system

Abstract

We provide the system. [Solution] A means for recording customer attribute information, A means for saving the customer's order details, A means of generating recommended menus based on the season and events, A means of setting the system to revisit the table after a certain amount of time has passed since the end of the meal, A means for displaying and providing voice guidance on recommended menus during the aforementioned return visit, A means of receiving customer feedback and processing additional orders, A system that includes this.

Description

Technical Field

[0004] , , , , , ,

[0005] , , , , ,

[0003] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the current food service industry, labor shortages have become a serious problem, and it is difficult for staff to actively encourage additional orders. Proposing additional orders by human staff involves a psychological burden, and as a result, opportunities to increase sales are often missed. Furthermore, in order to propose an optimal menu according to a specific time or customer attributes, the staff themselves have to process a lot of information, which is inefficient. To solve such problems, there is a need for a food delivery robot that boldly proposes additional orders repeatedly and automatically proposes an optimal menu.

Means for Solving the Problems

[0005] This invention provides a system for a serving robot that includes means for recording customer attribute information, means for saving order details, means for generating recommended menus based on seasons and events, means for setting the robot to revisit the table after a certain period of time has elapsed since the end of the meal, means for displaying and providing voice guidance for recommended menus upon revisiting, and means for providing feedback on customer reactions and processing additional orders. In particular, a machine learning model is used when generating recommended menus to provide the most suitable suggestions for the customer. Furthermore, when an additional order is placed, the system notifies the kitchen of the order details and processes it quickly, thereby improving customer satisfaction and increasing store sales.

[0006] "Customer attribute information" refers to personal data about customers, such as age group, gender, and allergy information.

[0007] "Order details" refers to the detailed information of the menu items that the customer actually ordered.

[0008] "Seasons and events" are concepts that refer to specific periods of time (for example, summer or winter) or special occasions (for example, Christmas or New Year's).

[0009] A "recommended menu" is a list of menu items that have been deemed appropriate for a particular customer.

[0010] A "machine learning model" is an algorithm or system that learns patterns and rules based on data and performs inferences on new data.

[0011] "Revisiting" refers to the act of a serving robot returning to a table it has already visited.

[0012] "Display and voice guidance" refers to displaying information on a screen and providing voice guidance through a speaker.

[0013] "Feedback" is the process of obtaining information about customer reactions and behaviors and returning that information to the system.

[0014] An "additional order" refers to a new order placed following the initial order.

[0015] A "kitchen notification" is a process of communicating the order details from the customer to the cooking department.

[0016] A "meal delivery robot" is an automated device or machine used to transport food and beverages to the table.

Brief Explanation of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] [[ID=??]]It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention relates to a system for a food service robot that records customer attribute information, saves order details, generates recommended menus based on the season and events, and proposes them to customers on their return visits. The following describes a specific method for implementing this invention.

[0039] Server Processing

[0040] The server has the function of recording information entered by customers when they place their first order (such as age group, gender, and allergy information). For example, information entered via an application or tablet is stored in the database by the server. Similarly, each time a customer places an order, the details of that order (menu items, quantity, etc.) are also saved.

[0041] The server generates optimal recommended menus for customers based on the season and events. For example, in the summer it suggests cold desserts and drinks, and during the Christmas season it suggests a special Christmas menu. A machine learning model is used to generate these recommended menus. Based on past data, it automatically selects the most suitable menu items and generates a customized list for each customer.

[0042] Terminal processing

[0043] The serving robot's terminal receives customer information and recommended menu items transmitted from the server. After a certain period of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice prompts such as, "Would you like dessert?" The terminal also features a touch panel, allowing customers to enter additional orders.

[0044] User processing

[0045] The customer (user) decides whether to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they want to reject the suggestion, they can either leave it blank or press the cancel button.

[0046] Processing additional orders

[0047] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen's display. This allows cooking to begin quickly and accurately.

[0048] As described above, the system of the present invention can record customer attribute information, generate optimal recommended menus, and propose them during follow-up visits, thereby alleviating labor shortages and improving customer satisfaction and sales.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The server records attribute information (age group, gender, allergy information, etc.) entered by the customer when they place their first order.

[0052] The server receives data sent from tablets and applications.

[0053] The server stores this data in a database and associates it with the customer ID.

[0054] Step 2:

[0055] The server saves the details of an order (menu items, quantity, etc.) each time a customer places an order.

[0056] The server records the order details in a database in JSON format.

[0057] The server tracks order history for each customer ID.

[0058] Step 3:

[0059] The server generates recommended menus based on the season, events, and past order history.

[0060] The server uses a machine learning model to execute an algorithm that selects the appropriate recommended menu.

[0061] The server creates a list of recommended menu items and saves it, associating it with the customer ID.

[0062] Step 4:

[0063] The server instructs the serving robot to revisit the table a certain amount of time after the meal has finished.

[0064] The server uses a reminder function to set a time for a return visit.

[0065] Once the timer settings are complete, the server sends that information to the robot's terminal.

[0066] Step 5:

[0067] The terminal receives a list of recommended menu items and information on when to revisit from the server.

[0068] The device prepares its display and speaker and enters a standby state for the next operation.

[0069] Step 6:

[0070] The terminal revisits the table after a set time has elapsed and displays and provides voice guidance to the customer regarding recommended menu items.

[0071] The device displays a recommended menu on its screen.

[0072] The terminal plays voice prompts such as, "Would you like dessert?"

[0073] Step 7:

[0074] The user responds to the robot's suggested menu.

[0075] Users can use the touch panel to select additional orders from the recommended menu or cancel the suggestions.

[0076] Step 8:

[0077] When the terminal receives an additional order from a user, it sends that information to the server.

[0078] The terminal sends the user's selection to the server in JSON format.

[0079] Step 9:

[0080] The server saves the received additional order to the database and notifies the kitchen.

[0081] The server creates a notification to communicate the order details to the cooking department and displays it on the kitchen display.

[0082] The above describes the specific processing of the program in this invention. This makes it possible to alleviate labor shortages while improving customer satisfaction and sales.

[0083] (Example 1)

[0084] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] Traditional food service systems have difficulty effectively utilizing customer attribute information and order history, limiting improvements in customer satisfaction and sales growth. Specifically, there were problems such as difficulty in providing seasonal or event-specific recommended menus and in suggesting timely additional orders. Furthermore, communication of additional orders could be time-consuming, resulting in a decline in service quality.

[0086] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0087] In this invention, the server includes means for recording customer attribute information, means for storing the customer's order details, and means for generating recommended menus based on seasons and events. This enables the suggestion of the most suitable menu for each customer, improving customer satisfaction and increasing sales.

[0088] Furthermore, the system includes means for receiving customer information and recommended menu items transmitted from the server, and means for storing received additional orders in a database and notifying the kitchen. This enables efficient service delivery and ensures that additional orders are processed quickly and accurately.

[0089] "Customer attribute information" refers to data that shows personal characteristics of customers, such as their age group, gender, and allergy information.

[0090] "Order details" refers to information indicating the menu items and quantities ordered by the customer.

[0091] "Recommended menu" refers to menu suggestions that are best suited to the customer, generated using machine learning models based on the season and events.

[0092] "Revisit" means that the serving robot will come back to the table a certain amount of time after the meal has finished.

[0093] "Voice guidance" refers to the function of the serving robot that provides suggestions and guidance via voice.

[0094] "Feedback" refers to recording customer reactions and returning that information to the system.

[0095] An "additional order" refers to a new order placed during or after a meal.

[0096] A "database" refers to a system that systematically stores data such as customer information and order details.

[0097] A "machine learning model" refers to an algorithm composed of mathematical approaches used to make predictions and classifications based on large amounts of data.

[0098] "Notifying the kitchen" means promptly informing the cooking area of ​​any additional orders that have been placed.

[0099] This invention relates to a system for a food service robot that records customer attribute information, saves order details, generates recommended menus based on the season and events, and suggests them to customers on their return visits.

[0100] Server Processing

[0101] The server has the function of recording information entered by customers when they place their first order (such as age group, gender, and allergy information). For example, information entered via a tablet device or mobile application is sent to the server as an HTTP request and then stored in a database (such as MySQL® or PostgreSQL). Similarly, each time a customer places an order, its details (menu items, quantity, etc.) are also saved.

[0102] The server generates optimal recommended menus for customers based on the season and events. This uses machine learning models (for example, models using TENSORFLOW® or PyTorch). By analyzing past data and selecting the most suitable menu items, a customized list is generated for each customer. For example, for a customer with attributes such as being a woman in her 40s with no allergies, the server might suggest a cold mango pudding and iced tea during the summer.

[0103] Example of a prompt:

[0104] "Please suggest a recommended summer dessert and drink for a female customer in her 40s who has no allergies."

[0105] Terminal processing

[0106] The serving robot's terminal receives customer information and recommended menu items sent from the server. It receives data from the server via HTTP requests and stores it in the terminal's local memory. After a certain amount of time has passed since the meal was finished, the terminal is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" The terminal also has a touch panel, allowing customers to enter additional orders.

[0107] One specific example is a robot that returns to the table 10 minutes after the meal is finished and asks, "Would you like some mango pudding and iced tea?"

[0108] Example of a prompt:

[0109] "Ten minutes after the meal ends, please suggest recommended desserts and drinks to the guests at Table 5."

[0110] User processing

[0111] The customer (user) decides whether to accept the robot's suggestion. If they accept the suggestion, they type "I would like to order an additional dessert" on the touch panel; if they reject it, they press the cancel button. Specifically, the customer might type "I would like to order an additional mango pudding" on the touch panel, or they might press the cancel button to reject the suggestion.

[0112] Processing additional orders

[0113] When the terminal receives an additional order from a customer, it sends it to the server. The additional order data is sent to the server using an HTTP request, and the server stores the received additional order in its database. It then immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" appears on the kitchen display. This allows cooking to begin quickly and accurately.

[0114] A concrete example would be a notification sent to the kitchen stating, "Table 5 has placed a new order of mango pudding and iced tea."

[0115] Example of a prompt:

[0116] "Please notify the kitchen of Table 5, who has just ordered a new dessert."

[0117] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0118] Server Processing

[0119] Step 1: Record customer attribute information

[0120] The server receives customer attribute information (age group, gender, allergy information, etc.) sent from tablet devices and mobile applications. This information arrives as an HTTP request. The server parses this request and stores it in the database as JSON data.

[0121] input:

[0122] Customer attribute information (in JSON format) sent from a tablet device.

[0123] output:

[0124] Customer attribute information stored in the database

[0125] Specific actions:

[0126] The system receives JSON-formatted requests sent from tablet devices, parses them, and saves them to the "Customer Information" table in the database.

[0127] Step 2: Save your order

[0128] The server receives customer order details (menu items, quantities, etc.) sent from tablet devices or mobile applications. The order information is also received as an HTTP request and stored in the database.

[0129] input:

[0130] Order details (in JSON format) sent from a tablet device.

[0131] output:

[0132] Order details stored in the database

[0133] Specific actions:

[0134] "Receive an order for two cold drinks from Table 5 and save it to the 'Order History' table in the database."

[0135] Step 3: Generate Recommended Menus

[0136] The server generates optimal recommended menus for customers based on seasons and events. It uses machine learning models (for example, models using TensorFlow or PyTorch) to analyze past data and select the most suitable menu.

[0137] input:

[0138] Information about seasons and events, customer attribute information and order history

[0139] output:

[0140] List of recommended menus

[0141] Specific actions:

[0142] Since it's summer, we'll run a Python script to generate recommended menus from a machine learning model to suggest cold desserts and drinks.

[0143] Terminal processing

[0144] Step 4: Receive the recommended menu

[0145] The serving robot's terminal receives customer information and recommended menu items sent from the server. It receives data from the server via HTTP requests and stores it in the terminal's local memory.

[0146] input:

[0147] Customer information and recommended menu (in JSON format) sent from the server.

[0148] output:

[0149] Customer information and recommended menus stored in local memory

[0150] Specific actions:

[0151] The recommended menu received from the server is cached in local memory and prepared for the next visit.

[0152] Step 5: Proposal for follow-up visit

[0153] After a certain amount of time has passed since the meal was finished, the terminal revisits the table. Upon revisiting, the suggested menu items are displayed on the screen, and voice guidance is also provided. The display is equipped with a touch panel, allowing customers to enter additional orders.

[0154] input:

[0155] Recommended menu saved in local memory

[0156] output:

[0157] Recommended menus and voice guidance displayed on the screen.

[0158] Specific actions:

[0159] "Ten minutes after the meal at Table 5 is finished, the robot will revisit the table and display recommended menu items on the screen, along with a voice prompt asking, 'Would you like dessert?'"

[0160] User processing

[0161] Step 6: Accept or reject the proposal

[0162] The customer (user) decides whether to accept the robot's suggestion. If they accept, they type "I would like to order dessert" on the touch panel; if they reject, they press the cancel button.

[0163] input:

[0164] Additional orders or cancellations entered via the touch panel.

[0165] output:

[0166] Additional order data or cancellation information

[0167] Specific actions:

[0168] The customer enters "I would like to order an additional mango pudding" into the touch panel, or presses the cancel button to decline the offer.

[0169] Processing additional orders

[0170] Step 7: Submit additional order

[0171] When the terminal receives an additional order from a customer, it sends it to the server. It uses an HTTP request to send the additional order data to the server.

[0172] input:

[0173] Additional orders entered via touch panel (JSON format)

[0174] output:

[0175] Additional orders sent to the server

[0176] Specific actions:

[0177] "Send mango pudding to the server as an additional order from Table 5."

[0178] Step 8: Save and notify of additional orders

[0179] The server saves the received additional order to its database and immediately notifies the kitchen. For example, it might display a message on the kitchen's display saying, "Table 5 has ordered a new dessert."

[0180] input:

[0181] Additional orders sent to the server

[0182] output:

[0183] Additional orders stored in the database, notifications to the kitchen

[0184] Specific actions:

[0185] "Save Table 5's additional order for mango pudding in the database and display 'Table 5 has ordered a new mango pudding' on the kitchen display."

[0186] (Application Example 1)

[0187] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0188] In the current food service industry, personalized menu suggestions based on individual customer preferences and past order history are rarely offered. As a result, customer satisfaction declines, and acquiring repeat customers becomes difficult. Furthermore, the lack of seasonal or event-specific menu suggestions can lead to missed sales opportunities. In addition, food delivery services lack real-time menu recommendations, making it a challenge to improve the customer experience.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0190] In this invention, the server includes means for recording customer attribute information, means for storing the customer's order details, means for generating recommended menus based on seasons and events, and means for presenting recommended menus to the user via push notifications according to the timing of food delivery. This enables personalized menu suggestions based on customer attribute information and order history, realizing appropriate menu suggestions according to seasons and events, and real-time recommended menu guidance in food delivery services, thereby improving customer satisfaction and increasing sales.

[0191] "Means of recording customer attribute information" refers to methods for collecting personal information such as customers' age, gender, and allergy information, and storing it in a database.

[0192] "Means for saving the customer's order details" refers to means for recording the menu items and quantities ordered by the customer and saving this information in a database.

[0193] "Methods for generating recommended menus based on seasons and events" refers to methods for automatically selecting the most suitable menu for customers in accordance with seasonal changes and specific events, and generating a list of recommended menus.

[0194] "Means for setting the robot to revisit the table after a certain period of time has elapsed since the end of the meal" refers to a means for controlling the serving robot to revisit the table after a certain period of time has elapsed since the customer finished their meal.

[0195] "Means for displaying recommended menus and providing voice guidance upon a return visit" refers to means by which the serving robot displays recommended menus on a display and provides voice guidance to the customer upon a return visit.

[0196] "A method for presenting recommended menus to users via push notifications according to the timing of food delivery" refers to a method for presenting recommended menus via push notifications through a smartphone application to users of a food delivery service at the time of delivery.

[0197] "Means for providing customer feedback and processing additional orders" refers to a means of recording customer responses to suggested menu items, accepting additional orders based on those responses, and notifying the kitchen accordingly.

[0198] "Using machine learning models" refers to a method of selecting the optimal recommended menu using machine learning algorithms based on past order history and attribute information.

[0199] "Means of notifying the cooking area" refers to the means of communicating the details of an additional order to the kitchen or cooking area.

[0200] This invention relates to a system that utilizes customer attribute information and order history to generate optimal recommended menus tailored to the season and events, and proposes them to customers through serving robots or food delivery services. Specific methods for implementing this invention are described in detail below.

[0201] Server Processing

[0202] The server first collects and records customer attribute information (e.g., age, gender, allergy information, etc.). This information is entered via an application or tablet and stored in a database by the server. In addition, the customer's order history is also stored in the database.

[0203] The server generates optimal recommended menus for customers based on the season and events. This is achieved using a machine learning model (e.g., RandomForestClassifier). This model uses past order history and user preference information as training data to select the most suitable menu.

[0204] For example, during the summer months, cold desserts and drinks are recommended, and during the Christmas season, a special Christmas menu is suggested. This recommended menu is generated as a customized list for each customer.

[0205] Terminal processing

[0206] The terminal receives customer information and recommended menu items from the server and is configured to revisit the table after a certain period of time has passed since the meal was finished. Upon revisiting, the terminal displays the recommended menu items and provides voice guidance such as, "Would you like dessert?" The terminal also has a touch panel, allowing customers to enter additional orders.

[0207] Suggestions for food delivery timing

[0208] In food delivery services, recommended menu items are presented to users via push notifications through a smartphone application, depending on the delivery timing. This enables real-time menu suggestions and improves the customer experience.

[0209] User processing

[0210] The user decides whether to accept the suggestions from the robot or application. For example, they might review the suggested menu and enter "I'd like to add dessert" on the touch panel. If they wish to decline the suggestion, they can either leave the input blank or press the cancel button.

[0211] Processing additional orders

[0212] When a terminal or application receives an additional order from a customer, it sends it to the server. The server stores the received additional order in a database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen display. This allows cooking to begin quickly and accurately.

[0213] Specific example

[0214] If a user has previously ordered "pizza" and "salad," and the current season is summer, the server will generate summer-appropriate recommended menu items such as "ice cream" and "coffee." The serving robot and smartphone application will then present these recommended menu items to the user and suggest "Would you like some ice cream?" via voice guidance or push notifications.

[0215] Example of a prompt

[0216] User ID: user_1, Attributes: 25-year-old male, Allergy information: None

[0217] Past order history: Pizza, salad

[0218] Current season: Summer

[0219] Recommended menu: Ice cream, coffee

[0220] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0221] Step 1: The server collects and records user information.

[0222] The server stores customer attribute information (e.g., age, gender, allergy information, etc.) entered via applications or tablets into a database. The entered data, along with the user ID, is stored in the database. This ensures that the attributes of each individual user are recorded.

[0223] Input: Customer attribute information (age, gender, allergy information, etc.)

[0224] Output: User attribute information recorded in the database

[0225] Step 2: The server saves the order history.

[0226] When a customer places an order, the order details (e.g., menu items, quantity, etc.) are sent to the server and stored in the database. This allows for the accumulation of past order history.

[0227] Input: Order details (menu items, quantity)

[0228] Output: Order history stored in the database

[0229] Step 3: The server generates the recommended menu.

[0230] Based on seasonal and event information, the server uses a machine learning model (e.g., RandomForestClassifier) ​​to generate optimal recommended menus using past order history and user attribute information as input data.

[0231] Input: Seasonal information, event information, customer order history, attribute information

[0232] Output: Customized recommended menu list

[0233] Step 4: The server sends the recommended menu to the terminal.

[0234] The generated recommended menu is sent from the server to the terminal (serving robot or smartphone application). This allows the terminal to receive information in real time.

[0235] Input: Customized recommended menu list

[0236] Output: Recommended menu sent to the terminal

[0237] Step 5: The device will display a recommended menu and provide voice guidance.

[0238] The terminal displays the received recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?". Upon returning, users can place additional orders using the touch panel.

[0239] Input: Recommended Menu

[0240] Output: Display and voice guidance

[0241] Step 6: Send push notifications at the time of food delivery.

[0242] In the case of food delivery services, a smartphone application sends push notifications to users suggesting menu items based on the delivery timing. Through these notifications, menu suggestions are provided in real time.

[0243] Input: Recommended Menu

[0244] Output: Push notification to the user

[0245] Step 7: The user decides whether to accept the proposal.

[0246] Users view recommended menus on their devices or applications and decide whether or not to place an additional order. For example, they might type "I'd like to order dessert" on the touchscreen or application.

[0247] Input: Recommended menu guide

[0248] Output: User response (additional order or cancellation)

[0249] Step 8: The terminal sends the additional order to the server.

[0250] When a customer places an additional order, the terminal sends the order details to the server. The server records the received order in its database and notifies the kitchen in real time.

[0251] Input: Additional order details

[0252] Output: Recording of additional orders to the server and notification to the cooking area.

[0253] By implementing these steps through concrete examples, an efficient order management system utilizing food delivery services and serving robots can be built, resulting in improved customer satisfaction and increased sales.

[0254] Example of a prompt

[0255] User ID: user_1, Attributes: 25-year-old male, Allergy information: None

[0256] Past order history: Pizza, salad

[0257] Current season: Summer

[0258] Recommended menu: Ice cream, coffee

[0259] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0260] This invention relates to a system for a food service robot that combines a system for recording customer attribute information, saving order details, generating recommended menus based on seasons and events, and suggesting them upon return visits, with an emotion engine that recognizes user emotions. The following describes a specific method for carrying out this invention.

[0261] Server Processing

[0262] The server has the function of recording attribute information (age group, gender, allergy information, etc.) entered by customers when they place their first order. For example, information entered via an application or tablet is stored in the database by the server. Similarly, each time a customer places an order, its details (menu items, quantity, etc.) are also saved.

[0263] The server generates optimal menu recommendations for each customer based on the season, events, and past order history. For example, it suggests cold desserts and drinks in the summer, and a special Christmas menu during the Christmas season. A machine learning model is used to generate these recommendations. Based on past data, it automatically selects the most suitable menu items and generates a customized list for each customer.

[0264] Terminal processing

[0265] The serving robot's terminal receives customer information and recommended menu items transmitted from the server. The terminal is also equipped with an emotion engine that recognizes user emotions, allowing it to acquire emotional data in real time from the user's facial expressions and tone of voice.

[0266] After a certain amount of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" However, the content of the voice guidance can be adjusted based on the user's emotional data acquired by the emotion engine. For example, if the user is relaxed, it will make suggestions in a more friendly tone, and if the user is clearly dissatisfied, it will make suggestions in a more subdued tone. The recommended menu items are also optimized based on the emotional data.

[0267] User processing

[0268] The customer (user) decides whether to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they reject the suggestion, they can either leave it blank or press the cancel button. This emotional data is also fed back to the server and used to improve future suggestions.

[0269] Processing additional orders

[0270] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen's display. This allows cooking to begin quickly and accurately.

[0271] Specific example

[0272] One summer day, a male customer in his 30s uses the system for the first time. Since he has never ordered before, the server generates a recommended menu based on his attribute information and the seasonal information for that day. After the meal, the serving robot revisits and suggests, "Would you like a cold dessert?" The emotion engine recognizes that the customer is looking pleased, and the robot continues in an even more friendly tone, "I recommend our special mango sorbet, available only this time of year." The user enters "I'd like to place an additional order" on the touch panel, and the order is notified to the kitchen.

[0273] As described above, the system of the present invention not only records customer attribute information, generates optimal recommended menus, and proposes them upon return visits, but also recognizes user emotions and optimizes the content of the suggestions, thereby alleviating labor shortages and improving customer satisfaction and sales.

[0274] The following describes the processing flow.

[0275] Step 1:

[0276] The server records the attribute information (age group, gender, allergy information, etc.) entered when the customer places the first order.

[0277] The server receives data sent from tablets or applications.

[0278] The server stores this data in a database and associates it with the customer ID.

[0279] Step 2:

[0280] Every time the customer places an order, the server saves the order details (menu items, quantity, etc.).

[0281] The server records the order details in the database in JSON format.

[0282] The server tracks the order history for each customer ID.

[0283] Step 3:

[0284] The server generates recommended menus based on seasons, events, and past order histories.

[0285] The server executes an algorithm that uses a machine learning model to select appropriate recommended menus.

[0286] The server creates a recommended menu list and saves it associated with the customer ID.

[0287] Step 4:

[0288] The terminal receives the recommended menu list and revisit timing information sent from the server.

[0289] The terminal prepares the display and speaker and enters the standby state for the next operation.

[0290] Step 5:

[0291] The emotion engine built into the device acquires emotional data in real time from the user's facial expressions and tone of voice.

[0292] The device uses its camera and microphone to analyze the user's facial expressions and voice using an emotion engine.

[0293] The device processes the acquired emotional data and sends it to the server.

[0294] Step 6:

[0295] The server optimizes recommended menus and voice guidance based on emotion data.

[0296] The server analyzes emotional data to determine whether the user is relaxed or stressed.

[0297] The server adjusts the recommended menu and voice guidance content and sends it to the terminal.

[0298] Step 7:

[0299] After the set time has elapsed, the terminal will revisit the table and display recommended menus and provide voice guidance.

[0300] The device displays a recommended menu on its screen.

[0301] The device plays voice prompts such as "Would you like dessert?" in an appropriate tone based on emotional data.

[0302] Step 8:

[0303] The user responds to the robot's suggested menu.

[0304] Users can use the touch panel to select additional orders from the recommended menu or cancel the suggestions.

[0305] Step 9:

[0306] When the terminal receives the user's additional order, it transmits the information to the server.

[0307] The terminal transmits the user's selection to the server in JSON format.

[0308] Step 10:

[0309] The server saves the received additional order in the database and notifies the kitchen.

[0310] The server creates a notification for transmitting the order details to the cooking department and displays it on the kitchen display.

[0311] The above is the specific processing of the system combined with the emotion engine in the present invention. Thereby, it is possible to eliminate the shortage of manpower while improving customer satisfaction and sales.

[0312] (Example 2)

[0313] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0314] In the modern food service industry, in order to improve customer satisfaction, it is required to provide services tailored to the needs of individual customers. However, in the conventional system, there is a problem that customer attribute information and order history cannot be appropriately utilized, and only a uniform service can be provided. In addition, it is difficult to provide individual responses based on the emotions of customers, and the customer experience cannot be improved. As a result, there is a concern that it may lead to customer churn and a decline in sales. Furthermore, there is also a problem that the speed and accuracy of service are reduced due to delays in processing additional orders and notifying the kitchen.

[0315] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0316] In this invention, the server includes means for recording customer attribute information, means for storing order details, and means for generating recommended menus based on seasons and events. This enables optimal menu suggestions based on each customer's individual information. Furthermore, the serving robot's terminal includes means for recognizing emotions and means for adjusting the content of voice guidance based on emotion data, enabling real-time customer service. It also includes means for processing additional orders and means for notifying the cooking area, enabling the provision of quick and accurate service, thereby improving customer satisfaction and sales.

[0317] "Customer attribute information" refers to data that represents the characteristics of individual customers, such as age group, gender, and allergy information.

[0318] "Order details" refers to information indicating the menu items and quantities selected by the customer.

[0319] A "recommended menu" is a list of the best menu items suggested to a customer based on the season, events, customer attribute information, and order history.

[0320] "Revisit" refers to the serving robot returning to the table after a certain amount of time has passed since the meal was finished.

[0321] The "emotion engine" is a system that analyzes a customer's facial expressions and tone of voice to recognize their emotional state at that time.

[0322] "Voice guidance" refers to the service robot providing menu suggestions and other information to customers via voice.

[0323] "Feedback" is the process of sending customer reactions and emotional data to a server to help improve future services.

[0324] An "additional order" refers to an order placed by a customer after their initial order.

[0325] A "machine learning model" is a system composed of algorithms that analyze past data to make suggestions or predictions about the future.

[0326] The "cooking area" is the area in a restaurant where food is prepared and cooked.

[0327] The present invention combines a food service robot system that records customer attribute information, saves order details, generates recommended menus based on seasons and events, and suggests them on return visits, with an emotion engine that recognizes user emotions. The specific methods for implementing the present invention are described below.

[0328] Server Processing

[0329] The server has a function to record attribute information (age group, gender, allergy information, etc.) entered by customers when they place their first order. For example, information entered via input devices such as tablets is stored in the database by the server. Database software used includes MySQL and PostgreSQL. In addition, each time a customer places an order, the details of that order (menu items, quantity, etc.) are also saved. The order details are used to analyze customers' food selection trends.

[0330] Furthermore, the server can use machine learning models (TensorFlow or PyTorch) to generate optimal menu recommendations for customers based on the season, events, and past order history. For example, it might suggest "cold desserts" and "cold drinks" in the summer, or a special "Christmas menu" during the Christmas season. In this way, it becomes possible to suggest menus that meet the individual needs of each customer.

[0331] Terminal processing

[0332] The food delivery robot's terminal has the function of receiving customer information and recommended menus transmitted from the server. The terminal is equipped with an emotion engine that recognizes the user's emotions and can acquire emotion data in real time from the user's facial expressions and tone of voice.

[0333] After a certain amount of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" At this time, the content of the voice guidance can be adjusted based on the user's emotional data acquired by the emotion engine. For example, if the user is relaxed, it will make suggestions in a more friendly tone, and if the user is clearly dissatisfied, it will make suggestions in a more subdued tone. The recommended menu items are also optimized based on the emotional data.

[0334] User processing

[0335] Customers (users) decide whether or not to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they want to reject the suggestion, they can either leave it blank or press the cancel button. This emotional data is also fed back to the server and may be reflected in future suggestions.

[0336] Processing additional orders

[0337] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the cooking area. For example, a message such as "Table 5 has ordered a new dessert" is displayed on the cooking area's screen. This allows cooking to begin quickly and accurately.

[0338] Specific example

[0339] For example, consider a scenario where a male customer in his 30s uses the system for the first time on a summer day. When this customer enters his age group, gender, allergy information, etc., into a tablet, that information is immediately sent to and stored on the server. Next, when he orders food, the order details are also stored on the server. After the meal, the serving robot revisits and suggests, "Would you like a cold dessert?" The emotion engine recognizes that the customer has a positive expression and continues in a friendly tone, "We recommend our special mango sorbet, available only this season." The customer enters "I'd like to order more" on the touch panel, the order is sent to the server, and a notification is sent to the cooking area.

[0340] Example of a prompt

[0341] The following are examples of prompts to input into the generating AI model.

[0342] "Please describe a system for serving robots that suggests cold desserts on a summer day."

[0343] As described above, the system of the present invention not only records customer attribute information, generates optimal recommended menus, and proposes them upon return visits, but also recognizes user emotions and optimizes the suggested content, thereby improving customer satisfaction and sales.

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1:

[0346] The server receives customer attribute information (age group, gender, allergy information, etc.) entered via a tablet. The data entered is provided by the user. The server uses database software (e.g., MySQL, PostgreSQL) to store this information in a database.

[0347] Input: Customer attribute information

[0348] Output: Database containing attribute information

[0349] Step 2:

[0350] The server receives the order details (menu items, quantities, etc.) entered by the user. The entered data represents the order details based on the user's selections. The server saves this data to a database, thereby maintaining a record of the order.

[0351] Input: User's order details

[0352] Output: Database where order details are stored

[0353] Step 3:

[0354] The server uses machine learning models (e.g., TensorFlow, PyTorch) to generate recommended menus based on stored attribute information, order history, and seasonal and event information. Past order history and attribute information are used as input data, and customized recommended menus are generated as output.

[0355] Input: Attribute information, order history, seasonal information, event information

[0356] Output: Customized recommended menu

[0357] Step 4:

[0358] The server sends the generated recommended menu to the serving robot's terminal. This provides the terminal with the information it needs for the next step.

[0359] Input: Customized Recommended Menu

[0360] Output: Recommended menu sent to the terminal

[0361] Step 5:

[0362] The device prepares to display recommended menus received from the server. It also starts an emotion engine to recognize the user's emotions, acquiring emotional data from the user's facial expressions and tone of voice.

[0363] Input: Recommended Menu

[0364] Output: Sentiment data acquired in real time

[0365] Step 6:

[0366] After a certain amount of time has passed since the meal was finished, the robot revisits the table and displays recommended menu items on its screen. At the same time, it provides voice guidance such as, "Would you like dessert?" An emotion engine analyzes the user's emotional data in real time and adjusts the content and tone of the voice guidance based on that data.

[0367] Input: Acquired sentiment data, recommended menu

[0368] Output: Emotion-based voice guidance, display

[0369] Step 7:

[0370] The user decides whether to accept the robot's suggestion via a touch panel. For example, they might input, "I'd like to order an additional dessert." The entered order data is then sent to the server by the terminal.

[0371] Input: User's additional order details

[0372] Output: Additional order data sent to the server

[0373] Step 8:

[0374] The server saves the received additional order to the database and immediately notifies the cooking area. In the cooking area, a message such as "Table 5 has ordered a new dessert" is displayed on the screen. This allows cooking to begin quickly and accurately.

[0375] Input: Additional order data

[0376] Output: Additional orders saved in the database, notifications to the cooking area.

[0377] In this way, by explaining the specific actions performed at each step and the flow of their processing, it is clearly demonstrated how the system of the present invention functions.

[0378] (Application Example 2)

[0379] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0380] Conventional food delivery robot systems were unable to provide individually optimized suggestions based on customer attribute information and order history, nor could they recognize customer emotions and adjust suggestions in real time, making it difficult to improve customer satisfaction. In particular, brick-and-mortar stores are required to provide services that meet the individual needs of each customer, and maintaining high service quality efficiently amidst labor shortages has been a challenge.

[0381] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording customer attribute information, means for saving the customer's order details, means for generating recommended menus based on seasons and events, means for setting the server to revisit the table after a certain period of time has elapsed since the end of the meal, means for displaying and providing voice guidance for the recommended menus upon the revisit, means for providing feedback on the customer's reaction and processing additional orders, an emotion recognition engine for acquiring customer emotion data in real time, and means for adjusting the content of the recommended menus and voice guidance based on the emotion data. This makes it possible to provide optimal service tailored to the individual needs of customers, improve customer satisfaction, and enable efficient operation in physical stores.

[0382] "Customer attribute information" refers to information that indicates the characteristics of individual customers, such as age group, gender, and allergy information.

[0383] "Order details" refers to the specific product or service selections made by the customer, including detailed information such as menu items and quantities purchased.

[0384] A "recommended menu" is a list of products and services best suited to a customer, generated based on the season, events, and the customer's past order history.

[0385] The "revisiting the table" feature allows the serving robot to revisit the table after the meal has been finished and offer additional services or products.

[0386] "Means of display and audio guidance" refers to a function that displays recommended menus on a screen and provides audio guidance to customers.

[0387] "Means for providing feedback on responses and processing additional orders" refers to a function that records and analyzes customer responses, optimizes future suggestions based on that information, and simultaneously accepts and processes additional orders.

[0388] An "emotion recognition engine" is a system that analyzes a customer's facial expressions and tone of voice to recognize their emotional state in real time.

[0389] "Means for adjusting the content of recommended menus and voice guidance" refers to a function that adaptively changes the recommended products and services, and the way they are presented, based on recognized emotion data.

[0390] This invention relates to a system that utilizes a food delivery robot to provide personalized customer service in physical stores based on customer attribute information and emotional data. Specifically, it realizes the following system configuration and operation.

[0391] System Configuration

[0392] 1. Hardware

[0393] Tablet device: Used by customers to enter attribute information upon their first visit.

[0394] Camera and microphone: Equipped on the serving robot to capture customers' facial expressions and voice tones.

[0395] Serving robots: They revisit tables and suggest products and services.

[0396] 2. Software

[0397] Server: Customer information and order history are managed using AWS® or Google® Cloud Platform.

[0398] Emotion Recognition Engine: Uses Microsoft® Azure® Cognitive Services to acquire and analyze emotion data in real time.

[0399] Machine Learning Model: Build a model using TensorFlow or PyTorch to generate recommended menus.

[0400] Database: Uses an RDBMS such as MySQL to manage stored data.

[0401] Program processing and explanation in natural language

[0402] 1. Recording customer attributes

[0403] The customer enters their initial attribute information on a tablet device. This information is sent to the server and stored in a MySQL database.

[0404] 2. Updating purchase history data

[0405] Each time an order is completed, its history data is sent to the server and stored in the database. This information is later used to suggest the most suitable products to the customer.

[0406] 3. Generating recommended products

[0407] Based on each customer's attribute information, purchase history, and seasonal and event information, a machine learning model generates an optimal list of recommended products. This model is built using TensorFlow or PyTorch based on historical data.

[0408] 4. Acquisition and analysis of emotional data

[0409] The serving robot's built-in camera and microphone capture the customer's facial expressions and voice tone, and perform real-time sentiment analysis using Azure Cognitive Services. This allows for the acquisition of customer sentiment data.

[0410] 5. Optimizing the proposed content

[0411] Based on emotional data, recommended menus and voice guidance are adjusted. For example, a relaxed customer will be recommended products in a friendly tone, while a dissatisfied customer will receive suggestions in a more subdued tone.

[0412] 6. Processing additional orders

[0413] When a customer selects an additional order on the touch panel, the order details are sent to the server and notified to the kitchen in a timely manner. The kitchen staff then quickly prepares the new order.

[0414] Specific example

[0415] For example, suppose a male customer in his 30s visits the store for the first time on a summer day and enters his attribute information on a tablet device. The server generates recommended menu items based on this information, and the emotion recognition engine recognizes the customer's relaxed expression. A serving robot then suggests in a friendly tone, "Would you like a cold dessert?" Examples of prompt phrases in this scenario include:

[0416] Generate a response for when the user asks, "What do you recommend today?" The user is in the summer and has a history of ordering cold desserts. Current emotion recognition indicates they are relaxed.

[0417] As described above, this system utilizes customer attribute information and real-time sentiment data to provide high-quality, personalized service.

[0418] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0419] Step 1:

[0420] The server retrieves attribute information entered by the customer on a tablet device during their first visit. The information entered on the tablet (age group, gender, allergy information, etc.) is sent to the server and stored in a MySQL database. This prepares the basic customer information needed for subsequent steps.

[0421] Step 2:

[0422] The server records customer order details. Specifically, when a customer selects an item from a menu, the order details are sent to the server. The server stores this information in a database and updates the customer's purchase history. This allows for future recommendations based on customer preferences.

[0423] Step 3:

[0424] The server takes attribute information, order history, and seasonal / event information as input to generate recommended menus. It uses machine learning models (TensorFlow or PyTorch) to generate the optimal menu. These recommended menus are customized for each customer and sent from the server to the serving robots. This enables appropriate suggestions tailored to customer needs.

[0425] Step 4:

[0426] The terminal (serving robot) uses a camera and microphone to capture the customer's facial expressions and tone of voice in real time to interact with them. This data is analyzed using Microsoft Azure Cognitive Services to obtain customer sentiment data. This sentiment data is used in the next step.

[0427] Step 5:

[0428] The terminal (serving robot) adjusts its recommended menu and voice guidance based on the emotional data it acquires. For example, if the customer is relaxed, it makes suggestions in a friendly tone, and if the customer appears dissatisfied, it makes suggestions in a more reserved tone. This ensures that the optimal service is provided according to the customer's emotional state.

[0429] Step 6:

[0430] The terminal (serving robot) revisits the table and guides the customer through recommended menu items via display and voice. Based on emotional data-driven adjustments, it then makes suggestions such as, "Would you like a cold dessert?" The system then confirms whether the customer accepts the suggestion.

[0431] Step 7:

[0432] Users (customers) place additional orders using a touch panel. When a customer selects additional desserts or drinks, that information is sent to the server. The server stores the received additional order in a database and simultaneously notifies the kitchen. This ensures that additional orders are processed efficiently.

[0433] Step 8:

[0434] The server analyzes customer reactions and feedback on additional orders, updating the database to provide even better suggestions for future visits. This allows for the accumulation of data to continuously improve customer satisfaction and provide more personalized service.

[0435] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0436] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0437] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0438] [Second Embodiment]

[0439] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0440] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0441] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0442] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0443] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0444] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0445] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0446] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0447] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0448] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0449] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0450] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0451] This invention relates to a system for a food service robot that records customer attribute information, saves order details, generates recommended menus based on the season and events, and proposes them to customers on their return visits. The following describes a specific method for implementing this invention.

[0452] Server Processing

[0453] The server has the function of recording information entered by customers when they place their first order (such as age group, gender, and allergy information). For example, information entered via an application or tablet is stored in the database by the server. Similarly, each time a customer places an order, the details of that order (menu items, quantity, etc.) are also saved.

[0454] The server generates optimal recommended menus for customers based on the season and events. For example, in the summer it suggests cold desserts and drinks, and during the Christmas season it suggests a special Christmas menu. A machine learning model is used to generate these recommended menus. Based on past data, it automatically selects the most suitable menu items and generates a customized list for each customer.

[0455] Terminal processing

[0456] The serving robot's terminal receives customer information and recommended menu items transmitted from the server. After a certain period of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice prompts such as, "Would you like dessert?" The terminal also features a touch panel, allowing customers to enter additional orders.

[0457] User processing

[0458] The customer (user) decides whether to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they want to reject the suggestion, they can either leave it blank or press the cancel button.

[0459] Processing additional orders

[0460] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen's display. This allows cooking to begin quickly and accurately.

[0461] As described above, the system of the present invention can record customer attribute information, generate optimal recommended menus, and propose them during follow-up visits, thereby alleviating labor shortages and improving customer satisfaction and sales.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The server records attribute information (age group, gender, allergy information, etc.) entered by the customer when they place their first order.

[0465] The server receives data sent from tablets and applications.

[0466] The server stores this data in a database and associates it with the customer ID.

[0467] Step 2:

[0468] The server saves the details of an order (menu items, quantity, etc.) each time a customer places an order.

[0469] The server records the order details in a database in JSON format.

[0470] The server tracks order history for each customer ID.

[0471] Step 3:

[0472] The server generates recommended menus based on the season, events, and past order history.

[0473] The server uses a machine learning model to execute an algorithm that selects the appropriate recommended menu.

[0474] The server creates a list of recommended menu items and saves it, associating it with the customer ID.

[0475] Step 4:

[0476] The server instructs the serving robot to revisit the table a certain amount of time after the meal has finished.

[0477] The server uses a reminder function to set a time for a return visit.

[0478] Once the timer settings are complete, the server sends that information to the robot's terminal.

[0479] Step 5:

[0480] The terminal receives a list of recommended menu items and information on when to revisit from the server.

[0481] The device prepares its display and speaker and enters a standby state for the next operation.

[0482] Step 6:

[0483] The terminal revisits the table after a set time has elapsed and displays and provides voice guidance to the customer regarding recommended menu items.

[0484] The device displays a recommended menu on its screen.

[0485] The terminal plays voice prompts such as, "Would you like dessert?"

[0486] Step 7:

[0487] The user responds to the robot's suggested menu.

[0488] Users can use the touch panel to select additional orders from the recommended menu or cancel the suggestions.

[0489] Step 8:

[0490] When the terminal receives an additional order from a user, it sends that information to the server.

[0491] The terminal sends the user's selection to the server in JSON format.

[0492] Step 9:

[0493] The server saves the received additional order to the database and notifies the kitchen.

[0494] The server creates a notification to communicate the order details to the cooking department and displays it on the kitchen display.

[0495] The above describes the specific processing of the program in this invention. This makes it possible to alleviate labor shortages while improving customer satisfaction and sales.

[0496] (Example 1)

[0497] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0498] Traditional food service systems have difficulty effectively utilizing customer attribute information and order history, limiting improvements in customer satisfaction and sales growth. Specifically, there were problems such as difficulty in providing seasonal or event-specific recommended menus and in suggesting timely additional orders. Furthermore, communication of additional orders could be time-consuming, resulting in a decline in service quality.

[0499] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0500] In this invention, the server includes means for recording customer attribute information, means for storing the customer's order details, and means for generating recommended menus based on seasons and events. This enables the suggestion of the most suitable menu for each customer, improving customer satisfaction and increasing sales.

[0501] Furthermore, the system includes means for receiving customer information and recommended menu items transmitted from the server, and means for storing received additional orders in a database and notifying the kitchen. This enables efficient service delivery and ensures that additional orders are processed quickly and accurately.

[0502] "Customer attribute information" refers to data that shows personal characteristics of customers, such as their age group, gender, and allergy information.

[0503] "Order details" refers to information indicating the menu items and quantities ordered by the customer.

[0504] "Recommended menu" refers to menu suggestions that are best suited to the customer, generated using machine learning models based on the season and events.

[0505] "Revisit" means that the serving robot will come back to the table a certain amount of time after the meal has finished.

[0506] "Voice guidance" refers to the function of the serving robot that provides suggestions and guidance via voice.

[0507] "Feedback" refers to recording customer reactions and returning that information to the system.

[0508] An "additional order" refers to a new order placed during or after a meal.

[0509] A "database" refers to a system that systematically stores data such as customer information and order details.

[0510] A "machine learning model" refers to an algorithm composed of mathematical approaches used to make predictions and classifications based on large amounts of data.

[0511] "Notifying the kitchen" means promptly informing the cooking area of ​​any additional orders that have been placed.

[0512] This invention relates to a system for a food service robot that records customer attribute information, saves order details, generates recommended menus based on the season and events, and suggests them to customers on their return visits.

[0513] Server Processing

[0514] The server has the function of recording information entered by customers when they place their first order (such as age group, gender, and allergy information). For example, information entered via a tablet device or mobile application is sent to the server as an HTTP request and then stored in a database (such as MySQL or PostgreSQL). Similarly, each time a customer places an order, its details (menu items, quantity, etc.) are also saved.

[0515] The server generates optimal recommended menus for customers based on the season and events. This uses machine learning models (for example, models using TensorFlow or PyTorch). By analyzing past data and selecting the most suitable menu items, a customized list is generated for each customer. For example, for a customer with attributes such as being a woman in her 40s with no allergies, the server might suggest a cold mango pudding and iced tea during the summer.

[0516] Example of a prompt:

[0517] "Please suggest a recommended summer dessert and drink for a female customer in her 40s who has no allergies."

[0518] Terminal processing

[0519] The serving robot's terminal receives customer information and recommended menu items sent from the server. It receives data from the server via HTTP requests and stores it in the terminal's local memory. After a certain amount of time has passed since the meal was finished, the terminal is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" The terminal also has a touch panel, allowing customers to enter additional orders.

[0520] One specific example is a robot that returns to the table 10 minutes after the meal is finished and asks, "Would you like some mango pudding and iced tea?"

[0521] Example of a prompt:

[0522] "Ten minutes after the meal ends, please suggest recommended desserts and drinks to the guests at Table 5."

[0523] User processing

[0524] The customer (user) decides whether to accept the robot's suggestion. If they accept the suggestion, they type "I would like to order an additional dessert" on the touch panel; if they reject it, they press the cancel button. Specifically, the customer might type "I would like to order an additional mango pudding" on the touch panel, or they might press the cancel button to reject the suggestion.

[0525] Processing additional orders

[0526] When the terminal receives an additional order from a customer, it sends it to the server. The additional order data is sent to the server using an HTTP request, and the server stores the received additional order in its database. It then immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" appears on the kitchen display. This allows cooking to begin quickly and accurately.

[0527] A concrete example would be a notification sent to the kitchen stating, "Table 5 has placed a new order of mango pudding and iced tea."

[0528] Example of a prompt:

[0529] "Please notify the kitchen of Table 5, who has just ordered a new dessert."

[0530] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0531] Server Processing

[0532] Step 1: Record customer attribute information

[0533] The server receives customer attribute information (age group, gender, allergy information, etc.) sent from tablet devices and mobile applications. This information arrives as an HTTP request. The server parses this request and stores it in the database as JSON data.

[0534] input:

[0535] Customer attribute information (in JSON format) sent from a tablet device.

[0536] output:

[0537] Customer attribute information stored in the database

[0538] Specific actions:

[0539] The system receives JSON-formatted requests sent from tablet devices, parses them, and saves them to the "Customer Information" table in the database.

[0540] Step 2: Save your order

[0541] The server receives customer order details (menu items, quantities, etc.) sent from tablet devices or mobile applications. The order information is also received as an HTTP request and stored in the database.

[0542] input:

[0543] Order details (in JSON format) sent from a tablet device.

[0544] output:

[0545] Order details stored in the database

[0546] Specific actions:

[0547] "Receive an order for two cold drinks from Table 5 and save it to the 'Order History' table in the database."

[0548] Step 3: Generate Recommended Menus

[0549] The server generates optimal recommended menus for customers based on seasons and events. It uses machine learning models (for example, models using TensorFlow or PyTorch) to analyze past data and select the most suitable menu.

[0550] input:

[0551] Information about seasons and events, customer attribute information and order history

[0552] output:

[0553] List of recommended menus

[0554] Specific actions:

[0555] Since it's summer, we'll run a Python script to generate recommended menus from a machine learning model to suggest cold desserts and drinks.

[0556] Terminal processing

[0557] Step 4: Receive the recommended menu

[0558] The serving robot's terminal receives customer information and recommended menu items sent from the server. It receives data from the server via HTTP requests and stores it in the terminal's local memory.

[0559] input:

[0560] Customer information and recommended menu (in JSON format) sent from the server.

[0561] output:

[0562] Customer information and recommended menus stored in local memory

[0563] Specific actions:

[0564] The recommended menu received from the server is cached in local memory and prepared for the next visit.

[0565] Step 5: Proposal for follow-up visit

[0566] After a certain amount of time has passed since the meal was finished, the terminal revisits the table. Upon revisiting, the suggested menu items are displayed on the screen, and voice guidance is also provided. The display is equipped with a touch panel, allowing customers to enter additional orders.

[0567] input:

[0568] Recommended menu saved in local memory

[0569] output:

[0570] Recommended menus and voice guidance displayed on the screen.

[0571] Specific actions:

[0572] "Ten minutes after the meal at Table 5 is finished, the robot will revisit the table and display recommended menu items on the screen, along with a voice prompt asking, 'Would you like dessert?'"

[0573] User processing

[0574] Step 6: Accept or reject the proposal

[0575] The customer (user) decides whether to accept the robot's suggestion. If they accept, they type "I would like to order dessert" on the touch panel; if they reject, they press the cancel button.

[0576] input:

[0577] Additional orders or cancellations entered via the touch panel.

[0578] output:

[0579] Additional order data or cancellation information

[0580] Specific actions:

[0581] The customer enters "I would like to order an additional mango pudding" into the touch panel, or presses the cancel button to decline the offer.

[0582] Processing additional orders

[0583] Step 7: Submit additional order

[0584] When the terminal receives an additional order from a customer, it sends it to the server. It uses an HTTP request to send the additional order data to the server.

[0585] input:

[0586] Additional orders entered via touch panel (JSON format)

[0587] output:

[0588] Additional orders sent to the server

[0589] Specific actions:

[0590] "Send mango pudding to the server as an additional order from Table 5."

[0591] Step 8: Save and notify of additional orders

[0592] The server saves the received additional order to its database and immediately notifies the kitchen. For example, it might display a message on the kitchen's display saying, "Table 5 has ordered a new dessert."

[0593] input:

[0594] Additional orders sent to the server

[0595] output:

[0596] Additional orders stored in the database, notifications to the kitchen

[0597] Specific actions:

[0598] "Save Table 5's additional order for mango pudding in the database and display 'Table 5 has ordered a new mango pudding' on the kitchen display."

[0599] (Application Example 1)

[0600] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0601] In the current food service industry, personalized menu suggestions based on individual customer preferences and past order history are rarely offered. As a result, customer satisfaction declines, and acquiring repeat customers becomes difficult. Furthermore, the lack of seasonal or event-specific menu suggestions can lead to missed sales opportunities. In addition, food delivery services lack real-time menu recommendations, making it a challenge to improve the customer experience.

[0602] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0603] In this invention, the server includes means for recording customer attribute information, means for storing the customer's order details, means for generating recommended menus based on seasons and events, and means for presenting recommended menus to the user via push notifications according to the timing of food delivery. This enables personalized menu suggestions based on customer attribute information and order history, realizing appropriate menu suggestions according to seasons and events, and real-time recommended menu guidance in food delivery services, thereby improving customer satisfaction and increasing sales.

[0604] "Means of recording customer attribute information" refers to methods for collecting personal information such as customers' age, gender, and allergy information, and storing it in a database.

[0605] "Means for saving the customer's order details" refers to means for recording the menu items and quantities ordered by the customer and saving this information in a database.

[0606] "Methods for generating recommended menus based on seasons and events" refers to methods for automatically selecting the most suitable menu for customers in accordance with seasonal changes and specific events, and generating a list of recommended menus.

[0607] "Means for setting the robot to revisit the table after a certain period of time has elapsed since the end of the meal" refers to a means for controlling the serving robot to revisit the table after a certain period of time has elapsed since the customer finished their meal.

[0608] "Means for displaying recommended menus and providing voice guidance upon a return visit" refers to means by which the serving robot displays recommended menus on a display and provides voice guidance to the customer upon a return visit.

[0609] "A method for presenting recommended menus to users via push notifications according to the timing of food delivery" refers to a method for presenting recommended menus via push notifications through a smartphone application to users of a food delivery service at the time of delivery.

[0610] "Means for providing customer feedback and processing additional orders" refers to a means of recording customer responses to suggested menu items, accepting additional orders based on those responses, and notifying the kitchen accordingly.

[0611] "Using machine learning models" refers to a method of selecting the optimal recommended menu using machine learning algorithms based on past order history and attribute information.

[0612] "Means of notifying the cooking area" refers to the means of communicating the details of an additional order to the kitchen or cooking area.

[0613] This invention relates to a system that utilizes customer attribute information and order history to generate optimal recommended menus tailored to the season and events, and proposes them to customers through serving robots or food delivery services. Specific methods for implementing this invention are described in detail below.

[0614] Server Processing

[0615] The server first collects and records customer attribute information (e.g., age, gender, allergy information, etc.). This information is entered via an application or tablet and stored in a database by the server. In addition, the customer's order history is also stored in the database.

[0616] The server generates optimal recommended menus for customers based on the season and events. This is achieved using a machine learning model (e.g., RandomForestClassifier). This model uses past order history and user preference information as training data to select the most suitable menu.

[0617] For example, during the summer months, cold desserts and drinks are recommended, and during the Christmas season, a special Christmas menu is suggested. This recommended menu is generated as a customized list for each customer.

[0618] Terminal processing

[0619] The terminal receives customer information and recommended menu items from the server and is configured to revisit the table after a certain period of time has passed since the meal was finished. Upon revisiting, the terminal displays the recommended menu items and provides voice guidance such as, "Would you like dessert?" The terminal also has a touch panel, allowing customers to enter additional orders.

[0620] Suggestions for food delivery timing

[0621] In food delivery services, recommended menu items are presented to users via push notifications through a smartphone application, depending on the delivery timing. This enables real-time menu suggestions and improves the customer experience.

[0622] User processing

[0623] The user decides whether to accept the suggestions from the robot or application. For example, they might review the suggested menu and enter "I'd like to add dessert" on the touch panel. If they wish to decline the suggestion, they can either leave the input blank or press the cancel button.

[0624] Processing additional orders

[0625] When a terminal or application receives an additional order from a customer, it sends it to the server. The server stores the received additional order in a database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen display. This allows cooking to begin quickly and accurately.

[0626] Specific example

[0627] If a user has previously ordered "pizza" and "salad," and the current season is summer, the server will generate summer-appropriate recommended menu items such as "ice cream" and "coffee." The serving robot and smartphone application will then present these recommended menu items to the user and suggest "Would you like some ice cream?" via voice guidance or push notifications.

[0628] Example of a prompt

[0629] User ID: user_1, Attributes: 25-year-old male, Allergy information: None

[0630] Past order history: Pizza, salad

[0631] Current season: Summer

[0632] Recommended menu: Ice cream, coffee

[0633] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0634] Step 1: The server collects and records user information.

[0635] The server stores customer attribute information (e.g., age, gender, allergy information, etc.) entered via applications or tablets into a database. The entered data, along with the user ID, is stored in the database. This ensures that the attributes of each individual user are recorded.

[0636] Input: Customer attribute information (age, gender, allergy information, etc.)

[0637] Output: User attribute information recorded in the database

[0638] Step 2: The server saves the order history.

[0639] When a customer places an order, the order details (e.g., menu items, quantity, etc.) are sent to the server and stored in the database. This allows for the accumulation of past order history.

[0640] Input: Order details (menu items, quantity)

[0641] Output: Order history stored in the database

[0642] Step 3: The server generates the recommended menu.

[0643] Based on seasonal and event information, the server uses a machine learning model (e.g., RandomForestClassifier) ​​to generate optimal recommended menus using past order history and user attribute information as input data.

[0644] Input: Seasonal information, event information, customer order history, attribute information

[0645] Output: Customized recommended menu list

[0646] Step 4: The server sends the recommended menu to the terminal.

[0647] The generated recommended menu is sent from the server to the terminal (serving robot or smartphone application). This allows the terminal to receive information in real time.

[0648] Input: Customized recommended menu list

[0649] Output: Recommended menu sent to the terminal

[0650] Step 5: The device will display a recommended menu and provide voice guidance.

[0651] The terminal displays the received recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?". Upon returning, users can place additional orders using the touch panel.

[0652] Input: Recommended Menu

[0653] Output: Display and voice guidance

[0654] Step 6: Send push notifications at the time of food delivery.

[0655] In the case of food delivery services, a smartphone application sends push notifications to users suggesting menu items based on the delivery timing. Through these notifications, menu suggestions are provided in real time.

[0656] Input: Recommended Menu

[0657] Output: Push notification to the user

[0658] Step 7: The user decides whether to accept the proposal.

[0659] Users view recommended menus on their devices or applications and decide whether or not to place an additional order. For example, they might type "I'd like to order dessert" on the touchscreen or application.

[0660] Input: Recommended menu guide

[0661] Output: User response (additional order or cancellation)

[0662] Step 8: The terminal sends the additional order to the server.

[0663] When a customer places an additional order, the terminal sends the order details to the server. The server records the received order in its database and notifies the kitchen in real time.

[0664] Input: Additional order details

[0665] Output: Recording of additional orders to the server and notification to the cooking area.

[0666] By implementing these steps through concrete examples, an efficient order management system utilizing food delivery services and serving robots can be built, resulting in improved customer satisfaction and increased sales.

[0667] Example of a prompt

[0668] User ID: user_1, Attributes: 25-year-old male, Allergy information: None

[0669] Past order history: Pizza, salad

[0670] Current season: Summer

[0671] Recommended menu: Ice cream, coffee

[0672] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0673] This invention relates to a system for a food service robot that combines a system for recording customer attribute information, saving order details, generating recommended menus based on seasons and events, and suggesting them upon return visits, with an emotion engine that recognizes user emotions. The following describes a specific method for carrying out this invention.

[0674] Server Processing

[0675] The server has the function of recording attribute information (age group, gender, allergy information, etc.) entered by customers when they place their first order. For example, information entered via an application or tablet is stored in the database by the server. Similarly, each time a customer places an order, its details (menu items, quantity, etc.) are also saved.

[0676] The server generates optimal menu recommendations for each customer based on the season, events, and past order history. For example, it suggests cold desserts and drinks in the summer, and a special Christmas menu during the Christmas season. A machine learning model is used to generate these recommendations. Based on past data, it automatically selects the most suitable menu items and generates a customized list for each customer.

[0677] Terminal processing

[0678] The serving robot's terminal receives customer information and recommended menu items transmitted from the server. The terminal is also equipped with an emotion engine that recognizes user emotions, allowing it to acquire emotional data in real time from the user's facial expressions and tone of voice.

[0679] After a certain amount of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" However, the content of the voice guidance can be adjusted based on the user's emotional data acquired by the emotion engine. For example, if the user is relaxed, it will make suggestions in a more friendly tone, and if the user is clearly dissatisfied, it will make suggestions in a more subdued tone. The recommended menu items are also optimized based on the emotional data.

[0680] User processing

[0681] The customer (user) decides whether to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they reject the suggestion, they can either leave it blank or press the cancel button. This emotional data is also fed back to the server and used to improve future suggestions.

[0682] Processing additional orders

[0683] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen's display. This allows cooking to begin quickly and accurately.

[0684] Specific example

[0685] One summer day, a male customer in his 30s uses the system for the first time. Since he has never ordered before, the server generates a recommended menu based on his attribute information and the seasonal information for that day. After the meal, the serving robot revisits and suggests, "Would you like a cold dessert?" The emotion engine recognizes that the customer is looking pleased, and the robot continues in an even more friendly tone, "I recommend our special mango sorbet, available only this time of year." The user enters "I'd like to place an additional order" on the touch panel, and the order is notified to the kitchen.

[0686] As described above, the system of the present invention not only records customer attribute information, generates optimal recommended menus, and proposes them upon return visits, but also recognizes user emotions and optimizes the content of the suggestions, thereby alleviating labor shortages and improving customer satisfaction and sales.

[0687] The following describes the processing flow.

[0688] Step 1:

[0689] The server records attribute information (age group, gender, allergy information, etc.) entered by the customer when they place their first order.

[0690] The server receives data sent from tablets and applications.

[0691] The server stores this data in a database and associates it with the customer ID.

[0692] Step 2:

[0693] The server saves the details of an order (menu items, quantity, etc.) each time a customer places an order.

[0694] The server records the order details in a database in JSON format.

[0695] The server tracks order history for each customer ID.

[0696] Step 3:

[0697] The server generates recommended menus based on the season, events, and past order history.

[0698] The server uses a machine learning model to execute an algorithm that selects the appropriate recommended menu.

[0699] The server creates a list of recommended menu items and saves it, associating it with the customer ID.

[0700] Step 4:

[0701] The terminal receives a list of recommended menu items and information on when to revisit from the server.

[0702] The device prepares its display and speaker and enters a standby state for the next operation.

[0703] Step 5:

[0704] The emotion engine built into the device acquires emotional data in real time from the user's facial expressions and tone of voice.

[0705] The device uses its camera and microphone to analyze the user's facial expressions and voice using an emotion engine.

[0706] The device processes the acquired emotional data and sends it to the server.

[0707] Step 6:

[0708] The server optimizes recommended menus and voice guidance based on emotion data.

[0709] The server analyzes emotional data to determine whether the user is relaxed or stressed.

[0710] The server adjusts the recommended menu and voice guidance content and sends it to the terminal.

[0711] Step 7:

[0712] After the set time has elapsed, the terminal will revisit the table and display recommended menus and provide voice guidance.

[0713] The device displays a recommended menu on its screen.

[0714] The device plays voice prompts such as "Would you like dessert?" in an appropriate tone based on emotional data.

[0715] Step 8:

[0716] The user responds to the robot's suggested menu.

[0717] Users can use the touch panel to select additional orders from the recommended menu or cancel the suggestions.

[0718] Step 9:

[0719] When the terminal receives an additional order from a user, it sends that information to the server.

[0720] The terminal sends the user's selection to the server in JSON format.

[0721] Step 10:

[0722] The server saves the received additional order to the database and notifies the kitchen.

[0723] The server creates a notification to communicate the order details to the cooking department and displays it on the kitchen display.

[0724] The above describes the specific processing of the system that combines the emotion engine in this invention. This makes it possible to improve customer satisfaction and sales while resolving labor shortages.

[0725] (Example 2)

[0726] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0727] In today's restaurant industry, improving customer satisfaction requires providing services tailored to the individual needs of each customer. However, traditional systems have the problem of not being able to properly utilize customer attribute information and order history, resulting in only uniform service. Furthermore, it is difficult to provide individualized service based on customer emotions, making it difficult to improve the customer experience, which may lead to customer churn and decreased sales. In addition, delays in processing additional orders and notifying the kitchen can reduce the speed and accuracy of service.

[0728] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0729] In this invention, the server includes means for recording customer attribute information, means for storing order details, and means for generating recommended menus based on seasons and events. This enables optimal menu suggestions based on each customer's individual information. Furthermore, the serving robot's terminal includes means for recognizing emotions and means for adjusting the content of voice guidance based on emotion data, enabling real-time customer service. It also includes means for processing additional orders and means for notifying the cooking area, enabling the provision of quick and accurate service, thereby improving customer satisfaction and sales.

[0730] "Customer attribute information" refers to data that represents the characteristics of individual customers, such as age group, gender, and allergy information.

[0731] "Order details" refers to information indicating the menu items and quantities selected by the customer.

[0732] A "recommended menu" is a list of the best menu items suggested to a customer based on the season, events, customer attribute information, and order history.

[0733] "Revisit" refers to the serving robot returning to the table after a certain amount of time has passed since the meal was finished.

[0734] The "emotion engine" is a system that analyzes a customer's facial expressions and tone of voice to recognize their emotional state at that time.

[0735] "Voice guidance" refers to the service robot providing menu suggestions and other information to customers via voice.

[0736] "Feedback" is the process of sending customer reactions and emotional data to a server to help improve future services.

[0737] An "additional order" refers to an order placed by a customer after their initial order.

[0738] A "machine learning model" is a system composed of algorithms that analyze past data to make suggestions or predictions about the future.

[0739] The "cooking area" is the area in a restaurant where food is prepared and cooked.

[0740] The present invention combines a food service robot system that records customer attribute information, saves order details, generates recommended menus based on seasons and events, and suggests them on return visits, with an emotion engine that recognizes user emotions. The specific methods for implementing the present invention are described below.

[0741] Server Processing

[0742] The server has a function to record attribute information (age group, gender, allergy information, etc.) entered by customers when they place their first order. For example, information entered via input devices such as tablets is stored in the database by the server. Database software used includes MySQL and PostgreSQL. In addition, each time a customer places an order, the details of that order (menu items, quantity, etc.) are also saved. The order details are used to analyze customers' food selection trends.

[0743] Furthermore, the server can use machine learning models (TensorFlow or PyTorch) to generate optimal menu recommendations for customers based on the season, events, and past order history. For example, it might suggest "cold desserts" and "cold drinks" in the summer, or a special "Christmas menu" during the Christmas season. In this way, it becomes possible to suggest menus that meet the individual needs of each customer.

[0744] Terminal processing

[0745] The food delivery robot's terminal has the function of receiving customer information and recommended menus transmitted from the server. The terminal is equipped with an emotion engine that recognizes the user's emotions and can acquire emotion data in real time from the user's facial expressions and tone of voice.

[0746] After a certain amount of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" At this time, the content of the voice guidance can be adjusted based on the user's emotional data acquired by the emotion engine. For example, if the user is relaxed, it will make suggestions in a more friendly tone, and if the user is clearly dissatisfied, it will make suggestions in a more subdued tone. The recommended menu items are also optimized based on the emotional data.

[0747] User processing

[0748] Customers (users) decide whether or not to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they want to reject the suggestion, they can either leave it blank or press the cancel button. This emotional data is also fed back to the server and may be reflected in future suggestions.

[0749] Processing additional orders

[0750] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the cooking area. For example, a message such as "Table 5 has ordered a new dessert" is displayed on the cooking area's screen. This allows cooking to begin quickly and accurately.

[0751] Specific example

[0752] For example, consider a scenario where a male customer in his 30s uses the system for the first time on a summer day. When this customer enters his age group, gender, allergy information, etc., into a tablet, that information is immediately sent to and stored on the server. Next, when he orders food, the order details are also stored on the server. After the meal, the serving robot revisits and suggests, "Would you like a cold dessert?" The emotion engine recognizes that the customer has a positive expression and continues in a friendly tone, "We recommend our special mango sorbet, available only this season." The customer enters "I'd like to order more" on the touch panel, the order is sent to the server, and a notification is sent to the cooking area.

[0753] Example of a prompt

[0754] The following are examples of prompts to input into the generating AI model.

[0755] "Please describe a system for serving robots that suggests cold desserts on a summer day."

[0756] As described above, the system of the present invention not only records customer attribute information, generates optimal recommended menus, and proposes them upon return visits, but also recognizes user emotions and optimizes the suggested content, thereby improving customer satisfaction and sales.

[0757] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0758] Step 1:

[0759] The server receives customer attribute information (age group, gender, allergy information, etc.) entered via a tablet. The data entered is provided by the user. The server uses database software (e.g., MySQL, PostgreSQL) to store this information in a database.

[0760] Input: Customer attribute information

[0761] Output: Database containing attribute information

[0762] Step 2:

[0763] The server receives the order details (menu items, quantities, etc.) entered by the user. The entered data represents the order details based on the user's selections. The server saves this data to a database, thereby maintaining a record of the order.

[0764] Input: User's order details

[0765] Output: Database where order details are stored

[0766] Step 3:

[0767] The server uses machine learning models (e.g., TensorFlow, PyTorch) to generate recommended menus based on stored attribute information, order history, and seasonal and event information. Past order history and attribute information are used as input data, and customized recommended menus are generated as output.

[0768] Input: Attribute information, order history, seasonal information, event information

[0769] Output: Customized recommended menu

[0770] Step 4:

[0771] The server sends the generated recommended menu to the serving robot's terminal. This provides the terminal with the information it needs for the next step.

[0772] Input: Customized Recommended Menu

[0773] Output: Recommended menu sent to the terminal

[0774] Step 5:

[0775] The device prepares to display recommended menus received from the server. It also starts an emotion engine to recognize the user's emotions, acquiring emotional data from the user's facial expressions and tone of voice.

[0776] Input: Recommended Menu

[0777] Output: Sentiment data acquired in real time

[0778] Step 6:

[0779] After a certain amount of time has passed since the meal was finished, the robot revisits the table and displays recommended menu items on its screen. At the same time, it provides voice guidance such as, "Would you like dessert?" An emotion engine analyzes the user's emotional data in real time and adjusts the content and tone of the voice guidance based on that data.

[0780] Input: Acquired sentiment data, recommended menu

[0781] Output: Emotion-based voice guidance, display

[0782] Step 7:

[0783] The user decides whether to accept the robot's suggestion via a touch panel. For example, they might input, "I'd like to order an additional dessert." The entered order data is then sent to the server by the terminal.

[0784] Input: User's additional order details

[0785] Output: Additional order data sent to the server

[0786] Step 8:

[0787] The server saves the received additional order to the database and immediately notifies the cooking area. In the cooking area, a message such as "Table 5 has ordered a new dessert" is displayed on the screen. This allows cooking to begin quickly and accurately.

[0788] Input: Additional order data

[0789] Output: Additional orders saved in the database, notifications to the cooking area.

[0790] In this way, by explaining the specific actions performed at each step and the flow of their processing, it is clearly demonstrated how the system of the present invention functions.

[0791] (Application Example 2)

[0792] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0793] Conventional food delivery robot systems were unable to provide individually optimized suggestions based on customer attribute information and order history, nor could they recognize customer emotions and adjust suggestions in real time, making it difficult to improve customer satisfaction. In particular, brick-and-mortar stores are required to provide services that meet the individual needs of each customer, and maintaining high service quality efficiently amidst labor shortages has been a challenge.

[0794] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording customer attribute information, means for saving the customer's order details, means for generating recommended menus based on seasons and events, means for setting the server to revisit the table after a certain period of time has elapsed since the end of the meal, means for displaying and providing voice guidance for the recommended menus upon the revisit, means for providing feedback on the customer's reaction and processing additional orders, an emotion recognition engine for acquiring customer emotion data in real time, and means for adjusting the content of the recommended menus and voice guidance based on the emotion data. This makes it possible to provide optimal service tailored to the individual needs of customers, improve customer satisfaction, and enable efficient operation in physical stores.

[0795] "Customer attribute information" refers to information that indicates the characteristics of individual customers, such as age group, gender, and allergy information.

[0796] "Order details" refers to the specific product or service selections made by the customer, including detailed information such as menu items and quantities purchased.

[0797] A "recommended menu" is a list of products and services best suited to a customer, generated based on the season, events, and the customer's past order history.

[0798] The "revisiting the table" feature allows the serving robot to revisit the table after the meal has been finished and offer additional services or products.

[0799] "Means of display and audio guidance" refers to a function that displays recommended menus on a screen and provides audio guidance to customers.

[0800] "Means for providing feedback on responses and processing additional orders" refers to a function that records and analyzes customer responses, optimizes future suggestions based on that information, and simultaneously accepts and processes additional orders.

[0801] An "emotion recognition engine" is a system that analyzes a customer's facial expressions and tone of voice to recognize their emotional state in real time.

[0802] "Means for adjusting the content of recommended menus and voice guidance" refers to a function that adaptively changes the recommended products and services, and the way they are presented, based on recognized emotion data.

[0803] This invention relates to a system that utilizes a food delivery robot to provide personalized customer service in physical stores based on customer attribute information and emotional data. Specifically, it realizes the following system configuration and operation.

[0804] System Configuration

[0805] 1. Hardware

[0806] Tablet device: Used by customers to enter attribute information upon their first visit.

[0807] Camera and microphone: Equipped on the serving robot to capture customers' facial expressions and voice tones.

[0808] Serving robots: They revisit tables and suggest products and services.

[0809] 2. Software

[0810] Server: AWS or Google Cloud Platform is used to manage customer information and order history.

[0811] Emotion Recognition Engine: Uses Microsoft Azure Cognitive Services to acquire and analyze emotion data in real time.

[0812] Machine learning model: Build a model using TensorFlow or PyTorch to generate recommended menus.

[0813] Database: Uses an RDBMS such as MySQL to manage stored data.

[0814] Program processing and explanation in natural language

[0815] 1. Recording customer attributes

[0816] The customer enters their initial attribute information on a tablet device. This information is sent to the server and stored in a MySQL database.

[0817] 2. Updating purchase history data

[0818] Each time an order is completed, its history data is sent to the server and stored in the database. This information is later used to suggest the most suitable products to the customer.

[0819] 3. Generating recommended products

[0820] Based on each customer's attribute information, purchase history, and seasonal and event information, a machine learning model generates an optimal list of recommended products. This model is built using TensorFlow or PyTorch based on historical data.

[0821] 4. Acquisition and analysis of emotional data

[0822] The serving robot's built-in camera and microphone capture the customer's facial expressions and voice tone, and perform real-time sentiment analysis using Azure Cognitive Services. This allows for the acquisition of customer sentiment data.

[0823] 5. Optimizing the proposed content

[0824] Based on emotional data, recommended menus and voice guidance are adjusted. For example, a relaxed customer will be recommended products in a friendly tone, while a dissatisfied customer will receive suggestions in a more subdued tone.

[0825] 6. Processing additional orders

[0826] When a customer selects an additional order on the touch panel, the order details are sent to the server and notified to the kitchen in a timely manner. The kitchen staff then quickly prepares the new order.

[0827] Specific example

[0828] For example, suppose a male customer in his 30s visits the store for the first time on a summer day and enters his attribute information on a tablet device. The server generates recommended menu items based on this information, and the emotion recognition engine recognizes the customer's relaxed expression. A serving robot then suggests in a friendly tone, "Would you like a cold dessert?" Examples of prompt phrases in this scenario include:

[0829] Generate a response for when the user asks, "What do you recommend today?" The user is in the summer and has a history of ordering cold desserts. Current emotion recognition indicates they are relaxed.

[0830] As described above, this system utilizes customer attribute information and real-time sentiment data to provide high-quality, personalized service.

[0831] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0832] Step 1:

[0833] The server retrieves attribute information entered by the customer on a tablet device during their first visit. The information entered on the tablet (age group, gender, allergy information, etc.) is sent to the server and stored in a MySQL database. This prepares the basic customer information needed for subsequent steps.

[0834] Step 2:

[0835] The server records customer order details. Specifically, when a customer selects an item from a menu, the order details are sent to the server. The server stores this information in a database and updates the customer's purchase history. This allows for future recommendations based on customer preferences.

[0836] Step 3:

[0837] The server takes attribute information, order history, and seasonal / event information as input to generate recommended menus. It uses machine learning models (TensorFlow or PyTorch) to generate the optimal menu. These recommended menus are customized for each customer and sent from the server to the serving robots. This enables appropriate suggestions tailored to customer needs.

[0838] Step 4:

[0839] The terminal (serving robot) uses a camera and microphone to capture the customer's facial expressions and tone of voice in real time to interact with them. This data is analyzed using Microsoft Azure Cognitive Services to obtain customer sentiment data. This sentiment data is used in the next step.

[0840] Step 5:

[0841] The terminal (serving robot) adjusts its recommended menu and voice guidance based on the emotional data it acquires. For example, if the customer is relaxed, it makes suggestions in a friendly tone, and if dissatisfaction is observed, it makes suggestions in a more subdued tone. This ensures that the optimal service is provided according to the customer's emotional state.

[0842] Step 6:

[0843] The terminal (serving robot) revisits the table and guides the customer through recommended menu items via display and voice. Based on emotional data, it then makes suggestions such as, "Would you like a cold dessert?" The system confirms whether the customer accepts the suggestion.

[0844] Step 7:

[0845] Users (customers) place additional orders using a touch panel. When a customer selects additional desserts or drinks, that information is sent to the server. The server stores the received additional order in a database and simultaneously notifies the kitchen. This ensures that additional orders are processed efficiently.

[0846] Step 8:

[0847] The server analyzes customer reactions and feedback on additional orders, updating the database to provide even better suggestions for future visits. This allows for the accumulation of data to continuously improve customer satisfaction and enable more personalized service.

[0848] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0849] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0850] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0851] [Third Embodiment]

[0852] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0853] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0854] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0855] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0856] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0857] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0858] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0859] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0860] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0861] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0862] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0863] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0864] This invention relates to a system for a food service robot that records customer attribute information, saves order details, generates recommended menus based on the season and events, and proposes them to customers on their return visits. The following describes a specific method for implementing this invention.

[0865] Server Processing

[0866] The server has the function of recording information entered by customers when they place their first order (such as age group, gender, and allergy information). For example, information entered via an application or tablet is stored in the database by the server. Similarly, each time a customer places an order, the details of that order (menu items, quantity, etc.) are also saved.

[0867] The server generates optimal recommended menus for customers based on the season and events. For example, in the summer it suggests cold desserts and drinks, and during the Christmas season it suggests a special Christmas menu. A machine learning model is used to generate these recommended menus. Based on past data, it automatically selects the most suitable menu items and generates a customized list for each customer.

[0868] Terminal processing

[0869] The serving robot's terminal receives customer information and recommended menu items transmitted from the server. After a certain period of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice prompts such as, "Would you like dessert?" The terminal also features a touch panel, allowing customers to enter additional orders.

[0870] User processing

[0871] The customer (user) decides whether to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they want to reject the suggestion, they can either leave it blank or press the cancel button.

[0872] Processing additional orders

[0873] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen's display. This allows cooking to begin quickly and accurately.

[0874] As described above, the system of the present invention can record customer attribute information, generate optimal recommended menus, and propose them during follow-up visits, thereby alleviating labor shortages and improving customer satisfaction and sales.

[0875] The following describes the processing flow.

[0876] Step 1:

[0877] The server records attribute information (age group, gender, allergy information, etc.) entered by the customer when they place their first order.

[0878] The server receives data sent from tablets and applications.

[0879] The server stores this data in a database and associates it with the customer ID.

[0880] Step 2:

[0881] The server saves the details of an order (menu items, quantity, etc.) each time a customer places an order.

[0882] The server records the order details in a database in JSON format.

[0883] The server tracks order history for each customer ID.

[0884] Step 3:

[0885] The server generates recommended menus based on the season, events, and past order history.

[0886] The server uses a machine learning model to execute an algorithm that selects the appropriate recommended menu.

[0887] The server creates a list of recommended menu items and saves it, associating it with the customer ID.

[0888] Step 4:

[0889] The server instructs the serving robot to revisit the table a certain amount of time after the meal has finished.

[0890] The server uses a reminder function to set a time for a return visit.

[0891] Once the timer settings are complete, the server sends that information to the robot's terminal.

[0892] Step 5:

[0893] The terminal receives a list of recommended menu items and information on when to revisit from the server.

[0894] The device prepares its display and speaker and enters a standby state for the next operation.

[0895] Step 6:

[0896] The terminal revisits the table after a set time has elapsed and displays and provides voice guidance to the customer regarding recommended menu items.

[0897] The device displays a recommended menu on its screen.

[0898] The terminal plays voice prompts such as, "Would you like dessert?"

[0899] Step 7:

[0900] The user responds to the robot's suggested menu.

[0901] Users can use the touch panel to select additional orders from the recommended menu or cancel the suggestions.

[0902] Step 8:

[0903] When the terminal receives an additional order from a user, it sends that information to the server.

[0904] The terminal sends the user's selection to the server in JSON format.

[0905] Step 9:

[0906] The server saves the received additional order to the database and notifies the kitchen.

[0907] The server creates a notification to communicate the order details to the cooking department and displays it on the kitchen display.

[0908] The above describes the specific processing of the program in this invention. This makes it possible to alleviate labor shortages while improving customer satisfaction and sales.

[0909] (Example 1)

[0910] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0911] Traditional food service systems have difficulty effectively utilizing customer attribute information and order history, limiting improvements in customer satisfaction and sales growth. Specifically, there were problems such as difficulty in providing seasonal or event-specific recommended menus and in suggesting timely additional orders. Furthermore, communication of additional orders could be time-consuming, resulting in a decline in service quality.

[0912] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0913] In this invention, the server includes means for recording customer attribute information, means for storing the customer's order details, and means for generating recommended menus based on seasons and events. This enables the suggestion of the most suitable menu for each customer, improving customer satisfaction and increasing sales.

[0914] Furthermore, the system includes means for receiving customer information and recommended menu items transmitted from the server, and means for storing received additional orders in a database and notifying the kitchen. This enables efficient service delivery and ensures that additional orders are processed quickly and accurately.

[0915] "Customer attribute information" refers to data that shows personal characteristics of customers, such as their age group, gender, and allergy information.

[0916] "Order details" refers to information indicating the menu items and quantities ordered by the customer.

[0917] "Recommended menu" refers to menu suggestions that are best suited to the customer, generated using machine learning models based on the season and events.

[0918] "Revisit" means that the serving robot will come back to the table a certain amount of time after the meal has finished.

[0919] "Voice guidance" refers to the function of the serving robot that provides suggestions and guidance via voice.

[0920] "Feedback" refers to recording customer reactions and returning that information to the system.

[0921] An "additional order" refers to a new order placed during or after a meal.

[0922] A "database" refers to a system that systematically stores data such as customer information and order details.

[0923] A "machine learning model" refers to an algorithm composed of mathematical approaches used to make predictions and classifications based on large amounts of data.

[0924] "Notifying the kitchen" means promptly informing the cooking area of ​​any additional orders that have been placed.

[0925] This invention relates to a system for a food service robot that records customer attribute information, saves order details, generates recommended menus based on the season and events, and suggests them to customers on their return visits.

[0926] Server Processing

[0927] The server has the function of recording information entered by customers when they place their first order (such as age group, gender, and allergy information). For example, information entered via a tablet device or mobile application is sent to the server as an HTTP request and then stored in a database (such as MySQL or PostgreSQL). Similarly, each time a customer places an order, its details (menu items, quantity, etc.) are also saved.

[0928] The server generates optimal recommended menus for customers based on the season and events. This uses machine learning models (for example, models using TensorFlow or PyTorch). By analyzing past data and selecting the most suitable menu items, a customized list is generated for each customer. For example, for a customer with attributes such as being a woman in her 40s with no allergies, the server might suggest a cold mango pudding and iced tea during the summer.

[0929] Example of a prompt:

[0930] "Please suggest a recommended summer dessert and drink for a female customer in her 40s who has no allergies."

[0931] Terminal processing

[0932] The serving robot's terminal receives customer information and recommended menu items sent from the server. It receives data from the server via HTTP requests and stores it in the terminal's local memory. After a certain amount of time has passed since the meal was finished, the terminal is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" The terminal also has a touch panel, allowing customers to enter additional orders.

[0933] One specific example is a robot that returns to the table 10 minutes after the meal is finished and asks, "Would you like some mango pudding and iced tea?"

[0934] Example of a prompt:

[0935] "Ten minutes after the meal ends, please suggest recommended desserts and drinks to the guests at Table 5."

[0936] User processing

[0937] The customer (user) decides whether to accept the robot's suggestion. If they accept the suggestion, they type "I would like to order an additional dessert" on the touch panel; if they reject it, they press the cancel button. Specifically, the customer might type "I would like to order an additional mango pudding" on the touch panel, or they might press the cancel button to reject the suggestion.

[0938] Processing additional orders

[0939] When the terminal receives an additional order from a customer, it sends it to the server. The additional order data is sent to the server using an HTTP request, and the server stores the received additional order in its database. It then immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" appears on the kitchen display. This allows cooking to begin quickly and accurately.

[0940] A concrete example would be a notification sent to the kitchen stating, "Table 5 has placed a new order of mango pudding and iced tea."

[0941] Example of a prompt:

[0942] "Please notify the kitchen of Table 5, who has just ordered a new dessert."

[0943] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0944] Server Processing

[0945] Step 1: Record customer attribute information

[0946] The server receives customer attribute information (age group, gender, allergy information, etc.) sent from tablet devices and mobile applications. This information arrives as an HTTP request. The server parses this request and stores it in the database as JSON data.

[0947] input:

[0948] Customer attribute information (in JSON format) sent from a tablet device.

[0949] output:

[0950] Customer attribute information stored in the database

[0951] Specific actions:

[0952] The system receives JSON-formatted requests sent from tablet devices, parses them, and saves them to the "Customer Information" table in the database.

[0953] Step 2: Save your order

[0954] The server receives customer order details (menu items, quantities, etc.) sent from tablet devices or mobile applications. The order information is also received as an HTTP request and stored in the database.

[0955] input:

[0956] Order details (in JSON format) sent from a tablet device.

[0957] output:

[0958] Order details stored in the database

[0959] Specific actions:

[0960] "Receive an order for two cold drinks from Table 5 and save it to the 'Order History' table in the database."

[0961] Step 3: Generate Recommended Menus

[0962] The server generates optimal recommended menus for customers based on seasons and events. It uses machine learning models (for example, models using TensorFlow or PyTorch) to analyze past data and select the most suitable menu.

[0963] input:

[0964] Information about seasons and events, customer attribute information and order history

[0965] output:

[0966] List of recommended menus

[0967] Specific actions:

[0968] Since it's summer, we'll run a Python script to generate recommended menus from a machine learning model to suggest cold desserts and drinks.

[0969] Terminal processing

[0970] Step 4: Receive the recommended menu

[0971] The serving robot's terminal receives customer information and recommended menu items sent from the server. It receives data from the server via HTTP requests and stores it in the terminal's local memory.

[0972] input:

[0973] Customer information and recommended menu (in JSON format) sent from the server.

[0974] output:

[0975] Customer information and recommended menus stored in local memory

[0976] Specific actions:

[0977] The recommended menu received from the server is cached in local memory and prepared for the next visit.

[0978] Step 5: Proposal for follow-up visit

[0979] After a certain amount of time has passed since the meal was finished, the terminal revisits the table. Upon revisiting, the suggested menu items are displayed on the screen, and voice guidance is also provided. The display is equipped with a touch panel, allowing customers to enter additional orders.

[0980] input:

[0981] Recommended menu saved in local memory

[0982] output:

[0983] Recommended menus and voice guidance displayed on the screen.

[0984] Specific actions:

[0985] "Ten minutes after the meal at Table 5 is finished, the robot will revisit the table and display recommended menu items on the screen, along with a voice prompt asking, 'Would you like dessert?'"

[0986] User processing

[0987] Step 6: Accept or reject the proposal

[0988] The customer (user) decides whether to accept the robot's suggestion. If they accept, they type "I would like to order dessert" on the touch panel; if they reject, they press the cancel button.

[0989] input:

[0990] Additional orders or cancellations entered via the touch panel.

[0991] output:

[0992] Additional order data or cancellation information

[0993] Specific actions:

[0994] The customer enters "I would like to order an additional mango pudding" into the touch panel, or presses the cancel button to decline the offer.

[0995] Processing additional orders

[0996] Step 7: Submit additional order

[0997] When the terminal receives an additional order from a customer, it sends it to the server. It uses an HTTP request to send the additional order data to the server.

[0998] input:

[0999] Additional orders entered via touch panel (JSON format)

[1000] output:

[1001] Additional orders sent to the server

[1002] Specific actions:

[1003] "Send mango pudding to the server as an additional order from Table 5."

[1004] Step 8: Save and notify of additional orders

[1005] The server saves the received additional order to its database and immediately notifies the kitchen. For example, it might display a message on the kitchen's display saying, "Table 5 has ordered a new dessert."

[1006] input:

[1007] Additional orders sent to the server

[1008] output:

[1009] Additional orders stored in the database, notifications to the kitchen

[1010] Specific actions:

[1011] "Save Table 5's additional order for mango pudding in the database and display 'Table 5 has ordered a new mango pudding' on the kitchen display."

[1012] (Application Example 1)

[1013] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1014] In the current food service industry, personalized menu suggestions based on individual customer preferences and past order history are rarely offered. As a result, customer satisfaction declines, and acquiring repeat customers becomes difficult. Furthermore, the lack of seasonal or event-specific menu suggestions can lead to missed sales opportunities. In addition, food delivery services lack real-time menu recommendations, making it a challenge to improve the customer experience.

[1015] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1016] In this invention, the server includes means for recording customer attribute information, means for storing the customer's order details, means for generating recommended menus based on seasons and events, and means for presenting recommended menus to the user via push notifications according to the timing of food delivery. This enables personalized menu suggestions based on customer attribute information and order history, realizing appropriate menu suggestions according to seasons and events, and real-time recommended menu guidance in food delivery services, thereby improving customer satisfaction and increasing sales.

[1017] "Means of recording customer attribute information" refers to methods for collecting personal information such as customers' age, gender, and allergy information, and storing it in a database.

[1018] "Means for saving the customer's order details" refers to means for recording the menu items and quantities ordered by the customer and saving this information in a database.

[1019] "Methods for generating recommended menus based on seasons and events" refers to methods for automatically selecting the most suitable menu for customers in accordance with seasonal changes and specific events, and generating a list of recommended menus.

[1020] "Means for setting the robot to revisit the table after a certain period of time has elapsed since the end of the meal" refers to a means for controlling the serving robot to revisit the table after a certain period of time has elapsed since the customer finished their meal.

[1021] "Means for displaying recommended menus and providing voice guidance upon a return visit" refers to means by which the serving robot displays recommended menus on a display and provides voice guidance to the customer upon a return visit.

[1022] "A method for presenting recommended menus to users via push notifications according to the timing of food delivery" refers to a method for presenting recommended menus via push notifications through a smartphone application to users of a food delivery service at the time of delivery.

[1023] "Means for providing customer feedback and processing additional orders" refers to a means of recording customer responses to suggested menu items, accepting additional orders based on those responses, and notifying the kitchen accordingly.

[1024] "Using machine learning models" refers to a method of selecting the optimal recommended menu using machine learning algorithms based on past order history and attribute information.

[1025] "Means of notifying the cooking area" refers to the means of communicating the details of an additional order to the kitchen or cooking area.

[1026] This invention relates to a system that utilizes customer attribute information and order history to generate optimal recommended menus tailored to the season and events, and proposes them to customers through serving robots or food delivery services. Specific methods for implementing this invention are described in detail below.

[1027] Server Processing

[1028] The server first collects and records customer attribute information (e.g., age, gender, allergy information, etc.). This information is entered via an application or tablet and stored in a database by the server. In addition, the customer's order history is also stored in the database.

[1029] The server generates optimal recommended menus for customers based on the season and events. This is achieved using a machine learning model (e.g., RandomForestClassifier). This model uses past order history and user preference information as training data to select the most suitable menu.

[1030] For example, during the summer months, cold desserts and drinks are recommended, and during the Christmas season, a special Christmas menu is suggested. This recommended menu is generated as a customized list for each customer.

[1031] Terminal processing

[1032] The terminal receives customer information and recommended menu items from the server and is configured to revisit the table after a certain period of time has passed since the meal was finished. Upon revisiting, the terminal displays the recommended menu items and provides voice guidance such as, "Would you like dessert?" The terminal also has a touch panel, allowing customers to enter additional orders.

[1033] Suggestions for food delivery timing

[1034] In food delivery services, recommended menu items are presented to users via push notifications through a smartphone application, depending on the delivery timing. This enables real-time menu suggestions and improves the customer experience.

[1035] User processing

[1036] The user decides whether to accept the suggestions from the robot or application. For example, they might review the suggested menu and enter "I'd like to add dessert" on the touch panel. If they wish to decline the suggestion, they can either leave the input blank or press the cancel button.

[1037] Processing additional orders

[1038] When a terminal or application receives an additional order from a customer, it sends it to the server. The server stores the received additional order in a database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen display. This allows cooking to begin quickly and accurately.

[1039] Specific example

[1040] If a user has previously ordered "pizza" and "salad," and the current season is summer, the server will generate summer-appropriate recommended menu items such as "ice cream" and "coffee." The serving robot and smartphone application will then present these recommended menu items to the user and suggest "Would you like some ice cream?" via voice guidance or push notifications.

[1041] Example of a prompt

[1042] User ID: user_1, Attributes: 25-year-old male, Allergy information: None

[1043] Past order history: Pizza, salad

[1044] Current season: Summer

[1045] Recommended menu: Ice cream, coffee

[1046] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1047] Step 1: The server collects and records user information.

[1048] The server stores customer attribute information (e.g., age, gender, allergy information, etc.) entered via applications or tablets into a database. The entered data, along with the user ID, is stored in the database. This ensures that the attributes of each individual user are recorded.

[1049] Input: Customer attribute information (age, gender, allergy information, etc.)

[1050] Output: User attribute information recorded in the database

[1051] Step 2: The server saves the order history.

[1052] When a customer places an order, the order details (e.g., menu items, quantity, etc.) are sent to the server and stored in the database. This allows for the accumulation of past order history.

[1053] Input: Order details (menu items, quantity)

[1054] Output: Order history stored in the database

[1055] Step 3: The server generates the recommended menu.

[1056] Based on seasonal and event information, the server uses a machine learning model (e.g., RandomForestClassifier) ​​to generate optimal recommended menus using past order history and user attribute information as input data.

[1057] Input: Seasonal information, event information, customer order history, attribute information

[1058] Output: Customized recommended menu list

[1059] Step 4: The server sends the recommended menu to the terminal.

[1060] The generated recommended menu is sent from the server to the terminal (serving robot or smartphone application). This allows the terminal to receive information in real time.

[1061] Input: Customized recommended menu list

[1062] Output: Recommended menu sent to the terminal

[1063] Step 5: The device will display a recommended menu and provide voice guidance.

[1064] The terminal displays the received recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?". Upon returning, users can place additional orders using the touch panel.

[1065] Input: Recommended Menu

[1066] Output: Display and voice guidance

[1067] Step 6: Send push notifications at the time of food delivery.

[1068] In the case of food delivery services, a smartphone application sends push notifications to users suggesting menu items based on the delivery timing. Through these notifications, menu suggestions are provided in real time.

[1069] Input: Recommended Menu

[1070] Output: Push notification to the user

[1071] Step 7: The user decides whether to accept the proposal.

[1072] Users view recommended menus on their devices or applications and decide whether or not to place an additional order. For example, they might type "I'd like to order dessert" on the touchscreen or application.

[1073] Input: Recommended menu guide

[1074] Output: User response (additional order or cancellation)

[1075] Step 8: The terminal sends the additional order to the server.

[1076] When a customer places an additional order, the terminal sends the order details to the server. The server records the received order in its database and notifies the kitchen in real time.

[1077] Input: Additional order details

[1078] Output: Recording of additional orders to the server and notification to the cooking area.

[1079] By implementing these steps through concrete examples, an efficient order management system utilizing food delivery services and serving robots can be built, resulting in improved customer satisfaction and increased sales.

[1080] Example of a prompt

[1081] User ID: user_1, Attributes: 25-year-old male, Allergy information: None

[1082] Past order history: Pizza, salad

[1083] Current season: Summer

[1084] Recommended menu: Ice cream, coffee

[1085] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1086] This invention relates to a system for a food service robot that combines a system for recording customer attribute information, saving order details, generating recommended menus based on seasons and events, and suggesting them upon return visits, with an emotion engine that recognizes user emotions. The following describes a specific method for carrying out this invention.

[1087] Server Processing

[1088] The server has the function of recording attribute information (age group, gender, allergy information, etc.) entered by customers when they place their first order. For example, information entered via an application or tablet is stored in the database by the server. Similarly, each time a customer places an order, its details (menu items, quantity, etc.) are also saved.

[1089] The server generates optimal menu recommendations for each customer based on the season, events, and past order history. For example, it suggests cold desserts and drinks in the summer, and a special Christmas menu during the Christmas season. A machine learning model is used to generate these recommendations. Based on past data, it automatically selects the most suitable menu items and generates a customized list for each customer.

[1090] Terminal processing

[1091] The serving robot's terminal receives customer information and recommended menu items transmitted from the server. The terminal is also equipped with an emotion engine that recognizes user emotions, allowing it to acquire emotional data in real time from the user's facial expressions and tone of voice.

[1092] After a certain amount of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" However, the content of the voice guidance can be adjusted based on the user's emotional data acquired by the emotion engine. For example, if the user is relaxed, it will make suggestions in a more friendly tone, and if the user is clearly dissatisfied, it will make suggestions in a more subdued tone. The recommended menu items are also optimized based on the emotional data.

[1093] User processing

[1094] The customer (user) decides whether to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they reject the suggestion, they can either leave it blank or press the cancel button. This emotional data is also fed back to the server and used to improve future suggestions.

[1095] Processing additional orders

[1096] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen's display. This allows cooking to begin quickly and accurately.

[1097] Specific example

[1098] One summer day, a male customer in his 30s uses the system for the first time. Since he has never ordered before, the server generates a recommended menu based on his attribute information and the seasonal information for that day. After the meal, the serving robot revisits and suggests, "Would you like a cold dessert?" The emotion engine recognizes that the customer is looking pleased, and the robot continues in an even more friendly tone, "I recommend our special mango sorbet, available only this time of year." The user enters "I'd like to place an additional order" on the touch panel, and the order is notified to the kitchen.

[1099] As described above, the system of the present invention not only records customer attribute information, generates optimal recommended menus, and proposes them upon return visits, but also recognizes user emotions and optimizes the content of the suggestions, thereby alleviating labor shortages and improving customer satisfaction and sales.

[1100] The following describes the processing flow.

[1101] Step 1:

[1102] The server records attribute information (age group, gender, allergy information, etc.) entered by the customer when they place their first order.

[1103] The server receives data sent from tablets and applications.

[1104] The server stores this data in a database and associates it with the customer ID.

[1105] Step 2:

[1106] The server saves the details of an order (menu items, quantity, etc.) each time a customer places an order.

[1107] The server records the order details in a database in JSON format.

[1108] The server tracks order history for each customer ID.

[1109] Step 3:

[1110] The server generates recommended menus based on the season, events, and past order history.

[1111] The server uses a machine learning model to execute an algorithm that selects the appropriate recommended menu.

[1112] The server creates a list of recommended menu items and saves it, associating it with the customer ID.

[1113] Step 4:

[1114] The terminal receives a list of recommended menu items and information on when to revisit from the server.

[1115] The device prepares its display and speaker and enters a standby state for the next operation.

[1116] Step 5:

[1117] The emotion engine built into the device acquires emotional data in real time from the user's facial expressions and tone of voice.

[1118] The device uses its camera and microphone to analyze the user's facial expressions and voice using an emotion engine.

[1119] The device processes the acquired emotional data and sends it to the server.

[1120] Step 6:

[1121] The server optimizes recommended menus and voice guidance based on emotion data.

[1122] The server analyzes emotional data to determine whether the user is relaxed or stressed.

[1123] The server adjusts the recommended menu and voice guidance content and sends it to the terminal.

[1124] Step 7:

[1125] After the set time has elapsed, the terminal will revisit the table and display recommended menus and provide voice guidance.

[1126] The device displays a recommended menu on its screen.

[1127] The device plays voice prompts such as "Would you like dessert?" in an appropriate tone based on emotional data.

[1128] Step 8:

[1129] The user responds to the robot's suggested menu.

[1130] Users can use the touch panel to select additional orders from the recommended menu or cancel the suggestions.

[1131] Step 9:

[1132] When the terminal receives an additional order from a user, it sends that information to the server.

[1133] The terminal sends the user's selection to the server in JSON format.

[1134] Step 10:

[1135] The server saves the received additional order to the database and notifies the kitchen.

[1136] The server creates a notification to communicate the order details to the cooking department and displays it on the kitchen display.

[1137] The above describes the specific processing of the system that combines the emotion engine in this invention. This makes it possible to improve customer satisfaction and sales while resolving labor shortages.

[1138] (Example 2)

[1139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1140] In today's restaurant industry, improving customer satisfaction requires providing services tailored to the individual needs of each customer. However, traditional systems have the problem of not being able to properly utilize customer attribute information and order history, resulting in only uniform service. Furthermore, it is difficult to provide individualized service based on customer emotions, making it difficult to improve the customer experience, which may lead to customer churn and decreased sales. In addition, delays in processing additional orders and notifying the kitchen can reduce the speed and accuracy of service.

[1141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1142] In this invention, the server includes means for recording customer attribute information, means for storing order details, and means for generating recommended menus based on seasons and events. This enables optimal menu suggestions based on each customer's individual information. Furthermore, the serving robot's terminal includes means for recognizing emotions and means for adjusting the content of voice guidance based on emotion data, enabling real-time customer service. It also includes means for processing additional orders and means for notifying the cooking area, enabling the provision of quick and accurate service, thereby improving customer satisfaction and sales.

[1143] "Customer attribute information" refers to data that represents the characteristics of individual customers, such as age group, gender, and allergy information.

[1144] "Order details" refers to information indicating the menu items and quantities selected by the customer.

[1145] A "recommended menu" is a list of the best menu items suggested to a customer based on the season, events, customer attribute information, and order history.

[1146] "Revisit" refers to the serving robot returning to the table after a certain amount of time has passed since the meal was finished.

[1147] The "emotion engine" is a system that analyzes a customer's facial expressions and tone of voice to recognize their emotional state at that time.

[1148] "Voice guidance" refers to the service robot providing menu suggestions and other information to customers via voice.

[1149] "Feedback" is the process of sending customer reactions and emotional data to a server to help improve future services.

[1150] An "additional order" refers to an order placed by a customer after their initial order.

[1151] A "machine learning model" is a system composed of algorithms that analyze past data to make suggestions or predictions about the future.

[1152] The "cooking area" is the area in a restaurant where food is prepared and cooked.

[1153] The present invention combines a food service robot system that records customer attribute information, saves order details, generates recommended menus based on seasons and events, and suggests them on return visits, with an emotion engine that recognizes user emotions. The specific methods for implementing the present invention are described below.

[1154] Server Processing

[1155] The server has a function to record attribute information (age group, gender, allergy information, etc.) entered by customers when they place their first order. For example, information entered via input devices such as tablets is stored in the database by the server. Database software used includes MySQL and PostgreSQL. In addition, each time a customer places an order, the details of that order (menu items, quantity, etc.) are also saved. The order details are used to analyze customers' food selection trends.

[1156] Furthermore, the server can use machine learning models (TensorFlow or PyTorch) to generate optimal menu recommendations for customers based on the season, events, and past order history. For example, it might suggest "cold desserts" and "cold drinks" in the summer, or a special "Christmas menu" during the Christmas season. In this way, it becomes possible to suggest menus that meet the individual needs of each customer.

[1157] Terminal processing

[1158] The food delivery robot's terminal has the function of receiving customer information and recommended menus transmitted from the server. The terminal is equipped with an emotion engine that recognizes the user's emotions and can acquire emotion data in real time from the user's facial expressions and tone of voice.

[1159] After a certain amount of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" At this time, the content of the voice guidance can be adjusted based on the user's emotional data acquired by the emotion engine. For example, if the user is relaxed, it will make suggestions in a more friendly tone, and if the user is clearly dissatisfied, it will make suggestions in a more subdued tone. The recommended menu items are also optimized based on the emotional data.

[1160] User processing

[1161] Customers (users) decide whether or not to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they want to reject the suggestion, they can either leave it blank or press the cancel button. This emotional data is also fed back to the server and may be reflected in future suggestions.

[1162] Processing additional orders

[1163] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the cooking area. For example, a message such as "Table 5 has ordered a new dessert" is displayed on the cooking area's screen. This allows cooking to begin quickly and accurately.

[1164] Specific example

[1165] For example, consider a scenario where a male customer in his 30s uses the system for the first time on a summer day. When this customer enters his age group, gender, allergy information, etc., into a tablet, that information is immediately sent to and stored on the server. Next, when he orders food, the order details are also stored on the server. After the meal, the serving robot revisits and suggests, "Would you like a cold dessert?" The emotion engine recognizes that the customer has a positive expression and continues in a friendly tone, "We recommend our special mango sorbet, available only this season." The customer enters "I'd like to order more" on the touch panel, the order is sent to the server, and a notification is sent to the cooking area.

[1166] Example of a prompt

[1167] The following are examples of prompts to input into the generating AI model.

[1168] "Please describe a system for serving robots that suggests cold desserts on a summer day."

[1169] As described above, the system of the present invention not only records customer attribute information, generates optimal recommended menus, and proposes them upon return visits, but also recognizes user emotions and optimizes the suggested content, thereby improving customer satisfaction and sales.

[1170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1171] Step 1:

[1172] The server receives customer attribute information (age group, gender, allergy information, etc.) entered via a tablet. The data entered is provided by the user. The server uses database software (e.g., MySQL, PostgreSQL) to store this information in a database.

[1173] Input: Customer attribute information

[1174] Output: Database containing attribute information

[1175] Step 2:

[1176] The server receives the order details (menu items, quantities, etc.) entered by the user. The entered data represents the order details based on the user's selections. The server saves this data to a database, thereby maintaining a record of the order.

[1177] Input: User's order details

[1178] Output: Database where order details are stored

[1179] Step 3:

[1180] The server uses machine learning models (e.g., TensorFlow, PyTorch) to generate recommended menus based on stored attribute information, order history, and seasonal and event information. Past order history and attribute information are used as input data, and customized recommended menus are generated as output.

[1181] Input: Attribute information, order history, seasonal information, event information

[1182] Output: Customized recommended menu

[1183] Step 4:

[1184] The server sends the generated recommended menu to the serving robot's terminal. This provides the terminal with the information it needs for the next step.

[1185] Input: Customized Recommended Menu

[1186] Output: Recommended menu sent to the terminal

[1187] Step 5:

[1188] The device prepares to display recommended menus received from the server. It also starts an emotion engine to recognize the user's emotions, acquiring emotional data from the user's facial expressions and tone of voice.

[1189] Input: Recommended Menu

[1190] Output: Sentiment data acquired in real time

[1191] Step 6:

[1192] After a certain amount of time has passed since the meal was finished, the robot revisits the table and displays recommended menu items on its screen. At the same time, it provides voice guidance such as, "Would you like dessert?" An emotion engine analyzes the user's emotional data in real time and adjusts the content and tone of the voice guidance based on that data.

[1193] Input: Acquired sentiment data, recommended menu

[1194] Output: Emotion-based voice guidance, display

[1195] Step 7:

[1196] The user decides whether to accept the robot's suggestion via a touch panel. For example, they might input, "I'd like to order an additional dessert." The entered order data is then sent to the server by the terminal.

[1197] Input: User's additional order details

[1198] Output: Additional order data sent to the server

[1199] Step 8:

[1200] The server saves the received additional order to the database and immediately notifies the cooking area. In the cooking area, a message such as "Table 5 has ordered a new dessert" is displayed on the screen. This allows cooking to begin quickly and accurately.

[1201] Input: Additional order data

[1202] Output: Additional orders saved in the database, notifications to the cooking area.

[1203] In this way, by explaining the specific actions performed at each step and the flow of their processing, it is clearly demonstrated how the system of the present invention functions.

[1204] (Application Example 2)

[1205] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1206] Conventional food delivery robot systems were unable to provide individually optimized suggestions based on customer attribute information and order history, nor could they recognize customer emotions and adjust suggestions in real time, making it difficult to improve customer satisfaction. In particular, brick-and-mortar stores are required to provide services that meet the individual needs of each customer, and maintaining high service quality efficiently amidst labor shortages has been a challenge.

[1207] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording customer attribute information, means for saving the customer's order details, means for generating recommended menus based on seasons and events, means for setting the server to revisit the table after a certain period of time has elapsed since the end of the meal, means for displaying and providing voice guidance for the recommended menus upon the revisit, means for providing feedback on the customer's reaction and processing additional orders, an emotion recognition engine for acquiring customer emotion data in real time, and means for adjusting the content of the recommended menus and voice guidance based on the emotion data. This makes it possible to provide optimal service tailored to the individual needs of customers, improve customer satisfaction, and enable efficient operation in physical stores.

[1208] "Customer attribute information" refers to information that indicates the characteristics of individual customers, such as age group, gender, and allergy information.

[1209] "Order details" refers to the specific product or service selections made by the customer, including detailed information such as menu items and quantities purchased.

[1210] A "recommended menu" is a list of products and services best suited to a customer, generated based on the season, events, and the customer's past order history.

[1211] The "revisiting the table" feature allows the serving robot to revisit the table after the meal has been finished and offer additional services or products.

[1212] "Means of display and audio guidance" refers to a function that displays recommended menus on a screen and provides audio guidance to customers.

[1213] "Means for providing feedback on responses and processing additional orders" refers to a function that records and analyzes customer responses, optimizes future suggestions based on that information, and simultaneously accepts and processes additional orders.

[1214] An "emotion recognition engine" is a system that analyzes a customer's facial expressions and tone of voice to recognize their emotional state in real time.

[1215] "Means for adjusting the content of recommended menus and voice guidance" refers to a function that adaptively changes the recommended products and services, and the way they are presented, based on recognized emotion data.

[1216] This invention relates to a system that utilizes a food delivery robot to provide personalized customer service in physical stores based on customer attribute information and emotional data. Specifically, it realizes the following system configuration and operation.

[1217] System Configuration

[1218] 1. Hardware

[1219] Tablet device: Used by customers to enter attribute information upon their first visit.

[1220] Camera and microphone: Equipped on the serving robot to capture customers' facial expressions and voice tones.

[1221] Serving robots: They revisit tables and suggest products and services.

[1222] 2. Software

[1223] Server: AWS or Google Cloud Platform is used to manage customer information and order history.

[1224] Emotion Recognition Engine: Uses Microsoft Azure Cognitive Services to acquire and analyze emotion data in real time.

[1225] Machine learning model: Build a model using TensorFlow or PyTorch to generate recommended menus.

[1226] Database: Uses an RDBMS such as MySQL to manage stored data.

[1227] Program processing and explanation in natural language

[1228] 1. Recording customer attributes

[1229] The customer enters their initial attribute information on a tablet device. This information is sent to the server and stored in a MySQL database.

[1230] 2. Updating purchase history data

[1231] Each time an order is completed, its history data is sent to the server and stored in the database. This information is later used to suggest the most suitable products to the customer.

[1232] 3. Generating recommended products

[1233] Based on each customer's attribute information, purchase history, and seasonal and event information, a machine learning model generates an optimal list of recommended products. This model is built using TensorFlow or PyTorch based on historical data.

[1234] 4. Acquisition and analysis of emotional data

[1235] The serving robot's built-in camera and microphone capture the customer's facial expressions and voice tone, and perform real-time sentiment analysis using Azure Cognitive Services. This allows for the acquisition of customer sentiment data.

[1236] 5. Optimizing the proposed content

[1237] Based on emotional data, recommended menus and voice guidance are adjusted. For example, a relaxed customer will be recommended products in a friendly tone, while a dissatisfied customer will receive suggestions in a more subdued tone.

[1238] 6. Processing additional orders

[1239] When a customer selects an additional order on the touch panel, the order details are sent to the server and notified to the kitchen in a timely manner. The kitchen staff then quickly prepares the new order.

[1240] Specific example

[1241] For example, suppose a male customer in his 30s visits the store for the first time on a summer day and enters his attribute information on a tablet device. The server generates recommended menu items based on this information, and the emotion recognition engine recognizes the customer's relaxed expression. A serving robot then suggests in a friendly tone, "Would you like a cold dessert?" Examples of prompt phrases in this scenario include:

[1242] Generate a response for when the user asks, "What do you recommend today?" The user is in the summer and has a history of ordering cold desserts. Current emotion recognition indicates they are relaxed.

[1243] As described above, this system utilizes customer attribute information and real-time sentiment data to provide high-quality, personalized service.

[1244] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1245] Step 1:

[1246] The server retrieves attribute information entered by the customer on a tablet device during their first visit. The information entered on the tablet (age group, gender, allergy information, etc.) is sent to the server and stored in a MySQL database. This prepares the basic customer information needed for subsequent steps.

[1247] Step 2:

[1248] The server records customer order details. Specifically, when a customer selects an item from a menu, the order details are sent to the server. The server stores this information in a database and updates the customer's purchase history. This allows for future recommendations based on customer preferences.

[1249] Step 3:

[1250] The server takes attribute information, order history, and seasonal / event information as input to generate recommended menus. It uses machine learning models (TensorFlow or PyTorch) to generate the optimal menu. These recommended menus are customized for each customer and sent from the server to the serving robots. This enables appropriate suggestions tailored to customer needs.

[1251] Step 4:

[1252] The terminal (serving robot) uses a camera and microphone to capture the customer's facial expressions and tone of voice in real time to interact with them. This data is analyzed using Microsoft Azure Cognitive Services to obtain customer sentiment data. This sentiment data is used in the next step.

[1253] Step 5:

[1254] The terminal (serving robot) adjusts its recommended menu and voice guidance based on the emotional data it acquires. For example, if the customer is relaxed, it makes suggestions in a friendly tone, and if dissatisfaction is observed, it makes suggestions in a more subdued tone. This ensures that the optimal service is provided according to the customer's emotional state.

[1255] Step 6:

[1256] The terminal (serving robot) revisits the table and guides the customer through recommended menu items via display and voice. Based on emotional data, it then makes suggestions such as, "Would you like a cold dessert?" The system confirms whether the customer accepts the suggestion.

[1257] Step 7:

[1258] Users (customers) place additional orders using a touch panel. When a customer selects additional desserts or drinks, that information is sent to the server. The server stores the received additional order in a database and simultaneously notifies the kitchen. This ensures that additional orders are processed efficiently.

[1259] Step 8:

[1260] The server analyzes customer reactions and feedback on additional orders, updating the database to provide even better suggestions for future visits. This allows for the accumulation of data to continuously improve customer satisfaction and enable more personalized service.

[1261] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1262] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1263] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1264] [Fourth Embodiment]

[1265] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1266] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1267] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1268] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1269] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1270] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1271] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1272] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1273] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1274] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1275] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1276] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1277] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1278] This invention relates to a system for a food service robot that records customer attribute information, saves order details, generates recommended menus based on the season and events, and proposes them to customers on their return visits. The following describes a specific method for implementing this invention.

[1279] Server Processing

[1280] The server has the function of recording information entered by customers when they place their first order (such as age group, gender, and allergy information). For example, information entered via an application or tablet is stored in the database by the server. Similarly, each time a customer places an order, the details of that order (menu items, quantity, etc.) are also saved.

[1281] The server generates optimal recommended menus for customers based on the season and events. For example, in the summer it suggests cold desserts and drinks, and during the Christmas season it suggests a special Christmas menu. A machine learning model is used to generate these recommended menus. Based on past data, it automatically selects the most suitable menu items and generates a customized list for each customer.

[1282] Terminal processing

[1283] The serving robot's terminal receives customer information and recommended menu items transmitted from the server. After a certain period of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice prompts such as, "Would you like dessert?" The terminal also features a touch panel, allowing customers to enter additional orders.

[1284] User processing

[1285] The customer (user) decides whether to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they want to reject the suggestion, they can either leave it blank or press the cancel button.

[1286] Processing additional orders

[1287] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen's display. This allows cooking to begin quickly and accurately.

[1288] As described above, the system of the present invention can record customer attribute information, generate optimal recommended menus, and propose them during follow-up visits, thereby alleviating labor shortages and improving customer satisfaction and sales.

[1289] The following describes the processing flow.

[1290] Step 1:

[1291] The server records attribute information (age group, gender, allergy information, etc.) entered by the customer when they place their first order.

[1292] The server receives data sent from tablets and applications.

[1293] The server stores this data in a database and associates it with the customer ID.

[1294] Step 2:

[1295] The server saves the details of an order (menu items, quantity, etc.) each time a customer places an order.

[1296] The server records the order details in a database in JSON format.

[1297] The server tracks order history for each customer ID.

[1298] Step 3:

[1299] The server generates recommended menus based on the season, events, and past order history.

[1300] The server uses a machine learning model to execute an algorithm that selects the appropriate recommended menu.

[1301] The server creates a list of recommended menu items and saves it, associating it with the customer ID.

[1302] Step 4:

[1303] The server instructs the serving robot to revisit the table a certain amount of time after the meal has finished.

[1304] The server uses a reminder function to set a time for a return visit.

[1305] Once the timer settings are complete, the server sends that information to the robot's terminal.

[1306] Step 5:

[1307] The terminal receives a list of recommended menu items and information on when to revisit from the server.

[1308] The device prepares its display and speaker and enters a standby state for the next operation.

[1309] Step 6:

[1310] The terminal revisits the table after a set time has elapsed and displays and provides voice guidance to the customer regarding recommended menu items.

[1311] The device displays a recommended menu on its screen.

[1312] The terminal plays voice prompts such as, "Would you like dessert?"

[1313] Step 7:

[1314] The user responds to the robot's suggested menu.

[1315] Users can use the touch panel to select additional orders from the recommended menu or cancel the suggestions.

[1316] Step 8:

[1317] When the terminal receives an additional order from a user, it sends that information to the server.

[1318] The terminal sends the user's selection to the server in JSON format.

[1319] Step 9:

[1320] The server saves the received additional order to the database and notifies the kitchen.

[1321] The server creates a notification to communicate the order details to the cooking department and displays it on the kitchen display.

[1322] The above describes the specific processing of the program in this invention. This makes it possible to alleviate labor shortages while improving customer satisfaction and sales.

[1323] (Example 1)

[1324] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1325] Traditional food service systems have difficulty effectively utilizing customer attribute information and order history, limiting improvements in customer satisfaction and sales growth. Specifically, there were problems such as difficulty in providing seasonal or event-specific recommended menus and in suggesting timely additional orders. Furthermore, communication of additional orders could be time-consuming, resulting in a decline in service quality.

[1326] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1327] In this invention, the server includes means for recording customer attribute information, means for storing the customer's order details, and means for generating recommended menus based on seasons and events. This enables the suggestion of the most suitable menu for each customer, improving customer satisfaction and increasing sales.

[1328] Furthermore, the system includes means for receiving customer information and recommended menu items transmitted from the server, and means for storing received additional orders in a database and notifying the kitchen. This enables efficient service delivery and ensures that additional orders are processed quickly and accurately.

[1329] "Customer attribute information" refers to data that shows personal characteristics of customers, such as their age group, gender, and allergy information.

[1330] "Order details" refers to information indicating the menu items and quantities ordered by the customer.

[1331] "Recommended menu" refers to menu suggestions that are best suited to the customer, generated using machine learning models based on the season and events.

[1332] "Revisit" means that the serving robot will come back to the table a certain amount of time after the meal has finished.

[1333] "Voice guidance" refers to the function of the serving robot that provides suggestions and guidance via voice.

[1334] "Feedback" refers to recording customer reactions and returning that information to the system.

[1335] An "additional order" refers to a new order placed during or after a meal.

[1336] A "database" refers to a system that systematically stores data such as customer information and order details.

[1337] A "machine learning model" refers to an algorithm composed of mathematical approaches used to make predictions and classifications based on large amounts of data.

[1338] "Notifying the kitchen" means promptly informing the cooking area of ​​any additional orders that have been placed.

[1339] This invention relates to a system for a food service robot that records customer attribute information, saves order details, generates recommended menus based on the season and events, and suggests them to customers on their return visits.

[1340] Server Processing

[1341] The server has the function of recording information entered by customers when they place their first order (such as age group, gender, and allergy information). For example, information entered via a tablet device or mobile application is sent to the server as an HTTP request and then stored in a database (such as MySQL or PostgreSQL). Similarly, each time a customer places an order, its details (menu items, quantity, etc.) are also saved.

[1342] The server generates optimal recommended menus for customers based on the season and events. This uses machine learning models (for example, models using TensorFlow or PyTorch). By analyzing past data and selecting the most suitable menu items, a customized list is generated for each customer. For example, for a customer with attributes such as being a woman in her 40s with no allergies, the server might suggest a cold mango pudding and iced tea during the summer.

[1343] Example of a prompt:

[1344] "Please suggest a recommended summer dessert and drink for a female customer in her 40s who has no allergies."

[1345] Terminal processing

[1346] The serving robot's terminal receives customer information and recommended menu items sent from the server. It receives data from the server via HTTP requests and stores it in the terminal's local memory. After a certain amount of time has passed since the meal was finished, the terminal is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" The terminal also has a touch panel, allowing customers to enter additional orders.

[1347] One specific example is a robot that returns to the table 10 minutes after the meal is finished and asks, "Would you like some mango pudding and iced tea?"

[1348] Example of a prompt:

[1349] "Ten minutes after the meal ends, please suggest recommended desserts and drinks to the guests at Table 5."

[1350] User processing

[1351] The customer (user) decides whether to accept the robot's suggestion. If they accept the suggestion, they type "I would like to order an additional dessert" on the touch panel; if they reject it, they press the cancel button. Specifically, the customer might type "I would like to order an additional mango pudding" on the touch panel, or they might press the cancel button to reject the suggestion.

[1352] Processing additional orders

[1353] When the terminal receives an additional order from a customer, it sends it to the server. The additional order data is sent to the server using an HTTP request, and the server stores the received additional order in its database. It then immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" appears on the kitchen display. This allows cooking to begin quickly and accurately.

[1354] A concrete example would be a notification sent to the kitchen stating, "Table 5 has placed a new order of mango pudding and iced tea."

[1355] Example of a prompt:

[1356] "Please notify the kitchen of Table 5, who has just ordered a new dessert."

[1357] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1358] Server Processing

[1359] Step 1: Record customer attribute information

[1360] The server receives customer attribute information (age group, gender, allergy information, etc.) sent from tablet devices and mobile applications. This information arrives as an HTTP request. The server parses this request and stores it in the database as JSON data.

[1361] input:

[1362] Customer attribute information (in JSON format) sent from a tablet device.

[1363] output:

[1364] Customer attribute information stored in the database

[1365] Specific actions:

[1366] The system receives JSON-formatted requests sent from tablet devices, parses them, and saves them to the "Customer Information" table in the database.

[1367] Step 2: Save your order

[1368] The server receives customer order details (menu items, quantities, etc.) sent from tablet devices or mobile applications. The order information is also received as an HTTP request and stored in the database.

[1369] input:

[1370] Order details (in JSON format) sent from a tablet device.

[1371] output:

[1372] Order details stored in the database

[1373] Specific actions:

[1374] "Receive an order for two cold drinks from Table 5 and save it to the 'Order History' table in the database."

[1375] Step 3: Generate Recommended Menus

[1376] The server generates optimal recommended menus for customers based on seasons and events. It uses machine learning models (for example, models using TensorFlow or PyTorch) to analyze past data and select the most suitable menu.

[1377] input:

[1378] Information about seasons and events, customer attribute information and order history

[1379] output:

[1380] List of recommended menus

[1381] Specific actions:

[1382] Since it's summer, we'll run a Python script to generate recommended menus from a machine learning model to suggest cold desserts and drinks.

[1383] Terminal processing

[1384] Step 4: Receive the recommended menu

[1385] The serving robot's terminal receives customer information and recommended menu items sent from the server. It receives data from the server via HTTP requests and stores it in the terminal's local memory.

[1386] input:

[1387] Customer information and recommended menu (in JSON format) sent from the server.

[1388] output:

[1389] Customer information and recommended menus stored in local memory

[1390] Specific actions:

[1391] The recommended menu received from the server is cached in local memory and prepared for the next visit.

[1392] Step 5: Proposal for follow-up visit

[1393] After a certain amount of time has passed since the meal was finished, the terminal revisits the table. Upon revisiting, the suggested menu items are displayed on the screen, and voice guidance is also provided. The display is equipped with a touch panel, allowing customers to enter additional orders.

[1394] input:

[1395] Recommended menu saved in local memory

[1396] output:

[1397] Recommended menus and voice guidance displayed on the screen.

[1398] Specific actions:

[1399] "Ten minutes after the meal at Table 5 is finished, the robot will revisit the table and display recommended menu items on the screen, along with a voice prompt asking, 'Would you like dessert?'"

[1400] User processing

[1401] Step 6: Accept or reject the proposal

[1402] The customer (user) decides whether to accept the robot's suggestion. If they accept, they type "I would like to order dessert" on the touch panel; if they reject, they press the cancel button.

[1403] input:

[1404] Additional orders or cancellations entered via the touch panel.

[1405] output:

[1406] Additional order data or cancellation information

[1407] Specific actions:

[1408] The customer enters "I would like to order an additional mango pudding" into the touch panel, or presses the cancel button to decline the offer.

[1409] Processing additional orders

[1410] Step 7: Submit additional order

[1411] When the terminal receives an additional order from a customer, it sends it to the server. It uses an HTTP request to send the additional order data to the server.

[1412] input:

[1413] Additional orders entered via touch panel (JSON format)

[1414] output:

[1415] Additional orders sent to the server

[1416] Specific actions:

[1417] "Send mango pudding to the server as an additional order from Table 5."

[1418] Step 8: Save and notify of additional orders

[1419] The server saves the received additional order to its database and immediately notifies the kitchen. For example, it might display a message on the kitchen's display saying, "Table 5 has ordered a new dessert."

[1420] input:

[1421] Additional orders sent to the server

[1422] output:

[1423] Additional orders stored in the database, notifications to the kitchen

[1424] Specific actions:

[1425] "Save Table 5's additional order for mango pudding in the database and display 'Table 5 has ordered a new mango pudding' on the kitchen display."

[1426] (Application Example 1)

[1427] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1428] In the current food service industry, personalized menu suggestions based on individual customer preferences and past order history are rarely offered. As a result, customer satisfaction declines, and acquiring repeat customers becomes difficult. Furthermore, the lack of seasonal or event-specific menu suggestions can lead to missed sales opportunities. In addition, food delivery services lack real-time menu recommendations, making it a challenge to improve the customer experience.

[1429] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1430] In this invention, the server includes means for recording customer attribute information, means for storing the customer's order details, means for generating recommended menus based on seasons and events, and means for presenting recommended menus to the user via push notifications according to the timing of food delivery. This enables personalized menu suggestions based on customer attribute information and order history, realizing appropriate menu suggestions according to seasons and events, and real-time recommended menu guidance in food delivery services, thereby improving customer satisfaction and increasing sales.

[1431] "Means of recording customer attribute information" refers to methods for collecting personal information such as customers' age, gender, and allergy information, and storing it in a database.

[1432] "Means for saving the customer's order details" refers to means for recording the menu items and quantities ordered by the customer and saving this information in a database.

[1433] "Methods for generating recommended menus based on seasons and events" refers to methods for automatically selecting the most suitable menu for customers in accordance with seasonal changes and specific events, and generating a list of recommended menus.

[1434] "Means for setting the robot to revisit the table after a certain period of time has elapsed since the end of the meal" refers to a means for controlling the serving robot to revisit the table after a certain period of time has elapsed since the customer finished their meal.

[1435] "Means for displaying recommended menus and providing voice guidance upon a return visit" refers to means by which the serving robot displays recommended menus on a display and provides voice guidance to the customer upon a return visit.

[1436] "A method for presenting recommended menus to users via push notifications according to the timing of food delivery" refers to a method for presenting recommended menus via push notifications through a smartphone application to users of a food delivery service at the time of delivery.

[1437] "Means for providing customer feedback and processing additional orders" refers to a means of recording customer responses to suggested menu items, accepting additional orders based on those responses, and notifying the kitchen accordingly.

[1438] "Using machine learning models" refers to a method of selecting the optimal recommended menu using machine learning algorithms based on past order history and attribute information.

[1439] "Means of notifying the cooking area" refers to the means of communicating the details of an additional order to the kitchen or cooking area.

[1440] This invention relates to a system that utilizes customer attribute information and order history to generate optimal recommended menus tailored to the season and events, and proposes them to customers through serving robots or food delivery services. Specific methods for implementing this invention are described in detail below.

[1441] Server Processing

[1442] The server first collects and records customer attribute information (e.g., age, gender, allergy information, etc.). This information is entered via an application or tablet and stored in a database by the server. In addition, the customer's order history is also stored in the database.

[1443] The server generates optimal recommended menus for customers based on the season and events. This is achieved using a machine learning model (e.g., RandomForestClassifier). This model uses past order history and user preference information as training data to select the most suitable menu.

[1444] For example, during the summer months, cold desserts and drinks are recommended, and during the Christmas season, a special Christmas menu is suggested. This recommended menu is generated as a customized list for each customer.

[1445] Terminal processing

[1446] The terminal receives customer information and recommended menu items from the server and is configured to revisit the table after a certain period of time has passed since the meal was finished. Upon revisiting, the terminal displays the recommended menu items and provides voice guidance such as, "Would you like dessert?" The terminal also has a touch panel, allowing customers to enter additional orders.

[1447] Suggestions for food delivery timing

[1448] In food delivery services, recommended menu items are presented to users via push notifications through a smartphone application, depending on the delivery timing. This enables real-time menu suggestions and improves the customer experience.

[1449] User processing

[1450] The user decides whether to accept the suggestions from the robot or application. For example, they might review the suggested menu and enter "I'd like to add dessert" on the touch panel. If they wish to decline the suggestion, they can either leave the input blank or press the cancel button.

[1451] Processing additional orders

[1452] When a terminal or application receives an additional order from a customer, it sends it to the server. The server stores the received additional order in a database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen display. This allows cooking to begin quickly and accurately.

[1453] Specific example

[1454] If a user has previously ordered "pizza" and "salad," and the current season is summer, the server will generate summer-appropriate recommended menu items such as "ice cream" and "coffee." The serving robot and smartphone application will then present these recommended menu items to the user and suggest "Would you like some ice cream?" via voice guidance or push notifications.

[1455] Example of a prompt

[1456] User ID: user_1, Attributes: 25-year-old male, Allergy information: None

[1457] Past order history: Pizza, salad

[1458] Current season: Summer

[1459] Recommended menu: Ice cream, coffee

[1460] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1461] Step 1: The server collects and records user information.

[1462] The server stores customer attribute information (e.g., age, gender, allergy information, etc.) entered via applications or tablets into a database. The entered data, along with the user ID, is stored in the database. This ensures that the attributes of each individual user are recorded.

[1463] Input: Customer attribute information (age, gender, allergy information, etc.)

[1464] Output: User attribute information recorded in the database

[1465] Step 2: The server saves the order history.

[1466] When a customer places an order, the order details (e.g., menu items, quantity, etc.) are sent to the server and stored in the database. This allows for the accumulation of past order history.

[1467] Input: Order details (menu items, quantity)

[1468] Output: Order history stored in the database

[1469] Step 3: The server generates the recommended menu.

[1470] Based on seasonal and event information, the server uses a machine learning model (e.g., RandomForestClassifier) ​​to generate optimal recommended menus using past order history and user attribute information as input data.

[1471] Input: Seasonal information, event information, customer order history, attribute information

[1472] Output: Customized recommended menu list

[1473] Step 4: The server sends the recommended menu to the terminal.

[1474] The generated recommended menu is sent from the server to the terminal (serving robot or smartphone application). This allows the terminal to receive information in real time.

[1475] Input: Customized recommended menu list

[1476] Output: Recommended menu sent to the terminal

[1477] Step 5: The device will display a recommended menu and provide voice guidance.

[1478] The terminal displays the received recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?". Upon returning, users can place additional orders using the touch panel.

[1479] Input: Recommended Menu

[1480] Output: Display and voice guidance

[1481] Step 6: Send push notifications at the time of food delivery.

[1482] In the case of food delivery services, a smartphone application sends push notifications to users suggesting menu items based on the delivery timing. Through these notifications, menu suggestions are provided in real time.

[1483] Input: Recommended Menu

[1484] Output: Push notification to the user

[1485] Step 7: The user decides whether to accept the proposal.

[1486] Users view recommended menus on their devices or applications and decide whether or not to place an additional order. For example, they might type "I'd like to order dessert" on the touchscreen or application.

[1487] Input: Recommended menu guide

[1488] Output: User response (additional order or cancellation)

[1489] Step 8: The terminal sends the additional order to the server.

[1490] When a customer places an additional order, the terminal sends the order details to the server. The server records the received order in its database and notifies the kitchen in real time.

[1491] Input: Additional order details

[1492] Output: Recording of additional orders to the server and notification to the cooking area.

[1493] By implementing these steps through concrete examples, an efficient order management system utilizing food delivery services and serving robots can be built, resulting in improved customer satisfaction and increased sales.

[1494] Example of a prompt

[1495] User ID: user_1, Attributes: 25-year-old male, Allergy information: None

[1496] Past order history: Pizza, salad

[1497] Current season: Summer

[1498] Recommended menu: Ice cream, coffee

[1499] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1500] This invention relates to a system for a food service robot that combines a system for recording customer attribute information, saving order details, generating recommended menus based on seasons and events, and suggesting them upon return visits, with an emotion engine that recognizes user emotions. The following describes a specific method for carrying out this invention.

[1501] Server Processing

[1502] The server has the function of recording attribute information (age group, gender, allergy information, etc.) entered by customers when they place their first order. For example, information entered via an application or tablet is stored in the database by the server. Similarly, each time a customer places an order, its details (menu items, quantity, etc.) are also saved.

[1503] The server generates optimal menu recommendations for each customer based on the season, events, and past order history. For example, it suggests cold desserts and drinks in the summer, and a special Christmas menu during the Christmas season. A machine learning model is used to generate these recommendations. Based on past data, it automatically selects the most suitable menu items and generates a customized list for each customer.

[1504] Terminal processing

[1505] The serving robot's terminal receives customer information and recommended menu items transmitted from the server. The terminal is also equipped with an emotion engine that recognizes user emotions, allowing it to acquire emotional data in real time from the user's facial expressions and tone of voice.

[1506] After a certain amount of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" However, the content of the voice guidance can be adjusted based on the user's emotional data acquired by the emotion engine. For example, if the user is relaxed, it will make suggestions in a more friendly tone, and if the user is clearly dissatisfied, it will make suggestions in a more subdued tone. The recommended menu items are also optimized based on the emotional data.

[1507] User processing

[1508] The customer (user) decides whether to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they reject the suggestion, they can either leave it blank or press the cancel button. This emotional data is also fed back to the server and used to improve future suggestions.

[1509] Processing additional orders

[1510] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the kitchen. For example, a message such as "Table 5 has ordered a new dessert" will appear on the kitchen's display. This allows cooking to begin quickly and accurately.

[1511] Specific example

[1512] One summer day, a male customer in his 30s uses the system for the first time. Since he has never ordered before, the server generates a recommended menu based on his attribute information and the seasonal information for that day. After the meal, the serving robot revisits and suggests, "Would you like a cold dessert?" The emotion engine recognizes that the customer is looking pleased, and the robot continues in an even more friendly tone, "I recommend our special mango sorbet, available only this time of year." The user enters "I'd like to place an additional order" on the touch panel, and the order is notified to the kitchen.

[1513] As described above, the system of the present invention not only records customer attribute information, generates optimal recommended menus, and proposes them upon return visits, but also recognizes user emotions and optimizes the content of the suggestions, thereby alleviating labor shortages and improving customer satisfaction and sales.

[1514] The following describes the processing flow.

[1515] Step 1:

[1516] The server records attribute information (age group, gender, allergy information, etc.) entered by the customer when they place their first order.

[1517] The server receives data sent from tablets and applications.

[1518] The server stores this data in a database and associates it with the customer ID.

[1519] Step 2:

[1520] The server saves the details of an order (menu items, quantity, etc.) each time a customer places an order.

[1521] The server records the order details in a database in JSON format.

[1522] The server tracks order history for each customer ID.

[1523] Step 3:

[1524] The server generates recommended menus based on the season, events, and past order history.

[1525] The server uses a machine learning model to execute an algorithm that selects the appropriate recommended menu.

[1526] The server creates a list of recommended menu items and saves it, associating it with the customer ID.

[1527] Step 4:

[1528] The terminal receives a list of recommended menu items and information on when to revisit from the server.

[1529] The device prepares its display and speaker and enters a standby state for the next operation.

[1530] Step 5:

[1531] The emotion engine built into the device acquires emotional data in real time from the user's facial expressions and tone of voice.

[1532] The device uses its camera and microphone to analyze the user's facial expressions and voice using an emotion engine.

[1533] The device processes the acquired emotional data and sends it to the server.

[1534] Step 6:

[1535] The server optimizes recommended menus and voice guidance based on emotion data.

[1536] The server analyzes emotional data to determine whether the user is relaxed or stressed.

[1537] The server adjusts the recommended menu and voice guidance content and sends it to the terminal.

[1538] Step 7:

[1539] After the set time has elapsed, the terminal will revisit the table and display recommended menus and provide voice guidance.

[1540] The device displays a recommended menu on its screen.

[1541] The device plays voice prompts such as "Would you like dessert?" in an appropriate tone based on emotional data.

[1542] Step 8:

[1543] The user responds to the robot's suggested menu.

[1544] Users can use the touch panel to select additional orders from the recommended menu or cancel the suggestions.

[1545] Step 9:

[1546] When the terminal receives an additional order from a user, it sends that information to the server.

[1547] The terminal sends the user's selection to the server in JSON format.

[1548] Step 10:

[1549] The server saves the received additional order to the database and notifies the kitchen.

[1550] The server creates a notification to communicate the order details to the cooking department and displays it on the kitchen display.

[1551] The above describes the specific processing of the system that combines the emotion engine in this invention. This makes it possible to improve customer satisfaction and sales while resolving labor shortages.

[1552] (Example 2)

[1553] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1554] In today's restaurant industry, improving customer satisfaction requires providing services tailored to the individual needs of each customer. However, traditional systems have the problem of not being able to properly utilize customer attribute information and order history, resulting in only uniform service. Furthermore, it is difficult to provide individualized service based on customer emotions, making it difficult to improve the customer experience, which may lead to customer churn and decreased sales. In addition, delays in processing additional orders and notifying the kitchen can reduce the speed and accuracy of service.

[1555] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1556] In this invention, the server includes means for recording customer attribute information, means for storing order details, and means for generating recommended menus based on seasons and events. This enables optimal menu suggestions based on each customer's individual information. Furthermore, the serving robot's terminal includes means for recognizing emotions and means for adjusting the content of voice guidance based on emotion data, enabling real-time customer service. It also includes means for processing additional orders and means for notifying the cooking area, enabling the provision of quick and accurate service, thereby improving customer satisfaction and sales.

[1557] "Customer attribute information" refers to data that represents the characteristics of individual customers, such as age group, gender, and allergy information.

[1558] "Order details" refers to information indicating the menu items and quantities selected by the customer.

[1559] A "recommended menu" is a list of the best menu items suggested to a customer based on the season, events, customer attribute information, and order history.

[1560] "Revisit" refers to the serving robot returning to the table after a certain amount of time has passed since the meal was finished.

[1561] The "emotion engine" is a system that analyzes a customer's facial expressions and tone of voice to recognize their emotional state at that time.

[1562] "Voice guidance" refers to the service robot providing menu suggestions and other information to customers via voice.

[1563] "Feedback" is the process of sending customer reactions and emotional data to a server to help improve future services.

[1564] An "additional order" refers to an order placed by a customer after their initial order.

[1565] A "machine learning model" is a system composed of algorithms that analyze past data to make suggestions or predictions about the future.

[1566] The "cooking area" is the area in a restaurant where food is prepared and cooked.

[1567] The present invention combines a food service robot system that records customer attribute information, saves order details, generates recommended menus based on seasons and events, and suggests them on return visits, with an emotion engine that recognizes user emotions. The specific methods for implementing the present invention are described below.

[1568] Server Processing

[1569] The server has a function to record attribute information (age group, gender, allergy information, etc.) entered by customers when they place their first order. For example, information entered via input devices such as tablets is stored in the database by the server. Database software used includes MySQL and PostgreSQL. In addition, each time a customer places an order, the details of that order (menu items, quantity, etc.) are also saved. The order details are used to analyze customers' food selection trends.

[1570] Furthermore, the server can use machine learning models (TensorFlow or PyTorch) to generate optimal menu recommendations for customers based on the season, events, and past order history. For example, it might suggest "cold desserts" and "cold drinks" in the summer, or a special "Christmas menu" during the Christmas season. In this way, it becomes possible to suggest menus that meet the individual needs of each customer.

[1571] Terminal processing

[1572] The food delivery robot's terminal has the function of receiving customer information and recommended menus transmitted from the server. The terminal is equipped with an emotion engine that recognizes the user's emotions and can acquire emotion data in real time from the user's facial expressions and tone of voice.

[1573] After a certain amount of time has passed since the meal was finished, the robot is programmed to revisit the table. Upon revisiting, it displays recommended menu items on its screen and provides voice guidance such as, "Would you like dessert?" At this time, the content of the voice guidance can be adjusted based on the user's emotional data acquired by the emotion engine. For example, if the user is relaxed, it will make suggestions in a more friendly tone, and if the user is clearly dissatisfied, it will make suggestions in a more subdued tone. The recommended menu items are also optimized based on the emotional data.

[1574] User processing

[1575] Customers (users) decide whether or not to accept the robot's suggestion. For example, they might look at the suggested menu and enter "I'd like to add dessert" on the touch panel. If they want to reject the suggestion, they can either leave it blank or press the cancel button. This emotional data is also fed back to the server and may be reflected in future suggestions.

[1576] Processing additional orders

[1577] When the terminal receives an additional order from a customer, it sends it to the server. The server stores the received additional order in its database and immediately notifies the cooking area. For example, a message such as "Table 5 has ordered a new dessert" is displayed on the cooking area's screen. This allows cooking to begin quickly and accurately.

[1578] Specific example

[1579] For example, consider a scenario where a male customer in his 30s uses the system for the first time on a summer day. When this customer enters his age group, gender, allergy information, etc., into a tablet, that information is immediately sent to and stored on the server. Next, when he orders food, the order details are also stored on the server. After the meal, the serving robot revisits and suggests, "Would you like a cold dessert?" The emotion engine recognizes that the customer has a positive expression and continues in a friendly tone, "We recommend our special mango sorbet, available only this season." The customer enters "I'd like to order more" on the touch panel, the order is sent to the server, and a notification is sent to the cooking area.

[1580] Example of a prompt

[1581] The following are examples of prompts to input into the generating AI model.

[1582] "Please describe a system for serving robots that suggests cold desserts on a summer day."

[1583] As described above, the system of the present invention not only records customer attribute information, generates optimal recommended menus, and proposes them upon return visits, but also recognizes user emotions and optimizes the suggested content, thereby improving customer satisfaction and sales.

[1584] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1585] Step 1:

[1586] The server receives customer attribute information (age group, gender, allergy information, etc.) entered via a tablet. The data entered is provided by the user. The server uses database software (e.g., MySQL, PostgreSQL) to store this information in a database.

[1587] Input: Customer attribute information

[1588] Output: Database containing attribute information

[1589] Step 2:

[1590] The server receives the order details (menu items, quantities, etc.) entered by the user. The entered data represents the order details based on the user's selections. The server saves this data to a database, thereby maintaining a record of the order.

[1591] Input: User's order details

[1592] Output: Database where order details are stored

[1593] Step 3:

[1594] The server uses machine learning models (e.g., TensorFlow, PyTorch) to generate recommended menus based on stored attribute information, order history, and seasonal and event information. Past order history and attribute information are used as input data, and customized recommended menus are generated as output.

[1595] Input: Attribute information, order history, seasonal information, event information

[1596] Output: Customized recommended menu

[1597] Step 4:

[1598] The server sends the generated recommended menu to the serving robot's terminal. This provides the terminal with the information it needs for the next step.

[1599] Input: Customized Recommended Menu

[1600] Output: Recommended menu sent to the terminal

[1601] Step 5:

[1602] The device prepares to display recommended menus received from the server. It also starts an emotion engine to recognize the user's emotions, acquiring emotional data from the user's facial expressions and tone of voice.

[1603] Input: Recommended Menu

[1604] Output: Sentiment data acquired in real time

[1605] Step 6:

[1606] After a certain amount of time has passed since the meal was finished, the robot revisits the table and displays recommended menu items on its screen. At the same time, it provides voice guidance such as, "Would you like dessert?" An emotion engine analyzes the user's emotional data in real time and adjusts the content and tone of the voice guidance based on that data.

[1607] Input: Acquired sentiment data, recommended menu

[1608] Output: Emotion-based voice guidance, display

[1609] Step 7:

[1610] The user decides whether to accept the robot's suggestion via a touch panel. For example, they might input, "I'd like to order an additional dessert." The entered order data is then sent to the server by the terminal.

[1611] Input: User's additional order details

[1612] Output: Additional order data sent to the server

[1613] Step 8:

[1614] The server saves the received additional order to the database and immediately notifies the cooking area. In the cooking area, a message such as "Table 5 has ordered a new dessert" is displayed on the screen. This allows cooking to begin quickly and accurately.

[1615] Input: Additional order data

[1616] Output: Additional orders saved in the database, notifications to the cooking area.

[1617] In this way, by explaining the specific actions performed at each step and the flow of their processing, it is clearly demonstrated how the system of the present invention functions.

[1618] (Application Example 2)

[1619] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1620] Conventional food delivery robot systems were unable to provide individually optimized suggestions based on customer attribute information and order history, nor could they recognize customer emotions and adjust suggestions in real time, making it difficult to improve customer satisfaction. In particular, brick-and-mortar stores are required to provide services that meet the individual needs of each customer, and maintaining high service quality efficiently amidst labor shortages has been a challenge.

[1621] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording customer attribute information, means for saving the customer's order details, means for generating recommended menus based on seasons and events, means for setting the server to revisit the table after a certain period of time has elapsed since the end of the meal, means for displaying and providing voice guidance for the recommended menus upon the revisit, means for providing feedback on the customer's reaction and processing additional orders, an emotion recognition engine for acquiring customer emotion data in real time, and means for adjusting the content of the recommended menus and voice guidance based on the emotion data. This makes it possible to provide optimal service tailored to the individual needs of customers, improve customer satisfaction, and enable efficient operation in physical stores.

[1622] "Customer attribute information" refers to information that indicates the characteristics of individual customers, such as age group, gender, and allergy information.

[1623] "Order details" refers to the specific product or service selections made by the customer, including detailed information such as menu items and quantities purchased.

[1624] A "recommended menu" is a list of products and services best suited to a customer, generated based on the season, events, and the customer's past order history.

[1625] The "revisiting the table" feature allows the serving robot to revisit the table after the meal has been finished and offer additional services or products.

[1626] "Means of display and audio guidance" refers to a function that displays recommended menus on a screen and provides audio guidance to customers.

[1627] "Means for providing feedback on responses and processing additional orders" refers to a function that records and analyzes customer responses, optimizes future suggestions based on that information, and simultaneously accepts and processes additional orders.

[1628] An "emotion recognition engine" is a system that analyzes a customer's facial expressions and tone of voice to recognize their emotional state in real time.

[1629] "Means for adjusting the content of recommended menus and voice guidance" refers to a function that adaptively changes the recommended products and services, and the way they are presented, based on recognized emotion data.

[1630] This invention relates to a system that utilizes a food delivery robot to provide personalized customer service in physical stores based on customer attribute information and emotional data. Specifically, it realizes the following system configuration and operation.

[1631] System Configuration

[1632] 1. Hardware

[1633] Tablet device: Used by customers to enter attribute information upon their first visit.

[1634] Camera and microphone: Equipped on the serving robot to capture customers' facial expressions and voice tones.

[1635] Serving robots: They revisit tables and suggest products and services.

[1636] 2. Software

[1637] Server: AWS or Google Cloud Platform is used to manage customer information and order history.

[1638] Emotion Recognition Engine: Uses Microsoft Azure Cognitive Services to acquire and analyze emotion data in real time.

[1639] Machine learning model: Build a model using TensorFlow or PyTorch to generate recommended menus.

[1640] Database: Uses an RDBMS such as MySQL to manage stored data.

[1641] Program processing and explanation in natural language

[1642] 1. Recording customer attributes

[1643] The customer enters their initial attribute information on a tablet device. This information is sent to the server and stored in a MySQL database.

[1644] 2. Updating purchase history data

[1645] Each time an order is completed, its history data is sent to the server and stored in the database. This information is later used to suggest the most suitable products to the customer.

[1646] 3. Generating recommended products

[1647] Based on each customer's attribute information, purchase history, and seasonal and event information, a machine learning model generates an optimal list of recommended products. This model is built using TensorFlow or PyTorch based on historical data.

[1648] 4. Acquisition and analysis of emotional data

[1649] The serving robot's built-in camera and microphone capture the customer's facial expressions and voice tone, and perform real-time sentiment analysis using Azure Cognitive Services. This allows for the acquisition of customer sentiment data.

[1650] 5. Optimizing the proposed content

[1651] Based on emotional data, recommended menus and voice guidance are adjusted. For example, a relaxed customer will be recommended products in a friendly tone, while a dissatisfied customer will receive suggestions in a more subdued tone.

[1652] 6. Processing additional orders

[1653] When a customer selects an additional order on the touch panel, the order details are sent to the server and notified to the kitchen in a timely manner. The kitchen staff then quickly prepares the new order.

[1654] Specific example

[1655] For example, suppose a male customer in his 30s visits the store for the first time on a summer day and enters his attribute information on a tablet device. The server generates recommended menu items based on this information, and the emotion recognition engine recognizes the customer's relaxed expression. A serving robot then suggests in a friendly tone, "Would you like a cold dessert?" Examples of prompt phrases in this scenario include:

[1656] Generate a response for when the user asks, "What do you recommend today?" The user is in the summer and has a history of ordering cold desserts. Current emotion recognition indicates they are relaxed.

[1657] As described above, this system utilizes customer attribute information and real-time sentiment data to provide high-quality, personalized service.

[1658] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1659] Step 1:

[1660] The server retrieves attribute information entered by the customer on a tablet device during their first visit. The information entered on the tablet (age group, gender, allergy information, etc.) is sent to the server and stored in a MySQL database. This prepares the basic customer information needed for subsequent steps.

[1661] Step 2:

[1662] The server records customer order details. Specifically, when a customer selects an item from a menu, the order details are sent to the server. The server stores this information in a database and updates the customer's purchase history. This allows for future recommendations based on customer preferences.

[1663] Step 3:

[1664] The server takes attribute information, order history, and seasonal / event information as input to generate recommended menus. It uses machine learning models (TensorFlow or PyTorch) to generate the optimal menu. These recommended menus are customized for each customer and sent from the server to the serving robots. This enables appropriate suggestions tailored to customer needs.

[1665] Step 4:

[1666] The terminal (serving robot) uses a camera and microphone to capture the customer's facial expressions and tone of voice in real time to interact with them. This data is analyzed using Microsoft Azure Cognitive Services to obtain customer sentiment data. This sentiment data is used in the next step.

[1667] Step 5:

[1668] The terminal (serving robot) adjusts its recommended menu and voice guidance based on the emotional data it acquires. For example, if the customer is relaxed, it makes suggestions in a friendly tone, and if dissatisfaction is observed, it makes suggestions in a more subdued tone. This ensures that the optimal service is provided according to the customer's emotional state.

[1669] Step 6:

[1670] The terminal (serving robot) revisits the table and guides the customer through recommended menu items via display and voice. Based on emotional data, it then makes suggestions such as, "Would you like a cold dessert?" The system confirms whether the customer accepts the suggestion.

[1671] Step 7:

[1672] Users (customers) place additional orders using a touch panel. When a customer selects additional desserts or drinks, that information is sent to the server. The server stores the received additional order in a database and simultaneously notifies the kitchen. This ensures that additional orders are processed efficiently.

[1673] Step 8:

[1674] The server analyzes customer reactions and feedback on additional orders, updating the database to provide even better suggestions for future visits. This allows for the accumulation of data to continuously improve customer satisfaction and enable more personalized service.

[1675] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1676] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1677] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1678] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1679] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1680] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1681] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1682] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1683] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1684] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1685] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1686] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1687] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1688] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1689] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1690] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1691] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1692] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1693] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1694] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1695] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1696] The following is further disclosed regarding the embodiments described above.

[1697] (Claim 1)

[1698] Means for recording customer attribute information,

[1699] A means for saving the customer's order details,

[1700] A means of generating recommended menus based on the season and events,

[1701] A means of setting the system to revisit the table after a certain amount of time has passed since the end of the meal,

[1702] A means for displaying and providing voice guidance on recommended menus during the aforementioned return visit,

[1703] A means of receiving customer feedback and processing additional orders,

[1704] A system that includes this.

[1705] (Claim 2)

[1706] The system according to claim 1, further comprising means for using a machine learning model to generate recommended menus.

[1707] (Claim 3)

[1708] The system according to claim 1, further comprising means for notifying the kitchen of the details of an additional order when an additional order is placed.

[1709] "Example 1"

[1710] (Claim 1)

[1711] Means for recording customer attribute information,

[1712] A means for saving the customer's order details,

[1713] A means of generating recommended menus based on the season and events,

[1714] A means of setting the system to revisit the table after a certain amount of time has passed since the end of the meal,

[1715] A means for displaying and providing voice guidance on recommended menus during the aforementioned return visit,

[1716] A means of receiving customer feedback and processing additional orders,

[1717] A means of receiving customer information and recommended menus sent from the server,

[1718] A means of saving received additional orders to a database and notifying the kitchen,

[1719] A system that includes this.

[1720] (Claim 2)

[1721] The system according to claim 1, further comprising means for using a machine learning model to generate recommended menus.

[1722] (Claim 3)

[1723] The system according to claim 1, further comprising means for notifying the kitchen of the details of an additional order when an additional order is placed.

[1724] "Application Example 1"

[1725] (Claim 1)

[1726] Means for recording customer attribute information,

[1727] A means for saving the customer's order details,

[1728] A means of generating recommended menus based on the season and events,

[1729] A means of setting the system to revisit the table after a certain amount of time has passed since the end of the meal,

[1730] A means for displaying and providing voice guidance on recommended menus during the aforementioned return visit,

[1731] A method to present recommended menu items to users via push notifications depending on the timing of food delivery,

[1732] A means of receiving customer feedback and processing additional orders,

[1733] A system that includes this.

[1734] (Claim 2)

[1735] The system according to claim 1, further comprising means for using a machine learning model to generate recommended menus.

[1736] (Claim 3)

[1737] The system according to claim 1, further comprising means for notifying the cooking area of ​​the details of an additional order when an additional order is placed.

[1738] "Example 2 of combining an emotion engine"

[1739] (Claim 1)

[1740] Means for recording customer attribute information,

[1741] A means for saving the customer's order details,

[1742] A means of generating recommended menus based on the season and events,

[1743] A means of setting the system to revisit the table after a certain amount of time has passed since the end of the meal,

[1744] A means for displaying and providing voice guidance on recommended menus during the aforementioned return visit,

[1745] Means of recognizing customer emotions,

[1746] Means for adjusting the content of voice guidance based on the aforementioned emotion data,

[1747] A means of receiving customer feedback and processing additional orders,

[1748] A system that includes this.

[1749] (Claim 2)

[1750] The system according to claim 1, further comprising means for using a machine learning model to generate recommended menus.

[1751] (Claim 3)

[1752] The system according to claim 1, further comprising means for notifying the cooking area of ​​the details of an additional order when an additional order is placed.

[1753] "Application example 2 when combining with an emotional engine"

[1754] (Claim 1)

[1755] Means for recording customer attribute information,

[1756] A means for saving the customer's order details,

[1757] A means of generating recommended menus based on the season and events,

[1758] A means of setting the system to revisit the table after a certain amount of time has passed since the end of the meal,

[1759] A means for displaying and providing voice guidance on recommended menus during the aforementioned return visit,

[1760] A means of receiving customer feedback and processing additional orders,

[1761] An emotion recognition engine that acquires customer emotion data in real time,

[1762] Means for adjusting the content of recommended menus and voice guidance based on the aforementioned emotion data,

[1763] A system that includes this.

[1764] (Claim 2)

[1765] The system according to claim 1, further comprising means for using a machine learning model to generate recommended menus.

[1766] (Claim 3)

[1767] The system according to claim 1, further comprising means for notifying the kitchen of the details of an additional order when an additional order is placed. [Explanation of Symbols]

[1768] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for recording customer attribute information, A means for saving the customer's order details, A means of generating recommended menus based on the season and events, A means of setting the system to revisit the table after a certain amount of time has passed since the end of the meal, A means for displaying and providing voice guidance on recommended menus during the aforementioned return visit, A means of receiving customer feedback and processing additional orders, A system that includes this.

2. The system according to claim 1, further comprising means for using a machine learning model to generate recommended menus.

3. The system according to claim 1, further comprising means for notifying the kitchen of the details of an additional order when an additional order is placed.

Images