System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting local food culture, fashion trend, and seasonal food ingredient data from area information; means for acquiring customer attributes and customer health condition data; menu generation means including a generation model for proposing menu candidates generated based on the collected data; and means for reviewing the proposed menu candidates and selecting an optimal menu.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The food truck industry is currently saturated with intensifying competition. While there are many customers, it is difficult to select menus that suit each customer's health condition and preferences, which has led to sluggish sales. Furthermore, because the optimal menu varies depending on the region and customer demographic, a standardized menu often cannot meet demand. Furthermore, rapid order processing, sales analysis, service improvement, and effective marketing are also challenges. [Means for solving the problem]

[0005] This invention provides a system for mobile food trucks, or food service establishments, that utilizes a generative model to generate optimal menus based on area information, customer attributes, health status, and trend data. Specifically, the system collects food culture and trend data from area information and acquires customer attribute and health status data. The system then uses the generative model to propose optimal menu options and interacts with customers via their terminals to take their orders. Furthermore, the system analyzes sales trends based on payment data, and analyzes reviews and feedback to identify areas for service improvement. Finally, it generates a catchphrase and logo and formulates a marketing strategy. This allows food trucks to provide customized menus tailored to customer needs and differentiate themselves from other establishments.

[0006] "Area information" refers to information that indicates the characteristics unique to a particular area, such as the food culture, popular trends, and seasonal food ingredients in that area.

[0007] "Customer attributes" refers to basic profile information such as a customer's age, gender, occupation, and residential area.

[0008] "Health data" refers to health-related information such as a customer's allergies, diet information, and specific illnesses.

[0009] A "generative model" refers to an artificial intelligence algorithm or machine learning model that generates optimal menu options based on collected data.

[0010] The "menu generation means" is a system function that generates appropriate menu options based on collected area information, customer attributes, and health status data.

[0011] A "voice recognition system" is a technology that converts a customer's voice into text.

[0012] "Data analysis means" refers to the system's functionality for analyzing collected data and identifying patterns and trends.

[0013] "Feedback analysis means" is a system function that analyzes reviews and feedback from customers and identifies areas for improvement.

[0014] "Marketing analysis means" refers to the system's function for analyzing collected marketing data and generating optimal marketing strategies.

[0015] A "dashboard" is an interface for visually displaying important information such as analysis results.

[0016] The "operations team" refers to the staff responsible for operating and managing the food truck.

[0017] "Speech-input text" refers to character string data converted from speech through a speech recognition system. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a system that provides comprehensive support for a mobile food truck (a food truck) from menu development to order processing, sales analysis, service improvement, and marketing. Below, we will explain the outline of this system and each processing step in detail.

[0040] System Overview

[0041] This system operates based on communication between a server, terminals, and users. The server is responsible for key functions such as data collection, menu creation, sales analysis, feedback analysis, and marketing support. The terminals are devices inside the food truck that interact with customers and process orders. The users are the customers and operations team that use the system.

[0042] Menu Development

[0043] server:

[0044] Area information such as local food culture, popular trends, and seasonal food ingredient data is collected from an external API, and customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) are obtained from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[0045] Examples:

[0046] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[0047] Automated ordering system

[0048] Device:

[0049] The terminal receives voice input from the customer and converts it to text using a speech recognition system. It analyzes the customer's order and creates an order list using a generative model. It collects additional customer information (e.g., spiciness preference or allergies), verifies it, and then sends the final order to a staff member.

[0050] Examples:

[0051] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[0052] Sales Analysis

[0053] server:

[0054] All payment data is collected and stored, and data analysis algorithms are used to identify sales trends, peak times, popular menu items, etc. The analysis results are visualized and displayed on a dashboard, and the operations team is notified.

[0055] Examples:

[0056] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[0057] improvement

[0058] server:

[0059] It collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and suggests specific improvement measures.

[0060] Examples:

[0061] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[0062] marketing

[0063] server:

[0064] Collect customer purchasing patterns and segment information, and use generative models to generate taglines and logo designs. The final materials are presented to the operations team for use in marketing activities.

[0065] Examples:

[0066] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[0067] This system allows food trucks to provide menus tailored to customer needs, process orders quickly and efficiently, analyze sales, improve services through feedback, and conduct effective marketing. In this way, the present invention aims to improve the competitiveness of the food truck industry.

[0068] The processing flow will be explained below.

[0069] Menu Development

[0070] Step 1:

[0071] The server collects area information such as local food culture, popular trends, and seasonal food ingredient data from external APIs.

[0072] Step 2:

[0073] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) from the database.

[0074] Step 3:

[0075] The server acquires the customer's health condition data (allergy information, diet information, etc.).

[0076] Step 4:

[0077] The server inputs the collected data into a generative model to generate optimal menu candidates.

[0078] Step 5:

[0079] The server transmits the generated menu candidates to the terminal as a proposal list.

[0080] Automated ordering system

[0081] Step 1:

[0082] The terminal automatically launches the dialogue system when the customer arrives.

[0083] Step 2:

[0084] The user enters the order by voice.

[0085] Step 3:

[0086] The terminal converts the voice input into text using a voice recognition system.

[0087] Step 4:

[0088] The server parses the customer's order text to understand the order contents.

[0089] Step 5:

[0090] The server uses the generative model to create the order list.

[0091] Step 6:

[0092] The terminal collects additional information from the customer (spiciness adjustment, allergies, etc.) and confirms the final order.

[0093] Step 7:

[0094] The terminal transmits the final order information to the kitchen staff.

[0095] Sales Analysis

[0096] Step 1:

[0097] The server collects all payment data and stores it in a database.

[0098] Step 2:

[0099] The server uses data analysis algorithms to identify sales trends, peak times, popular menu items, and more.

[0100] Step 3:

[0101] The server visualizes the analysis results and displays them on a dashboard.

[0102] Step 4:

[0103] The server notifies the operation team of the analysis results.

[0104] improvement

[0105] Step 1:

[0106] The server collects reviews and feedback from customers and stores them in a database.

[0107] Step 2:

[0108] The server uses a feedback analysis algorithm to classify positive and negative feedback.

[0109] Step 3:

[0110] The server generates specific improvement measures based on the analysis results.

[0111] Step 4:

[0112] The server notifies the operations team of the remedial measures.

[0113] marketing

[0114] Step 1:

[0115] The server collects customer buying patterns and segment information.

[0116] Step 2:

[0117] The server generates a catchphrase using the generative model.

[0118] Step 3:

[0119] The server designs the logo using an image generation model.

[0120] Step 4:

[0121] The server proposes the generated slogans and logos to the operations team.

[0122] Step 5:

[0123] The operations team will use the proposed tagline and logo in their marketing activities.

[0124] Through these steps, food trucks can provide the best menu to meet customer needs, process orders efficiently, analyze sales trends, improve services based on feedback, and implement effective marketing strategies.

[0125] Example 1

[0126] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0127] In traditional restaurant operations, each process, from menu development to order processing, sales analysis, feedback analysis, and marketing, is managed separately, making it difficult to efficiently utilize data.In addition, it is difficult to quickly respond to diverse customer needs, limiting the improvement of service quality and efficiency.

[0128] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0129] In this invention, the server includes: means for collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attribute and health condition data; menu generation means including a generative model that proposes menu candidates based on the collected data; means for reviewing the proposed menu candidates and selecting the optimal menu; means for collecting payment data and saving it in a database; means for analyzing sales trends based on the saved payment data; and means for displaying the analysis results on a dashboard and notifying the operations team. This enables consistent data management and utilization in the food truck, enabling menu development that meets customer needs, efficient order processing, precise sales analysis, appropriate service improvements, and effective marketing.

[0130] "Area information" refers to data on food culture, popular trends, and seasonal ingredients in a specific region.

[0131] "Customer attributes" refers to personal information such as a customer's age, gender, occupation, and residential area.

[0132] "Customer health data" refers to data related to the customer's health, such as allergy information and diet information.

[0133] A "generative model" refers to an algorithm or program that generates optimal menu options based on collected data.

[0134] "Menu generator" refers to a tool or system that uses collected data to generate menu options.

[0135] "Review" refers to the process of evaluating proposed menu options and selecting the most suitable menu.

[0136] "Payment Data" means information relating to the payment made by a Customer at the time of purchase.

[0137] "Database" refers to a system for storing and managing collected data.

[0138] "Sales trends" refers to the sales patterns and sales trends of a product over a certain period of time.

[0139] "Analysis tools" refer to methods and tools used to analyze collected data.

[0140] "Dashboard" refers to an interface that visually displays analysis results.

[0141] An "operations team" refers to the group of staff who operate and manage the food truck.

[0142] This invention is a system that provides comprehensive support for mobile food trucks, from menu development to order processing, sales analysis, service improvement, and marketing. This system operates based on communication between a server, terminals, and users.

[0143] Menu Development

[0144] server:

[0145] The server collects area information such as local food culture, popular trends, and seasonal food data from an external API. It also obtains customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[0146] Examples:

[0147] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[0148] Automated ordering system

[0149] Device:

[0150] The terminal receives voice input from the customer and converts it to text using a speech recognition system. For example, it can use a speech recognition library such as IBM Watson. It analyzes the customer's order and creates an order list using a generative model. It collects additional customer information (such as spiciness preferences or allergies), verifies it, and then sends the final order to a staff member.

[0151] Examples:

[0152] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[0153] Sales Analysis

[0154] server:

[0155] The server collects and stores all payment data and stores it in a secure database, such as an AWS RDS database. Based on the stored data, data analysis algorithms are used to identify sales trends, peak times, popular menu items, and more. The analysis results are visualized and displayed on a dashboard, allowing the operations team to understand sales status in real time and develop strategies.

[0156] Examples:

[0157] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[0158] Service Improvement

[0159] server:

[0160] The server collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and then suggests specific improvement measures based on the classified feedback.

[0161] Examples:

[0162] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[0163] marketing

[0164] server:

[0165] The server collects customer purchasing patterns and segment information, and uses generative models to generate catchphrases and logo designs. The generated materials are then proposed to the operations team for use in marketing activities.

[0166] Examples:

[0167] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[0168] Examples of prompt statements

[0169] "What prompts can you give to a generative AI model that will suggest high-protein, low-calorie meals for a businessman in his 30s?"

[0170] "What is the program prompt that proposes specific measures to improve waiting times at food trucks?"

[0171] This system allows food trucks to provide menus tailored to customer needs, process orders quickly and efficiently, analyze sales, improve services through feedback, and conduct effective marketing. In this way, the present invention aims to improve the competitiveness of the food truck industry.

[0172] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0173] Menu Development

[0174] server:

[0175] Step 1: Collect and enter area data

[0176] The server collects data on food culture, popular trends, and seasonal ingredients for a specific region using an external API (e.g., Google Places API). This area data is provided to the server as input.

[0177] Step 2: Collect and enter customer data

[0178] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) from the database. This customer data is also provided to the server as input.

[0179] Step 3: Data analysis

[0180] The server then runs the collected location and customer data through an analytical algorithm, where the data is cross-referenced to identify ingredient and menu trends for specific customer segments. The output of the data analysis is statistical data and trend analysis reports reflecting customer preferences.

[0181] Step 4: Generate the menu

[0182] The server uses a generative AI model based on the analysis results to generate multiple menu options. The input is the analysis result data, and the output is a list of menus created by machine learning. This menu list is optimized based on area and customer information.

[0183] Step 5: Submit your proposal list

[0184] The generated menu candidates are sent to the terminal as a suggestion list. The input is the generated menu list, and the output is the suggestion list sent to the terminal.

[0185] Specific working example:

[0186] "The server collects data on business districts, generates high-protein, low-calorie menus for businessmen in their 30s, and sends the list of suggestions to the terminal."

[0187] Automated ordering system

[0188] Device:

[0189] Step 1: Receiving voice input

[0190] The terminal receives voice input from the customer through a microphone, which provides input to a voice recognition system.

[0191] Step 2: Voice Recognition

[0192] The terminal uses a speech recognition system (e.g., IBM Watson) to convert speech to text. The input to this process is the customer's voice data, and the output is the converted text data.

[0193] Step 3: Order Analysis

[0194] The terminal analyzes the converted text data and creates an order list using a generative AI model. The input is the voice text data, and the output is the analyzed order list.

[0195] Step 4: Gather additional information

[0196] The terminal collects additional information from the customer (such as spiciness adjustment or allergies) and reflects it in the order list. The input is text data of the additional information, and the output is the final order list.

[0197] Step 5: Submit your final order

[0198] The final order details are sent from the terminal to the staff. The input is the confirmed order list, and the output is the order data sent to the staff.

[0199] Specific working example:

[0200] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[0201] Sales Analysis

[0202] server:

[0203] Step 1: Collect payment data

[0204] The server collects payment data in real time, with the input being each customer's transaction data and the output being the collected payment data.

[0205] Step 2: Save your data

[0206] The collected payment data is stored in a secure database, such as an AWS RDS database. The input is the payment data and the output is the data stored in the database.

[0207] Step 3: Data analysis

[0208] The server analyzes the stored payment data to identify sales trends, peak times, popular menu items, etc. The input is the stored payment data, and the output is a report of the analysis results.

[0209] Step 4: Visualize and communicate results

[0210] The analysis results are visualized and displayed on a dashboard, and the results are then notified to the operations team. The input is the analysis result data, and the output is the dashboard displayed as graphs and tables, along with notification messages.

[0211] Specific working example:

[0212] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[0213] Service Improvement

[0214] server:

[0215] Step 1: Gather feedback

[0216] The server collects reviews and feedback from customers. The input is customer review and feedback data, and the output is the collected feedback.

[0217] Step 2: Save your data

[0218] The collected feedback data is stored in a secure database. The input is the feedback data and the output is the data stored in the database.

[0219] Step 3: Feedback analysis

[0220] The server classifies the feedback data using an analysis algorithm, where the input is the stored feedback data and the output is the classification of positive and negative feedback.

[0221] Step 4: Propose improvement measures

[0222] Based on the classified feedback, specific improvement measures are proposed. The input is the classification result data, and the output is a list of proposed improvement measures.

[0223] Specific working example:

[0224] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[0225] marketing

[0226] server:

[0227] Step 1: Collect purchasing patterns

[0228] The server collects customer purchasing patterns and segment information. The input is purchasing data, and the output is the collected purchasing pattern data.

[0229] Step 2: Data analysis and generation

[0230] The server uses a generative AI model to generate taglines and logo designs. The input is purchasing pattern data, and the output is generated marketing materials.

[0231] Step 3: Propose materials

[0232] The generated catchphrases and logo designs are then proposed to the operations team. The input is the generated marketing materials, and the output is the proposed design data.

[0233] Specific working example:

[0234] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[0235] By implementing the above processing steps, the food truck will be able to develop menus that meet customer needs, process orders efficiently, perform precise sales analysis, make appropriate service improvements, and carry out effective marketing.

[0236] (Application example 1)

[0237] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0238] When operating a food truck, it is difficult to comprehensively manage each process, including menu development, order processing, sales analysis, service improvement, and marketing. Furthermore, to operate efficiently while meeting diverse customer needs, a system capable of analyzing data in real time and responding quickly is required. Conventional methods lack the means to centrally manage these processes and respond quickly, making it difficult to improve operational efficiency and customer satisfaction.

[0239] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0240] In this invention, the server includes: means for collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attributes and health condition data; menu generation means including a generative model that proposes menu candidates based on the collected data; means for reviewing the proposed menu candidates and selecting the optimal menu; means for analyzing customer purchasing trends and generating slogans and logo designs; means for converting user voice input into text using a voice recognition system; and means for visualizing vending operations on a dashboard in conjunction with the analysis results. This enables comprehensive management of each process in the operation of a food truck, from menu development to order processing, sales analysis, service improvement, and marketing, and enables quick and efficient response.

[0241] "Area Information" means information about a specific geographic area, such as local food culture, popular trends, and seasonal food data.

[0242] "Customer attributes" refers to basic attribute data about individual customers, such as age, gender, occupation, and residential area.

[0243] "Customer health data" refers to data relating to a customer's health, such as allergy information and diet information.

[0244] A "generative model" refers to an algorithm or system that generates optimal menu options, order details, catchphrases, logo designs, etc. based on collected data.

[0245] "Menu Generation Means" means a system or algorithm for suggesting menu options generated based on collected or acquired data.

[0246] "Speech recognition system" refers to techniques and devices for converting a user's voice input into text.

[0247] "Database" refers to a system or structure that stores collected payment data, customer attribute data, etc., and allows for later analysis, search, reference, and updating.

[0248] "Dashboard" means a display interface that visualizes analysis results and enables users or operations teams to understand the situation in real time.

[0249] "Operations team" refers to the group of staff and personnel who operate and manage the food truck or food delivery service.

[0250] "Automated vending" refers to the process of linking order processing with sales results and managing sales in real time.

[0251] Overall overview

[0252] This invention is a system that comprehensively supports menu development, order processing, sales analysis, service improvement, and marketing in the operation of food trucks and food delivery services. This system operates based on communication between a server, terminals, and users. Each processing step is explained in detail below.

[0253] Server Processing

[0254] Data collection

[0255] The server uses external APIs to collect area information, such as local food culture, popular trends, and seasonal food ingredients. It also obtains customer attributes and health status data (allergy information, diet information, etc.) from the database.

[0256] Menu generation

[0257] Based on the collected data, the server uses a generative model to generate optimal menu options. For example, it can suggest high-protein, low-calorie menus for businessmen in their 30s. The generated menus are sent to the device.

[0258] Sales Analysis

[0259] The server collects all payment data and stores it in a database. Based on the collected payment data, data analysis algorithms are used to identify sales trends, peak times, and popular menu items. The analysis results are visualized on a dashboard and notified to the operations team.

[0260] Improvement and marketing support

[0261] The server collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and proposes specific improvement measures. It also uses a generative model to generate taglines and logo designs based on customer purchasing trends and segment information, and proposes them to the operations team.

[0262] Terminal handling

[0263] Voice Recognition and Order Fulfillment

[0264] The device receives voice input from the user and converts it into text using a speech recognition system. For example, a user question such as "Do you have any non-spicy menu items?" is converted into text. The device then analyzes the order using a generative model and creates a list of the customer's orders. Additional information from the customer (such as spiciness adjustments or allergies) is collected, and the final order is sent to the staff.

[0265] User operations

[0266] Usage example

[0267] When a user uses their smartphone to ask, "Do you have any low-calorie options?", the device converts this into text using a voice recognition system and suggests "high-protein salad." When the user confirms their order, the details are notified to the staff in real time.

[0268] Prompt Sentence Examples

[0269] 1. Menu suggestion prompt:

[0270] "Area information: Office district. Customer data: 30-year-old male. Please suggest a menu item that is high in protein and low in calories."

[0271] 2. Voice order prompts:

[0272] "User input: Do you have a low-calorie option? Suggestion: High-protein salad."

[0273] This will create a system in which all processes in running a kitchen car or food delivery service are seamlessly linked and can be executed quickly and efficiently.

[0274] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0275] Step 1:

[0276] The server collects area information from external APIs. For example, it collects information on the food culture, popular trends, and seasonal food ingredients of a particular region. This process receives area information as input, retrieves the necessary data from the external API based on that information, and stores it in a database. The input is area information, and the output is the collected data.

[0277] Step 2:

[0278] The server retrieves customer attribute and health condition data from the database. For example, it retrieves the customer's age, gender, occupation, residential area, allergy information, diet information, etc. In this process, it receives the customer ID as input and retrieves the corresponding customer data from the database based on that, which is used in the menu generation process. The input is the customer ID, and the output is the customer attribute and health condition data.

[0279] Step 3:

[0280] The server uses a generative model based on the collected data to generate menu options. For example, it might suggest a "high-protein, low-calorie menu for businessmen in their 30s." This process takes area information and customer data as input, generates optimal menu options using a generative AI model, and sends them to the terminal. The input is area information and customer data, and the output is menu options.

[0281] Step 4:

[0282] The terminal receives voice input from the user and converts it into text using a voice recognition system. For example, if a user asks, "Do you have any non-spicy menu items?", it converts this into text. In this process, voice data is received as input and converted into text data using a voice recognition system. The input is voice data, and the output is text data.

[0283] Step 5:

[0284] The terminal uses a generative model to analyze the order details and create a customer order list. In this process, the terminal uses a generative AI model to analyze the order details based on the voice input converted to text and generates an order list that meets the customer's requests. The input is text data converted by the voice recognition system, and the output is the order list.

[0285] Step 6:

[0286] The terminal collects additional information from the customer and confirms the final order details. For example, it collects information such as spiciness adjustments and whether or not the customer has any allergies. In this process, the additional information from the customer is entered as text data and reflected in the order list. The input is the additional information, and the output is the confirmed final order list.

[0287] Step 7:

[0288] The terminal sends the final order details to the staff member. This process receives the final confirmed order list as input and sends it to the staff member's terminal. The input is the final order list, and the output is the order information sent to the staff member's terminal.

[0289] Step 8:

[0290] The server collects all payment data and stores it in a database, such as the date, time, amount, and payment method of each transaction. This process takes transaction information as input and stores it in the database. The input is the transaction information and the output is the payment data stored in the database.

[0291] Step 9:

[0292] The server identifies sales trends using a generative model that analyzes customer purchasing habits based on collected payment data. For example, it analyzes peak times and popular menu items. This process takes payment data collected from the database as input and analyzes it using the generative AI model. The input is payment data, and the output is the sales trend analysis results.

[0293] Step 10:

[0294] The server visualizes the analysis results and displays them on a dashboard. For example, it displays the most popular menu items over a certain period of time or peak sales times as graphs. This process receives the results of sales trend analysis as input and visualizes the data. The input is the analysis results, and the output is the visual data displayed on the dashboard.

[0295] Step 11:

[0296] The server notifies the operations team of the analysis results. For example, it can inform the team that a particular menu item is very popular, facilitating a response to increase inventory. This process takes the data visualized on the dashboard as input and sends a notification to the team. The input is the visualized data, and the output is a notification to the operations team.

[0297] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0298] This invention is a system that provides a more advanced customized service by combining an emotion engine that recognizes user emotions with menu creation and order processing that are optimal for customer needs, sales analysis, service improvement, and marketing support for a mobile food truck (a type of restaurant). Below, we will provide an overview of this system and a detailed explanation of each processing step.

[0299] System Overview

[0300] This system operates based on communication between a server, terminals, users, and an emotion engine. The server is responsible for key functions such as data collection, menu creation, sales analysis, feedback analysis, and marketing support. The terminal is a device inside the food truck that interacts with customers, processes orders, and analyzes emotions. The user refers to the customers and operations team who use the system. The emotion engine analyzes the user's voice input and facial expressions to recognize the user's emotional state.

[0301] Menu Development

[0302] server:

[0303] Area information such as local food culture, popular trends, and seasonal food ingredient data is collected from an external API, and customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) are obtained from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[0304] Examples:

[0305] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[0306] Automated ordering system

[0307] Device:

[0308] The device analyzes the customer's voice input and facial expressions using an emotion engine to recognize the user's emotional state. The voice input is converted into text using a speech recognition system. Based on the analyzed emotion data and the order text, the server uses a generative model to create an order list. Additional information from the customer (e.g., spiciness preference or allergies) is collected, confirmed, and the final order details are sent to the staff.

[0309] Examples:

[0310] "If a user says to the device, 'I'm feeling down today,' the emotion engine will recognize their emotional state and provide a list of menu suggestions based on that information, including, for example, a chocolate dessert that is said to improve mood."

[0311] Sales Analysis

[0312] server:

[0313] All payment data is collected and stored, and data analysis algorithms are used to identify sales trends, peak times, popular menu items, etc. The analysis results are visualized and displayed on a dashboard, and the operations team is notified.

[0314] Examples:

[0315] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[0316] improvement

[0317] server:

[0318] It collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and suggests specific improvement measures. It also incorporates emotional state data from an emotion engine.

[0319] Examples:

[0320] "Analysis can be used to identify that multiple customers are dissatisfied with the length of their wait times, and recommendations can be made to increase staffing or revise processes. Furthermore, sentiment data can be used to identify that many customers are dissatisfied with the wait times."

[0321] marketing

[0322] server:

[0323] Customer purchasing patterns and segment information are collected, and a generative model is used to generate slogans and logo designs. Emotional data generated by an emotion engine is also used in marketing. The final materials are presented to the operations team for use in marketing activities.

[0324] Examples:

[0325] "We generate a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster. Furthermore, we use emotional data to present advertisements that take into account the fact that many customers are seeking refreshment at certain times of the day."

[0326] This system allows food trucks to propose menus and process orders while taking into account the emotional state of customers, analyze sales, improve services through feedback, and implement effective marketing strategies based on emotional data.In this way, the present invention aims to further improve the competitiveness of the food truck industry.

[0327] The processing flow will be explained below.

[0328] Menu Development

[0329] Step 1:

[0330] The server collects area information such as local food culture, popular trends, and seasonal food ingredient data from external APIs.

[0331] Step 2:

[0332] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) from the database.

[0333] Step 3:

[0334] The server acquires the customer's health condition data (allergy information, diet information, etc.).

[0335] Step 4:

[0336] The server inputs the collected data into a generative model to generate optimal menu candidates.

[0337] Step 5:

[0338] The server transmits the generated menu candidates to the terminal as a proposal list.

[0339] Automated ordering system

[0340] Step 1:

[0341] The terminal automatically launches the dialogue system when the customer arrives.

[0342] Step 2:

[0343] The user enters the order by voice.

[0344] Step 3:

[0345] The terminal converts the voice input into text using a voice recognition system.

[0346] Step 4:

[0347] The device analyzes the user's voice input and facial expressions using an emotion engine to recognize the user's emotional state.

[0348] Step 5:

[0349] The server uses a generative model to create an order list based on the analyzed emotion data and the order text.

[0350] Step 6:

[0351] The terminal collects additional information from the customer (e.g., spiciness preferences or allergies) and confirms the final order.

[0352] Step 7:

[0353] The terminal transmits the final order information to the kitchen staff.

[0354] Sales Analysis

[0355] Step 1:

[0356] The server collects all payment data and stores it in a database.

[0357] Step 2:

[0358] The server uses data analysis algorithms to identify sales trends, peak times, popular menu items, and more.

[0359] Step 3:

[0360] The server visualizes the analysis results and displays them on a dashboard.

[0361] Step 4:

[0362] The server notifies the operation team of the analysis results.

[0363] improvement

[0364] Step 1:

[0365] The server collects reviews and feedback from customers and stores them in a database.

[0366] Step 2:

[0367] The server uses a feedback analysis algorithm to categorize the positive and negative feedback.

[0368] Step 3:

[0369] The server generates specific improvement measures based on the analysis results.

[0370] Step 4:

[0371] The server notifies the operations team of the remedial measures.

[0372] marketing

[0373] Step 1:

[0374] The server collects customer buying patterns and segment information.

[0375] Step 2:

[0376] The server generates a catchy slogan using the generative model.

[0377] Step 3:

[0378] The server designs the logo using an image generation model.

[0379] Step 4:

[0380] The server proposes the generated slogans and logos to the operations team.

[0381] Step 5:

[0382] The operations team will use the proposed tagline and logo in their marketing activities.

[0383] Linking with the Emotion Engine

[0384] Step 1:

[0385] The device collects the user's voice input and facial expressions in real time.

[0386] Step 2:

[0387] The device uses an emotion engine to analyze the collected voice input and facial expressions to identify the user's emotional state.

[0388] Step 3:

[0389] The server obtains the emotional state identified by the emotion engine and reflects it in the generative model.

[0390] Step 4:

[0391] The server adjusts the menu options based on the emotional data and selects a menu that matches the emotional state.

[0392] Step 5:

[0393] The terminal presents tailored menu options to the user, providing an ordering experience that is responsive to the user's emotional state.

[0394] This will enable food trucks to make menu suggestions and process orders that take into account customer emotions, analyze sales, improve services based on feedback, and implement effective marketing strategies based on emotional data.

[0395] Example 2

[0396] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0397] In recent years, mobile food trucks have become popular due to their convenience and uniqueness. However, due to diversifying customer needs and intensifying competition, simply offering a menu is no longer enough to improve customer satisfaction and maintain competitiveness. In particular, there is a demand for menu suggestions tailored to each customer's emotional state and preferences, as well as fast and accurate order processing. Effective use of sales data and customer feedback to improve services and develop effective marketing strategies is also a major challenge.

[0398] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting data on food culture, fashion trends, and seasonal ingredients from regional information, a means for acquiring customer attributes and customer health condition data, and a menu generation means including a generative model that proposes menu candidates generated based on the collected data. This makes it possible to propose menus that meet the individual needs and preferences of each customer.

[0399] The server further includes a means for reviewing the proposed menu candidates and selecting an optimal menu, an emotion analysis means for recognizing the user's emotional state, and a means for customizing the menu based on the emotion data, thereby enabling more advanced customization that takes into account the customer's emotional state.

[0400] The terminal also includes a means for converting a customer's voice input into text using a voice recognition system, a means for analyzing the order details using a generative model and creating an order list for the customer, a means for collecting additional information from the customer and confirming the final order details, a means for transmitting the order information to a staff member, and a means for creating an order list that reflects the user's emotional state, thereby enabling fast and accurate order processing.

[0401] Furthermore, the server includes a means for collecting all payment data and storing it in a database, a data analysis means including a generative model that analyzes customer purchasing trends based on the collected payment data, a means for visualizing the analysis results and displaying them on a dashboard, a means for notifying the operation team of the analysis results, and a means for identifying sales trends including the emotion data analysis results, thereby enabling highly accurate sales analysis and service improvement based on sales data and customer emotion data.

[0402] These measures allow food trucks to provide highly customized services tailored to the individual needs and emotional state of their customers, improving customer satisfaction and strengthening their competitive edge.

[0403] "Regional information" refers to information such as food culture, popular trends, and seasonal food ingredients in a specific region.

[0404] "Customer attributes" refer to personal characteristics such as a customer's age, gender, occupation, and residential area.

[0405] "Health Data" refers to health-related data about a customer, such as allergy information, diet information, etc.

[0406] A "generative model" refers to an algorithm or machine learning model that generates optimal menu options based on collected data.

[0407] "Emotion analysis means" refers to the technology and algorithms used to analyze a user's voice input and facial expressions and recognize their emotional state.

[0408] "Speech recognition system" refers to a system or technology for converting voice input into text.

[0409] "Data analysis means" refers to technologies and algorithms used to analyze collected data and identify customer purchasing and sales trends.

[0410] "Dashboard" refers to an interface that visually displays the results of data analysis so that the operations team can easily understand them.

[0411] This invention is a system that generates optimal menus according to customer needs in kitchen cars, which are mobile restaurants, and handles orders, analyzes sales, improves services, and provides marketing support. In addition, by combining this with an emotion engine that recognizes user emotions, it provides an even more sophisticated customized service.

[0412] System Configuration

[0413] This system operates based on communication between the server, terminals, users, and emotion engine. Specifically, it has the following configuration:

[0414] server

[0415] The server has the following roles:

[0416] 1. Data collection: Collect regional information on food culture, popular trends, and seasonal food data from external APIs (e.g., food database APIs). Also, obtain customer attribute and health status data from an internal database.

[0417] 2. Menu generation: Based on the collected data, a generative AI model is used to generate optimal menu options and create a list of suggestions.

[0418] 3. Emotion Analysis: Recognize the user's emotional state and customize the menu based on the emotional data.

[0419] 4. Sales Analysis: Collect and store all payment data and use it to identify sales trends, peak times, popular menu items, etc.

[0420] 5. Feedback analysis: Collect customer feedback, categorize positive and negative feedback, and suggest improvement measures.

[0421] 6. Marketing Support: Analyze customer purchasing patterns and generate slogans and logo designs using generative AI models.

[0422] Terminal

[0423] The terminal interacts with customers inside the kitchen car and performs the following functions:

[0424] 1. Speech-to-text conversion: Converts customer voice input into text through a speech recognition system (e.g., Google Speech-to-Text API).

[0425] 2. Emotion Analysis: Using an emotion engine, analyze the customer's facial expressions to recognize their emotional state.

[0426] 3. Order processing: Based on the voice input and additional information, the server uses a generative AI model to create an order list, and then confirms the final order and sends it to the staff.

[0427] User

[0428] Users are the customers and operations team who use the system. Customers provide information such as voice input and facial expressions, and the operations team improves services based on sales data and feedback analysis provided by the server.

[0429] Specific examples

[0430] For example, the server can collect data from a business district and generate and suggest high-protein, low-calorie menus for a businessman in his 30s. If a user says, "I'm feeling down today," the emotion engine can recognize their emotional state and provide a list of menu options based on that. For example, it can suggest a menu that includes chocolate desserts, which are believed to improve mood.

[0431] In addition, the server can analyze payment data from the past month to determine that the "Salmon Avocado Salad" is the best-selling item at lunchtime and report this to the operations team. It can also analyze feedback from multiple customers and, if it identifies dissatisfaction with long wait times, it can suggest hiring more staff or revising processes.

[0432] Prompt Sentence Examples

[0433] "If a user says to the device, 'I want a hot stew on a cold day,' what kind of menu suggestions would you generate?"

[0434] This invention allows food trucks to propose menus and process orders taking into account the emotional state of customers, analyze sales, improve services through feedback, and implement effective marketing strategies based on emotional data, thereby improving customer satisfaction and strengthening competitiveness.

[0435] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0436] Step 1: Data collection

[0437] server:

[0438] The server collects data on food culture, popular trends, and seasonal ingredients from local information. Specifically, it obtains data by calling external APIs (e.g., ingredient database APIs and trend analysis APIs). The input is raw data from the API, and the output is a formatted dataset.

[0439] Input: Raw data from the API

[0440] Output: A formatted dataset

[0441] Specific behavior:

[0442] The server makes an API request to obtain regional food culture and trend data.

[0443] The acquired raw data is formatted, converted into the required format, and saved.

[0444] Step 2: Obtain customer information

[0445] server:

[0446] The server retrieves customer attribute data and health status data from an internal database. It uses SQL queries to pull information from the database. The input is the customer ID and request parameters, and the output is a record of customer data.

[0447] Input: Customer ID, request parameters

[0448] Output: Customer data records

[0449] Specific behavior:

[0450] The server accesses the database and retrieves attribute data corresponding to the particular customer.

[0451] The acquired data is stored in memory and used for subsequent processing.

[0452] Step 3: Create a menu

[0453] server:

[0454] The server uses a generative AI model based on the collected data to generate optimal menu options. The generative model receives various data as input and outputs an optimal menu list.

[0455] Input: Regional information data, customer data

[0456] Output: Menu candidate list

[0457] Specific behavior:

[0458] The server provides input data to the generative AI model and runs the menu generation algorithm.

[0459] The algorithmically generated menu candidate list is sent to the terminal.

[0460] Step 4: Speech and emotion analysis

[0461] Device:

[0462] The device receives voice input and facial expression information from the customer and performs emotion analysis, converting the voice input into text through a voice recognition system and recognizing the customer's emotional state using a facial expression analysis engine.

[0463] Input: Voice input, facial expression image

[0464] Output: Text data, emotion data

[0465] Specific behavior:

[0466] A speech recognition system converts voice input into text.

[0467] The facial expression analysis engine uses image data acquired from the camera to analyze the emotional state.

[0468] Step 5: Create an order list

[0469] server:

[0470] The server uses a generative AI model to create an order list based on the analyzed voice-to-text and emotion data, and also incorporates additional information from the customer.

[0471] Input: Speech text, emotion data, additional information

[0472] Output: Order list

[0473] Specific behavior:

[0474] The server provides the voice text and emotion data to a generative AI model to analyze the order.

[0475] Based on the analysis results and additional customer information, a final order list is created and sent to staff.

[0476] Step 6: Collect and analyze sales data

[0477] server:

[0478] The server collects all payment data and stores it in a database, which is then used to analyze sales and purchasing trends using generative AI models.

[0479] Input: Payment data

[0480] Output: Sales trends, buying trends

[0481] Specific behavior:

[0482] The server collects the payment data and stores it in a database.

[0483] Generative AI models are used to analyze collected data and identify sales and purchasing trends.

[0484] Step 7: Feedback and Service Improvement

[0485] server:

[0486] The server collects customer feedback, categorizes and analyzes positive and negative feedback, and also utilizes sentiment data.

[0487] Input: Feedback data, emotion data

[0488] Output: Improvement suggestions

[0489] Specific behavior:

[0490] Categorize and analyze feedback data collected from customers.

[0491] We propose specific service improvement measures based on emotional data.

[0492] Step 8: Marketing Support

[0493] server:

[0494] The server analyzes customer purchasing patterns and segment information, and generates catchphrases and logo designs using generative AI models. Emotional data is also used for marketing.

[0495] Input: Purchasing data, emotion data

[0496] Output: Catchphrase, logo design

[0497] Specific behavior:

[0498] It collects and analyzes customer purchasing data and uses generative AI models to generate marketing slogans and logo designs.

[0499] Provide proposed marketing materials to the operations team for use in campaigns.

[0500] (Application example 2)

[0501] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0502] Conventional food trucks and food delivery services have had difficulty proposing menus that take into account the individual emotions and mood of each customer. Furthermore, the lack of personalized service based on customer emotions has made it difficult to improve customer satisfaction and attract repeat customers. The present invention aims to solve these problems and provide a service that is sensitive to the emotions of customers.

[0503] The identification processing by the identification 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 collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attributes and customer health condition data; menu generation means including a generative model that proposes menu candidates generated based on the collected data; means for reviewing the proposed menu candidates and selecting an optimal menu; an emotion recognition engine that analyzes the customer's voice input and facial expressions to recognize their emotional state; and means for providing an optimal menu taking the user's emotional state into consideration. This enables personalized menu suggestions and order processing according to the customer's emotions.

[0504] "Area information" refers to data about culture, trends, seasonal ingredients, and other information related to a specific region.

[0505] "Customer attributes" refers to basic information about customers, such as age, gender, occupation, and residential area.

[0506] "Health data" refers to health-related data such as a customer's allergy information, diet information, and medical history.

[0507] A "generative model" refers to a machine learning model that generates a specific output (in this case, menu candidates) based on collected data.

[0508] An "emotion recognition engine" refers to software or hardware that analyzes a user's voice input and facial expressions and recognizes their emotional state.

[0509] "Menu generation means" refers to a mechanism that generates and suggests menu candidates using a generative model from collected data.

[0510] "Means for analyzing order details" refers to a system for analyzing and listing specific order details based on voice input or text data from customers.

[0511] "Visualization" refers to visually displaying analyzed data as graphs or tables.

[0512] "Dashboard" refers to an interface for visualizing and managing data in real time.

[0513] "Personalized suggestions" refer to providing specialized menus and services based on a customer's individual emotional state and past behavioral data.

[0514] This invention is a system for food trucks and food delivery services that proposes menus that take into account customer emotions, processes customized orders, analyzes sales, improves services, and provides marketing support. The entire system is described in detail below.

[0515] System configuration

[0516] This system operates based on communication between a server, a terminal, a user, and an emotion recognition engine.

[0517] Server Features

[0518] The server has the following main functions:

[0519] 1. Data collection: Local food culture, popular trends, and seasonal food ingredient data are collected from area information via external APIs, and customer attributes (age, gender, occupation, residential area, etc.) and health data (allergy information, diet information, etc.) are obtained from the database.

[0520] 2. Menu generation: Based on this data, the generative model generates optimal menu candidates and sends the proposal list to the device.

[0521] 3. Sales Analysis: Collect and store all payment data and use data analysis algorithms to identify sales trends, peak times, popular menu items, etc.

[0522] 4. Feedback analysis and service improvement: Collect and store customer reviews and feedback, use an analysis algorithm to classify positive and negative feedback, and propose specific improvement measures. It also reflects emotional state data.

[0523] 5. Marketing support: Collect customer purchasing patterns and segment information, and use generative models to generate slogans and advertising materials.

[0524] Device Features

[0525] The terminal refers to the terminal inside the food truck or the smartphone carried by the customer, and performs the following processes.

[0526] 1. Speech and emotion recognition: The voice input and facial expressions from the customer are analyzed using an emotion recognition engine and converted into text.

[0527] 2. Order Processing: The voice recognition system converts the customer's voice input into text, analyzes the order using a generative model, creates a list of the customer's orders, collects additional information from the customer (e.g., spiciness preference, allergies), and sends the final order to the staff after confirmation.

[0528] User Roles

[0529] Users include both customers and the operations team. Customers can speak to the device or point their face at it to input their voice and facial expressions, and receive personalized menu suggestions. The operations team then carries out actual operations and marketing activities based on sales analysis results and suggestions from the server.

[0530] Specific examples

[0531] Menu Development

[0532] A customer speaks to their smartphone saying, "I'm tired today and want to eat something sweet." The emotion recognition engine reads the "tired" emotion from the customer's facial expression, and the voice recognition system converts the speech into text. The server uses a generative model to suggest menu options for "sweet desserts to soothe fatigue." For example, it might recommend "chocolate cake" or "cream pudding."

[0533] Sales Analysis

[0534] The server collects past sales data and displays analytical results on a dashboard, such as "Salmon Avocado Salad is the best-selling item at lunchtime." This information is also sent to the operations team, who use it to manage inventory and improve the menu.

[0535] Marketing using emotional data

[0536] Using data from its emotion recognition engine, the server determines that many customers are looking for "refreshment" at certain times of the day, and launches an advertising campaign for lemon pie with the tagline "The perfect treat for a refreshing afternoon."

[0537] Implementation environment

[0538] Hardware: Smartphones, tablets, and devices with cameras

[0539] Software: Python, TensorFlow, OpenCV, external API (obtaining local information and food ingredient data)

[0540] Emotion Recognition Engine: Uses pre-trained models to recognize emotions from customers' voices and facial expressions

[0541] Prompt Sentence Examples

[0542] User Input:

[0543] "I'm tired and feeling sick"

[0544] System response:

[0545] "You've had a very hard day today. How about this 'Chicken and Broccoli Cream Pasta' to replenish your energy?"

[0546] Generate AI model prompt:

[0547] "The user's emotion has been determined to be 'sad'. Please suggest the best menu to improve the user's physical condition. For example, high-calorie meals or foods that improve mood."

[0548] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0549] Step 1:

[0550] The server collects area information from an external API. The input is the area specification and the external API call, and the output is area information such as local food culture, popular trends, and seasonal food ingredient data. Specifically, the API is called to obtain area information and it is stored in a database.

[0551] Step 2:

[0552] The server retrieves customer attributes and health status data from a database. The input is customer identification information, and the output is attribute data such as the customer's age, gender, occupation, residential area, allergy information, and diet information. Specifically, the server executes a database query to retrieve customer information.

[0553] Step 3:

[0554] The server uses a generative model to generate menu candidates based on the data collected. The input is area information and customer information, and the output is a list of suggested menu candidates. Specifically, data is input into the generative model to generate the optimal menu candidates.

[0555] Step 4:

[0556] The device analyzes the customer's voice input and facial expressions using an emotion recognition engine. The input is the customer's voice data and camera video data, and the output is text-translated voice data and recognized emotional information. Specifically, the voice recognition system converts the voice into text, and a facial recognition algorithm is used to determine emotions from facial expressions.

[0557] Step 5:

[0558] The server uses a generative model to analyze the order details based on the emotion-recognized data and voice-text data, and creates a customer order list. The input is emotion-recognized data and voice-text data, and the output is an order list. Specifically, data is input into the generative model, and the order details are analyzed.

[0559] Step 6:

[0560] The terminal collects additional information from the customer (such as spiciness adjustments and allergies) and sends the final order details to the server. The input is the customer's additional information, and the output is the final order list. Specifically, the customer enters the additional information via a GUI and then sends it to the server.

[0561] Step 7:

[0562] The server collects all payment data and stores it in a database. The input is the payment transaction data and the output is the stored payment data. Specifically, it retrieves data from the payment system and records it in the database.

[0563] Step 8:

[0564] Based on the payment data collected by the server, a generative model is used to analyze customer purchasing trends. The input is payment data, and the output is the analysis results of purchasing trends. Specifically, the payment data is processed by an analytical algorithm to identify purchasing trends and peak times.

[0565] Step 9:

[0566] The server visualizes the analysis results and displays them on a dashboard. The input is the analysis result data, and the output is the visually displayed data. Specifically, the data is plotted on graphs and charts and displayed in the interface.

[0567] Step 10:

[0568] Based on the analysis results and emotion data, the server notifies the operations team and marketing activities with the necessary information. The input is the analysis results and emotion data, and the output is notification information. Specifically, the server sends relevant information to relevant parties through the notification system.

[0569] Step 11:

[0570] The server collects and analyzes customer feedback and proposes service improvement proposals. The input is customer reviews and feedback data, and the output is improvement proposals. Specifically, it analyzes the feedback data, classifies negative feedback, and identifies areas for improvement.

[0571] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0572] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0573] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0574] [Second embodiment]

[0575] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0576] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0577] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0578] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0579] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0580] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0581] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0582] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0583] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0584] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0585] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0586] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0587] This invention is a system that provides comprehensive support for a mobile food truck (a food truck) from menu development to order processing, sales analysis, service improvement, and marketing. Below, we will explain the outline of this system and each processing step in detail.

[0588] System Overview

[0589] This system operates based on communication between a server, terminals, and users. The server is responsible for key functions such as data collection, menu creation, sales analysis, feedback analysis, and marketing support. The terminals are devices inside the food truck that interact with customers and process orders. The users are the customers and operations team that use the system.

[0590] Menu Development

[0591] server:

[0592] Area information such as local food culture, popular trends, and seasonal food ingredient data is collected from an external API, and customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) are obtained from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[0593] Examples:

[0594] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[0595] Automated ordering system

[0596] Device:

[0597] The terminal receives voice input from the customer and converts it to text using a speech recognition system. It analyzes the customer's order and creates an order list using a generative model. It collects additional customer information (e.g., spiciness preference or allergies), verifies it, and then sends the final order to a staff member.

[0598] Examples:

[0599] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[0600] Sales Analysis

[0601] server:

[0602] All payment data is collected and stored, and data analysis algorithms are used to identify sales trends, peak times, popular menu items, etc. The analysis results are visualized and displayed on a dashboard, and the operations team is notified.

[0603] Examples:

[0604] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[0605] improvement

[0606] server:

[0607] It collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and suggests specific improvement measures.

[0608] Examples:

[0609] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[0610] marketing

[0611] server:

[0612] Collect customer purchasing patterns and segment information, and use generative models to generate taglines and logo designs. The final materials are presented to the operations team for use in marketing activities.

[0613] Examples:

[0614] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[0615] This system allows food trucks to provide menus tailored to customer needs, process orders quickly and efficiently, analyze sales, improve services through feedback, and conduct effective marketing. In this way, the present invention aims to improve the competitiveness of the food truck industry.

[0616] The processing flow will be explained below.

[0617] Menu Development

[0618] Step 1:

[0619] The server collects area information such as local food culture, popular trends, and seasonal food ingredient data from external APIs.

[0620] Step 2:

[0621] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) from the database.

[0622] Step 3:

[0623] The server acquires the customer's health condition data (allergy information, diet information, etc.).

[0624] Step 4:

[0625] The server inputs the collected data into a generative model to generate optimal menu candidates.

[0626] Step 5:

[0627] The server transmits the generated menu candidates to the terminal as a proposal list.

[0628] Automated ordering system

[0629] Step 1:

[0630] The terminal automatically launches the dialogue system when the customer arrives.

[0631] Step 2:

[0632] The user enters the order by voice.

[0633] Step 3:

[0634] The terminal converts the voice input into text using a voice recognition system.

[0635] Step 4:

[0636] The server parses the customer's order text to understand the order contents.

[0637] Step 5:

[0638] The server uses the generative model to create the order list.

[0639] Step 6:

[0640] The terminal collects additional information from the customer (spiciness adjustment, allergies, etc.) and confirms the final order.

[0641] Step 7:

[0642] The terminal transmits the final order information to the kitchen staff.

[0643] Sales Analysis

[0644] Step 1:

[0645] The server collects all payment data and stores it in a database.

[0646] Step 2:

[0647] The server uses data analysis algorithms to identify sales trends, peak times, popular menu items, and more.

[0648] Step 3:

[0649] The server visualizes the analysis results and displays them on a dashboard.

[0650] Step 4:

[0651] The server notifies the operation team of the analysis results.

[0652] improvement

[0653] Step 1:

[0654] The server collects reviews and feedback from customers and stores them in a database.

[0655] Step 2:

[0656] The server uses a feedback analysis algorithm to classify positive and negative feedback.

[0657] Step 3:

[0658] The server generates specific improvement measures based on the analysis results.

[0659] Step 4:

[0660] The server notifies the operations team of the remedial measures.

[0661] marketing

[0662] Step 1:

[0663] The server collects customer buying patterns and segment information.

[0664] Step 2:

[0665] The server generates a catchphrase using the generative model.

[0666] Step 3:

[0667] The server designs the logo using an image generation model.

[0668] Step 4:

[0669] The server proposes the generated slogans and logos to the operations team.

[0670] Step 5:

[0671] The operations team will use the proposed tagline and logo in their marketing activities.

[0672] Through these steps, food trucks can provide the best menu to meet customer needs, process orders efficiently, analyze sales trends, improve services based on feedback, and implement effective marketing strategies.

[0673] Example 1

[0674] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0675] In traditional restaurant operations, each process, from menu development to order processing, sales analysis, feedback analysis, and marketing, is managed separately, making it difficult to efficiently utilize data.In addition, it is difficult to quickly respond to diverse customer needs, limiting the improvement of service quality and efficiency.

[0676] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0677] In this invention, the server includes: means for collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attribute and health condition data; menu generation means including a generative model that proposes menu candidates based on the collected data; means for reviewing the proposed menu candidates and selecting the optimal menu; means for collecting payment data and saving it in a database; means for analyzing sales trends based on the saved payment data; and means for displaying the analysis results on a dashboard and notifying the operations team. This enables consistent data management and utilization in the food truck, enabling menu development that meets customer needs, efficient order processing, precise sales analysis, appropriate service improvements, and effective marketing.

[0678] "Area information" refers to data on food culture, popular trends, and seasonal ingredients in a specific region.

[0679] "Customer attributes" refers to personal information such as a customer's age, gender, occupation, and residential area.

[0680] "Customer health data" refers to data related to the customer's health, such as allergy information and diet information.

[0681] A "generative model" refers to an algorithm or program that generates optimal menu options based on collected data.

[0682] "Menu generator" refers to a tool or system that uses collected data to generate menu options.

[0683] "Review" refers to the process of evaluating proposed menu options and selecting the most suitable menu.

[0684] "Payment Data" means information relating to the payment made by a Customer at the time of purchase.

[0685] "Database" refers to a system for storing and managing collected data.

[0686] "Sales trends" refers to the sales patterns and sales trends of a product over a certain period of time.

[0687] "Analysis tools" refer to methods and tools used to analyze collected data.

[0688] "Dashboard" refers to an interface that visually displays analysis results.

[0689] An "operations team" refers to the group of staff who operate and manage the food truck.

[0690] This invention is a system that provides comprehensive support for mobile food trucks, from menu development to order processing, sales analysis, service improvement, and marketing. This system operates based on communication between a server, terminals, and users.

[0691] Menu Development

[0692] server:

[0693] The server collects area information such as local food culture, popular trends, and seasonal food data from an external API. It also obtains customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[0694] Examples:

[0695] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[0696] Automated ordering system

[0697] Device:

[0698] The terminal receives voice input from the customer and converts it to text using a speech recognition system. For example, it can use a speech recognition library such as IBM Watson. It analyzes the customer's order and creates an order list using a generative model. It collects additional customer information (such as spiciness preferences or allergies), verifies it, and then sends the final order to a staff member.

[0699] Examples:

[0700] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[0701] Sales Analysis

[0702] server:

[0703] The server collects and stores all payment data and stores it in a secure database, such as an AWS RDS database. Based on the stored data, data analysis algorithms are used to identify sales trends, peak times, popular menu items, and more. The analysis results are visualized and displayed on a dashboard, allowing the operations team to understand sales status in real time and develop strategies.

[0704] Examples:

[0705] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[0706] Service Improvement

[0707] server:

[0708] The server collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and then suggests specific improvement measures based on the classified feedback.

[0709] Examples:

[0710] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[0711] marketing

[0712] server:

[0713] The server collects customer purchasing patterns and segment information, and uses generative models to generate catchphrases and logo designs. The generated materials are then proposed to the operations team for use in marketing activities.

[0714] Examples:

[0715] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[0716] Examples of prompt statements

[0717] "What prompts can you give to a generative AI model that will suggest high-protein, low-calorie meals for a businessman in his 30s?"

[0718] "What is the program prompt that proposes specific measures to improve waiting times at food trucks?"

[0719] This system allows food trucks to provide menus tailored to customer needs, process orders quickly and efficiently, analyze sales, improve services through feedback, and conduct effective marketing. In this way, the present invention aims to improve the competitiveness of the food truck industry.

[0720] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0721] Menu Development

[0722] server:

[0723] Step 1: Collect and enter area data

[0724] The server collects data on food culture, popular trends, and seasonal ingredients for a specific region using an external API (e.g., Google Places API). This area data is provided to the server as input.

[0725] Step 2: Collect and enter customer data

[0726] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) from the database. This customer data is also provided to the server as input.

[0727] Step 3: Data analysis

[0728] The server then runs the collected location and customer data through an analytical algorithm, where the data is cross-referenced to identify ingredient and menu trends for specific customer segments. The output of the data analysis is statistical data and trend analysis reports reflecting customer preferences.

[0729] Step 4: Generate the menu

[0730] The server uses a generative AI model based on the analysis results to generate multiple menu options. The input is the analysis result data, and the output is a list of menus created by machine learning. This menu list is optimized based on area and customer information.

[0731] Step 5: Submit your proposal list

[0732] The generated menu candidates are sent to the terminal as a suggestion list. The input is the generated menu list, and the output is the suggestion list sent to the terminal.

[0733] Specific working example:

[0734] "The server collects data on business districts, generates high-protein, low-calorie menus for businessmen in their 30s, and sends the list of suggestions to the terminal."

[0735] Automated ordering system

[0736] Device:

[0737] Step 1: Receiving voice input

[0738] The terminal receives voice input from the customer through a microphone, which provides input to a voice recognition system.

[0739] Step 2: Voice Recognition

[0740] The terminal uses a speech recognition system (e.g., IBM Watson) to convert speech to text. The input to this process is the customer's voice data, and the output is the converted text data.

[0741] Step 3: Order Analysis

[0742] The terminal analyzes the converted text data and creates an order list using a generative AI model. The input is the voice text data, and the output is the analyzed order list.

[0743] Step 4: Gather additional information

[0744] The terminal collects additional information from the customer (such as spiciness adjustment or allergies) and reflects it in the order list. The input is text data of the additional information, and the output is the final order list.

[0745] Step 5: Submit your final order

[0746] The final order details are sent from the terminal to the staff. The input is the confirmed order list, and the output is the order data sent to the staff.

[0747] Specific working example:

[0748] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[0749] Sales Analysis

[0750] server:

[0751] Step 1: Collect payment data

[0752] The server collects payment data in real time, with the input being each customer's transaction data and the output being the collected payment data.

[0753] Step 2: Save your data

[0754] The collected payment data is stored in a secure database, such as an AWS RDS database. The input is the payment data and the output is the data stored in the database.

[0755] Step 3: Data analysis

[0756] The server analyzes the stored payment data to identify sales trends, peak times, popular menu items, etc. The input is the stored payment data, and the output is a report of the analysis results.

[0757] Step 4: Visualize and communicate results

[0758] The analysis results are visualized and displayed on a dashboard, and the results are then notified to the operations team. The input is the analysis result data, and the output is the dashboard displayed as graphs and tables, along with notification messages.

[0759] Specific working example:

[0760] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[0761] Service Improvement

[0762] server:

[0763] Step 1: Gather feedback

[0764] The server collects reviews and feedback from customers. The input is customer review and feedback data, and the output is the collected feedback.

[0765] Step 2: Save your data

[0766] The collected feedback data is stored in a secure database. The input is the feedback data and the output is the data stored in the database.

[0767] Step 3: Feedback analysis

[0768] The server classifies the feedback data using an analysis algorithm, where the input is the stored feedback data and the output is the classification of positive and negative feedback.

[0769] Step 4: Propose improvement measures

[0770] Based on the classified feedback, specific improvement measures are proposed. The input is the classification result data, and the output is a list of proposed improvement measures.

[0771] Specific working example:

[0772] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[0773] marketing

[0774] server:

[0775] Step 1: Collect purchasing patterns

[0776] The server collects customer purchasing patterns and segment information. The input is purchasing data, and the output is the collected purchasing pattern data.

[0777] Step 2: Data analysis and generation

[0778] The server uses a generative AI model to generate taglines and logo designs. The input is purchasing pattern data, and the output is generated marketing materials.

[0779] Step 3: Propose materials

[0780] The generated catchphrases and logo designs are then proposed to the operations team. The input is the generated marketing materials, and the output is the proposed design data.

[0781] Specific working example:

[0782] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[0783] By implementing the above processing steps, the food truck will be able to develop menus that meet customer needs, process orders efficiently, perform precise sales analysis, make appropriate service improvements, and carry out effective marketing.

[0784] (Application example 1)

[0785] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0786] When operating a food truck, it is difficult to comprehensively manage each process, including menu development, order processing, sales analysis, service improvement, and marketing. Furthermore, to operate efficiently while meeting diverse customer needs, a system capable of analyzing data in real time and responding quickly is required. Conventional methods lack the means to centrally manage these processes and respond quickly, making it difficult to improve operational efficiency and customer satisfaction.

[0787] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0788] In this invention, the server includes: means for collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attributes and health condition data; menu generation means including a generative model that proposes menu candidates based on the collected data; means for reviewing the proposed menu candidates and selecting the optimal menu; means for analyzing customer purchasing trends and generating slogans and logo designs; means for converting user voice input into text using a voice recognition system; and means for visualizing vending operations on a dashboard in conjunction with the analysis results. This enables comprehensive management of each process in the operation of a food truck, from menu development to order processing, sales analysis, service improvement, and marketing, and enables quick and efficient response.

[0789] "Area Information" means information about a specific geographic area, such as local food culture, popular trends, and seasonal food data.

[0790] "Customer attributes" refers to basic attribute data about individual customers, such as age, gender, occupation, and residential area.

[0791] "Customer health data" refers to data relating to a customer's health, such as allergy information and diet information.

[0792] A "generative model" refers to an algorithm or system that generates optimal menu options, order details, catchphrases, logo designs, etc. based on collected data.

[0793] "Menu Generation Means" means a system or algorithm for suggesting menu options generated based on collected or acquired data.

[0794] "Speech recognition system" refers to techniques and devices for converting a user's voice input into text.

[0795] "Database" refers to a system or structure that stores collected payment data, customer attribute data, etc., and allows for later analysis, search, reference, and updating.

[0796] "Dashboard" means a display interface that visualizes analysis results and enables users or operations teams to understand the situation in real time.

[0797] "Operations team" refers to the group of staff and personnel who operate and manage the food truck or food delivery service.

[0798] "Automated vending" refers to the process of linking order processing with sales results and managing sales in real time.

[0799] Overall overview

[0800] This invention is a system that comprehensively supports menu development, order processing, sales analysis, service improvement, and marketing in the operation of food trucks and food delivery services. This system operates based on communication between a server, terminals, and users. Each processing step is explained in detail below.

[0801] Server Processing

[0802] Data collection

[0803] The server uses external APIs to collect area information, such as local food culture, popular trends, and seasonal food ingredients. It also obtains customer attributes and health status data (allergy information, diet information, etc.) from the database.

[0804] Menu generation

[0805] Based on the collected data, the server uses a generative model to generate optimal menu options. For example, it can suggest high-protein, low-calorie menus for businessmen in their 30s. The generated menus are sent to the device.

[0806] Sales Analysis

[0807] The server collects all payment data and stores it in a database. Based on the collected payment data, data analysis algorithms are used to identify sales trends, peak times, and popular menu items. The analysis results are visualized on a dashboard and notified to the operations team.

[0808] Improvement and marketing support

[0809] The server collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and proposes specific improvement measures. It also uses a generative model to generate taglines and logo designs based on customer purchasing trends and segment information, and proposes them to the operations team.

[0810] Terminal handling

[0811] Voice Recognition and Order Fulfillment

[0812] The device receives voice input from the user and converts it into text using a speech recognition system. For example, a user question such as "Do you have any non-spicy menu items?" is converted into text. The device then analyzes the order using a generative model and creates a list of the customer's orders. Additional information from the customer (such as spiciness adjustments or allergies) is collected, and the final order is sent to the staff.

[0813] User operations

[0814] Usage example

[0815] When a user uses their smartphone to ask, "Do you have any low-calorie options?", the device converts this into text using a voice recognition system and suggests "high-protein salad." When the user confirms their order, the details are notified to the staff in real time.

[0816] Prompt Sentence Examples

[0817] 1. Menu suggestion prompt:

[0818] "Area information: Office district. Customer data: 30-year-old male. Please suggest a menu item that is high in protein and low in calories."

[0819] 2. Voice order prompts:

[0820] "User input: Do you have a low-calorie option? Suggestion: High-protein salad."

[0821] This will create a system in which all processes in running a kitchen car or food delivery service are seamlessly linked and can be executed quickly and efficiently.

[0822] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0823] Step 1:

[0824] The server collects area information from external APIs. For example, it collects information on the food culture, popular trends, and seasonal food ingredients of a particular region. This process receives area information as input, retrieves the necessary data from the external API based on that information, and stores it in a database. The input is area information, and the output is the collected data.

[0825] Step 2:

[0826] The server retrieves customer attribute and health condition data from the database. For example, it retrieves the customer's age, gender, occupation, residential area, allergy information, diet information, etc. In this process, it receives the customer ID as input and retrieves the corresponding customer data from the database based on that, which is used in the menu generation process. The input is the customer ID, and the output is the customer attribute and health condition data.

[0827] Step 3:

[0828] The server uses a generative model based on the collected data to generate menu options. For example, it might suggest a "high-protein, low-calorie menu for businessmen in their 30s." This process takes area information and customer data as input, generates optimal menu options using a generative AI model, and sends them to the terminal. The input is area information and customer data, and the output is menu options.

[0829] Step 4:

[0830] The terminal receives voice input from the user and converts it into text using a voice recognition system. For example, if a user asks, "Do you have any non-spicy menu items?", it converts this into text. In this process, voice data is received as input and converted into text data using a voice recognition system. The input is voice data, and the output is text data.

[0831] Step 5:

[0832] The terminal uses a generative model to analyze the order details and create a customer order list. In this process, the terminal uses a generative AI model to analyze the order details based on the voice input converted to text and generates an order list that meets the customer's requests. The input is text data converted by the voice recognition system, and the output is the order list.

[0833] Step 6:

[0834] The terminal collects additional information from the customer and confirms the final order details. For example, it collects information such as spiciness adjustments and whether or not the customer has any allergies. In this process, the additional information from the customer is entered as text data and reflected in the order list. The input is the additional information, and the output is the confirmed final order list.

[0835] Step 7:

[0836] The terminal sends the final order details to the staff member. This process receives the final confirmed order list as input and sends it to the staff member's terminal. The input is the final order list, and the output is the order information sent to the staff member's terminal.

[0837] Step 8:

[0838] The server collects all payment data and stores it in a database, such as the date, time, amount, and payment method of each transaction. This process takes transaction information as input and stores it in the database. The input is the transaction information and the output is the payment data stored in the database.

[0839] Step 9:

[0840] The server identifies sales trends using a generative model that analyzes customer purchasing habits based on collected payment data. For example, it analyzes peak times and popular menu items. This process takes payment data collected from the database as input and analyzes it using the generative AI model. The input is payment data, and the output is the sales trend analysis results.

[0841] Step 10:

[0842] The server visualizes the analysis results and displays them on a dashboard. For example, it displays the most popular menu items over a certain period of time or peak sales times as graphs. This process receives the results of sales trend analysis as input and visualizes the data. The input is the analysis results, and the output is the visual data displayed on the dashboard.

[0843] Step 11:

[0844] The server notifies the operations team of the analysis results. For example, it can inform the team that a particular menu item is very popular, facilitating a response to increase inventory. This process takes the data visualized on the dashboard as input and sends a notification to the team. The input is the visualized data, and the output is a notification to the operations team.

[0845] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0846] This invention is a system that provides a more advanced customized service by combining an emotion engine that recognizes user emotions with menu creation and order processing that are optimal for customer needs, sales analysis, service improvement, and marketing support for a mobile food truck (a type of restaurant). Below, we will provide an overview of this system and a detailed explanation of each processing step.

[0847] System Overview

[0848] This system operates based on communication between a server, terminals, users, and an emotion engine. The server is responsible for key functions such as data collection, menu creation, sales analysis, feedback analysis, and marketing support. The terminal is a device inside the food truck that interacts with customers, processes orders, and analyzes emotions. The user refers to the customers and operations team who use the system. The emotion engine analyzes the user's voice input and facial expressions to recognize the user's emotional state.

[0849] Menu Development

[0850] server:

[0851] Area information such as local food culture, popular trends, and seasonal food ingredient data is collected from an external API, and customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) are obtained from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[0852] Examples:

[0853] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[0854] Automated ordering system

[0855] Device:

[0856] The device analyzes the customer's voice input and facial expressions using an emotion engine to recognize the user's emotional state. The voice input is converted into text using a speech recognition system. Based on the analyzed emotion data and the order text, the server uses a generative model to create an order list. Additional information from the customer (e.g., spiciness preference or allergies) is collected, confirmed, and the final order details are sent to the staff.

[0857] Examples:

[0858] "If a user says to the device, 'I'm feeling down today,' the emotion engine will recognize their emotional state and provide a list of menu suggestions based on that information, including, for example, a chocolate dessert that is said to improve mood."

[0859] Sales Analysis

[0860] server:

[0861] All payment data is collected and stored, and data analysis algorithms are used to identify sales trends, peak times, popular menu items, etc. The analysis results are visualized and displayed on a dashboard, and the operations team is notified.

[0862] Examples:

[0863] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[0864] improvement

[0865] server:

[0866] It collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and suggests specific improvement measures. It also incorporates emotional state data from an emotion engine.

[0867] Examples:

[0868] "Analysis can be used to identify that multiple customers are dissatisfied with the length of their wait times, and recommendations can be made to increase staffing or revise processes. Furthermore, sentiment data can be used to identify that many customers are dissatisfied with the wait times."

[0869] marketing

[0870] server:

[0871] Customer purchasing patterns and segment information are collected, and a generative model is used to generate slogans and logo designs. Emotional data generated by an emotion engine is also used in marketing. The final materials are presented to the operations team for use in marketing activities.

[0872] Examples:

[0873] "We generate a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster. Furthermore, we use emotional data to present advertisements that take into account the fact that many customers are seeking refreshment at certain times of the day."

[0874] This system allows food trucks to propose menus and process orders while taking into account the emotional state of customers, analyze sales, improve services through feedback, and implement effective marketing strategies based on emotional data.In this way, the present invention aims to further improve the competitiveness of the food truck industry.

[0875] The processing flow will be explained below.

[0876] Menu Development

[0877] Step 1:

[0878] The server collects area information such as local food culture, popular trends, and seasonal food ingredient data from external APIs.

[0879] Step 2:

[0880] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) from the database.

[0881] Step 3:

[0882] The server acquires the customer's health condition data (allergy information, diet information, etc.).

[0883] Step 4:

[0884] The server inputs the collected data into a generative model to generate optimal menu candidates.

[0885] Step 5:

[0886] The server transmits the generated menu candidates to the terminal as a proposal list.

[0887] Automated ordering system

[0888] Step 1:

[0889] The terminal automatically launches the dialogue system when the customer arrives.

[0890] Step 2:

[0891] The user enters the order by voice.

[0892] Step 3:

[0893] The terminal converts the voice input into text using a voice recognition system.

[0894] Step 4:

[0895] The device analyzes the user's voice input and facial expressions using an emotion engine to recognize the user's emotional state.

[0896] Step 5:

[0897] The server uses a generative model to create an order list based on the analyzed emotion data and the order text.

[0898] Step 6:

[0899] The terminal collects additional information from the customer (e.g., spiciness preferences or allergies) and confirms the final order.

[0900] Step 7:

[0901] The terminal transmits the final order information to the kitchen staff.

[0902] Sales Analysis

[0903] Step 1:

[0904] The server collects all payment data and stores it in a database.

[0905] Step 2:

[0906] The server uses data analysis algorithms to identify sales trends, peak times, popular menu items, and more.

[0907] Step 3:

[0908] The server visualizes the analysis results and displays them on a dashboard.

[0909] Step 4:

[0910] The server notifies the operation team of the analysis results.

[0911] improvement

[0912] Step 1:

[0913] The server collects reviews and feedback from customers and stores them in a database.

[0914] Step 2:

[0915] The server uses a feedback analysis algorithm to categorize the positive and negative feedback.

[0916] Step 3:

[0917] The server generates specific improvement measures based on the analysis results.

[0918] Step 4:

[0919] The server notifies the operations team of the remedial measures.

[0920] marketing

[0921] Step 1:

[0922] The server collects customer buying patterns and segment information.

[0923] Step 2:

[0924] The server generates a catchy slogan using the generative model.

[0925] Step 3:

[0926] The server designs the logo using an image generation model.

[0927] Step 4:

[0928] The server proposes the generated slogans and logos to the operations team.

[0929] Step 5:

[0930] The operations team will use the proposed tagline and logo in their marketing activities.

[0931] Linking with the Emotion Engine

[0932] Step 1:

[0933] The device collects the user's voice input and facial expressions in real time.

[0934] Step 2:

[0935] The device uses an emotion engine to analyze the collected voice input and facial expressions to identify the user's emotional state.

[0936] Step 3:

[0937] The server obtains the emotional state identified by the emotion engine and reflects it in the generative model.

[0938] Step 4:

[0939] The server adjusts the menu options based on the emotional data and selects a menu that matches the emotional state.

[0940] Step 5:

[0941] The terminal presents tailored menu options to the user, providing an ordering experience that is responsive to the user's emotional state.

[0942] This will enable food trucks to make menu suggestions and process orders that take into account customer emotions, analyze sales, improve services based on feedback, and implement effective marketing strategies based on emotional data.

[0943] Example 2

[0944] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0945] In recent years, mobile food trucks have become popular due to their convenience and uniqueness. However, due to diversifying customer needs and intensifying competition, simply offering a menu is no longer enough to improve customer satisfaction and maintain competitiveness. In particular, there is a demand for menu suggestions tailored to each customer's emotional state and preferences, as well as fast and accurate order processing. Effective use of sales data and customer feedback to improve services and develop effective marketing strategies is also a major challenge.

[0946] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting data on food culture, fashion trends, and seasonal ingredients from regional information, a means for acquiring customer attributes and customer health condition data, and a menu generation means including a generative model that proposes menu candidates generated based on the collected data. This makes it possible to propose menus that meet the individual needs and preferences of each customer.

[0947] The server further includes a means for reviewing the proposed menu candidates and selecting an optimal menu, an emotion analysis means for recognizing the user's emotional state, and a means for customizing the menu based on the emotion data, thereby enabling more advanced customization that takes into account the customer's emotional state.

[0948] The terminal also includes a means for converting a customer's voice input into text using a voice recognition system, a means for analyzing the order details using a generative model and creating an order list for the customer, a means for collecting additional information from the customer and confirming the final order details, a means for transmitting the order information to a staff member, and a means for creating an order list that reflects the user's emotional state, thereby enabling fast and accurate order processing.

[0949] Furthermore, the server includes a means for collecting all payment data and storing it in a database, a data analysis means including a generative model that analyzes customer purchasing trends based on the collected payment data, a means for visualizing the analysis results and displaying them on a dashboard, a means for notifying the operation team of the analysis results, and a means for identifying sales trends including the emotion data analysis results, thereby enabling highly accurate sales analysis and service improvement based on sales data and customer emotion data.

[0950] These measures allow food trucks to provide highly customized services tailored to the individual needs and emotional state of their customers, improving customer satisfaction and strengthening their competitive edge.

[0951] "Regional information" refers to information such as food culture, popular trends, and seasonal food ingredients in a specific region.

[0952] "Customer attributes" refer to personal characteristics such as a customer's age, gender, occupation, and residential area.

[0953] "Health Data" refers to health-related data about a customer, such as allergy information, diet information, etc.

[0954] A "generative model" refers to an algorithm or machine learning model that generates optimal menu options based on collected data.

[0955] "Emotion analysis means" refers to the technology and algorithms used to analyze a user's voice input and facial expressions and recognize their emotional state.

[0956] "Speech recognition system" refers to a system or technology for converting voice input into text.

[0957] "Data analysis means" refers to technologies and algorithms used to analyze collected data and identify customer purchasing and sales trends.

[0958] "Dashboard" refers to an interface that visually displays the results of data analysis so that the operations team can easily understand them.

[0959] This invention is a system that generates optimal menus according to customer needs in kitchen cars, which are mobile restaurants, and handles orders, analyzes sales, improves services, and provides marketing support. In addition, by combining this with an emotion engine that recognizes user emotions, it provides an even more sophisticated customized service.

[0960] System Configuration

[0961] This system operates based on communication between the server, terminals, users, and emotion engine. Specifically, it has the following configuration:

[0962] server

[0963] The server has the following roles:

[0964] 1. Data collection: Collect regional information on food culture, popular trends, and seasonal food data from external APIs (e.g., food database APIs). Also, obtain customer attribute and health status data from an internal database.

[0965] 2. Menu generation: Based on the collected data, a generative AI model is used to generate optimal menu options and create a list of suggestions.

[0966] 3. Emotion Analysis: Recognize the user's emotional state and customize the menu based on the emotional data.

[0967] 4. Sales Analysis: Collect and store all payment data and use it to identify sales trends, peak times, popular menu items, etc.

[0968] 5. Feedback analysis: Collect customer feedback, categorize positive and negative feedback, and suggest improvement measures.

[0969] 6. Marketing Support: Analyze customer purchasing patterns and generate slogans and logo designs using generative AI models.

[0970] Terminal

[0971] The terminal interacts with customers inside the kitchen car and performs the following functions:

[0972] 1. Speech-to-text conversion: Converts customer voice input into text through a speech recognition system (e.g., Google Speech-to-Text API).

[0973] 2. Emotion Analysis: Using an emotion engine, analyze the customer's facial expressions to recognize their emotional state.

[0974] 3. Order processing: Based on the voice input and additional information, the server uses a generative AI model to create an order list, and then confirms the final order and sends it to the staff.

[0975] User

[0976] Users are the customers and operations team who use the system. Customers provide information such as voice input and facial expressions, and the operations team improves services based on sales data and feedback analysis provided by the server.

[0977] Specific examples

[0978] For example, the server can collect data from a business district and generate and suggest high-protein, low-calorie menus for a businessman in his 30s. If a user says, "I'm feeling down today," the emotion engine can recognize their emotional state and provide a list of menu options based on that. For example, it can suggest a menu that includes chocolate desserts, which are believed to improve mood.

[0979] In addition, the server can analyze payment data from the past month to determine that the "Salmon Avocado Salad" is the best-selling item at lunchtime and report this to the operations team. It can also analyze feedback from multiple customers and, if it identifies dissatisfaction with long wait times, it can suggest hiring more staff or revising processes.

[0980] Prompt Sentence Examples

[0981] "If a user says to the device, 'I want a hot stew on a cold day,' what kind of menu suggestions would you generate?"

[0982] This invention allows food trucks to propose menus and process orders taking into account the emotional state of customers, analyze sales, improve services through feedback, and implement effective marketing strategies based on emotional data, thereby improving customer satisfaction and strengthening competitiveness.

[0983] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0984] Step 1: Data collection

[0985] server:

[0986] The server collects data on food culture, popular trends, and seasonal ingredients from local information. Specifically, it obtains data by calling external APIs (e.g., ingredient database APIs and trend analysis APIs). The input is raw data from the API, and the output is a formatted dataset.

[0987] Input: Raw data from the API

[0988] Output: A formatted dataset

[0989] Specific behavior:

[0990] The server makes an API request to obtain regional food culture and trend data.

[0991] The acquired raw data is formatted, converted into the required format, and saved.

[0992] Step 2: Obtain customer information

[0993] server:

[0994] The server retrieves customer attribute data and health status data from an internal database. It uses SQL queries to pull information from the database. The input is the customer ID and request parameters, and the output is a record of customer data.

[0995] Input: Customer ID, request parameters

[0996] Output: Customer data records

[0997] Specific behavior:

[0998] The server accesses the database and retrieves attribute data corresponding to the particular customer.

[0999] The acquired data is stored in memory and used for subsequent processing.

[1000] Step 3: Create a menu

[1001] server:

[1002] The server uses a generative AI model based on the collected data to generate optimal menu options. The generative model receives various data as input and outputs an optimal menu list.

[1003] Input: Regional information data, customer data

[1004] Output: Menu candidate list

[1005] Specific behavior:

[1006] The server provides input data to the generative AI model and runs the menu generation algorithm.

[1007] The algorithmically generated menu candidate list is sent to the terminal.

[1008] Step 4: Speech and emotion analysis

[1009] Device:

[1010] The device receives voice input and facial expression information from the customer and performs emotion analysis, converting the voice input into text through a voice recognition system and recognizing the customer's emotional state using a facial expression analysis engine.

[1011] Input: Voice input, facial expression image

[1012] Output: Text data, emotion data

[1013] Specific behavior:

[1014] A speech recognition system converts voice input into text.

[1015] The facial expression analysis engine uses image data acquired from the camera to analyze the emotional state.

[1016] Step 5: Create an order list

[1017] server:

[1018] The server uses a generative AI model to create an order list based on the analyzed voice-to-text and emotion data, and also incorporates additional information from the customer.

[1019] Input: Speech text, emotion data, additional information

[1020] Output: Order list

[1021] Specific behavior:

[1022] The server provides the voice text and emotion data to a generative AI model to analyze the order.

[1023] Based on the analysis results and additional customer information, a final order list is created and sent to staff.

[1024] Step 6: Collect and analyze sales data

[1025] server:

[1026] The server collects all payment data and stores it in a database, which is then used to analyze sales and purchasing trends using generative AI models.

[1027] Input: Payment data

[1028] Output: Sales trends, buying trends

[1029] Specific behavior:

[1030] The server collects the payment data and stores it in a database.

[1031] Generative AI models are used to analyze collected data and identify sales and purchasing trends.

[1032] Step 7: Feedback and Service Improvement

[1033] server:

[1034] The server collects customer feedback, categorizes and analyzes positive and negative feedback, and also utilizes sentiment data.

[1035] Input: Feedback data, emotion data

[1036] Output: Improvement suggestions

[1037] Specific behavior:

[1038] Categorize and analyze feedback data collected from customers.

[1039] We propose specific service improvement measures based on emotional data.

[1040] Step 8: Marketing Support

[1041] server:

[1042] The server analyzes customer purchasing patterns and segment information, and generates catchphrases and logo designs using generative AI models. Emotional data is also used for marketing.

[1043] Input: Purchasing data, emotion data

[1044] Output: Catchphrase, logo design

[1045] Specific behavior:

[1046] It collects and analyzes customer purchasing data and uses generative AI models to generate marketing slogans and logo designs.

[1047] Provide proposed marketing materials to the operations team for use in campaigns.

[1048] (Application example 2)

[1049] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1050] Conventional food trucks and food delivery services have had difficulty proposing menus that take into account the individual emotions and mood of each customer. Furthermore, the lack of personalized service based on customer emotions has made it difficult to improve customer satisfaction and attract repeat customers. The present invention aims to solve these problems and provide a service that is sensitive to the emotions of customers.

[1051] The identification processing by the identification 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 collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attributes and customer health condition data; menu generation means including a generative model that proposes menu candidates generated based on the collected data; means for reviewing the proposed menu candidates and selecting an optimal menu; an emotion recognition engine that analyzes the customer's voice input and facial expressions to recognize their emotional state; and means for providing an optimal menu taking the user's emotional state into consideration. This enables personalized menu suggestions and order processing according to the customer's emotions.

[1052] "Area information" refers to data about culture, trends, seasonal ingredients, and other information related to a specific region.

[1053] "Customer attributes" refers to basic information about customers, such as age, gender, occupation, and residential area.

[1054] "Health data" refers to health-related data such as a customer's allergy information, diet information, and medical history.

[1055] A "generative model" refers to a machine learning model that generates a specific output (in this case, menu candidates) based on collected data.

[1056] An "emotion recognition engine" refers to software or hardware that analyzes a user's voice input and facial expressions and recognizes their emotional state.

[1057] "Menu generation means" refers to a mechanism that generates and suggests menu candidates using a generative model from collected data.

[1058] "Means for analyzing order details" refers to a system for analyzing and listing specific order details based on voice input or text data from customers.

[1059] "Visualization" refers to visually displaying analyzed data as graphs or tables.

[1060] "Dashboard" refers to an interface for visualizing and managing data in real time.

[1061] "Personalized suggestions" refer to providing specialized menus and services based on a customer's individual emotional state and past behavioral data.

[1062] This invention is a system for food trucks and food delivery services that proposes menus that take into account customer emotions, processes customized orders, analyzes sales, improves services, and provides marketing support. The entire system is described in detail below.

[1063] System configuration

[1064] This system operates based on communication between a server, a terminal, a user, and an emotion recognition engine.

[1065] Server Features

[1066] The server has the following main functions:

[1067] 1. Data collection: Local food culture, popular trends, and seasonal food ingredient data are collected from area information via external APIs, and customer attributes (age, gender, occupation, residential area, etc.) and health data (allergy information, diet information, etc.) are obtained from the database.

[1068] 2. Menu generation: Based on this data, the generative model generates optimal menu candidates and sends the proposal list to the device.

[1069] 3. Sales Analysis: Collect and store all payment data and use data analysis algorithms to identify sales trends, peak times, popular menu items, etc.

[1070] 4. Feedback analysis and service improvement: Collect and store customer reviews and feedback, use an analysis algorithm to classify positive and negative feedback, and propose specific improvement measures. It also reflects emotional state data.

[1071] 5. Marketing support: Collect customer purchasing patterns and segment information, and use generative models to generate slogans and advertising materials.

[1072] Device Features

[1073] The terminal refers to the terminal inside the food truck or the smartphone carried by the customer, and performs the following processes.

[1074] 1. Speech and emotion recognition: The voice input and facial expressions from the customer are analyzed using an emotion recognition engine and converted into text.

[1075] 2. Order Processing: The voice recognition system converts the customer's voice input into text, analyzes the order using a generative model, creates a list of the customer's orders, collects additional information from the customer (e.g., spiciness preference, allergies), and sends the final order to the staff after confirmation.

[1076] User Roles

[1077] Users include both customers and the operations team. Customers can speak to the device or point their face at it to input their voice and facial expressions, and receive personalized menu suggestions. The operations team then carries out actual operations and marketing activities based on sales analysis results and suggestions from the server.

[1078] Specific examples

[1079] Menu Development

[1080] A customer speaks to their smartphone saying, "I'm tired today and want to eat something sweet." The emotion recognition engine reads the "tired" emotion from the customer's facial expression, and the voice recognition system converts the speech into text. The server uses a generative model to suggest menu options for "sweet desserts to soothe fatigue." For example, it might recommend "chocolate cake" or "cream pudding."

[1081] Sales Analysis

[1082] The server collects past sales data and displays analytical results on a dashboard, such as "Salmon Avocado Salad is the best-selling item at lunchtime." This information is also sent to the operations team, who use it to manage inventory and improve the menu.

[1083] Marketing using emotional data

[1084] Using data from its emotion recognition engine, the server determines that many customers are looking for "refreshment" at certain times of the day, and launches an advertising campaign for lemon pie with the tagline "The perfect treat for a refreshing afternoon."

[1085] Implementation environment

[1086] Hardware: Smartphones, tablets, and devices with cameras

[1087] Software: Python, TensorFlow, OpenCV, external API (obtaining local information and food ingredient data)

[1088] Emotion Recognition Engine: Uses pre-trained models to recognize emotions from customers' voices and facial expressions

[1089] Prompt Sentence Examples

[1090] User Input:

[1091] "I'm tired and feeling sick"

[1092] System response:

[1093] "You've had a very hard day today. How about this 'Chicken and Broccoli Cream Pasta' to replenish your energy?"

[1094] Generate AI model prompt:

[1095] "The user's emotion has been determined to be 'sad'. Please suggest the best menu to improve the user's physical condition. For example, high-calorie meals or foods that improve mood."

[1096] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1097] Step 1:

[1098] The server collects area information from an external API. The input is the area specification and the external API call, and the output is area information such as local food culture, popular trends, and seasonal food ingredient data. Specifically, the API is called to obtain area information and it is stored in a database.

[1099] Step 2:

[1100] The server retrieves customer attributes and health status data from a database. The input is customer identification information, and the output is attribute data such as the customer's age, gender, occupation, residential area, allergy information, and diet information. Specifically, the server executes a database query to retrieve customer information.

[1101] Step 3:

[1102] The server uses a generative model to generate menu candidates based on the data collected. The input is area information and customer information, and the output is a list of suggested menu candidates. Specifically, data is input into the generative model to generate the optimal menu candidates.

[1103] Step 4:

[1104] The device analyzes the customer's voice input and facial expressions using an emotion recognition engine. The input is the customer's voice data and camera video data, and the output is text-translated voice data and recognized emotional information. Specifically, the voice recognition system converts the voice into text, and a facial recognition algorithm is used to determine emotions from facial expressions.

[1105] Step 5:

[1106] The server uses a generative model to analyze the order details based on the emotion-recognized data and voice-text data, and creates a customer order list. The input is emotion-recognized data and voice-text data, and the output is an order list. Specifically, data is input into the generative model, and the order details are analyzed.

[1107] Step 6:

[1108] The terminal collects additional information from the customer (such as spiciness adjustments and allergies) and sends the final order details to the server. The input is the customer's additional information, and the output is the final order list. Specifically, the customer enters the additional information via a GUI and then sends it to the server.

[1109] Step 7:

[1110] The server collects all payment data and stores it in a database. The input is the payment transaction data and the output is the stored payment data. Specifically, it retrieves data from the payment system and records it in the database.

[1111] Step 8:

[1112] Based on the payment data collected by the server, a generative model is used to analyze customer purchasing trends. The input is payment data, and the output is the analysis results of purchasing trends. Specifically, the payment data is processed by an analytical algorithm to identify purchasing trends and peak times.

[1113] Step 9:

[1114] The server visualizes the analysis results and displays them on a dashboard. The input is the analysis result data, and the output is the visually displayed data. Specifically, the data is plotted on graphs and charts and displayed in the interface.

[1115] Step 10:

[1116] Based on the analysis results and emotion data, the server notifies the operations team and marketing activities with the necessary information. The input is the analysis results and emotion data, and the output is notification information. Specifically, the server sends relevant information to relevant parties through the notification system.

[1117] Step 11:

[1118] The server collects and analyzes customer feedback and proposes service improvement proposals. The input is customer reviews and feedback data, and the output is improvement proposals. Specifically, it analyzes the feedback data, classifies negative feedback, and identifies areas for improvement.

[1119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1121] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1122] [Third embodiment]

[1123] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1126] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1127] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1131] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1133] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1134] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1135] This invention is a system that provides comprehensive support for a mobile food truck (a food truck) from menu development to order processing, sales analysis, service improvement, and marketing. Below, we will explain the outline of this system and each processing step in detail.

[1136] System Overview

[1137] This system operates based on communication between a server, terminals, and users. The server is responsible for key functions such as data collection, menu creation, sales analysis, feedback analysis, and marketing support. The terminals are devices inside the food truck that interact with customers and process orders. The users are the customers and operations team that use the system.

[1138] Menu Development

[1139] server:

[1140] Area information such as local food culture, popular trends, and seasonal food ingredient data is collected from an external API, and customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) are obtained from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[1141] Examples:

[1142] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[1143] Automated ordering system

[1144] Device:

[1145] The terminal receives voice input from the customer and converts it to text using a speech recognition system. It analyzes the customer's order and creates an order list using a generative model. It collects additional customer information (e.g., spiciness preference or allergies), verifies it, and then sends the final order to a staff member.

[1146] Examples:

[1147] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[1148] Sales Analysis

[1149] server:

[1150] All payment data is collected and stored, and data analysis algorithms are used to identify sales trends, peak times, popular menu items, etc. The analysis results are visualized and displayed on a dashboard, and the operations team is notified.

[1151] Examples:

[1152] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[1153] improvement

[1154] server:

[1155] It collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and suggests specific improvement measures.

[1156] Examples:

[1157] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[1158] marketing

[1159] server:

[1160] Collect customer purchasing patterns and segment information, and use generative models to generate taglines and logo designs. The final materials are presented to the operations team for use in marketing activities.

[1161] Examples:

[1162] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[1163] This system allows food trucks to provide menus tailored to customer needs, process orders quickly and efficiently, analyze sales, improve services through feedback, and conduct effective marketing. In this way, the present invention aims to improve the competitiveness of the food truck industry.

[1164] The processing flow will be explained below.

[1165] Menu Development

[1166] Step 1:

[1167] The server collects area information such as local food culture, popular trends, and seasonal food ingredient data from external APIs.

[1168] Step 2:

[1169] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) from the database.

[1170] Step 3:

[1171] The server acquires the customer's health condition data (allergy information, diet information, etc.).

[1172] Step 4:

[1173] The server inputs the collected data into a generative model to generate optimal menu candidates.

[1174] Step 5:

[1175] The server transmits the generated menu candidates to the terminal as a proposal list.

[1176] Automated ordering system

[1177] Step 1:

[1178] The terminal automatically launches the dialogue system when the customer arrives.

[1179] Step 2:

[1180] The user enters the order by voice.

[1181] Step 3:

[1182] The terminal converts the voice input into text using a voice recognition system.

[1183] Step 4:

[1184] The server parses the customer's order text to understand the order contents.

[1185] Step 5:

[1186] The server uses the generative model to create the order list.

[1187] Step 6:

[1188] The terminal collects additional information from the customer (spiciness adjustment, allergies, etc.) and confirms the final order.

[1189] Step 7:

[1190] The terminal transmits the final order information to the kitchen staff.

[1191] Sales Analysis

[1192] Step 1:

[1193] The server collects all payment data and stores it in a database.

[1194] Step 2:

[1195] The server uses data analysis algorithms to identify sales trends, peak times, popular menu items, and more.

[1196] Step 3:

[1197] The server visualizes the analysis results and displays them on a dashboard.

[1198] Step 4:

[1199] The server notifies the operation team of the analysis results.

[1200] improvement

[1201] Step 1:

[1202] The server collects reviews and feedback from customers and stores them in a database.

[1203] Step 2:

[1204] The server uses a feedback analysis algorithm to classify positive and negative feedback.

[1205] Step 3:

[1206] The server generates specific improvement measures based on the analysis results.

[1207] Step 4:

[1208] The server notifies the operations team of the remedial measures.

[1209] marketing

[1210] Step 1:

[1211] The server collects customer buying patterns and segment information.

[1212] Step 2:

[1213] The server generates a catchphrase using the generative model.

[1214] Step 3:

[1215] The server designs the logo using an image generation model.

[1216] Step 4:

[1217] The server proposes the generated slogans and logos to the operations team.

[1218] Step 5:

[1219] The operations team will use the proposed tagline and logo in their marketing activities.

[1220] Through these steps, food trucks can provide the best menu to meet customer needs, process orders efficiently, analyze sales trends, improve services based on feedback, and implement effective marketing strategies.

[1221] Example 1

[1222] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1223] In traditional restaurant operations, each process, from menu development to order processing, sales analysis, feedback analysis, and marketing, is managed separately, making it difficult to efficiently utilize data.In addition, it is difficult to quickly respond to diverse customer needs, limiting the improvement of service quality and efficiency.

[1224] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1225] In this invention, the server includes: means for collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attribute and health condition data; menu generation means including a generative model that proposes menu candidates based on the collected data; means for reviewing the proposed menu candidates and selecting the optimal menu; means for collecting payment data and saving it in a database; means for analyzing sales trends based on the saved payment data; and means for displaying the analysis results on a dashboard and notifying the operations team. This enables consistent data management and utilization in the food truck, enabling menu development that meets customer needs, efficient order processing, precise sales analysis, appropriate service improvements, and effective marketing.

[1226] "Area information" refers to data on food culture, popular trends, and seasonal ingredients in a specific region.

[1227] "Customer attributes" refers to personal information such as a customer's age, gender, occupation, and residential area.

[1228] "Customer health data" refers to data related to the customer's health, such as allergy information and diet information.

[1229] A "generative model" refers to an algorithm or program that generates optimal menu options based on collected data.

[1230] "Menu generator" refers to a tool or system that uses collected data to generate menu options.

[1231] "Review" refers to the process of evaluating proposed menu options and selecting the most suitable menu.

[1232] "Payment Data" means information relating to the payment made by a Customer at the time of purchase.

[1233] "Database" refers to a system for storing and managing collected data.

[1234] "Sales trends" refers to the sales patterns and sales trends of a product over a certain period of time.

[1235] "Analysis tools" refer to methods and tools used to analyze collected data.

[1236] "Dashboard" refers to an interface that visually displays analysis results.

[1237] An "operations team" refers to the group of staff who operate and manage the food truck.

[1238] This invention is a system that provides comprehensive support for mobile food trucks, from menu development to order processing, sales analysis, service improvement, and marketing. This system operates based on communication between a server, terminals, and users.

[1239] Menu Development

[1240] server:

[1241] The server collects area information such as local food culture, popular trends, and seasonal food data from an external API. It also obtains customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[1242] Examples:

[1243] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[1244] Automated ordering system

[1245] Device:

[1246] The terminal receives voice input from the customer and converts it to text using a speech recognition system. For example, it can use a speech recognition library such as IBM Watson. It analyzes the customer's order and creates an order list using a generative model. It collects additional customer information (such as spiciness preferences or allergies), verifies it, and then sends the final order to a staff member.

[1247] Examples:

[1248] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[1249] Sales Analysis

[1250] server:

[1251] The server collects and stores all payment data and stores it in a secure database, such as an AWS RDS database. Based on the stored data, data analysis algorithms are used to identify sales trends, peak times, popular menu items, and more. The analysis results are visualized and displayed on a dashboard, allowing the operations team to understand sales status in real time and develop strategies.

[1252] Examples:

[1253] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[1254] Service Improvement

[1255] server:

[1256] The server collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and then suggests specific improvement measures based on the classified feedback.

[1257] Examples:

[1258] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[1259] marketing

[1260] server:

[1261] The server collects customer purchasing patterns and segment information, and uses generative models to generate catchphrases and logo designs. The generated materials are then proposed to the operations team for use in marketing activities.

[1262] Examples:

[1263] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[1264] Examples of prompt statements

[1265] "What prompts can you give to a generative AI model that will suggest high-protein, low-calorie meals for a businessman in his 30s?"

[1266] "What is the program prompt that proposes specific measures to improve waiting times at food trucks?"

[1267] This system allows food trucks to provide menus tailored to customer needs, process orders quickly and efficiently, analyze sales, improve services through feedback, and conduct effective marketing. In this way, the present invention aims to improve the competitiveness of the food truck industry.

[1268] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1269] Menu Development

[1270] server:

[1271] Step 1: Collect and enter area data

[1272] The server collects data on food culture, popular trends, and seasonal ingredients for a specific region using an external API (e.g., Google Places API). This area data is provided to the server as input.

[1273] Step 2: Collect and enter customer data

[1274] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) from the database. This customer data is also provided to the server as input.

[1275] Step 3: Data analysis

[1276] The server then runs the collected location and customer data through an analytical algorithm, where the data is cross-referenced to identify ingredient and menu trends for specific customer segments. The output of the data analysis is statistical data and trend analysis reports reflecting customer preferences.

[1277] Step 4: Generate the menu

[1278] The server uses a generative AI model based on the analysis results to generate multiple menu options. The input is the analysis result data, and the output is a list of menus created by machine learning. This menu list is optimized based on area and customer information.

[1279] Step 5: Submit your proposal list

[1280] The generated menu candidates are sent to the terminal as a suggestion list. The input is the generated menu list, and the output is the suggestion list sent to the terminal.

[1281] Specific working example:

[1282] "The server collects data on business districts, generates high-protein, low-calorie menus for businessmen in their 30s, and sends the list of suggestions to the terminal."

[1283] Automated ordering system

[1284] Device:

[1285] Step 1: Receiving voice input

[1286] The terminal receives voice input from the customer through a microphone, which provides input to a voice recognition system.

[1287] Step 2: Voice Recognition

[1288] The terminal uses a speech recognition system (e.g., IBM Watson) to convert speech to text. The input to this process is the customer's voice data, and the output is the converted text data.

[1289] Step 3: Order Analysis

[1290] The terminal analyzes the converted text data and creates an order list using a generative AI model. The input is the voice text data, and the output is the analyzed order list.

[1291] Step 4: Gather additional information

[1292] The terminal collects additional information from the customer (such as spiciness adjustment or allergies) and reflects it in the order list. The input is text data of the additional information, and the output is the final order list.

[1293] Step 5: Submit your final order

[1294] The final order details are sent from the terminal to the staff. The input is the confirmed order list, and the output is the order data sent to the staff.

[1295] Specific working example:

[1296] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[1297] Sales Analysis

[1298] server:

[1299] Step 1: Collect payment data

[1300] The server collects payment data in real time, with the input being each customer's transaction data and the output being the collected payment data.

[1301] Step 2: Save your data

[1302] The collected payment data is stored in a secure database, such as an AWS RDS database. The input is the payment data and the output is the data stored in the database.

[1303] Step 3: Data analysis

[1304] The server analyzes the stored payment data to identify sales trends, peak times, popular menu items, etc. The input is the stored payment data, and the output is a report of the analysis results.

[1305] Step 4: Visualize and communicate results

[1306] The analysis results are visualized and displayed on a dashboard, and the results are then notified to the operations team. The input is the analysis result data, and the output is the dashboard displayed as graphs and tables, along with notification messages.

[1307] Specific working example:

[1308] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[1309] Service Improvement

[1310] server:

[1311] Step 1: Gather feedback

[1312] The server collects reviews and feedback from customers. The input is customer review and feedback data, and the output is the collected feedback.

[1313] Step 2: Save your data

[1314] The collected feedback data is stored in a secure database. The input is the feedback data and the output is the data stored in the database.

[1315] Step 3: Feedback analysis

[1316] The server classifies the feedback data using an analysis algorithm, where the input is the stored feedback data and the output is the classification of positive and negative feedback.

[1317] Step 4: Propose improvement measures

[1318] Based on the classified feedback, specific improvement measures are proposed. The input is the classification result data, and the output is a list of proposed improvement measures.

[1319] Specific working example:

[1320] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[1321] marketing

[1322] server:

[1323] Step 1: Collect purchasing patterns

[1324] The server collects customer purchasing patterns and segment information. The input is purchasing data, and the output is the collected purchasing pattern data.

[1325] Step 2: Data analysis and generation

[1326] The server uses a generative AI model to generate taglines and logo designs. The input is purchasing pattern data, and the output is generated marketing materials.

[1327] Step 3: Propose materials

[1328] The generated catchphrases and logo designs are then proposed to the operations team. The input is the generated marketing materials, and the output is the proposed design data.

[1329] Specific working example:

[1330] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[1331] By implementing the above processing steps, the food truck will be able to develop menus that meet customer needs, process orders efficiently, perform precise sales analysis, make appropriate service improvements, and carry out effective marketing.

[1332] (Application example 1)

[1333] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1334] When operating a food truck, it is difficult to comprehensively manage each process, including menu development, order processing, sales analysis, service improvement, and marketing. Furthermore, to operate efficiently while meeting diverse customer needs, a system capable of analyzing data in real time and responding quickly is required. Conventional methods lack the means to centrally manage these processes and respond quickly, making it difficult to improve operational efficiency and customer satisfaction.

[1335] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1336] In this invention, the server includes: means for collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attributes and health condition data; menu generation means including a generative model that proposes menu candidates based on the collected data; means for reviewing the proposed menu candidates and selecting the optimal menu; means for analyzing customer purchasing trends and generating slogans and logo designs; means for converting user voice input into text using a voice recognition system; and means for visualizing vending operations on a dashboard in conjunction with the analysis results. This enables comprehensive management of each process in the operation of a food truck, from menu development to order processing, sales analysis, service improvement, and marketing, and enables quick and efficient response.

[1337] "Area Information" means information about a specific geographic area, such as local food culture, popular trends, and seasonal food data.

[1338] "Customer attributes" refers to basic attribute data about individual customers, such as age, gender, occupation, and residential area.

[1339] "Customer health data" refers to data relating to a customer's health, such as allergy information and diet information.

[1340] A "generative model" refers to an algorithm or system that generates optimal menu options, order details, catchphrases, logo designs, etc. based on collected data.

[1341] "Menu Generation Means" means a system or algorithm for suggesting menu options generated based on collected or acquired data.

[1342] "Speech recognition system" refers to techniques and devices for converting a user's voice input into text.

[1343] "Database" refers to a system or structure that stores collected payment data, customer attribute data, etc., and allows for later analysis, search, reference, and updating.

[1344] "Dashboard" means a display interface that visualizes analysis results and enables users or operations teams to understand the situation in real time.

[1345] "Operations team" refers to the group of staff and personnel who operate and manage the food truck or food delivery service.

[1346] "Automated vending" refers to the process of linking order processing with sales results and managing sales in real time.

[1347] Overall overview

[1348] This invention is a system that comprehensively supports menu development, order processing, sales analysis, service improvement, and marketing in the operation of food trucks and food delivery services. This system operates based on communication between a server, terminals, and users. Each processing step is explained in detail below.

[1349] Server Processing

[1350] Data collection

[1351] The server uses external APIs to collect area information, such as local food culture, popular trends, and seasonal food ingredients. It also obtains customer attributes and health status data (allergy information, diet information, etc.) from the database.

[1352] Menu generation

[1353] Based on the collected data, the server uses a generative model to generate optimal menu options. For example, it can suggest high-protein, low-calorie menus for businessmen in their 30s. The generated menus are sent to the device.

[1354] Sales Analysis

[1355] The server collects all payment data and stores it in a database. Based on the collected payment data, data analysis algorithms are used to identify sales trends, peak times, and popular menu items. The analysis results are visualized on a dashboard and notified to the operations team.

[1356] Improvement and marketing support

[1357] The server collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and proposes specific improvement measures. It also uses a generative model to generate taglines and logo designs based on customer purchasing trends and segment information, and proposes them to the operations team.

[1358] Terminal handling

[1359] Voice Recognition and Order Fulfillment

[1360] The device receives voice input from the user and converts it into text using a speech recognition system. For example, a user question such as "Do you have any non-spicy menu items?" is converted into text. The device then analyzes the order using a generative model and creates a list of the customer's orders. Additional information from the customer (such as spiciness adjustments or allergies) is collected, and the final order is sent to the staff.

[1361] User operations

[1362] Usage example

[1363] When a user uses their smartphone to ask, "Do you have any low-calorie options?", the device converts this into text using a voice recognition system and suggests "high-protein salad." When the user confirms their order, the details are notified to the staff in real time.

[1364] Prompt Sentence Examples

[1365] 1. Menu suggestion prompt:

[1366] "Area information: Office district. Customer data: 30-year-old male. Please suggest a menu item that is high in protein and low in calories."

[1367] 2. Voice order prompts:

[1368] "User input: Do you have a low-calorie option? Suggestion: High-protein salad."

[1369] This will create a system in which all processes in running a kitchen car or food delivery service are seamlessly linked and can be executed quickly and efficiently.

[1370] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1371] Step 1:

[1372] The server collects area information from external APIs. For example, it collects information on the food culture, popular trends, and seasonal food ingredients of a particular region. This process receives area information as input, retrieves the necessary data from the external API based on that information, and stores it in a database. The input is area information, and the output is the collected data.

[1373] Step 2:

[1374] The server retrieves customer attribute and health condition data from the database. For example, it retrieves the customer's age, gender, occupation, residential area, allergy information, diet information, etc. In this process, it receives the customer ID as input and retrieves the corresponding customer data from the database based on that, which is used in the menu generation process. The input is the customer ID, and the output is the customer attribute and health condition data.

[1375] Step 3:

[1376] The server uses a generative model based on the collected data to generate menu options. For example, it might suggest a "high-protein, low-calorie menu for businessmen in their 30s." This process takes area information and customer data as input, generates optimal menu options using a generative AI model, and sends them to the terminal. The input is area information and customer data, and the output is menu options.

[1377] Step 4:

[1378] The terminal receives voice input from the user and converts it into text using a voice recognition system. For example, if a user asks, "Do you have any non-spicy menu items?", it converts this into text. In this process, voice data is received as input and converted into text data using a voice recognition system. The input is voice data, and the output is text data.

[1379] Step 5:

[1380] The terminal uses a generative model to analyze the order details and create a customer order list. In this process, the terminal uses a generative AI model to analyze the order details based on the voice input converted to text and generates an order list that meets the customer's requests. The input is text data converted by the voice recognition system, and the output is the order list.

[1381] Step 6:

[1382] The terminal collects additional information from the customer and confirms the final order details. For example, it collects information such as spiciness adjustments and whether or not the customer has any allergies. In this process, the additional information from the customer is entered as text data and reflected in the order list. The input is the additional information, and the output is the confirmed final order list.

[1383] Step 7:

[1384] The terminal sends the final order details to the staff member. This process receives the final confirmed order list as input and sends it to the staff member's terminal. The input is the final order list, and the output is the order information sent to the staff member's terminal.

[1385] Step 8:

[1386] The server collects all payment data and stores it in a database, such as the date, time, amount, and payment method of each transaction. This process takes transaction information as input and stores it in the database. The input is the transaction information and the output is the payment data stored in the database.

[1387] Step 9:

[1388] The server identifies sales trends using a generative model that analyzes customer purchasing habits based on collected payment data. For example, it analyzes peak times and popular menu items. This process takes payment data collected from the database as input and analyzes it using the generative AI model. The input is payment data, and the output is the sales trend analysis results.

[1389] Step 10:

[1390] The server visualizes the analysis results and displays them on a dashboard. For example, it displays the most popular menu items over a certain period of time or peak sales times as graphs. This process receives the results of sales trend analysis as input and visualizes the data. The input is the analysis results, and the output is the visual data displayed on the dashboard.

[1391] Step 11:

[1392] The server notifies the operations team of the analysis results. For example, it can inform the team that a particular menu item is very popular, facilitating a response to increase inventory. This process takes the data visualized on the dashboard as input and sends a notification to the team. The input is the visualized data, and the output is a notification to the operations team.

[1393] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1394] This invention is a system that provides a more advanced customized service by combining an emotion engine that recognizes user emotions with menu creation and order processing that are optimal for customer needs, sales analysis, service improvement, and marketing support for a mobile food truck (a type of restaurant). Below, we will provide an overview of this system and a detailed explanation of each processing step.

[1395] System Overview

[1396] This system operates based on communication between a server, terminals, users, and an emotion engine. The server is responsible for key functions such as data collection, menu creation, sales analysis, feedback analysis, and marketing support. The terminal is a device inside the food truck that interacts with customers, processes orders, and analyzes emotions. The user refers to the customers and operations team who use the system. The emotion engine analyzes the user's voice input and facial expressions to recognize the user's emotional state.

[1397] Menu Development

[1398] server:

[1399] Area information such as local food culture, popular trends, and seasonal food ingredient data is collected from an external API, and customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) are obtained from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[1400] Examples:

[1401] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[1402] Automated ordering system

[1403] Device:

[1404] The device analyzes the customer's voice input and facial expressions using an emotion engine to recognize the user's emotional state. The voice input is converted into text using a speech recognition system. Based on the analyzed emotion data and the order text, the server uses a generative model to create an order list. Additional information from the customer (e.g., spiciness preference or allergies) is collected, confirmed, and the final order details are sent to the staff.

[1405] Examples:

[1406] "If a user says to the device, 'I'm feeling down today,' the emotion engine will recognize their emotional state and provide a list of menu suggestions based on that information, including, for example, a chocolate dessert that is said to improve mood."

[1407] Sales Analysis

[1408] server:

[1409] All payment data is collected and stored, and data analysis algorithms are used to identify sales trends, peak times, popular menu items, etc. The analysis results are visualized and displayed on a dashboard, and the operations team is notified.

[1410] Examples:

[1411] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[1412] improvement

[1413] server:

[1414] It collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and suggests specific improvement measures. It also incorporates emotional state data from an emotion engine.

[1415] Examples:

[1416] "Analysis can be used to identify that multiple customers are dissatisfied with the length of their wait times, and recommendations can be made to increase staffing or revise processes. Furthermore, sentiment data can be used to identify that many customers are dissatisfied with the wait times."

[1417] marketing

[1418] server:

[1419] Customer purchasing patterns and segment information are collected, and a generative model is used to generate slogans and logo designs. Emotional data generated by an emotion engine is also used in marketing. The final materials are presented to the operations team for use in marketing activities.

[1420] Examples:

[1421] "We generate a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster. Furthermore, we use emotional data to present advertisements that take into account the fact that many customers are seeking refreshment at certain times of the day."

[1422] This system allows food trucks to propose menus and process orders while taking into account the emotional state of customers, analyze sales, improve services through feedback, and implement effective marketing strategies based on emotional data.In this way, the present invention aims to further improve the competitiveness of the food truck industry.

[1423] The processing flow will be explained below.

[1424] Menu Development

[1425] Step 1:

[1426] The server collects area information such as local food culture, popular trends, and seasonal food ingredient data from external APIs.

[1427] Step 2:

[1428] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) from the database.

[1429] Step 3:

[1430] The server acquires the customer's health condition data (allergy information, diet information, etc.).

[1431] Step 4:

[1432] The server inputs the collected data into a generative model to generate optimal menu candidates.

[1433] Step 5:

[1434] The server transmits the generated menu candidates to the terminal as a proposal list.

[1435] Automated ordering system

[1436] Step 1:

[1437] The terminal automatically launches the dialogue system when the customer arrives.

[1438] Step 2:

[1439] The user enters the order by voice.

[1440] Step 3:

[1441] The terminal converts the voice input into text using a voice recognition system.

[1442] Step 4:

[1443] The device analyzes the user's voice input and facial expressions using an emotion engine to recognize the user's emotional state.

[1444] Step 5:

[1445] The server uses a generative model to create an order list based on the analyzed emotion data and the order text.

[1446] Step 6:

[1447] The terminal collects additional information from the customer (e.g., spiciness preferences or allergies) and confirms the final order.

[1448] Step 7:

[1449] The terminal transmits the final order information to the kitchen staff.

[1450] Sales Analysis

[1451] Step 1:

[1452] The server collects all payment data and stores it in a database.

[1453] Step 2:

[1454] The server uses data analysis algorithms to identify sales trends, peak times, popular menu items, and more.

[1455] Step 3:

[1456] The server visualizes the analysis results and displays them on a dashboard.

[1457] Step 4:

[1458] The server notifies the operation team of the analysis results.

[1459] improvement

[1460] Step 1:

[1461] The server collects reviews and feedback from customers and stores them in a database.

[1462] Step 2:

[1463] The server uses a feedback analysis algorithm to categorize the positive and negative feedback.

[1464] Step 3:

[1465] The server generates specific improvement measures based on the analysis results.

[1466] Step 4:

[1467] The server notifies the operations team of the remedial measures.

[1468] marketing

[1469] Step 1:

[1470] The server collects customer buying patterns and segment information.

[1471] Step 2:

[1472] The server generates a catchy slogan using the generative model.

[1473] Step 3:

[1474] The server designs the logo using an image generation model.

[1475] Step 4:

[1476] The server proposes the generated slogans and logos to the operations team.

[1477] Step 5:

[1478] The operations team will use the proposed tagline and logo in their marketing activities.

[1479] Linking with the Emotion Engine

[1480] Step 1:

[1481] The device collects the user's voice input and facial expressions in real time.

[1482] Step 2:

[1483] The device uses an emotion engine to analyze the collected voice input and facial expressions to identify the user's emotional state.

[1484] Step 3:

[1485] The server obtains the emotional state identified by the emotion engine and reflects it in the generative model.

[1486] Step 4:

[1487] The server adjusts the menu options based on the emotional data and selects a menu that matches the emotional state.

[1488] Step 5:

[1489] The terminal presents tailored menu options to the user, providing an ordering experience that is responsive to the user's emotional state.

[1490] This will enable food trucks to make menu suggestions and process orders that take into account customer emotions, analyze sales, improve services based on feedback, and implement effective marketing strategies based on emotional data.

[1491] Example 2

[1492] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1493] In recent years, mobile food trucks have become popular due to their convenience and uniqueness. However, due to diversifying customer needs and intensifying competition, simply offering a menu is no longer enough to improve customer satisfaction and maintain competitiveness. In particular, there is a demand for menu suggestions tailored to each customer's emotional state and preferences, as well as fast and accurate order processing. Effective use of sales data and customer feedback to improve services and develop effective marketing strategies is also a major challenge.

[1494] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting data on food culture, fashion trends, and seasonal ingredients from regional information, a means for acquiring customer attributes and customer health condition data, and a menu generation means including a generative model that proposes menu candidates generated based on the collected data. This makes it possible to propose menus that meet the individual needs and preferences of each customer.

[1495] The server further includes a means for reviewing the proposed menu candidates and selecting an optimal menu, an emotion analysis means for recognizing the user's emotional state, and a means for customizing the menu based on the emotion data, thereby enabling more advanced customization that takes into account the customer's emotional state.

[1496] The terminal also includes a means for converting a customer's voice input into text using a voice recognition system, a means for analyzing the order details using a generative model and creating an order list for the customer, a means for collecting additional information from the customer and confirming the final order details, a means for transmitting the order information to a staff member, and a means for creating an order list that reflects the user's emotional state, thereby enabling fast and accurate order processing.

[1497] Furthermore, the server includes a means for collecting all payment data and storing it in a database, a data analysis means including a generative model that analyzes customer purchasing trends based on the collected payment data, a means for visualizing the analysis results and displaying them on a dashboard, a means for notifying the operation team of the analysis results, and a means for identifying sales trends including the emotion data analysis results, thereby enabling highly accurate sales analysis and service improvement based on sales data and customer emotion data.

[1498] These measures allow food trucks to provide highly customized services tailored to the individual needs and emotional state of their customers, improving customer satisfaction and strengthening their competitive edge.

[1499] "Regional information" refers to information such as food culture, popular trends, and seasonal food ingredients in a specific region.

[1500] "Customer attributes" refer to personal characteristics such as a customer's age, gender, occupation, and residential area.

[1501] "Health Data" refers to health-related data about a customer, such as allergy information, diet information, etc.

[1502] A "generative model" refers to an algorithm or machine learning model that generates optimal menu options based on collected data.

[1503] "Emotion analysis means" refers to the technology and algorithms used to analyze a user's voice input and facial expressions and recognize their emotional state.

[1504] "Speech recognition system" refers to a system or technology for converting voice input into text.

[1505] "Data analysis means" refers to technologies and algorithms used to analyze collected data and identify customer purchasing and sales trends.

[1506] "Dashboard" refers to an interface that visually displays the results of data analysis so that the operations team can easily understand them.

[1507] This invention is a system that generates optimal menus according to customer needs in kitchen cars, which are mobile restaurants, and handles orders, analyzes sales, improves services, and provides marketing support. In addition, by combining this with an emotion engine that recognizes user emotions, it provides an even more sophisticated customized service.

[1508] System Configuration

[1509] This system operates based on communication between the server, terminals, users, and emotion engine. Specifically, it has the following configuration:

[1510] server

[1511] The server has the following roles:

[1512] 1. Data collection: Collect regional information on food culture, popular trends, and seasonal food data from external APIs (e.g., food database APIs). Also, obtain customer attribute and health status data from an internal database.

[1513] 2. Menu generation: Based on the collected data, a generative AI model is used to generate optimal menu options and create a list of suggestions.

[1514] 3. Emotion Analysis: Recognize the user's emotional state and customize the menu based on the emotional data.

[1515] 4. Sales Analysis: Collect and store all payment data and use it to identify sales trends, peak times, popular menu items, etc.

[1516] 5. Feedback analysis: Collect customer feedback, categorize positive and negative feedback, and suggest improvement measures.

[1517] 6. Marketing Support: Analyze customer purchasing patterns and generate slogans and logo designs using generative AI models.

[1518] Terminal

[1519] The terminal interacts with customers inside the kitchen car and performs the following functions:

[1520] 1. Speech-to-text conversion: Converts customer voice input into text through a speech recognition system (e.g., Google Speech-to-Text API).

[1521] 2. Emotion Analysis: Using an emotion engine, analyze the customer's facial expressions to recognize their emotional state.

[1522] 3. Order processing: Based on the voice input and additional information, the server uses a generative AI model to create an order list, and then confirms the final order and sends it to the staff.

[1523] User

[1524] Users are the customers and operations team who use the system. Customers provide information such as voice input and facial expressions, and the operations team improves services based on sales data and feedback analysis provided by the server.

[1525] Specific examples

[1526] For example, the server can collect data from a business district and generate and suggest high-protein, low-calorie menus for a businessman in his 30s. If a user says, "I'm feeling down today," the emotion engine can recognize their emotional state and provide a list of menu options based on that. For example, it can suggest a menu that includes chocolate desserts, which are believed to improve mood.

[1527] In addition, the server can analyze payment data from the past month to determine that the "Salmon Avocado Salad" is the best-selling item at lunchtime and report this to the operations team. It can also analyze feedback from multiple customers and, if it identifies dissatisfaction with long wait times, it can suggest hiring more staff or revising processes.

[1528] Prompt Sentence Examples

[1529] "If a user says to the device, 'I want a hot stew on a cold day,' what kind of menu suggestions would you generate?"

[1530] This invention allows food trucks to propose menus and process orders taking into account the emotional state of customers, analyze sales, improve services through feedback, and implement effective marketing strategies based on emotional data, thereby improving customer satisfaction and strengthening competitiveness.

[1531] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1532] Step 1: Data collection

[1533] server:

[1534] The server collects data on food culture, popular trends, and seasonal ingredients from local information. Specifically, it obtains data by calling external APIs (e.g., ingredient database APIs and trend analysis APIs). The input is raw data from the API, and the output is a formatted dataset.

[1535] Input: Raw data from the API

[1536] Output: A formatted dataset

[1537] Specific behavior:

[1538] The server makes an API request to obtain regional food culture and trend data.

[1539] The acquired raw data is formatted, converted into the required format, and saved.

[1540] Step 2: Obtain customer information

[1541] server:

[1542] The server retrieves customer attribute data and health status data from an internal database. It uses SQL queries to pull information from the database. The input is the customer ID and request parameters, and the output is a record of customer data.

[1543] Input: Customer ID, request parameters

[1544] Output: Customer data records

[1545] Specific behavior:

[1546] The server accesses the database and retrieves attribute data corresponding to the particular customer.

[1547] The acquired data is stored in memory and used for subsequent processing.

[1548] Step 3: Create a menu

[1549] server:

[1550] The server uses a generative AI model based on the collected data to generate optimal menu options. The generative model receives various data as input and outputs an optimal menu list.

[1551] Input: Regional information data, customer data

[1552] Output: Menu candidate list

[1553] Specific behavior:

[1554] The server provides input data to the generative AI model and runs the menu generation algorithm.

[1555] The algorithmically generated menu candidate list is sent to the terminal.

[1556] Step 4: Speech and emotion analysis

[1557] Device:

[1558] The device receives voice input and facial expression information from the customer and performs emotion analysis, converting the voice input into text through a voice recognition system and recognizing the customer's emotional state using a facial expression analysis engine.

[1559] Input: Voice input, facial expression image

[1560] Output: Text data, emotion data

[1561] Specific behavior:

[1562] A speech recognition system converts voice input into text.

[1563] The facial expression analysis engine uses image data acquired from the camera to analyze the emotional state.

[1564] Step 5: Create an order list

[1565] server:

[1566] The server uses a generative AI model to create an order list based on the analyzed voice-to-text and emotion data, and also incorporates additional information from the customer.

[1567] Input: Speech text, emotion data, additional information

[1568] Output: Order list

[1569] Specific behavior:

[1570] The server provides the voice text and emotion data to a generative AI model to analyze the order.

[1571] Based on the analysis results and additional customer information, a final order list is created and sent to staff.

[1572] Step 6: Collect and analyze sales data

[1573] server:

[1574] The server collects all payment data and stores it in a database, which is then used to analyze sales and purchasing trends using generative AI models.

[1575] Input: Payment data

[1576] Output: Sales trends, buying trends

[1577] Specific behavior:

[1578] The server collects the payment data and stores it in a database.

[1579] Generative AI models are used to analyze collected data and identify sales and purchasing trends.

[1580] Step 7: Feedback and Service Improvement

[1581] server:

[1582] The server collects customer feedback, categorizes and analyzes positive and negative feedback, and also utilizes sentiment data.

[1583] Input: Feedback data, emotion data

[1584] Output: Improvement suggestions

[1585] Specific behavior:

[1586] Categorize and analyze feedback data collected from customers.

[1587] We propose specific service improvement measures based on emotional data.

[1588] Step 8: Marketing Support

[1589] server:

[1590] The server analyzes customer purchasing patterns and segment information, and generates catchphrases and logo designs using generative AI models. Emotional data is also used for marketing.

[1591] Input: Purchasing data, emotion data

[1592] Output: Catchphrase, logo design

[1593] Specific behavior:

[1594] It collects and analyzes customer purchasing data and uses generative AI models to generate marketing slogans and logo designs.

[1595] Provide proposed marketing materials to the operations team for use in campaigns.

[1596] (Application example 2)

[1597] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1598] Conventional food trucks and food delivery services have had difficulty proposing menus that take into account the individual emotions and mood of each customer. Furthermore, the lack of personalized service based on customer emotions has made it difficult to improve customer satisfaction and attract repeat customers. The present invention aims to solve these problems and provide a service that is sensitive to the emotions of customers.

[1599] The identification processing by the identification 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 collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attributes and customer health condition data; menu generation means including a generative model that proposes menu candidates generated based on the collected data; means for reviewing the proposed menu candidates and selecting an optimal menu; an emotion recognition engine that analyzes the customer's voice input and facial expressions to recognize their emotional state; and means for providing an optimal menu taking the user's emotional state into consideration. This enables personalized menu suggestions and order processing according to the customer's emotions.

[1600] "Area information" refers to data about culture, trends, seasonal ingredients, and other information related to a specific region.

[1601] "Customer attributes" refers to basic information about customers, such as age, gender, occupation, and residential area.

[1602] "Health data" refers to health-related data such as a customer's allergy information, diet information, and medical history.

[1603] A "generative model" refers to a machine learning model that generates a specific output (in this case, menu candidates) based on collected data.

[1604] An "emotion recognition engine" refers to software or hardware that analyzes a user's voice input and facial expressions and recognizes their emotional state.

[1605] "Menu generation means" refers to a mechanism that generates and suggests menu candidates using a generative model from collected data.

[1606] "Means for analyzing order details" refers to a system for analyzing and listing specific order details based on voice input or text data from customers.

[1607] "Visualization" refers to visually displaying analyzed data as graphs or tables.

[1608] "Dashboard" refers to an interface for visualizing and managing data in real time.

[1609] "Personalized suggestions" refer to providing specialized menus and services based on a customer's individual emotional state and past behavioral data.

[1610] This invention is a system for food trucks and food delivery services that proposes menus that take into account customer emotions, processes customized orders, analyzes sales, improves services, and provides marketing support. The entire system is described in detail below.

[1611] System configuration

[1612] This system operates based on communication between a server, a terminal, a user, and an emotion recognition engine.

[1613] Server Features

[1614] The server has the following main functions:

[1615] 1. Data collection: Local food culture, popular trends, and seasonal food ingredient data are collected from area information via external APIs, and customer attributes (age, gender, occupation, residential area, etc.) and health data (allergy information, diet information, etc.) are obtained from the database.

[1616] 2. Menu generation: Based on this data, the generative model generates optimal menu candidates and sends the proposal list to the device.

[1617] 3. Sales Analysis: Collect and store all payment data and use data analysis algorithms to identify sales trends, peak times, popular menu items, etc.

[1618] 4. Feedback analysis and service improvement: Collect and store customer reviews and feedback, use an analysis algorithm to classify positive and negative feedback, and propose specific improvement measures. It also reflects emotional state data.

[1619] 5. Marketing support: Collect customer purchasing patterns and segment information, and use generative models to generate slogans and advertising materials.

[1620] Device Features

[1621] The terminal refers to the terminal inside the food truck or the smartphone carried by the customer, and performs the following processes.

[1622] 1. Speech and emotion recognition: The voice input and facial expressions from the customer are analyzed using an emotion recognition engine and converted into text.

[1623] 2. Order Processing: The voice recognition system converts the customer's voice input into text, analyzes the order using a generative model, creates a list of the customer's orders, collects additional information from the customer (e.g., spiciness preference, allergies), and sends the final order to the staff after confirmation.

[1624] User Roles

[1625] Users include both customers and the operations team. Customers can speak to the device or point their face at it to input their voice and facial expressions, and receive personalized menu suggestions. The operations team then carries out actual operations and marketing activities based on sales analysis results and suggestions from the server.

[1626] Specific examples

[1627] Menu Development

[1628] A customer speaks to their smartphone saying, "I'm tired today and want to eat something sweet." The emotion recognition engine reads the "tired" emotion from the customer's facial expression, and the voice recognition system converts the speech into text. The server uses a generative model to suggest menu options for "sweet desserts to soothe fatigue." For example, it might recommend "chocolate cake" or "cream pudding."

[1629] Sales Analysis

[1630] The server collects past sales data and displays analytical results on a dashboard, such as "Salmon Avocado Salad is the best-selling item at lunchtime." This information is also sent to the operations team, who use it to manage inventory and improve the menu.

[1631] Marketing using emotional data

[1632] Using data from its emotion recognition engine, the server determines that many customers are looking for "refreshment" at certain times of the day, and launches an advertising campaign for lemon pie with the tagline "The perfect treat for a refreshing afternoon."

[1633] Implementation environment

[1634] Hardware: Smartphones, tablets, and devices with cameras

[1635] Software: Python, TensorFlow, OpenCV, external API (obtaining local information and food ingredient data)

[1636] Emotion Recognition Engine: Uses pre-trained models to recognize emotions from customers' voices and facial expressions

[1637] Prompt Sentence Examples

[1638] User Input:

[1639] "I'm tired and feeling sick"

[1640] System response:

[1641] "You've had a very hard day today. How about this 'Chicken and Broccoli Cream Pasta' to replenish your energy?"

[1642] Generate AI model prompt:

[1643] "The user's emotion has been determined to be 'sad'. Please suggest the best menu to improve the user's physical condition. For example, high-calorie meals or foods that improve mood."

[1644] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1645] Step 1:

[1646] The server collects area information from an external API. The input is the area specification and the external API call, and the output is area information such as local food culture, popular trends, and seasonal food ingredient data. Specifically, the API is called to obtain area information and it is stored in a database.

[1647] Step 2:

[1648] The server retrieves customer attributes and health status data from a database. The input is customer identification information, and the output is attribute data such as the customer's age, gender, occupation, residential area, allergy information, and diet information. Specifically, the server executes a database query to retrieve customer information.

[1649] Step 3:

[1650] The server uses a generative model to generate menu candidates based on the data collected. The input is area information and customer information, and the output is a list of suggested menu candidates. Specifically, data is input into the generative model to generate the optimal menu candidates.

[1651] Step 4:

[1652] The device analyzes the customer's voice input and facial expressions using an emotion recognition engine. The input is the customer's voice data and camera video data, and the output is text-translated voice data and recognized emotional information. Specifically, the voice recognition system converts the voice into text, and a facial recognition algorithm is used to determine emotions from facial expressions.

[1653] Step 5:

[1654] The server uses a generative model to analyze the order details based on the emotion-recognized data and voice-text data, and creates a customer order list. The input is emotion-recognized data and voice-text data, and the output is an order list. Specifically, data is input into the generative model, and the order details are analyzed.

[1655] Step 6:

[1656] The terminal collects additional information from the customer (such as spiciness adjustments and allergies) and sends the final order details to the server. The input is the customer's additional information, and the output is the final order list. Specifically, the customer enters the additional information via a GUI and then sends it to the server.

[1657] Step 7:

[1658] The server collects all payment data and stores it in a database. The input is the payment transaction data and the output is the stored payment data. Specifically, it retrieves data from the payment system and records it in the database.

[1659] Step 8:

[1660] Based on the payment data collected by the server, a generative model is used to analyze customer purchasing trends. The input is payment data, and the output is the analysis results of purchasing trends. Specifically, the payment data is processed by an analytical algorithm to identify purchasing trends and peak times.

[1661] Step 9:

[1662] The server visualizes the analysis results and displays them on a dashboard. The input is the analysis result data, and the output is the visually displayed data. Specifically, the data is plotted on graphs and charts and displayed in the interface.

[1663] Step 10:

[1664] Based on the analysis results and emotion data, the server notifies the operations team and marketing activities with the necessary information. The input is the analysis results and emotion data, and the output is notification information. Specifically, the server sends relevant information to relevant parties through the notification system.

[1665] Step 11:

[1666] The server collects and analyzes customer feedback and proposes service improvement proposals. The input is customer reviews and feedback data, and the output is improvement proposals. Specifically, it analyzes the feedback data, classifies negative feedback, and identifies areas for improvement.

[1667] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1668] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1669] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1670] [Fourth embodiment]

[1671] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1672] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1673] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1674] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1675] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1676] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1677] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1678] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1679] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1680] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1681] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1682] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1683] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1684] This invention is a system that provides comprehensive support for a mobile food truck (a food truck) from menu development to order processing, sales analysis, service improvement, and marketing. Below, we will explain the outline of this system and each processing step in detail.

[1685] System Overview

[1686] This system operates based on communication between a server, terminals, and users. The server is responsible for key functions such as data collection, menu creation, sales analysis, feedback analysis, and marketing support. The terminals are devices inside the food truck that interact with customers and process orders. The users are the customers and operations team that use the system.

[1687] Menu Development

[1688] server:

[1689] Area information such as local food culture, popular trends, and seasonal food ingredient data is collected from an external API, and customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) are obtained from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[1690] Examples:

[1691] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[1692] Automated ordering system

[1693] Device:

[1694] The terminal receives voice input from the customer and converts it to text using a speech recognition system. It analyzes the customer's order and creates an order list using a generative model. It collects additional customer information (e.g., spiciness preference or allergies), verifies it, and then sends the final order to a staff member.

[1695] Examples:

[1696] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[1697] Sales Analysis

[1698] server:

[1699] All payment data is collected and stored, and data analysis algorithms are used to identify sales trends, peak times, popular menu items, etc. The analysis results are visualized and displayed on a dashboard, and the operations team is notified.

[1700] Examples:

[1701] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[1702] improvement

[1703] server:

[1704] It collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and suggests specific improvement measures.

[1705] Examples:

[1706] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[1707] marketing

[1708] server:

[1709] Collect customer purchasing patterns and segment information, and use generative models to generate taglines and logo designs. The final materials are presented to the operations team for use in marketing activities.

[1710] Examples:

[1711] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[1712] This system allows food trucks to provide menus tailored to customer needs, process orders quickly and efficiently, analyze sales, improve services through feedback, and conduct effective marketing. In this way, the present invention aims to improve the competitiveness of the food truck industry.

[1713] The processing flow will be explained below.

[1714] Menu Development

[1715] Step 1:

[1716] The server collects area information such as local food culture, popular trends, and seasonal food ingredient data from external APIs.

[1717] Step 2:

[1718] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) from the database.

[1719] Step 3:

[1720] The server acquires the customer's health condition data (allergy information, diet information, etc.).

[1721] Step 4:

[1722] The server inputs the collected data into a generative model to generate optimal menu candidates.

[1723] Step 5:

[1724] The server transmits the generated menu candidates to the terminal as a proposal list.

[1725] Automated ordering system

[1726] Step 1:

[1727] The terminal automatically launches the dialogue system when the customer arrives.

[1728] Step 2:

[1729] The user enters the order by voice.

[1730] Step 3:

[1731] The terminal converts the voice input into text using a voice recognition system.

[1732] Step 4:

[1733] The server parses the customer's order text to understand the order contents.

[1734] Step 5:

[1735] The server uses the generative model to create the order list.

[1736] Step 6:

[1737] The terminal collects additional information from the customer (spiciness adjustment, allergies, etc.) and confirms the final order.

[1738] Step 7:

[1739] The terminal transmits the final order information to the kitchen staff.

[1740] Sales Analysis

[1741] Step 1:

[1742] The server collects all payment data and stores it in a database.

[1743] Step 2:

[1744] The server uses data analysis algorithms to identify sales trends, peak times, popular menu items, and more.

[1745] Step 3:

[1746] The server visualizes the analysis results and displays them on a dashboard.

[1747] Step 4:

[1748] The server notifies the operation team of the analysis results.

[1749] improvement

[1750] Step 1:

[1751] The server collects reviews and feedback from customers and stores them in a database.

[1752] Step 2:

[1753] The server uses a feedback analysis algorithm to classify positive and negative feedback.

[1754] Step 3:

[1755] The server generates specific improvement measures based on the analysis results.

[1756] Step 4:

[1757] The server notifies the operations team of the remedial measures.

[1758] marketing

[1759] Step 1:

[1760] The server collects customer buying patterns and segment information.

[1761] Step 2:

[1762] The server generates a catchphrase using the generative model.

[1763] Step 3:

[1764] The server designs the logo using an image generation model.

[1765] Step 4:

[1766] The server proposes the generated slogans and logos to the operations team.

[1767] Step 5:

[1768] The operations team will use the proposed tagline and logo in their marketing activities.

[1769] Through these steps, food trucks can provide the best menu to meet customer needs, process orders efficiently, analyze sales trends, improve services based on feedback, and implement effective marketing strategies.

[1770] Example 1

[1771] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1772] In traditional restaurant operations, each process, from menu development to order processing, sales analysis, feedback analysis, and marketing, is managed separately, making it difficult to efficiently utilize data.In addition, it is difficult to quickly respond to diverse customer needs, limiting the improvement of service quality and efficiency.

[1773] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1774] In this invention, the server includes: means for collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attribute and health condition data; menu generation means including a generative model that proposes menu candidates based on the collected data; means for reviewing the proposed menu candidates and selecting the optimal menu; means for collecting payment data and saving it in a database; means for analyzing sales trends based on the saved payment data; and means for displaying the analysis results on a dashboard and notifying the operations team. This enables consistent data management and utilization in the food truck, enabling menu development that meets customer needs, efficient order processing, precise sales analysis, appropriate service improvements, and effective marketing.

[1775] "Area information" refers to data on food culture, popular trends, and seasonal ingredients in a specific region.

[1776] "Customer attributes" refers to personal information such as a customer's age, gender, occupation, and residential area.

[1777] "Customer health data" refers to data related to the customer's health, such as allergy information and diet information.

[1778] A "generative model" refers to an algorithm or program that generates optimal menu options based on collected data.

[1779] "Menu generator" refers to a tool or system that uses collected data to generate menu options.

[1780] "Review" refers to the process of evaluating proposed menu options and selecting the most suitable menu.

[1781] "Payment Data" means information relating to the payment made by a Customer at the time of purchase.

[1782] "Database" refers to a system for storing and managing collected data.

[1783] "Sales trends" refers to the sales patterns and sales trends of a product over a certain period of time.

[1784] "Analysis tools" refer to methods and tools used to analyze collected data.

[1785] "Dashboard" refers to an interface that visually displays analysis results.

[1786] An "operations team" refers to the group of staff who operate and manage the food truck.

[1787] This invention is a system that provides comprehensive support for mobile food trucks, from menu development to order processing, sales analysis, service improvement, and marketing. This system operates based on communication between a server, terminals, and users.

[1788] Menu Development

[1789] server:

[1790] The server collects area information such as local food culture, popular trends, and seasonal food data from an external API. It also obtains customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[1791] Examples:

[1792] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[1793] Automated ordering system

[1794] Device:

[1795] The terminal receives voice input from the customer and converts it to text using a speech recognition system. For example, it can use a speech recognition library such as IBM Watson. It analyzes the customer's order and creates an order list using a generative model. It collects additional customer information (such as spiciness preferences or allergies), verifies it, and then sends the final order to a staff member.

[1796] Examples:

[1797] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[1798] Sales Analysis

[1799] server:

[1800] The server collects and stores all payment data and stores it in a secure database, such as an AWS RDS database. Based on the stored data, data analysis algorithms are used to identify sales trends, peak times, popular menu items, and more. The analysis results are visualized and displayed on a dashboard, allowing the operations team to understand sales status in real time and develop strategies.

[1801] Examples:

[1802] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[1803] Service Improvement

[1804] server:

[1805] The server collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and then suggests specific improvement measures based on the classified feedback.

[1806] Examples:

[1807] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[1808] marketing

[1809] server:

[1810] The server collects customer purchasing patterns and segment information, and uses generative models to generate catchphrases and logo designs. The generated materials are then proposed to the operations team for use in marketing activities.

[1811] Examples:

[1812] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[1813] Examples of prompt statements

[1814] "What prompts can you give to a generative AI model that will suggest high-protein, low-calorie meals for a businessman in his 30s?"

[1815] "What is the program prompt that proposes specific measures to improve waiting times at food trucks?"

[1816] This system allows food trucks to provide menus tailored to customer needs, process orders quickly and efficiently, analyze sales, improve services through feedback, and conduct effective marketing. In this way, the present invention aims to improve the competitiveness of the food truck industry.

[1817] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1818] Menu Development

[1819] server:

[1820] Step 1: Collect and enter area data

[1821] The server collects data on food culture, popular trends, and seasonal ingredients for a specific region using an external API (e.g., Google Places API). This area data is provided to the server as input.

[1822] Step 2: Collect and enter customer data

[1823] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) from the database. This customer data is also provided to the server as input.

[1824] Step 3: Data analysis

[1825] The server then runs the collected location and customer data through an analytical algorithm, where the data is cross-referenced to identify ingredient and menu trends for specific customer segments. The output of the data analysis is statistical data and trend analysis reports reflecting customer preferences.

[1826] Step 4: Generate the menu

[1827] The server uses a generative AI model based on the analysis results to generate multiple menu options. The input is the analysis result data, and the output is a list of menus created by machine learning. This menu list is optimized based on area and customer information.

[1828] Step 5: Submit your proposal list

[1829] The generated menu candidates are sent to the terminal as a suggestion list. The input is the generated menu list, and the output is the suggestion list sent to the terminal.

[1830] Specific working example:

[1831] "The server collects data on business districts, generates high-protein, low-calorie menus for businessmen in their 30s, and sends the list of suggestions to the terminal."

[1832] Automated ordering system

[1833] Device:

[1834] Step 1: Receiving voice input

[1835] The terminal receives voice input from the customer through a microphone, which provides input to a voice recognition system.

[1836] Step 2: Voice Recognition

[1837] The terminal uses a speech recognition system (e.g., IBM Watson) to convert speech to text. The input to this process is the customer's voice data, and the output is the converted text data.

[1838] Step 3: Order Analysis

[1839] The terminal analyzes the converted text data and creates an order list using a generative AI model. The input is the voice text data, and the output is the analyzed order list.

[1840] Step 4: Gather additional information

[1841] The terminal collects additional information from the customer (such as spiciness adjustment or allergies) and reflects it in the order list. The input is text data of the additional information, and the output is the final order list.

[1842] Step 5: Submit your final order

[1843] The final order details are sent from the terminal to the staff. The input is the confirmed order list, and the output is the order data sent to the staff.

[1844] Specific working example:

[1845] "When a user asks, 'Do you have any non-spicy items?' the device responds, 'We have mild chicken curry,' and adds it to the order list."

[1846] Sales Analysis

[1847] server:

[1848] Step 1: Collect payment data

[1849] The server collects payment data in real time, with the input being each customer's transaction data and the output being the collected payment data.

[1850] Step 2: Save your data

[1851] The collected payment data is stored in a secure database, such as an AWS RDS database. The input is the payment data and the output is the data stored in the database.

[1852] Step 3: Data analysis

[1853] The server analyzes the stored payment data to identify sales trends, peak times, popular menu items, etc. The input is the stored payment data, and the output is a report of the analysis results.

[1854] Step 4: Visualize and communicate results

[1855] The analysis results are visualized and displayed on a dashboard, and the results are then notified to the operations team. The input is the analysis result data, and the output is the dashboard displayed as graphs and tables, along with notification messages.

[1856] Specific working example:

[1857] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[1858] Service Improvement

[1859] server:

[1860] Step 1: Gather feedback

[1861] The server collects reviews and feedback from customers. The input is customer review and feedback data, and the output is the collected feedback.

[1862] Step 2: Save your data

[1863] The collected feedback data is stored in a secure database. The input is the feedback data and the output is the data stored in the database.

[1864] Step 3: Feedback analysis

[1865] The server classifies the feedback data using an analysis algorithm, where the input is the stored feedback data and the output is the classification of positive and negative feedback.

[1866] Step 4: Propose improvement measures

[1867] Based on the classified feedback, specific improvement measures are proposed. The input is the classification result data, and the output is a list of proposed improvement measures.

[1868] Specific working example:

[1869] "Analysis identifies that multiple customers are dissatisfied with long wait times and suggests hiring more staff or reviewing processes."

[1870] marketing

[1871] server:

[1872] Step 1: Collect purchasing patterns

[1873] The server collects customer purchasing patterns and segment information. The input is purchasing data, and the output is the collected purchasing pattern data.

[1874] Step 2: Data analysis and generation

[1875] The server uses a generative AI model to generate taglines and logo designs. The input is purchasing pattern data, and the output is generated marketing materials.

[1876] Step 3: Propose materials

[1877] The generated catchphrases and logo designs are then proposed to the operations team. The input is the generated marketing materials, and the output is the proposed design data.

[1878] Specific working example:

[1879] "Create a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster."

[1880] By implementing the above processing steps, the food truck will be able to develop menus that meet customer needs, process orders efficiently, perform precise sales analysis, make appropriate service improvements, and carry out effective marketing.

[1881] (Application example 1)

[1882] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1883] When operating a food truck, it is difficult to comprehensively manage each process, including menu development, order processing, sales analysis, service improvement, and marketing. Furthermore, to operate efficiently while meeting diverse customer needs, a system capable of analyzing data in real time and responding quickly is required. Conventional methods lack the means to centrally manage these processes and respond quickly, making it difficult to improve operational efficiency and customer satisfaction.

[1884] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1885] In this invention, the server includes: means for collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attributes and health condition data; menu generation means including a generative model that proposes menu candidates based on the collected data; means for reviewing the proposed menu candidates and selecting the optimal menu; means for analyzing customer purchasing trends and generating slogans and logo designs; means for converting user voice input into text using a voice recognition system; and means for visualizing vending operations on a dashboard in conjunction with the analysis results. This enables comprehensive management of each process in the operation of a food truck, from menu development to order processing, sales analysis, service improvement, and marketing, and enables quick and efficient response.

[1886] "Area Information" means information about a specific geographic area, such as local food culture, popular trends, and seasonal food data.

[1887] "Customer attributes" refers to basic attribute data about individual customers, such as age, gender, occupation, and residential area.

[1888] "Customer health data" refers to data relating to a customer's health, such as allergy information and diet information.

[1889] A "generative model" refers to an algorithm or system that generates optimal menu options, order details, catchphrases, logo designs, etc. based on collected data.

[1890] "Menu Generation Means" means a system or algorithm for suggesting menu options generated based on collected or acquired data.

[1891] "Speech recognition system" refers to techniques and devices for converting a user's voice input into text.

[1892] "Database" refers to a system or structure that stores collected payment data, customer attribute data, etc., and allows for later analysis, search, reference, and updating.

[1893] "Dashboard" means a display interface that visualizes analysis results and enables users or operations teams to understand the situation in real time.

[1894] "Operations team" refers to the group of staff and personnel who operate and manage the food truck or food delivery service.

[1895] "Automated vending" refers to the process of linking order processing with sales results and managing sales in real time.

[1896] Overall overview

[1897] This invention is a system that comprehensively supports menu development, order processing, sales analysis, service improvement, and marketing in the operation of food trucks and food delivery services. This system operates based on communication between a server, terminals, and users. Each processing step is explained in detail below.

[1898] Server Processing

[1899] Data collection

[1900] The server uses external APIs to collect area information, such as local food culture, popular trends, and seasonal food ingredients. It also obtains customer attributes and health status data (allergy information, diet information, etc.) from the database.

[1901] Menu generation

[1902] Based on the collected data, the server uses a generative model to generate optimal menu options. For example, it can suggest high-protein, low-calorie menus for businessmen in their 30s. The generated menus are sent to the device.

[1903] Sales Analysis

[1904] The server collects all payment data and stores it in a database. Based on the collected payment data, data analysis algorithms are used to identify sales trends, peak times, and popular menu items. The analysis results are visualized on a dashboard and notified to the operations team.

[1905] Improvement and marketing support

[1906] The server collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and proposes specific improvement measures. It also uses a generative model to generate taglines and logo designs based on customer purchasing trends and segment information, and proposes them to the operations team.

[1907] Terminal handling

[1908] Voice Recognition and Order Fulfillment

[1909] The device receives voice input from the user and converts it into text using a speech recognition system. For example, a user question such as "Do you have any non-spicy menu items?" is converted into text. The device then analyzes the order using a generative model and creates a list of the customer's orders. Additional information from the customer (such as spiciness adjustments or allergies) is collected, and the final order is sent to the staff.

[1910] User operations

[1911] Usage example

[1912] When a user uses their smartphone to ask, "Do you have any low-calorie options?", the device converts this into text using a voice recognition system and suggests "high-protein salad." When the user confirms their order, the details are notified to the staff in real time.

[1913] Prompt Sentence Examples

[1914] 1. Menu suggestion prompt:

[1915] "Area information: Office district. Customer data: 30-year-old male. Please suggest a menu item that is high in protein and low in calories."

[1916] 2. Voice order prompts:

[1917] "User input: Do you have a low-calorie option? Suggestion: High-protein salad."

[1918] This will create a system in which all processes in running a kitchen car or food delivery service are seamlessly linked and can be executed quickly and efficiently.

[1919] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1920] Step 1:

[1921] The server collects area information from external APIs. For example, it collects information on the food culture, popular trends, and seasonal food ingredients of a particular region. This process receives area information as input, retrieves the necessary data from the external API based on that information, and stores it in a database. The input is area information, and the output is the collected data.

[1922] Step 2:

[1923] The server retrieves customer attribute and health condition data from the database. For example, it retrieves the customer's age, gender, occupation, residential area, allergy information, diet information, etc. In this process, it receives the customer ID as input and retrieves the corresponding customer data from the database based on that, which is used in the menu generation process. The input is the customer ID, and the output is the customer attribute and health condition data.

[1924] Step 3:

[1925] The server uses a generative model based on the collected data to generate menu options. For example, it might suggest a "high-protein, low-calorie menu for businessmen in their 30s." This process takes area information and customer data as input, generates optimal menu options using a generative AI model, and sends them to the terminal. The input is area information and customer data, and the output is menu options.

[1926] Step 4:

[1927] The terminal receives voice input from the user and converts it into text using a voice recognition system. For example, if a user asks, "Do you have any non-spicy menu items?", it converts this into text. In this process, voice data is received as input and converted into text data using a voice recognition system. The input is voice data, and the output is text data.

[1928] Step 5:

[1929] The terminal uses a generative model to analyze the order details and create a customer order list. In this process, the terminal uses a generative AI model to analyze the order details based on the voice input converted to text and generates an order list that meets the customer's requests. The input is text data converted by the voice recognition system, and the output is the order list.

[1930] Step 6:

[1931] The terminal collects additional information from the customer and confirms the final order details. For example, it collects information such as spiciness adjustments and whether or not the customer has any allergies. In this process, the additional information from the customer is entered as text data and reflected in the order list. The input is the additional information, and the output is the confirmed final order list.

[1932] Step 7:

[1933] The terminal sends the final order details to the staff member. This process receives the final confirmed order list as input and sends it to the staff member's terminal. The input is the final order list, and the output is the order information sent to the staff member's terminal.

[1934] Step 8:

[1935] The server collects all payment data and stores it in a database, such as the date, time, amount, and payment method of each transaction. This process takes transaction information as input and stores it in the database. The input is the transaction information and the output is the payment data stored in the database.

[1936] Step 9:

[1937] The server identifies sales trends using a generative model that analyzes customer purchasing habits based on collected payment data. For example, it analyzes peak times and popular menu items. This process takes payment data collected from the database as input and analyzes it using the generative AI model. The input is payment data, and the output is the sales trend analysis results.

[1938] Step 10:

[1939] The server visualizes the analysis results and displays them on a dashboard. For example, it displays the most popular menu items over a certain period of time or peak sales times as graphs. This process receives the results of sales trend analysis as input and visualizes the data. The input is the analysis results, and the output is the visual data displayed on the dashboard.

[1940] Step 11:

[1941] The server notifies the operations team of the analysis results. For example, it can inform the team that a particular menu item is very popular, facilitating a response to increase inventory. This process takes the data visualized on the dashboard as input and sends a notification to the team. The input is the visualized data, and the output is a notification to the operations team.

[1942] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1943] This invention is a system that provides a more advanced customized service by combining an emotion engine that recognizes user emotions with menu creation and order processing that are optimal for customer needs, sales analysis, service improvement, and marketing support for a mobile food truck (a type of restaurant). Below, we will provide an overview of this system and a detailed explanation of each processing step.

[1944] System Overview

[1945] This system operates based on communication between a server, terminals, users, and an emotion engine. The server is responsible for key functions such as data collection, menu creation, sales analysis, feedback analysis, and marketing support. The terminal is a device inside the food truck that interacts with customers, processes orders, and analyzes emotions. The user refers to the customers and operations team who use the system. The emotion engine analyzes the user's voice input and facial expressions to recognize the user's emotional state.

[1946] Menu Development

[1947] server:

[1948] Area information such as local food culture, popular trends, and seasonal food ingredient data is collected from an external API, and customer attributes (age, gender, occupation, residential area, etc.) and health status data (allergy information, diet information, etc.) are obtained from a database. Based on this data, a generative model generates optimal menu candidates and sends the proposal list to the device.

[1949] Examples:

[1950] "The server collects data from business districts and generates and suggests high-protein, low-calorie menus for businessmen in their 30s."

[1951] Automated ordering system

[1952] Device:

[1953] The device analyzes the customer's voice input and facial expressions using an emotion engine to recognize the user's emotional state. The voice input is converted into text using a speech recognition system. Based on the analyzed emotion data and the order text, the server uses a generative model to create an order list. Additional information from the customer (e.g., spiciness preference or allergies) is collected, confirmed, and the final order details are sent to the staff.

[1954] Examples:

[1955] "If a user says to the device, 'I'm feeling down today,' the emotion engine will recognize their emotional state and provide a list of menu suggestions based on that information, including, for example, a chocolate dessert that is said to improve mood."

[1956] Sales Analysis

[1957] server:

[1958] All payment data is collected and stored, and data analysis algorithms are used to identify sales trends, peak times, popular menu items, etc. The analysis results are visualized and displayed on a dashboard, and the operations team is notified.

[1959] Examples:

[1960] "The server will use data from the past month to determine that the 'Salmon Avocado Salad' is the best-selling item at lunchtime and report this to the operations team."

[1961] improvement

[1962] server:

[1963] It collects and stores customer reviews and feedback, uses an analytical algorithm to classify positive and negative feedback, and suggests specific improvement measures. It also incorporates emotional state data from an emotion engine.

[1964] Examples:

[1965] "Analysis can be used to identify that multiple customers are dissatisfied with the length of their wait times, and recommendations can be made to increase staffing or revise processes. Furthermore, sentiment data can be used to identify that many customers are dissatisfied with the wait times."

[1966] marketing

[1967] server:

[1968] Customer purchasing patterns and segment information are collected, and a generative model is used to generate slogans and logo designs. Emotional data generated by an emotion engine is also used in marketing. The final materials are presented to the operations team for use in marketing activities.

[1969] Examples:

[1970] "We generate a catchphrase for a new lemon pie product: 'A dish perfect for a refreshing afternoon,' and design it as a poster. Furthermore, we use emotional data to present advertisements that take into account the fact that many customers are seeking refreshment at certain times of the day."

[1971] This system allows food trucks to propose menus and process orders while taking into account the emotional state of customers, analyze sales, improve services through feedback, and implement effective marketing strategies based on emotional data.In this way, the present invention aims to further improve the competitiveness of the food truck industry.

[1972] The processing flow will be explained below.

[1973] Menu Development

[1974] Step 1:

[1975] The server collects area information such as local food culture, popular trends, and seasonal food ingredient data from external APIs.

[1976] Step 2:

[1977] The server retrieves customer attribute data (age, gender, occupation, residential area, etc.) from the database.

[1978] Step 3:

[1979] The server acquires the customer's health condition data (allergy information, diet information, etc.).

[1980] Step 4:

[1981] The server inputs the collected data into a generative model to generate optimal menu candidates.

[1982] Step 5:

[1983] The server transmits the generated menu candidates to the terminal as a proposal list.

[1984] Automated ordering system

[1985] Step 1:

[1986] The terminal automatically launches the dialogue system when the customer arrives.

[1987] Step 2:

[1988] The user enters the order by voice.

[1989] Step 3:

[1990] The terminal converts the voice input into text using a voice recognition system.

[1991] Step 4:

[1992] The device analyzes the user's voice input and facial expressions using an emotion engine to recognize the user's emotional state.

[1993] Step 5:

[1994] The server uses a generative model to create an order list based on the analyzed emotion data and the order text.

[1995] Step 6:

[1996] The terminal collects additional information from the customer (e.g., spiciness preferences or allergies) and confirms the final order.

[1997] Step 7:

[1998] The terminal transmits the final order information to the kitchen staff.

[1999] Sales Analysis

[2000] Step 1:

[2001] The server collects all payment data and stores it in a database.

[2002] Step 2:

[2003] The server uses data analysis algorithms to identify sales trends, peak times, popular menu items, and more.

[2004] Step 3:

[2005] The server visualizes the analysis results and displays them on a dashboard.

[2006] Step 4:

[2007] The server notifies the operation team of the analysis results.

[2008] improvement

[2009] Step 1:

[2010] The server collects reviews and feedback from customers and stores them in a database.

[2011] Step 2:

[2012] The server uses a feedback analysis algorithm to categorize the positive and negative feedback.

[2013] Step 3:

[2014] The server generates specific improvement measures based on the analysis results.

[2015] Step 4:

[2016] The server notifies the operations team of the remedial measures.

[2017] marketing

[2018] Step 1:

[2019] The server collects customer buying patterns and segment information.

[2020] Step 2:

[2021] The server generates a catchy slogan using the generative model.

[2022] Step 3:

[2023] The server designs the logo using an image generation model.

[2024] Step 4:

[2025] The server proposes the generated slogans and logos to the operations team.

[2026] Step 5:

[2027] The operations team will use the proposed tagline and logo in their marketing activities.

[2028] Linking with the Emotion Engine

[2029] Step 1:

[2030] The device collects the user's voice input and facial expressions in real time.

[2031] Step 2:

[2032] The device uses an emotion engine to analyze the collected voice input and facial expressions to identify the user's emotional state.

[2033] Step 3:

[2034] The server obtains the emotional state identified by the emotion engine and reflects it in the generative model.

[2035] Step 4:

[2036] The server adjusts the menu options based on the emotional data and selects a menu that matches the emotional state.

[2037] Step 5:

[2038] The terminal presents tailored menu options to the user, providing an ordering experience that is responsive to the user's emotional state.

[2039] This will enable food trucks to make menu suggestions and process orders that take into account customer emotions, analyze sales, improve services based on feedback, and implement effective marketing strategies based on emotional data.

[2040] Example 2

[2041] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2042] In recent years, mobile food trucks have become popular due to their convenience and uniqueness. However, due to diversifying customer needs and intensifying competition, simply offering a menu is no longer enough to improve customer satisfaction and maintain competitiveness. In particular, there is a demand for menu suggestions tailored to each customer's emotional state and preferences, as well as fast and accurate order processing. Effective use of sales data and customer feedback to improve services and develop effective marketing strategies is also a major challenge.

[2043] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting data on food culture, fashion trends, and seasonal ingredients from regional information, a means for acquiring customer attributes and customer health condition data, and a menu generation means including a generative model that proposes menu candidates generated based on the collected data. This makes it possible to propose menus that meet the individual needs and preferences of each customer.

[2044] The server further includes a means for reviewing the proposed menu candidates and selecting an optimal menu, an emotion analysis means for recognizing the user's emotional state, and a means for customizing the menu based on the emotion data, thereby enabling more advanced customization that takes into account the customer's emotional state.

[2045] The terminal also includes a means for converting a customer's voice input into text using a voice recognition system, a means for analyzing the order details using a generative model and creating an order list for the customer, a means for collecting additional information from the customer and confirming the final order details, a means for transmitting the order information to a staff member, and a means for creating an order list that reflects the user's emotional state, thereby enabling fast and accurate order processing.

[2046] Furthermore, the server includes a means for collecting all payment data and storing it in a database, a data analysis means including a generative model that analyzes customer purchasing trends based on the collected payment data, a means for visualizing the analysis results and displaying them on a dashboard, a means for notifying the operation team of the analysis results, and a means for identifying sales trends including the emotion data analysis results, thereby enabling highly accurate sales analysis and service improvement based on sales data and customer emotion data.

[2047] These measures allow food trucks to provide highly customized services tailored to the individual needs and emotional state of their customers, improving customer satisfaction and strengthening their competitive edge.

[2048] "Regional information" refers to information such as food culture, popular trends, and seasonal food ingredients in a specific region.

[2049] "Customer attributes" refer to personal characteristics such as a customer's age, gender, occupation, and residential area.

[2050] "Health Data" refers to health-related data about a customer, such as allergy information, diet information, etc.

[2051] A "generative model" refers to an algorithm or machine learning model that generates optimal menu options based on collected data.

[2052] "Emotion analysis means" refers to the technology and algorithms used to analyze a user's voice input and facial expressions and recognize their emotional state.

[2053] "Speech recognition system" refers to a system or technology for converting voice input into text.

[2054] "Data analysis means" refers to technologies and algorithms used to analyze collected data and identify customer purchasing and sales trends.

[2055] "Dashboard" refers to an interface that visually displays the results of data analysis so that the operations team can easily understand them.

[2056] This invention is a system that generates optimal menus according to customer needs in kitchen cars, which are mobile restaurants, and handles orders, analyzes sales, improves services, and provides marketing support. In addition, by combining this with an emotion engine that recognizes user emotions, it provides an even more sophisticated customized service.

[2057] System Configuration

[2058] This system operates based on communication between the server, terminals, users, and emotion engine. Specifically, it has the following configuration:

[2059] server

[2060] The server has the following roles:

[2061] 1. Data collection: Collect regional information on food culture, popular trends, and seasonal food data from external APIs (e.g., food database APIs). Also, obtain customer attribute and health status data from an internal database.

[2062] 2. Menu generation: Based on the collected data, a generative AI model is used to generate optimal menu options and create a list of suggestions.

[2063] 3. Emotion Analysis: Recognize the user's emotional state and customize the menu based on the emotional data.

[2064] 4. Sales Analysis: Collect and store all payment data and use it to identify sales trends, peak times, popular menu items, etc.

[2065] 5. Feedback analysis: Collect customer feedback, categorize positive and negative feedback, and suggest improvement measures.

[2066] 6. Marketing Support: Analyze customer purchasing patterns and generate slogans and logo designs using generative AI models.

[2067] Terminal

[2068] The terminal interacts with customers inside the kitchen car and performs the following functions:

[2069] 1. Speech-to-text conversion: Converts customer voice input into text through a speech recognition system (e.g., Google Speech-to-Text API).

[2070] 2. Emotion Analysis: Using an emotion engine, analyze the customer's facial expressions to recognize their emotional state.

[2071] 3. Order processing: Based on the voice input and additional information, the server uses a generative AI model to create an order list, and then confirms the final order and sends it to the staff.

[2072] User

[2073] Users are the customers and operations team who use the system. Customers provide information such as voice input and facial expressions, and the operations team improves services based on sales data and feedback analysis provided by the server.

[2074] Specific examples

[2075] For example, the server can collect data from a business district and generate and suggest high-protein, low-calorie menus for a businessman in his 30s. If a user says, "I'm feeling down today," the emotion engine can recognize their emotional state and provide a list of menu options based on that. For example, it can suggest a menu that includes chocolate desserts, which are believed to improve mood.

[2076] In addition, the server can analyze payment data from the past month to determine that the "Salmon Avocado Salad" is the best-selling item at lunchtime and report this to the operations team. It can also analyze feedback from multiple customers and, if it identifies dissatisfaction with long wait times, it can suggest hiring more staff or revising processes.

[2077] Prompt Sentence Examples

[2078] "If a user says to the device, 'I want a hot stew on a cold day,' what kind of menu suggestions would you generate?"

[2079] This invention allows food trucks to propose menus and process orders taking into account the emotional state of customers, analyze sales, improve services through feedback, and implement effective marketing strategies based on emotional data, thereby improving customer satisfaction and strengthening competitiveness.

[2080] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2081] Step 1: Data collection

[2082] server:

[2083] The server collects data on food culture, popular trends, and seasonal ingredients from local information. Specifically, it obtains data by calling external APIs (e.g., ingredient database APIs and trend analysis APIs). The input is raw data from the API, and the output is a formatted dataset.

[2084] Input: Raw data from the API

[2085] Output: A formatted dataset

[2086] Specific behavior:

[2087] The server makes an API request to obtain regional food culture and trend data.

[2088] The acquired raw data is formatted, converted into the required format, and saved.

[2089] Step 2: Obtain customer information

[2090] server:

[2091] The server retrieves customer attribute data and health status data from an internal database. It uses SQL queries to pull information from the database. The input is the customer ID and request parameters, and the output is a record of customer data.

[2092] Input: Customer ID, request parameters

[2093] Output: Customer data records

[2094] Specific behavior:

[2095] The server accesses the database and retrieves attribute data corresponding to the particular customer.

[2096] The acquired data is stored in memory and used for subsequent processing.

[2097] Step 3: Create a menu

[2098] server:

[2099] The server uses a generative AI model based on the collected data to generate optimal menu options. The generative model receives various data as input and outputs an optimal menu list.

[2100] Input: Regional information data, customer data

[2101] Output: Menu candidate list

[2102] Specific behavior:

[2103] The server provides input data to the generative AI model and runs the menu generation algorithm.

[2104] The algorithmically generated menu candidate list is sent to the terminal.

[2105] Step 4: Speech and emotion analysis

[2106] Device:

[2107] The device receives voice input and facial expression information from the customer and performs emotion analysis, converting the voice input into text through a voice recognition system and recognizing the customer's emotional state using a facial expression analysis engine.

[2108] Input: Voice input, facial expression image

[2109] Output: Text data, emotion data

[2110] Specific behavior:

[2111] A speech recognition system converts voice input into text.

[2112] The facial expression analysis engine uses image data acquired from the camera to analyze the emotional state.

[2113] Step 5: Create an order list

[2114] server:

[2115] The server uses a generative AI model to create an order list based on the analyzed voice-to-text and emotion data, and also incorporates additional information from the customer.

[2116] Input: Speech text, emotion data, additional information

[2117] Output: Order list

[2118] Specific behavior:

[2119] The server provides the voice text and emotion data to a generative AI model to analyze the order.

[2120] Based on the analysis results and additional customer information, a final order list is created and sent to staff.

[2121] Step 6: Collect and analyze sales data

[2122] server:

[2123] The server collects all payment data and stores it in a database, which is then used to analyze sales and purchasing trends using generative AI models.

[2124] Input: Payment data

[2125] Output: Sales trends, buying trends

[2126] Specific behavior:

[2127] The server collects the payment data and stores it in a database.

[2128] Generative AI models are used to analyze collected data and identify sales and purchasing trends.

[2129] Step 7: Feedback and Service Improvement

[2130] server:

[2131] The server collects customer feedback, categorizes and analyzes positive and negative feedback, and also utilizes sentiment data.

[2132] Input: Feedback data, emotion data

[2133] Output: Improvement suggestions

[2134] Specific behavior:

[2135] Categorize and analyze feedback data collected from customers.

[2136] We propose specific service improvement measures based on emotional data.

[2137] Step 8: Marketing Support

[2138] server:

[2139] The server analyzes customer purchasing patterns and segment information, and generates catchphrases and logo designs using generative AI models. Emotional data is also used for marketing.

[2140] Input: Purchasing data, emotion data

[2141] Output: Catchphrase, logo design

[2142] Specific behavior:

[2143] It collects and analyzes customer purchasing data and uses generative AI models to generate marketing slogans and logo designs.

[2144] Provide proposed marketing materials to the operations team for use in campaigns.

[2145] (Application example 2)

[2146] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2147] Conventional food trucks and food delivery services have had difficulty proposing menus that take into account the individual emotions and mood of each customer. Furthermore, the lack of personalized service based on customer emotions has made it difficult to improve customer satisfaction and attract repeat customers. The present invention aims to solve these problems and provide a service that is sensitive to the emotions of customers.

[2148] The identification processing by the identification 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 collecting data on local food culture, popular trends, and seasonal ingredients from area information; means for acquiring customer attributes and customer health condition data; menu generation means including a generative model that proposes menu candidates generated based on the collected data; means for reviewing the proposed menu candidates and selecting an optimal menu; an emotion recognition engine that analyzes the customer's voice input and facial expressions to recognize their emotional state; and means for providing an optimal menu taking the user's emotional state into consideration. This enables personalized menu suggestions and order processing according to the customer's emotions.

[2149] "Area information" refers to data about culture, trends, seasonal ingredients, and other information related to a specific region.

[2150] "Customer attributes" refers to basic information about customers, such as age, gender, occupation, and residential area.

[2151] "Health data" refers to health-related data such as a customer's allergy information, diet information, and medical history.

[2152] A "generative model" refers to a machine learning model that generates a specific output (in this case, menu candidates) based on collected data.

[2153] An "emotion recognition engine" refers to software or hardware that analyzes a user's voice input and facial expressions and recognizes their emotional state.

[2154] "Menu generation means" refers to a mechanism that generates and suggests menu candidates using a generative model from collected data.

[2155] "Means for analyzing order details" refers to a system for analyzing and listing specific order details based on voice input or text data from customers.

[2156] "Visualization" refers to visually displaying analyzed data as graphs or tables.

[2157] "Dashboard" refers to an interface for visualizing and managing data in real time.

[2158] "Personalized suggestions" refer to providing specialized menus and services based on a customer's individual emotional state and past behavioral data.

[2159] This invention is a system for food trucks and food delivery services that proposes menus that take into account customer emotions, processes customized orders, analyzes sales, improves services, and provides marketing support. The entire system is described in detail below.

[2160] System configuration

[2161] This system operates based on communication between a server, a terminal, a user, and an emotion recognition engine.

[2162] Server Features

[2163] The server has the following main functions:

[2164] 1. Data collection: Local food culture, popular trends, and seasonal food ingredient data are collected from area information via external APIs, and customer attributes (age, gender, occupation, residential area, etc.) and health data (allergy information, diet information, etc.) are obtained from the database.

[2165] 2. Menu generation: Based on this data, the generative model generates optimal menu candidates and sends the proposal list to the device.

[2166] 3. Sales Analysis: Collect and store all payment data and use data analysis algorithms to identify sales trends, peak times, popular menu items, etc.

[2167] 4. Feedback analysis and service improvement: Collect and store customer reviews and feedback, use an analysis algorithm to classify positive and negative feedback, and propose specific improvement measures. It also reflects emotional state data.

[2168] 5. Marketing support: Collect customer purchasing patterns and segment information, and use generative models to generate slogans and advertising materials.

[2169] Device Features

[2170] The terminal refers to the terminal inside the food truck or the smartphone carried by the customer, and performs the following processes.

[2171] 1. Speech and emotion recognition: The voice input and facial expressions from the customer are analyzed using an emotion recognition engine and converted into text.

[2172] 2. Order Processing: The voice recognition system converts the customer's voice input into text, analyzes the order using a generative model, creates a list of the customer's orders, collects additional information from the customer (e.g., spiciness preference, allergies), and sends the final order to the staff after confirmation.

[2173] User Roles

[2174] Users include both customers and the operations team. Customers can speak to the device or point their face at it to input their voice and facial expressions, and receive personalized menu suggestions. The operations team then carries out actual operations and marketing activities based on sales analysis results and suggestions from the server.

[2175] Specific examples

[2176] Menu Development

[2177] A customer speaks to their smartphone saying, "I'm tired today and want to eat something sweet." The emotion recognition engine reads the "tired" emotion from the customer's facial expression, and the voice recognition system converts the speech into text. The server uses a generative model to suggest menu options for "sweet desserts to soothe fatigue." For example, it might recommend "chocolate cake" or "cream pudding."

[2178] Sales Analysis

[2179] The server collects past sales data and displays analytical results on a dashboard, such as "Salmon Avocado Salad is the best-selling item at lunchtime." This information is also sent to the operations team, who use it to manage inventory and improve the menu.

[2180] Marketing using emotional data

[2181] Using data from its emotion recognition engine, the server determines that many customers are looking for "refreshment" at certain times of the day, and launches an advertising campaign for lemon pie with the tagline "The perfect treat for a refreshing afternoon."

[2182] Implementation environment

[2183] Hardware: Smartphones, tablets, and devices with cameras

[2184] Software: Python, TensorFlow, OpenCV, external API (obtaining local information and food ingredient data)

[2185] Emotion Recognition Engine: Uses pre-trained models to recognize emotions from customers' voices and facial expressions

[2186] Prompt Sentence Examples

[2187] User Input:

[2188] "I'm tired and feeling sick"

[2189] System response:

[2190] "You've had a very hard day today. How about this 'Chicken and Broccoli Cream Pasta' to replenish your energy?"

[2191] Generate AI model prompt:

[2192] "The user's emotion has been determined to be 'sad'. Please suggest the best menu to improve the user's physical condition. For example, high-calorie meals or foods that improve mood."

[2193] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2194] Step 1:

[2195] The server collects area information from an external API. The input is the area specification and the external API call, and the output is area information such as local food culture, popular trends, and seasonal food ingredient data. Specifically, the API is called to obtain area information and it is stored in a database.

[2196] Step 2:

[2197] The server retrieves customer attributes and health status data from a database. The input is customer identification information, and the output is attribute data such as the customer's age, gender, occupation, residential area, allergy information, and diet information. Specifically, the server executes a database query to retrieve customer information.

[2198] Step 3:

[2199] The server uses a generative model to generate menu candidates based on the data collected. The input is area information and customer information, and the output is a list of suggested menu candidates. Specifically, data is input into the generative model to generate the optimal menu candidates.

[2200] Step 4:

[2201] The device analyzes the customer's voice input and facial expressions using an emotion recognition engine. The input is the customer's voice data and camera video data, and the output is text-translated voice data and recognized emotional information. Specifically, the voice recognition system converts the voice into text, and a facial recognition algorithm is used to determine emotions from facial expressions.

[2202] Step 5:

[2203] The server uses a generative model to analyze the order details based on the emotion-recognized data and voice-text data, and creates a customer order list. The input is emotion-recognized data and voice-text data, and the output is an order list. Specifically, data is input into the generative model, and the order details are analyzed.

[2204] Step 6:

[2205] The terminal collects additional information from the customer (such as spiciness adjustments and allergies) and sends the final order details to the server. The input is the customer's additional information, and the output is the final order list. Specifically, the customer enters the additional information via a GUI and then sends it to the server.

[2206] Step 7:

[2207] The server collects all payment data and stores it in a database. The input is the payment transaction data and the output is the stored payment data. Specifically, it retrieves data from the payment system and records it in the database.

[2208] Step 8:

[2209] Based on the payment data collected by the server, a generative model is used to analyze customer purchasing trends. The input is payment data, and the output is the analysis results of purchasing trends. Specifically, the payment data is processed by an analytical algorithm to identify purchasing trends and peak times.

[2210] Step 9:

[2211] The server visualizes the analysis results and displays them on a dashboard. The input is the analysis result data, and the output is the visually displayed data. Specifically, the data is plotted on graphs and charts and displayed in the interface.

[2212] Step 10:

[2213] Based on the analysis results and emotion data, the server notifies the operations team and marketing activities with the necessary information. The input is the analysis results and emotion data, and the output is notification information. Specifically, the server sends relevant information to relevant parties through the notification system.

[2214] Step 11:

[2215] The server collects and analyzes customer feedback and proposes service improvement proposals. The input is customer reviews and feedback data, and the output is improvement proposals. Specifically, it analyzes the feedback data, classifies negative feedback, and identifies areas for improvement.

[2216] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2217] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The ...

Claims

1. A means of collecting information on local food culture, popular trends, and seasonal ingredients from area information, a means for obtaining customer attribute and customer health status data; a menu generation means including a generative model that proposes menu candidates generated based on the collected data; A means to review proposed menu options and select the most suitable menu; A system including:

2. means for converting a customer's voice input into text using a voice recognition system; a means for analyzing the order details using the generative model and generating a customer order list; A means of gathering additional information from the customer and confirming the final order; a means for transmitting order information to staff; The system of claim 1 , comprising:

3. A means of collecting all payment data and storing it in a database; a data analysis means including a generative model for analyzing customer purchasing trends based on the collected payment data; A means to visualize the analysis results and display them on a dashboard; A means of communicating the analysis results to the operations team; The system of claim 1 , comprising:

4. A means of collecting customer reviews and feedback and storing them in a database; A means of analyzing the feedback and categorizing the negative and positive points; an improvement suggestion means including a generative model that proposes specific improvement measures; The system of claim 1 , comprising:

5. A means of collecting customer purchasing patterns and segment information; A means for generating a catchphrase using a generative model; A means for designing a logo using an image generation model; The generated catchphrases and logos will be proposed to the operations team for use in marketing. The system of claim 1 , comprising:

6. a marketing analysis means including a generative model that analyzes the effects of marketing measures and generates an optimal marketing strategy; A means of communicating the generated marketing strategies to the operations team; The system of claim 5 , comprising:

Images