example, through the customer's smartphone application. The customer inputs the information on food allergies and preferences into the smartphone application, and the collection unit acquires the information. The collection unit can also collect information on the customer's food allergies and preferences from SNS accounts. Specifically, the smartphone application is designed to provide a user-friendly interface and allow the customer to easily input information. For example, a check box or a drop-down menu can be used to select specific ingredients or cooking methods. In addition, detailed preferences and allergy information can be freely described using a text input field. Furthermore, in collecting information from SNS accounts, the collection unit analyzes the customer's posting content and activities such as "likes" to grasp trends in food allergies and preferences. For example, if a customer frequently presses "like" on a specific dish or restaurant, the preference can be estimated based on that information. This allows the collection unit to collect information on the customer's food allergies and preferences from multiple angles and provide more accurate data. The information collected is stored in a secure database and encrypted for privacy purposes, minimizing the risk of unauthorized access to customers' personal information.

[0076] The suggestion unit uses the generation AI to suggest a menu based on the information collected by the collection unit. The generation AI can suggest a menu using, for example, a text generation AI (e.g., LLM). The generation AI suggests an optimal menu based on the customer's food allergies and preferences. The suggestion unit can also suggest a menu while interacting with the customer using an AI chatbot. Furthermore, the suggestion unit can estimate the customer's current health and psychological state and suggest a menu based on that. Specifically, the generation AI receives the customer's food allergies and preferences as input, and generates an optimal menu while referring to past data and a recipe database. For example, if the customer has a dairy allergy, the generation AI suggests a menu that does not contain dairy products. Also, if the customer likes spicy food, the generation AI preferentially suggests spicy dishes. The AI ​​chatbot uses natural language processing technology to interact with the customer and suggest menus in real time. For example, if the customer inputs, "I want to have a light meal today," the AI ​​chatbot suggests menus such as light meals and salads. Furthermore, the suggestion unit utilizes sensor data from wearable devices and smartphones to estimate the health and psychological state of the customer. For example, it can monitor the heart rate and stress level and suggest a menu that includes ingredients that have a relaxing effect based on the monitoring. This allows the suggestion unit to provide the optimal menu according to the individual needs of the customer and improve customer satisfaction.

[0077] The acquisition unit acquires past order history and trends. The acquisition unit can acquire the customer's past order history and trends, for example, by using database access or API call. Specifically, the acquisition unit collects detailed data such as the menus that the customer has ordered in the past, the frequency of ordering, and the circumstances at the time of ordering. This allows the customer's preferences and behavioral patterns to be understood and more personalized suggestions to be made. For example, if a customer frequently orders a specific dish, the dish can be preferentially suggested. The acquisition unit also collects trend information according to seasons and events. For example, cold drinks and light meals are often popular in the summer, so menus can be suggested based on such trends. Furthermore, the acquisition unit also utilizes the order history and trend information of other customers to understand popular menus and new trends. This allows new menus and promotions to be effectively introduced to customers. The acquired data is updated in real time, and suggestions are always made based on the latest information. This allows the acquisition unit to accurately understand the customer's past behavior and current trends and provide a foundation for making optimal suggestions.

[0078] The introduction unit introduces new menus and promotions to customers based on the information acquired by the acquisition unit. The introduction unit can introduce new menus and promotions to customers using, for example, a notification method or a display format. Specifically, new menu and promotion information can be quickly conveyed to customers using push notifications, emails, SMS, and the like of a smartphone application. For example, when a new seasonal menu is released, the customer can be notified through push notifications. In addition, it is also possible to visually appeal to the customer using banner advertisements and pop-up messages within the application. Furthermore, the introduction unit can make personalized suggestions based on the customer's past order history and preferences. For example, for a customer who has preferred to order a particular dish in the past, new menus and promotions related to that dish can be preferentially introduced. This allows the customer to enjoy new menus and advantageous promotions that suit their preferences without missing them. The introduction unit can also collect customer feedback and continuously improve the accuracy and effectiveness of the introduction content. For example, it can track whether the customer actually ordered the introduced menu and adjust the next introduction content based on the result. This allows the introduction unit to always provide optimal information to customers and improve customer satisfaction.

[0079] The processing unit processes customer orders and payments. The processing unit can process payments using, for example, blockchain technology. Examples of blockchain technology include, but are not limited to, Ethereum and Hyperledger. The processing unit can also prepare customer orders in advance using a predictive model. Examples of predictive models include, but are not limited to, regression models and time series predictive models. Specifically, after a customer confirms an order, the processing unit encrypts payment information using blockchain technology and safely processes the information. This can prevent tampering with or unauthorized access to payment information and protect customer privacy. Furthermore, the processing unit can use the predictive model to analyze customer order patterns and prepare necessary ingredients and cooking procedures in advance. For example, based on past order history and trend information, it can predict an increase in orders during a specific time period or day of the week, and ensure inventory of ingredients accordingly. This can improve the efficiency of order processing and reduce customer waiting time. Furthermore, the processing unit can flexibly respond to cases where a customer cancels or changes an order. For example, when the order content is changed, the processing unit can recalculate the predictive model and adjust the cooking procedure and preparation of ingredients based on the new order content. This enables the processing unit to efficiently and securely process customer orders and payments, improving customer satisfaction.

[0080] The collection unit can collect information on food allergies and preferences through a smartphone application of the customer. For example, the collection unit can acquire information by the customer inputting the information on food allergies and preferences into the smartphone application. Examples of smartphone applications include, but are not limited to, iOS apps, Android apps, and Web apps. This allows more accurate information to be acquired by collecting information through the smartphone application of the customer. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the information acquired from the smartphone application into AI and have the AI ​​analyze the information.

[0081] The suggestion unit can suggest an appropriate menu using the generation AI. The suggestion unit can suggest a menu based on information about a customer's food allergies and preferences, for example, using the generation AI. The generation AI suggests an optimal menu based on information about a customer's food allergies and preferences. For example, the generation AI receives information about a customer's food allergies and preferences as input, and generates a menu based on that information. In this way, by using the generation AI, it is possible to suggest an optimal menu to a customer. Some or all of the above-mentioned processing in the suggestion unit is performed using the generation AI.

[0082] The estimation unit estimates the health and psychological state of the customer, and the suggestion unit can suggest a menu based on the information. The estimation unit can estimate the health and psychological state of the customer using indicators such as the customer's heart rate, stress level, and emotion analysis. The suggestion unit suggests a menu based on the health and psychological state of the customer estimated by the estimation unit. For example, the estimation unit can collect heart rate data of the customer and estimate the stress level of the customer based on the data. The estimation unit can also analyze facial expression data of the customer and estimate the customer's emotion using an emotion analysis algorithm. This enables a more personalized suggestion by suggesting a menu based on the customer's health and psychological state. A part or all of the above-mentioned processing in the estimation unit and the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input the customer's heart rate data to AI and cause the AI ​​to execute stress level estimation.

[0083] The processing unit can process the payment using the blockchain technology. The processing unit can process the customer's payment using the blockchain technology, for example. Blockchain technology includes, but is not limited to, Ethereum and Hyperledger. By using the blockchain technology, the security and transparency of the payment are improved. For example, the processing unit can record the customer's payment information in the blockchain to prevent tampering with the transaction. The processing unit can also automatically process the payment using a smart contract. As a result, the security and transparency of the payment are improved by using the blockchain technology. A part or all of the above-mentioned processing in the processing unit may be performed using, for example, AI, or may be performed without using AI. For example, the processing unit can input the payment information into the AI ​​and cause the AI ​​to execute the payment processing.

[0084] The introduction unit can introduce a new menu based on the customer's location information. The introduction unit can acquire the customer's location information, for example, by using the customer's GPS information or Wi-Fi location information. Based on the location information, the introduction unit introduces a new menu to the customer. For example, when the customer is in a specific area, the introduction unit can introduce a new menu using ingredients from that area. Also, when the customer is traveling, the introduction unit can introduce a new menu using ingredients from the travel destination. This allows for more appropriate suggestions by introducing a new menu based on the customer's geographic location information. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input the location information into AI and cause the AI ​​to select the optimal menu.

[0085] The collection unit can collect information on food allergies and preferences from the customer's SNS account. Examples of SNS accounts include, but are not limited to, Facebook, Twitter, Instagram, and the like. The collection unit can analyze the information on food allergies and preferences of the customer based on the information acquired from the SNS account. This allows more information to be acquired by collecting information from the SNS account. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the information acquired from the SNS account into AI and have the AI ​​analyze the information.

[0086] The suggestion unit can suggest a menu while interacting with the customer using an AI chatbot. Examples of AI chatbots include, but are not limited to, Dialogflow and Rasa. The AI ​​chatbot collects information on the customer's food allergies and preferences through interaction with the customer, and suggests a menu based on that information. For example, the AI ​​chatbot may ask the customer, "What kind of ingredients do you like?" and suggest a menu based on the customer's answer. In this way, by using the AI ​​chatbot, a more appropriate menu can be suggested through interaction with the customer. A part or all of the above-mentioned processing in the suggestion unit is performed using a generation AI.

[0087] The collection unit can infer information on food allergies and preferences based on the purchase history of the customer. The collection unit can, for example, analyze the purchase history of the customer and infer information on the customer's food allergies and preferences based on the information. The purchase history includes, for example, online shopping history and POS data, but is not limited to such examples. The collection unit analyzes products purchased in the past and products avoided by the customer based on the purchase history, and infers information on food allergies and preferences. For example, the collection unit can infer information on the customer's preferences based on products frequently purchased by the customer in the past. The collection unit can also infer information on food allergies based on products avoided by the customer in the past. This makes it possible to obtain more accurate information by inferring information based on the purchase history. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input purchase history data into AI and have the AI ​​execute analysis of the information.

[0088] The collection unit can infer information on food allergies and preferences based on the past health check results of the customer. The collection unit can, for example, analyze the past health check results of the customer and infer information on food allergies and preferences of the customer based on the information. The health check results include, for example, blood test results and body measurement data, but are not limited to such examples. The collection unit infers the health condition and allergy information of the customer based on the health check results. For example, the collection unit can infer allergy information for a specific food ingredient based on the blood test results of the customer. The collection unit can also infer preference information based on the body measurement data of the customer. This makes it possible to obtain more accurate information by inferring information based on the health check results. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input health check result data to AI and have AI execute analysis of the information.

[0089] The processing unit can prepare customer orders in advance using a predictive model. Predictive models include, but are not limited to, for example, regression models and time series predictive models. The predictive model predicts future orders based on the customer's past order history and trends. For example, the processing unit can receive the customer's past order history as input and predict future orders using the predictive model. In this way, the customer's orders can be processed quickly by using the predictive model. Some or all of the above-mentioned processing in the processing unit may be performed using, for example, AI, or may be performed without using AI. For example, the processing unit can input order history data to AI and cause the AI ​​to execute order prediction.

[0090] The collection unit can analyze the customer's emotions and adjust the timing of collecting information on food allergies and preferences based on the analyzed customer's emotions. The collection unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. Emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The collection unit adjusts the timing of collecting information on food allergies and preferences based on the estimated customer's emotions. For example, if the customer is relaxed, the food allergy and preference information can be collected before a meal. Also, if the customer is stressed, the information can be collected after a meal. In this way, by adjusting the timing of collecting information based on the customer's emotions, the information can be collected at a more appropriate timing. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0091] The collection unit can analyze the customer's past meal history and select an appropriate collection method. Meal history includes, for example, a meal diary and a restaurant order history, but is not limited to such examples. The collection unit analyzes the menus that the customer frequently ordered and the menus that the customer avoided based on the past meal history and selects an appropriate collection method. For example, the collection unit can collect information on food allergies and preferences based on the menus that the customer frequently ordered in the past. The collection unit can also collect information on food allergies based on the menus that the customer avoided in the past. In this way, by analyzing the past meal history, information can be collected in a more appropriate manner. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input meal history data into AI and have AI execute analysis of the information.

[0092] The collection unit can filter the information on food allergies and preferences based on the customer's current health condition and lifestyle habits when collecting the information on food allergies and preferences. The collection unit can filter the information on food allergies and preferences based on, for example, the results of a health check and information on lifestyle habits of the customer. The health condition and lifestyle habits include, for example, the amount of exercise, sleep patterns, and dietary content, but are not limited to such examples. The collection unit filters the information on food allergies and preferences based on the results of a health check. For example, if a customer is on a specific diet, the information on food allergies and preferences can be filtered based on that information. In addition, if a customer has a specific exercise habit, the information on food allergies and preferences can also be filtered based on that information. In this way, more accurate information can be obtained by filtering information based on the health condition and lifestyle habits. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input health check result data to AI and have the AI ​​execute filtering of information.

[0093] The collection unit can analyze the customer's emotions and determine the priority of information to be collected based on the analyzed customer's emotions. The collection unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. Emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The collection unit determines the priority of information to be collected based on the estimated customer's emotions. For example, when the customer is relaxed, detailed food allergy and preference information can be preferentially collected. Also, when the customer is stressed, basic food allergy information can be preferentially collected. In this way, by determining the priority of information based on the customer's emotions, more important information can be preferentially collected. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0094] When collecting information on food allergies and preferences, the collection unit can preferentially collect information that is highly relevant to the customer, taking into account the customer's geographical location information. The collection unit can obtain the customer's geographical location information, for example, by using the customer's GPS information or Wi-Fi location information. Based on the location information, the collection unit preferentially collects information that is highly relevant to the customer. For example, if the customer is in a specific area, allergy information on ingredients in that area can be preferentially collected. Also, if the customer is traveling, allergy information on ingredients at the travel destination can be preferentially collected. In this way, more relevant information can be collected by taking the geographical location information into consideration. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input location information to AI and cause AI to select highly relevant information.

[0095] The collection unit can analyze the social media activity of the customer when collecting the information on food allergies and preferences, and collect related information. The collection unit can, for example, analyze the social media activity of the customer and collect the information on food allergies and preferences based on the information. Social media activity includes, for example, the content of posts, the number of likes, comments, and the like, but is not limited to such examples. The collection unit analyzes photos of meals shared by the customer on social media to collect the information on food allergies and preferences. For example, the allergy information can be collected based on ingredients mentioned by the customer on social media. In addition, the food-related accounts that the customer follows on social media can be analyzed to collect the information on preferences. In this way, more information can be collected by analyzing the social media activity. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input social media data into AI and have the AI ​​perform analysis of the information.

[0096] The suggestion unit can analyze the customer's emotions and adjust the way of expressing the menu proposal based on the analyzed customer's emotions. The suggestion unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. The emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The suggestion unit adjusts the way of expressing the menu proposal based on the estimated customer's emotions. For example, if the customer is relaxed, a menu proposal including detailed explanations can be made. Also, if the customer is stressed, a menu proposal that is simple and to the point can be made. This allows for more appropriate suggestions by adjusting the way of expressing the menu proposal based on the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit is performed using the generation AI.

[0097] When proposing a menu, the suggestion unit can adjust the level of detail of the suggestion based on the customer's meal history. The meal history includes, but is not limited to, for example, a restaurant order history and a meal diary. The suggestion unit can make a detailed suggestion based on a menu previously ordered by the customer. In addition, when the customer visits for the first time, a basic suggestion can be made. This allows a more appropriate suggestion to be made by adjusting the level of detail of the suggestion based on the meal history. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input meal history data into AI and cause the AI ​​to adjust the level of detail of the suggestion.

[0098] When proposing a menu, the suggestion unit can apply different suggestion algorithms depending on the food category of the customer. The suggestion algorithms include, but are not limited to, collaborative filtering and content-based filtering. If the customer is a vegetarian, the suggestion unit can apply a suggestion algorithm specialized for vegetarian menus. If the customer prefers gluten-free food, the suggestion unit can apply a suggestion algorithm specialized for gluten-free menus. This enables optimal suggestions according to food categories. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input food category data to AI and cause AI to apply the suggestion algorithm.

[0099] The suggestion unit can analyze the customer's emotions and adjust the length of the menu proposal based on the analyzed customer's emotions. The suggestion unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. The emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The suggestion unit adjusts the length of the menu proposal based on the estimated customer's emotions. For example, if the customer is relaxed, a detailed menu proposal can be made. Also, if the customer is stressed, a short and to the point menu proposal can be made. This allows for more appropriate proposals by adjusting the length of the menu proposal based on the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit is performed using the generation AI.

[0100] When proposing a menu, the suggestion unit can determine the priority of the suggestions based on the time of meal submission of the customer. The priority of the suggestions includes, for example, importance score and urgency, but is not limited to such examples. When the customer orders breakfast, the suggestion unit can preferentially suggest a breakfast menu. Also, when the customer orders at lunchtime, the suggestion unit can preferentially suggest a lunch menu. This allows more appropriate suggestions to be made by determining the priority of the suggestions based on the time of meal submission. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input meal submission time data to AI and cause AI to execute the determination of the priority of the suggestions.

[0101] The suggestion unit can adjust the order of suggestions based on the relevance of the customer's meals when suggesting a menu. The suggestion unit can, for example, analyze the customer's past order history and meal relevance, and adjust the order of suggestions based on the information. The order of suggestions includes, for example, relevance scores and chronological order, but is not limited to such examples. The suggestion unit can preferentially suggest new menus related to menus that the customer has ordered in the past. In addition, if the customer likes a specific ingredient, it can preferentially suggest menus that include the ingredient. This allows more appropriate suggestions to be made by adjusting the order of suggestions based on the relevance of meals. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input order history data to AI and cause AI to adjust the order of suggestions.

[0102] The acquisition unit can analyze the customer's emotions and adjust the timing of acquiring the order history and trends based on the analyzed customer's emotions. The acquisition unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. The emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The acquisition unit adjusts the timing of acquiring the order history and trends based on the estimated customer's emotions. For example, if the customer is relaxed, the order history and trends can be acquired after the meal. Also, if the customer is stressed, information can be acquired before the meal. In this way, by adjusting the acquisition timing based on the customer's emotions, information can be acquired at a more appropriate timing. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0103] The acquisition unit can analyze the customer's past order history and select an appropriate acquisition method. The acquisition method includes, but is not limited to, for example, an API call or a database query. The acquisition unit analyzes the menu items frequently ordered and avoided by the customer based on the past order history and selects an appropriate acquisition method. For example, the acquisition unit can acquire the order history based on the menu items frequently ordered by the customer in the past. The acquisition unit can also acquire the order history based on the menu items avoided by the customer in the past. This allows information to be acquired in a more appropriate manner by analyzing the past order history. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input the order history data into an AI and have the AI ​​execute the analysis of the information.

[0104] The acquisition unit can filter the order history and trends based on the customer's current living situation and areas of interest when acquiring the order history and trends. The acquisition unit can filter the order history and trends based on, for example, the customer's health check results and information on lifestyle habits. Filtering includes, for example, keyword filtering and attribute filtering, but is not limited to such examples. The acquisition unit filters the order history and trends based on the customer's health check results. For example, if the customer is on a specific diet, the order history and trends can be filtered based on that information. In addition, if the customer has a specific exercise habit, the order history and trends can also be filtered based on that information. This makes it possible to obtain more accurate information by filtering information based on the living situation and areas of interest. Part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input health check result data to AI and have AI execute filtering of information.

[0105] The acquisition unit can analyze the customer's emotions and determine the priority of order histories and trends to be acquired based on the analyzed customer's emotions. The acquisition unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. Emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The acquisition unit determines the priority of order histories and trends to be acquired based on the estimated customer's emotions. For example, when the customer is relaxed, detailed order histories and trends can be preferentially acquired. Also, when the customer is stressed, basic order history information can be preferentially acquired. In this way, by determining the priority of information based on the customer's emotions, more important information can be preferentially acquired. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the acquisition unit can input facial expression data to the generation AI and cause the generation AI to estimate emotions.

[0106] When acquiring order history and trends, the acquisition unit can preferentially acquire history with high relevance in consideration of geographical location information of the customer. The acquisition unit can acquire geographical location information of the customer, for example, by using GPS information or Wi-Fi location information of the customer. Based on the location information, the acquisition unit preferentially acquires history with high relevance to the customer. For example, when the customer is in a specific area, the order history and trends of that area can be preferentially acquired. In addition, when the customer is traveling, the order history and trends of the travel destination can also be preferentially acquired. In this way, by considering the geographical location information, more relevant information can be acquired. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input location information to AI and cause AI to select history with high relevance.

[0107] The acquisition unit can analyze the social media activities of the customer when acquiring the order history and trends, and acquire related history. The acquisition unit can, for example, analyze the social media activities of the customer and acquire the order history and trends based on the information. The social media activities include, for example, the content of the post, the number of likes, comments, etc., but are not limited to such examples. The acquisition unit analyzes the photos of the meal shared by the customer on social media to acquire the order history and trends. For example, the order history can be acquired based on the ingredients mentioned by the customer on social media. In addition, food-related accounts that the customer follows on social media can be analyzed to acquire trends. In this way, more information can be acquired by analyzing the social media activities. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input social media data into AI and have the AI ​​execute analysis of the information.

[0108] The introduction unit can analyze the customer's emotions and adjust the method of introducing new menus and promotions based on the analyzed customer's emotions. The introduction unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. Emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The introduction unit adjusts the method of introducing new menus and promotions based on the estimated customer's emotions. For example, if the customer is relaxed, the new menus and promotions can be introduced with detailed explanations. Also, if the customer is stressed, the new menus and promotions can be introduced with simple, to the point items. This allows for more appropriate introduction by adjusting the introduction method based on the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the introduction unit is performed using the generation AI.

[0109] The introduction unit can select an appropriate introduction method when introducing a new menu or promotion by analyzing the customer's past order history. The introduction unit can, for example, analyze the customer's past order history and select a method for introducing the new menu or promotion based on the information. The introduction method includes, for example, email, push notification, in-app notification, etc., but is not limited to such examples. The introduction unit can preferentially introduce new menus related to menus ordered by the customer in the past. In addition, if the customer likes a specific ingredient, the introduction unit can preferentially introduce new menus containing that ingredient. In this way, by analyzing the past order history, the new menus and promotions can be introduced in a more appropriate manner. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input order history data into AI and cause the AI ​​to select the introduction method.

[0110] The introduction unit can customize the means of introduction based on the customer's current living situation when introducing a new menu or promotion. The introduction unit can customize the means of introduction of the new menu or promotion based on, for example, the customer's health check result or information on the lifestyle habits. The introduction means include, for example, text, image, and sound, but are not limited to such examples. When the customer provides the health check result, the introduction unit can customize and introduce the new menu or promotion based on the information. Also, when the customer is on a specific diet, the introduction unit can customize and introduce the new menu or promotion based on the information. This allows more appropriate introduction by customizing the means of introduction based on the living situation. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input the health check result data into AI and have the AI ​​execute customization of the introduction means.

[0111] The introduction unit can analyze the customer's emotions and determine the priority of new menus and promotions based on the analyzed customer's emotions. The introduction unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. Emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The introduction unit determines the priority of new menus and promotions based on the estimated customer's emotions. For example, when the customer is relaxed, detailed new menus and promotions can be preferentially introduced. Also, when the customer is stressed, basic new menus and promotions can be preferentially introduced. In this way, by determining the priority based on the customer's emotions, more important information can be preferentially introduced. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the introduction unit is performed using the generation AI.

[0112] The introduction unit can select an appropriate introduction method in consideration of the geographical location information of the customer when introducing a new menu or promotion. The introduction unit can acquire the geographical location information of the customer, for example, by using the customer's GPS information or Wi-Fi location information. Based on the location information, the introduction unit selects an appropriate introduction method for the customer. For example, when the customer is in a specific area, new menus and promotions using ingredients from that area can be preferentially introduced. In addition, when the customer is traveling, new menus and promotions using ingredients from the travel destination can be preferentially introduced. In this way, by taking the geographical location information into consideration, new menus and promotions can be introduced in a more appropriate manner. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input the location information into AI and cause the AI ​​to select the introduction method.

[0113] The introduction unit can analyze the social media activity of the customer and propose a means of introduction when introducing a new menu or promotion. The introduction unit can, for example, analyze the social media activity of the customer and propose a means of introducing the new menu or promotion based on the information. Social media activity includes, for example, the content of the post, the number of likes, comments, etc., but is not limited to such examples. The introduction unit analyzes photos of meals shared by the customer on social media and proposes new menus and promotions. For example, the introduction unit can propose new menus and promotions based on ingredients mentioned by the customer on social media. In addition, the introduction unit can analyze food-related accounts that the customer follows on social media and propose new menus and promotions. In this way, by analyzing social media activity, it is possible to propose new menus and promotions based on more information. Part or all of the above-mentioned processing in the introduction unit may be performed, for example, using AI, or may be performed without using AI. For example, the introduction unit can input social media data into AI and have the AI ​​perform analysis of the information.

[0114] The processing unit can analyze the customer's emotions and adjust the order and payment processing method based on the analyzed customer's emotions. The processing unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. Emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The processing unit adjusts the order and payment processing method based on the estimated customer's emotions. For example, if the customer is relaxed, the order and payment processing can be performed with detailed explanations. Also, if the customer is stressed, the order and payment processing can be performed simply and quickly. This allows for more appropriate processing by adjusting the processing method based on the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the processing unit is performed using the generation AI.

[0115] The processing unit can select an optimal processing method by analyzing the customer's past payment history at the time of order and payment processing. Processing methods include, but are not limited to, payment methods and security measures, for example. The processing unit can perform optimal payment processing based on payment methods used by the customer in the past. Also, the processing unit can perform optimal payment processing based on payment methods avoided by the customer in the past. In this way, by analyzing the past payment history, payment processing can be performed in a more appropriate manner. A part or all of the above-mentioned processing in the processing unit may be performed using, for example, AI, or may be performed without using AI. For example, the processing unit can input payment history data into AI and have AI analyze the information.

[0116] The processing unit can customize the processing means based on the customer's current living situation at the time of order and payment processing. The processing unit can customize the processing means for order and payment based on, for example, the customer's medical checkup results and information on living habits. The processing means include, for example, but are not limited to, payment methods and security measures. When the customer provides a medical checkup result, the processing unit can customize the order and payment processing based on the information. Also, when the customer is on a specific diet, the processing unit can customize the order and payment processing based on the information. This enables more appropriate processing by customizing the processing means based on the living situation. Part or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can input medical checkup result data to AI and have AI execute customization of the processing means.

[0117] The processing unit can estimate the customer's emotions and determine the priority of orders and payments based on the estimated customer's emotions. The processing unit can, for example, analyze the customer's facial expressions and voice data and estimate the customer's emotions using an emotion analysis algorithm. Emotion analysis includes, for example, facial expression recognition, voice analysis, text analysis, and the like, but is not limited to such examples. The processing unit determines the priority of orders and payments based on the estimated customer's emotions. For example, if the customer is relaxed, detailed order and payment processing can be prioritized. Also, if the customer is stressed, basic order and payment processing can be prioritized. In this way, by determining the priority based on the customer's emotions, more important processing can be prioritized. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the processing unit is performed using the generation AI.

[0118] The processing unit can select the optimal processing method in consideration of the geographical location information of the customer when processing the order and payment. The processing unit can acquire the geographical location information of the customer, for example, by using the customer's GPS information or Wi-Fi location information. Based on the location information, the processing unit selects the optimal processing method for the customer. For example, if the customer is in a specific area, the processing unit can preferentially suggest a payment method for that area. Also, if the customer is traveling, the processing unit can preferentially suggest a payment method for the travel destination. In this way, by taking the geographical location information into consideration, the payment processing can be performed in a more appropriate manner. Part or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can input the location information into AI and have the AI ​​select the processing method.

[0119] The processing unit can analyze the social media activity of the customer and suggest a processing method at the time of order and payment processing. The processing unit can, for example, analyze the social media activity of the customer and suggest the optimal payment processing based on the information. Social media activity includes, for example, the content of posts, the number of likes, comments, etc., but is not limited to such examples. The processing unit analyzes the payment method shared by the customer on social media and suggests the optimal payment processing. For example, the processing unit can suggest the optimal payment processing based on the payment method mentioned by the customer on social media. In addition, the processing unit can analyze the payment-related accounts that the customer follows on social media and suggest the optimal payment processing. In this way, by analyzing the social media activity, the optimal payment processing can be suggested based on more information. Part or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can input social media data into AI and have the AI ​​perform analysis of the information.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The order support AI assistant system can further include a nutritional evaluation unit that evaluates the nutritional balance of a customer's meal. The nutritional evaluation unit evaluates the nutritional balance based on the customer's meal history and health check results, and provides the information to the proposal unit. For example, if a customer has not eaten many vegetables in the past, the nutritional evaluation unit can provide that information to the proposal unit, and the proposal unit can suggest a menu that contains a lot of vegetables. In addition, if a customer has been consuming excessive amounts of a particular nutrient, a balanced menu can be suggested based on that information. This makes it possible to suggest menus that take the customer's health into consideration.

[0122] The order support AI assistant system can further include a satisfaction evaluation unit that evaluates the customer's satisfaction with the meal. The satisfaction evaluation unit analyzes the customer's past feedback and reviews and provides the information to the suggestion unit. For example, it can suggest similar menu items based on menu items that the customer has given high ratings in the past. It can also suggest that the customer avoid menu items that the customer has given low ratings. This makes it possible to suggest menu items that will improve customer satisfaction.

[0123] The order support AI assistant system can further include an environmental evaluation unit that evaluates the environmental impact of the customer's meal. The environmental evaluation unit evaluates the production process and transportation distance of the ingredients of the menu to be proposed, and provides environmentally friendly menus to the proposal unit. For example, it can preferentially propose menus that use locally produced ingredients. In addition, it is also possible to reduce the environmental impact by proposing menus that use seasonal ingredients. This makes it possible to propose environmentally friendly menus.

[0124] The order support AI assistant system can further include a cultural evaluation unit that considers the cultural background of the customer's meal. The cultural evaluation unit considers the customer's cultural background and religious restrictions and provides the information to the suggestion unit. For example, it can suggest menus that take into account dietary restrictions based on a particular religion. It can also improve cultural satisfaction by suggesting traditional dishes from the customer's hometown. This makes it possible to suggest menus that take into account the customer's cultural background.

[0125] The order support AI assistant system can further include an economic evaluation unit that considers the economic background of the customer's meal. The economic evaluation unit analyzes the customer's budget and spending history and provides the information to the suggestion unit. For example, it can suggest the optimal menu within the customer's budget. It can also reduce the financial burden by suggesting a menu that takes into account certain promotions and discounts. This makes it possible to suggest menus that take into account the customer's economic background.

[0126] The suggestion unit can analyze the customer's emotions and adjust the timing of menu suggestions based on the analyzed customer's emotions. For example, if the customer is relaxed, a menu can be suggested before the meal. Also, if the customer is stressed, a menu can be suggested after the meal. This makes it possible to suggest menus at appropriate times based on the customer's emotions.

[0127] The suggestion unit can analyze the customer's emotions and adjust the contents of the menu suggestion based on the analyzed customer's emotions. For example, if the customer is relaxed, a menu suggestion including detailed explanations can be made. On the other hand, if the customer is stressed, a menu suggestion that is simple and to the point can be made. In this way, by adjusting the contents of the menu suggestion based on the customer's emotions, more appropriate suggestions can be made.

[0128] The suggestion unit can analyze the customer's emotions and adjust the format of the menu suggestions based on the analyzed customer's emotions. For example, if the customer is relaxed, a menu suggestion that makes extensive use of visuals can be made. On the other hand, if the customer is stressed, a simple menu suggestion that is mainly text can be made. In this way, by adjusting the format of the menu suggestion based on the customer's emotions, more appropriate suggestions can be made.

[0129] The suggestion unit can analyze the customer's emotions and adjust the frequency of menu suggestions based on the analyzed customer's emotions. For example, if the customer is relaxed, menu suggestions can be made more frequently. Also, if the customer is stressed, the frequency of suggestions can be reduced. In this way, by adjusting the frequency of menu suggestions based on the customer's emotions, more appropriate suggestions can be made.

[0130] The suggestion unit can analyze the customer's emotions and adjust the tone of the menu suggestions based on the analyzed customer's emotions. For example, if the customer is relaxed, the menu can be suggested in a friendly and casual tone. On the other hand, if the customer is stressed, the menu can be suggested in a formal and calm tone. In this way, by adjusting the tone of the menu suggestions based on the customer's emotions, more appropriate suggestions can be made.

[0131] The process flow of the second embodiment will be briefly described below.

[0132] Step 1: The collection department collects information on the customer's food allergies and preferences. The customer's food allergy and preference information includes specific ingredients, cooking methods, taste preferences, etc. The collection department collects information through the customer's smartphone application and SNS account. Step 2: The suggestion unit proposes a menu based on the information collected by the collection unit. Using a generation AI (e.g., a text generation AI or an AI chatbot), the unit proposes the optimal menu based on the customer's food allergies and preferences. It is also possible to estimate the customer's current health and psychological state and propose a menu based on that. Step 3: The acquisition unit acquires past order history and trends. The acquisition unit acquires the customer's past order history and trends using database access or API calls. Step 4: The introduction unit introduces new menus and promotions to the customer based on the information acquired by the acquisition unit. The introduction unit introduces the new menus and promotions to the customer using a notification method and a display format. Step 5: The processor processes customer orders and payments. The processor processes payments using blockchain technology (e.g., Ethereum or Hyperledger). It can also prepare customer orders in advance using predictive models (e.g., regression models or time series forecasting models).

[0133] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0135] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0136] For example, the collection unit is realized 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 suggestion unit is realized 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 acquisition unit is realized 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 introduction unit is realized 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 processing unit is realized 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 above-mentioned example, and various changes are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0144] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0147] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0149] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0152] For example, the collection unit is realized 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 suggestion unit is realized 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 acquisition unit is realized 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 introduction unit is realized 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 processing unit is realized 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 above-mentioned example, and various changes are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0155] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0160] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0163] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0168] For example, the collection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the suggestion unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the introduction unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the processing unit is realized by the control unit 46A of the headset type 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 above-mentioned example, and various changes are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0177] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0180] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] For example, the collection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the suggestion unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the introduction unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the processing unit is realized 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 above-mentioned example, and various changes are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0187] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0189] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0190] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0191] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0194] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0195] In addition, 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 upon request from the data processing device 12.

[0196] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0197] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0198] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0199] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0200] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0202] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0204] (Appendix 1) a collection department that collects customer food allergy and preference information; a suggestion unit that suggests a menu to the customer based on the information collected by the collection unit; An acquisition unit for acquiring past order history and trends; an introduction unit that introduces new menus and promotions to the customers based on the information acquired by the acquisition unit; a processing unit for processing orders and payments for said customers; A system characterized by: (Appendix 2) The collecting unit includes: Collecting food allergies and preferences through a customer's smartphone application 2. The system of claim 1, (Appendix 3) The suggestion unit, Using generative AI to suggest appropriate menu items 2. The system of claim 1, (Appendix 4) An estimation unit that estimates a health condition and a psychological state of a customer, The suggestion unit, A menu is proposed based on the health condition and psychological state of the customer estimated by the estimation unit. 2. The system of claim 1, (Appendix 5) The processing unit includes: Uses blockchain technology to process payments 2. The system of claim 1, (Appendix 6) The introduction unit is Recommend new menu items based on customer location 2. The system of claim 1, (Appendix 7) The collecting unit includes: Collect food allergies and preferences from customers' social media accounts 2. The system of claim 1, (Appendix 8) The suggestion unit, Using AI chatbots to suggest menu options while interacting with customers 2. The system of claim 1, (Appendix 9) The collecting unit includes: Inferring food allergies and preferences based on a customer's purchasing history 2. The system of claim 1, (Appendix 10) The collecting unit includes: Inferring food allergies and preferences based on a customer's past medical examination results 2. The system of claim 1, (Appendix 11) The processing unit includes: Use predictive models to prepare customer orders in advance 2. The system of claim 1, (Appendix 12) The collecting unit includes: Analyzing customer sentiment and adjusting the timing of collection of food allergy and preference information based on the analyzed customer sentiment 2. The system of claim 1, (Appendix 13) The collecting unit includes: Analyze the customer's past dietary history and select the appropriate collection method 2. The system of claim 1, (Appendix 14) The collecting unit includes: Filtering food allergy and preference information based on a customer's current health and lifestyle habits 2. The system of claim 1, (Appendix 15) The collecting unit includes: Analyze customer sentiment and prioritize the information to be collected based on the analyzed customer sentiment 2. The system of claim 1, (Appendix 16) The collecting unit includes: When collecting food allergies and preferences, take into account a customer's geographic location to prioritize collecting the most relevant information 2. The system of claim 1, (Appendix 17) The collecting unit includes: Analyzing customers' social media activity to gather relevant information when collecting food allergies and preferences 2. The system of claim 1, (Appendix 18) The suggestion unit, Analyze customer sentiment and adjust the presentation of menu suggestions based on the analyzed customer sentiment 2. The system of claim 1, (Appendix 19) The suggestion unit, When making menu suggestions, adjust the level of detail of the suggestions based on the customer's dining history 2. The system of claim 1, (Appendix 20) The suggestion unit, When making menu suggestions, apply different suggestion algorithms depending on the customer's food category 2. The system of claim 1, (Appendix 21) The suggestion unit, Analyze customer sentiment and adjust the length of menu suggestions based on the analyzed customer sentiment 2. The system of claim 1, (Appendix 22) The suggestion unit, When making menu suggestions, prioritize suggestions based on when a customer submitted their meal 2. The system of claim 1, (Appendix 23) The suggestion unit, When making menu suggestions, adjust the order of suggestions based on the customer's dietary relevance 2. The system of claim 1, (Appendix 24) The acquisition unit is Analyze customer sentiment and adjust the timing of retrieval of order history and trends based on the analyzed customer sentiment 2. The system of claim 1, (Appendix 25) The acquisition unit is Analyze the customer's past order history and choose the appropriate acquisition method 2. The system of claim 1, (Appendix 26) The acquisition unit is Filter order history and trends based on the customer's current life situation and interests 2. The system of claim 1, (Appendix 27) The acquisition unit is Analyze customer sentiment and prioritize order histories and trends to be retrieved based on the analyzed customer sentiment 2. The system of claim 1, (Appendix 28) The acquisition unit is When retrieving order history and trends, take into account the customer's geographic location to prioritize the most relevant history 2. The system of claim 1, (Appendix 29) The acquisition unit is Analyze customer social media activity and capture relevant history when capturing order history and trends 2. The system of claim 1, (Appendix 30) The introduction unit is Analyze customer sentiment and adjust how new menu items and promotions are presented based on that sentiment 2. The system of claim 1, (Appendix 31) The introduction unit is When introducing new menu items or promotions, analyze customers' past order history to choose the appropriate method of introduction 2. The system of claim 1, (Appendix 32) The introduction unit is When introducing new menu items or promotions, customize the introduction based on the customer's current life situation 2. The system of claim 1, (Appendix 33) The introduction unit is Analyze customer sentiment and prioritize new menu items and promotions based on the analyzed customer sentiment 2. The system of claim 1, (Appendix 34) The introduction unit is When introducing new menu items or promotions, choose the appropriate method to introduce them by taking into account the customer's geographic location 2. The system of claim 1, (Appendix 35) The introduction unit is When introducing new menu items or promotions, analyze customers' social media activity to suggest ways to introduce them 2. The system of claim 1, (Appendix 36) The processing unit includes: Analyze customer sentiment and adjust order and payment processing methods based on the analyzed customer sentiment 2. The system of claim 1, (Appendix 37) The processing unit includes: During order and payment processing, analyze a customer's past payment history to determine the most appropriate processing method 2. The system of claim 1, (Appendix 38) The processing unit includes: Customize order and payment experiences based on the customer's current life situation 2. The system of claim 1, (Appendix 39) The processing unit includes: Estimate customer sentiment and prioritize orders and payments based on estimated customer sentiment 2. The system of claim 1, (Appendix 40) The processing unit includes: When processing orders and payments, consider the customer's geographic location to determine the best method of processing 2. The system of claim 1, (Appendix 41) The processing unit includes: Analysing your social media activity to suggest processing options when processing orders and payments 2. The system of claim 1, [Explanation of symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection department that collects customer food allergy and preference information; a suggestion unit that suggests a menu to the customer based on the information collected by the collection unit; An acquisition unit for acquiring past order history and trends; an introduction unit that introduces new menus and promotions to the customers based on the information acquired by the acquisition unit; a processing unit for processing orders and payments for said customers; A system characterized by:

2. The collecting unit includes: Collecting food allergies and preferences through a customer's smartphone application 2. The system of claim 1 .

3. The suggestion unit, Using generative AI to suggest appropriate menus 2. The system of claim 1 .

4. An estimation unit that estimates a health condition and a psychological state of the customer, The suggestion unit, A menu is proposed based on the health condition and psychological state of the customer estimated by the estimation unit.

2. The system of claim 1 .

5. The processing unit includes: Uses blockchain technology to process payments 2. The system of claim 1 .

6. The introduction unit is Recommend new menu items based on the customer's location information 2. The system of claim 1 .

7. The collecting unit includes: Collecting information about food allergies and preferences from said customers' social media accounts 2. The system of claim 1 .

8. The suggestion unit, Using an AI chatbot to talk to the customer and suggest menu options 2. The system of claim 1 .

9. The collecting unit includes: Inferring food allergy and preference information based on the customer's purchasing history 2. The system of claim 1 .

10. The collecting unit includes: Inferring food allergy and preference information based on the customer's past medical examination results 2. The system of claim 1 .

Images