System

Abstract

A system is provided.SOLUTION: An order support system comprising: means for receiving order details input by a user; means for analyzing the order details using a generated AI model; means for converting the order details into an order format for each shop based on a result of the analysis; means for presenting the converted order details to the user; and means for receiving an order confirmation message from the shop and notifying the user of the order confirmation message.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 purpose of this invention is to eliminate the anxiety, misunderstandings, and communication problems that arise when ordering at a store for the first time, when multilingual support is required, or when diversity is a major concern. Conventional systems require users to follow the ordering format specific to each store, which can lead to numerous issues. It is also difficult for store staff to keep track of all customers' order histories and preferences. [Means for solving the problem]

[0005] The present invention provides an order assistance system in which a user terminal and a server are communicatively connected, comprising: a means for accepting order details entered by a user; a means for analyzing the order details using a generative AI model; a means for converting the order details into an order format specific to each store based on the analysis results; a means for presenting the converted order details to the user; a means for transmitting the order details finally confirmed by the user to the store; and a means for receiving an order confirmation message from the store and notifying the user. This system allows users to easily place orders without worrying about the store's order format, and allows store staff to efficiently serve customers. Furthermore, the system can meet various user needs by supporting multiple languages ​​and generating personalized suggestions.

[0006] "User terminal" refers to the device that a user uses to access the system and enter or confirm orders. This includes smartphones, tablets, and PCs.

[0007] "Server" refers to a computer system that is connected to a user terminal and can communicate with the user terminal, and that analyzes and converts order details and provides notifications. This primarily includes cloud servers and data center servers.

[0008] "Order details" refers to information such as product type, quantity, options, etc. that a user inputs or specifies using the system.

[0009] A "generative AI model" refers to an algorithm or program that uses machine learning and natural language processing techniques to analyze and understand the meaning of input order details.

[0010] "Analysis" refers to the process of using a generative AI model to interpret and understand the intent and meaning of an order.

[0011] "Conversion" refers to the process of adapting the order details to the order format of each store based on the analysis results.

[0012] "Presenting" refers to displaying the converted order details or proposals on the user terminal.

[0013] "Send" refers to a communication process in which order details or a confirmation message is sent from the server to the user terminal or from the server to the store.

[0014] "Notification" refers to a message sent to inform the user that the order has been confirmed and completed by the store.

[0015] "Multilingual support" refers to the system's ability to support multiple languages ​​and translate orders and messages based on the language selected by the user.

[0016] "Personalized suggestions" refers to a feature that suggests the most suitable products and options to a user, taking into account the user's past order history and preferences. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

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

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

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

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0032] 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.

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

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This system, "OrderBridge," connects the user's device and server for communication, allowing the user to smoothly place orders at stores they visit for the first time. When the user enters their order details, the details are analyzed by a generative AI model and converted into a format suitable for the store. The system also supports multiple languages ​​and provides personalized suggestions.

[0039] System Overview

[0040] 1. User Device

[0041] User terminals include devices such as smartphones, tablets, and personal computers. Users use these terminals to input order details, confirm the order, and finalize it.

[0042] 2. Server

[0043] The server is communicatively connected to the user terminal and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, sending them to the store, and notifying the user.

[0044] 3. Generative AI Models

[0045] The generative AI model includes machine learning algorithms used to analyze order content and generate recommendations, allowing it to interpret and convert order content entered by users in natural language into an appropriate format.

[0046] Program processing explanation

[0047] 1. User Order Entry

[0048] The user launches the application on the device, selects a language, and then enters their order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the device to the server.

[0049] 2. Server analyzes the order

[0050] The server passes the received order details to the generative AI model for analysis. The generative AI model analyzes the input and understands the intent of the order.

[0051] 3. Order Conversion

[0052] The server then converts the order into a store-specific format based on the analysis results returned by the generative AI model, such as "one cheeseburger and one fries."

[0053] 4. Multilingual support

[0054] The server translates the converted order content into the appropriate language based on the language selected by the user.

[0055] 5. Generate personalized suggestions

[0056] The server considers the user's past ordering history and preferences and suggests additional options (e.g., "Would you like to add a chocolate shake?").

[0057] 6. Confirm and confirm the order details after conversion

[0058] The server presents the converted order details and suggestions to the user, which are displayed on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button, after which the final order details are sent to the server.

[0059] 7. Sending and confirming orders to the store

[0060] The server sends the confirmed order details to the store, which receives the order details. The store staff processes the order and sends a confirmation message to the server after completion.

[0061] 8. Order completion notification

[0062] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check the notification and find out the redemption code, pick-up time, etc.

[0063] Specific examples

[0064] Restaurant orders:

[0065] A user launches the OrderBridge app and selects English.

[0066] The user enters, "I want to order a cheeseburger and fries."

[0067] The terminal sends the order details to the server.

[0068] The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[0069] The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[0070] The server considers the user's past history and suggests, "Would you like to add a chocolate shake?"

[0071] The user checks and confirms the order.

[0072] The terminal sends the final order details to the server.

[0073] The server sends the final order details to the store.

[0074] Store staff processes the order and sends a confirmation message to the server once completed.

[0075] The server sends an order completion notification to the user's terminal.

[0076] The present invention is expected to facilitate smooth communication between users and stores, significantly reducing troubles with orders.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The user launches the OrderBridge app and the home screen appears.

[0080] Step 2:

[0081] Users select the language they want to use on their home screen.

[0082] Step 3:

[0083] The terminal sends the selected language information to the OrderBridge server.

[0084] Step 4:

[0085] The server records the received language information and loads the corresponding language resource.

[0086] Step 5:

[0087] The user opens an order entry screen on their device and enters what they want to order (e.g., "I want to order a cheeseburger and fries").

[0088] Step 6:

[0089] The terminal sends the entered order details in text format to the OrderBridge server.

[0090] Step 7:

[0091] The server receives the order details and passes them to the generative AI model.

[0092] Step 8:

[0093] A generative AI model analyzes the order and extracts the intent behind it (e.g., recognizing two orders: "cheeseburger" and "fries").

[0094] Step 9:

[0095] The server receives the analysis results from the generative AI model and converts them into a store-specific order format (e.g., "one cheeseburger and one fries").

[0096] Step 10:

[0097] The server translates the converted order into the user's language of choice (e.g., English) (e.g., "Order 1 cheeseburger and 1 fries").

[0098] Step 11:

[0099] The server considers the user's past ordering history and preferences and suggests additional options (e.g., "Would you like to add a chocolate shake?").

[0100] Step 12:

[0101] The server sends the converted order details and proposals to the user terminal.

[0102] Step 13:

[0103] The terminal displays the order and additional suggestions to the user.

[0104] Step 14:

[0105] The user checks the order details, corrects them if necessary, and finally presses the confirm button.

[0106] Step 15:

[0107] The terminal sends the final order details to the OrderBridge server.

[0108] Step 16:

[0109] The server receives the final order details and sends them to the store's system.

[0110] Step 17:

[0111] The store's system receives the order and begins processing it.

[0112] Step 18:

[0113] Store staff prepare the order and, once complete, send a confirmation message to the OrderBridge server.

[0114] Step 19:

[0115] The server receives a confirmation message from the store.

[0116] Step 20:

[0117] The server sends an order completion notification to the user's terminal.

[0118] Step 21:

[0119] The terminal will display a code to the user to complete the order and redeem it.

[0120] Example 1

[0121] 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."

[0122] Conventional ordering support systems have problems such as difficulty in ordering at stores visited for the first time or in communicating in a foreign language, which can easily lead to problems. Furthermore, they often lack personalized suggestions based on the user's past preferences and order history, resulting in a poor user experience. To solve these problems, a new ordering support system with multilingual support and personalized suggestion functionality is needed.

[0123] 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.

[0124] In this invention, the server includes means for accepting order details entered by a user, means for analyzing the order details using a generative AI model, means for converting the order details into a format for each information system based on the analysis results, means for presenting the converted order details to the user, means for transmitting the order details finally confirmed by the user to the information processing device, means for receiving an order confirmation message from the information processing device and notifying the user, means for generating personalized suggestions based on the user's past order history and preferences, and means for appropriately translating the order details based on the selected language. This allows users to smoothly place orders even at stores they visit for the first time, and is expected to improve the user experience through multilingual support and personalized suggestions.

[0125] A "user terminal" is a computer device that allows a user to input, confirm, and finalize an order, and specifically includes a smartphone, tablet, PC, etc.

[0126] A "server" is a computer device that is communicatively connected to a user terminal and performs processes such as receiving order details, analyzing, converting, translating, generating suggestions, sending to stores, and notifying users.

[0127] A "generative AI model" is a model that uses machine learning algorithms to analyze input order details and convert the order details into a format specific to each store.

[0128] "Order details" refers to information about the product or service that the user wishes to purchase, which is input into the terminal.

[0129] The "order format" is a format that has been converted and formatted to make the analyzed order content easier for stores and information systems to process.

[0130] "Multilingual support" is a function that translates and displays order details based on the different languages ​​selected by the user when entering an order.

[0131] "Personalized Offers" refers to additional offers or options that are individually provided to a user based on the user's past order history and preference data.

[0132] An "order confirmation message" is a message that a store sends to a server after accepting a user's order and confirming its contents.

[0133] This invention is a system that allows users to input order details using a terminal, and a server analyzes and converts the details and transmits the order to the store in an appropriate format. This system uses the user terminal, server, and generative AI model to smoothly perform the entire process from order input to confirmation, confirmation, and notification, and also has multilingual support and personalized suggestion functions.

[0134] User terminal

[0135] A user terminal is a device that is directly operated by a user, and includes a smartphone, tablet, PC, etc. A dedicated application is installed on these devices, and the user launches this application to place an order.

[0136] server

[0137] The server is connected to the user's device and performs a series of processes, from receiving the order details to analyzing, converting, translating, generating suggestions, and sending them to the store. The server is equipped with a generative AI model and properly analyzes the user's natural language input.

[0138] Generative AI Models

[0139] The generative AI model is used to analyze orders using machine learning algorithms and convert them into store-specific order formats. The model also has multilingual support and can translate orders based on the language selected by the user.

[0140] Specific examples

[0141] Here's a sample order at a restaurant:

[0142] 1. The user launches the OrderBridge app and selects English.

[0143] 2. The user enters, "I want to order a cheeseburger and fries."

[0144] 3. The terminal sends the order details to the server.

[0145] 4. The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[0146] 5. The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[0147] 6. The server considers the user's past history and suggests, "Would you like to add a chocolate shake?"

[0148] 7. The user confirms and confirms the order.

[0149] 8. The terminal sends the final order details to the server.

[0150] 9. The server sends the final order details to the store.

[0151] 10. The store staff processes the order and sends a confirmation message to the server once completed.

[0152] 11. The server sends an order completion notification to the user's device.

[0153] This system allows users to place orders smoothly, regardless of language barriers, and allows stores to receive accurate orders. Furthermore, personalized suggestions are expected to improve the user experience.

[0154] Example prompt sentence:

[0155] "I want to order a cheeseburger and fries"

[0156] "Can I get a vegetarian pizza with extra cheese?"

[0157] "I would like to add a large coffee to my order"

[0158] The system of the present invention is expected to streamline the entire ordering process and strengthen communication between users and stores.

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Step 1:

[0161] User order entry

[0162] The user launches the OrderBridge app on their device (smartphone, tablet, or PC) and selects the language they wish to use. Next, the user enters the order details in natural language and presses the submit button. The order details entered by the user are then saved as text data on the device. For example, the user might enter "I want to order a cheeseburger and fries." This text data is sent to the server.

[0163] Input: User's natural language order details

[0164] Output: Text data of the order details sent to the server

[0165] Step 2:

[0166] Server parsing of order details

[0167] The server passes the text data received from the device to the generative AI model, which uses natural language processing technology to analyze the user's input. As a result of the analysis, the model extracts the ordering intent (e.g., "I would like to order a cheeseburger and fries") and generates semantic data in digital form.

[0168] Input: Text data of order details from the terminal

[0169] Output: Digital data of parsed order details

[0170] Step 3:

[0171] Order conversion

[0172] The server receives the analysis results from the generative AI model and converts the order content into a store-specific format based on the analysis results. For example, "I want to order a cheeseburger and fries" is converted into "1 cheeseburger and 1 fries."

[0173] Input: Analyzed digital data of order details

[0174] Output: Order details converted into a store-friendly format

[0175] Step 4:

[0176] Multilingual support

[0177] The server translates the converted order into the appropriate language based on the user's language selection: if the user selects English, the converted order will be translated as "Order 1 cheeseburger and 1 fries."

[0178] Input: Order details converted into store-appropriate format, user's preferred language setting

[0179] Output: Order details translated into the selected language

[0180] Step 5:

[0181] Generate personalized suggestions

[0182] The server will refer to the user's past order history and preference data to generate appropriate additional suggestions. For example, if a user has previously ordered a chocolate shake, the server will generate the suggestion "Would you like to add a chocolate shake?"

[0183] Input: User's past order history, preference data

[0184] Output: Personalized suggestions

[0185] Step 6:

[0186] Confirm and confirm the order details after conversion

[0187] The server presents the converted order and personalized suggestions to the user, who can then review the order on their device and make any necessary corrections. Finally, when the user presses the confirm button, the final order is sent to the server.

[0188] Input: translated order, personalized suggestions

[0189] Output: Order details and proposals presented to the user, and final order details

[0190] Step 7:

[0191] Sending and confirming orders to the store

[0192] The server sends the order details confirmed by the user to the store. The store's system receives the order details and begins processing the order. Once the order is processed, the store's system sends a confirmation message to the server.

[0193] Input: Final order details

[0194] Output: Order details sent to the store, confirmation message from the store

[0195] Step 8:

[0196] Order completion notification

[0197] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check information such as the redemption code and pickup time.

[0198] Input: Confirmation message from the store

[0199] Output: Order completion notification sent to the user

[0200] The above processing flow allows the user to place an order smoothly and the store to receive the order accurately.

[0201] (Application example 1)

[0202] 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."

[0203] In the modern restaurant and food delivery industry, ordering is often difficult when users are visiting a new restaurant or using a new platform. Meanwhile, there is a need to improve the user experience due to issues with translation between different languages ​​and a lack of appropriate suggestions based on user preferences. Furthermore, the lack of personalized suggestions based on past ordering history makes it difficult for users to efficiently order what suits their preferences.

[0204] 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.

[0205] In this invention, the server includes: means for being communicatively connected to a user terminal; means for accepting order details entered by a user; means for analyzing the order details using a generative AI model; means for converting the order details into an order format for each store based on the analysis results; means for presenting the converted order details to the user; means for sending the order details finally confirmed by the user to the store; means for receiving an order confirmation message from the store and notifying the user; means for translating the order details into a language selected by the user with a multilingual function; means for generating personalized suggestions based on the user's past ordering history and preferences; and means for transmitting the order details to affiliated restaurants. This allows users to smoothly order at stores or platforms they are using for the first time through appropriate suggestions based on translation issues between different languages ​​and user preferences, as well as personalized suggestions.

[0206] "User terminal" refers to a device used by a user to input order details, such as a smartphone, tablet, or PC.

[0207] "Server" refers to a computer system that is communicatively connected to a user terminal and performs processes such as receiving, analyzing, converting, translating, generating suggestions, sending to the restaurant, and notifying the user.

[0208] A "generative AI model" refers to a model that includes machine learning algorithms to interpret order details entered in natural language and convert them into an appropriate format.

[0209] "Multilingual support" refers to the ability to automatically translate orders based on the language selected by the user.

[0210] "Personalized suggestions" refers to the ability to generate additional options and suggestions based on a user's past ordering history and preferences.

[0211] "Food delivery service" refers to a service that allows users to order food and drinks from restaurants using their smartphones and have them delivered.

[0212] An "order confirmation message" refers to a message that confirms that the restaurant has accepted the order details confirmed by the user.

[0213] MODE FOR CARRYING OUT THE INVENTION

[0214] The present invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other. Below, the processing of a program for realizing this system and a specific example thereof will be described.

[0215] System Configuration

[0216] The system mainly consists of the following components:

[0217] 1. User Device

[0218] Smartphone (iOS or ANDROID (registered trademark))

[0219] tablet

[0220] PC

[0221] 2. Server

[0222] Cloud hosting (e.g., AWS (registered trademark))

[0223] Database (e.g. MongoDB)

[0224] Machine learning models (e.g., generative AI models using GPT-3 (registered trademark))

[0225] 3. Software

[0226] Frontend: React Native

[0227] Backend: Node.js, Express.js

[0228] Program processing explanation

[0229] 1. User Order Entry

[0230] A user launches a smartphone application, selects their preferred language, and then enters their order details in natural language into the application's input field. For example, they might enter, "I'd like to order a pizza and a cola."

[0231] 2. Server analyzes the order

[0232] The terminal sends the entered order details to the server. The server passes the order details to the generative AI model for analysis. The generative AI model analyzes the order details and understands the user's intentions.

[0233] 3. Order Conversion

[0234] Based on the analysis results, the server converts the order details into a format specific to the partner restaurant, such as "one pizza and one bottle of coke."

[0235] 4. Multilingual support

[0236] The server automatically translates the order based on the language selected by the user.

[0237] 5. Generate personalized suggestions

[0238] The server takes into account the user's past ordering history and preferences to make further recommendations, such as "Would you like some garlic bread as a side?"

[0239] 6. Confirm and confirm the order details after conversion

[0240] The server presents the converted order details and suggestions to the user. When the user confirms the details and finally presses the confirm button, the confirmed order details are sent to the server.

[0241] 7. Sending and confirming orders to restaurants

[0242] The server sends the confirmed order to the partner restaurant, which receives the order, and the restaurant's system receives it. The restaurant staff processes the order and sends a confirmation message to the server once it is complete.

[0243] 8. Order completion notification

[0244] The server receives a confirmation message from the restaurant and sends a completed order notification to the user's smartphone, along with information such as a redemption code and pickup time.

[0245] Specific examples

[0246] For example, a user launches the FoodEase app and selects English. Then, they enter, "I want to order a Hawaiian pizza and a coke." The input is sent to the server and analyzed by the generative AI model. The analysis results in "One Hawaiian pizza and one bottle of Coca-Cola." The model then suggests, "Would you like to add garlic bread to your order?" Once the user confirms and places the order, the server sends the final order details to the partner restaurant. The restaurant processes the order and sends a confirmation message to the server, which then sends the user a notification that the order is complete.

[0247] Prompt Sentence Examples

[0248] User order: "I want to order a cheeseburger and fries"

[0249] Response: "Your order was recognized as '1 cheeseburger, 1 fries'. Additional suggestion: 'Would you like to add a chocolate shake?'"

[0250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0251] Step 1:

[0252] The user starts up the device (smartphone) and launches the FoodEase application. The user selects their preferred language before entering their order. The input at this stage is the language setting of the application. There is no output to the server.

[0253] Step 2:

[0254] A user enters their order in natural language into an application's input field, for example, "I want to order a Hawaiian pizza and a coke." This input is sent from the device to the server, where it is forwarded to the server and prepared for analysis.

[0255] Step 3:

[0256] The server sends the received natural language order content to the generative AI model for analysis. The input for analysis is "I want to order a Hawaiian pizza and a coke." The generative AI model understands the order content and outputs formatted order data (e.g., "One Hawaiian pizza and one bottle of Coca-Cola").

[0257] Step 4:

[0258] The server converts the order details into a format specific to the partner restaurant based on the analysis results of the generative AI model. The input is the analyzed order data, and the output is the converted order data (e.g., "One Hawaiian pizza and one bottle of Coca-Cola"). The server then prepares this to be presented to the user.

[0259] Step 5:

[0260] The server translates the order based on the language selected by the user. For example, if the parsing result is "1 Hawaiian pizza and 1 Coca-Cola," it translates it into the selected language. In this case, the input is the parsing result, and the output is the translated order (e.g., "Order 1 Hawaiian pizza and 1 coke").

[0261] Step 6:

[0262] The server considers the user's past order history and preferences and suggests additional options. The input is the user's order history data and current order details, and the output is a recommendation (e.g., "Would you like to add garlic bread to your order?").

[0263] Step 7:

[0264] The server sends the converted and translated order details and suggestions to the user terminal. The user checks the details and finally presses the confirm button. The input is the suggested order details and additional suggestions, and the output is the user's final confirmation action.

[0265] Step 8:

[0266] When the user's final confirmation action is sent to the server, the server sends the confirmed order details to the partner restaurant. The input is the final confirmed order details, and the output is the order data for the restaurant. The restaurant accepts the order and starts processing it.

[0267] Step 9:

[0268] Once the restaurant has processed the order, it sends a confirmation message to the server. The server receives the confirmation message and sends a notification of order completion to the user's smartphone. The input is the confirmation message from the restaurant, and the output is a notification of order completion to the user's device.

[0269] This series of processing steps allows users to smoothly input and confirm order details even when using a store or platform for the first time.

[0270] 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.

[0271] This invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other, allowing users to smoothly place orders at stores they visit for the first time. This system uses a generative AI model to analyze order details and convert them into an order format specific to each store. It also supports multiple languages, provides personalized suggestions, and is equipped with an emotion engine that recognizes user emotions.

[0272] System Overview

[0273] 1. User Device

[0274] User terminals include devices such as smartphones, tablets, and personal computers. Users use these terminals to input order details, confirm the order, and finalize it.

[0275] 2. Server

[0276] The server is communicatively connected to the user terminal and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, analyzing emotions, sending to the store, and notifying the user.

[0277] 3. Generative AI Models

[0278] The generative AI model includes machine learning algorithms used to analyze order content and generate recommendations, allowing it to interpret and convert order content entered by users in natural language into an appropriate format.

[0279] 4. Emotion Engine

[0280] The emotion engine analyzes the user's emotions from their voice and text input, and provides information and suggestions appropriate to the user based on the analysis results, enabling appropriate responses to be made according to the user's emotions.

[0281] Program processing explanation

[0282] 1. User Order Entry

[0283] The user launches the application on the device, selects the language they want to use, and then enters their order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the device to the server.

[0284] 2. Server analyzes the order

[0285] The server passes the received order details to the generative AI model for analysis. The generative AI model analyzes the input and understands the intent of the order.

[0286] 3. Order Conversion

[0287] The server then converts the order into a store-specific format based on the analysis results returned by the generative AI model, such as "one cheeseburger and one fries."

[0288] 4. Multilingual support

[0289] The server translates the converted order into the appropriate language based on the user's language selection (e.g., "Order 1 cheeseburger and 1 fries").

[0290] 5. User sentiment analysis

[0291] The emotion engine analyzes the text and voice data entered by the user to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[0292] 6. Generating personalized suggestions

[0293] The server suggests additional options (e.g., "Would you like to add a chocolate shake?") based on the user's past order history and the results of emotional analysis. Depending on the user's emotional state, it can respond by suggesting simple suggestions if the user is stressed, or new products if the user is relaxed.

[0294] 7. Confirm and confirm the converted order details

[0295] The server presents the converted order details and suggestions to the user, which are displayed on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button, after which the final order details are sent to the server.

[0296] 8. Sending and confirming orders to the store

[0297] The server sends the confirmed order details to the store, which receives the order details. The store staff processes the order and sends a confirmation message to the server after completion.

[0298] 9. Order completion notification

[0299] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check the notification and find out the redemption code, pick-up time, etc.

[0300] Specific examples

[0301] Restaurant orders:

[0302] A user launches the OrderBridge app and selects English.

[0303] The user enters, "I want to order a cheeseburger and fries."

[0304] The terminal sends the order details to the server.

[0305] The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[0306] The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[0307] The emotion engine analyzes the user's emotional state from their text and voice and determines that they are relaxed.

[0308] The server considers the user's past history and presents "Would you like to add a chocolate shake?" as a new suggestion suitable for relaxation.

[0309] The user checks and confirms the order.

[0310] The terminal sends the final order details to the server.

[0311] The server sends the final order details to the store.

[0312] Store staff processes the order and sends a confirmation message to the server once completed.

[0313] The server sends an order completion notification to the user's terminal.

[0314] The present invention is expected to facilitate smoother communication between users and stores, significantly reducing ordering problems, and improve user satisfaction by providing services tailored to the user's emotional state.

[0315] The processing flow will be explained below.

[0316] Step 1:

[0317] The user launches the OrderBridge app and the home screen appears.

[0318] Step 2:

[0319] Users select the language they want to use on their home screen.

[0320] Step 3:

[0321] The terminal sends the selected language information to the OrderBridge server.

[0322] Step 4:

[0323] The server records the received language information and loads the corresponding language resource.

[0324] Step 5:

[0325] The user opens an order entry screen on their device and enters what they want to order (e.g., "I want to order a cheeseburger and fries").

[0326] Step 6:

[0327] The terminal sends the entered order details in text format to the OrderBridge server.

[0328] Step 7:

[0329] The server receives the order details and passes them to the generative AI model.

[0330] Step 8:

[0331] A generative AI model analyzes the order and extracts the intent behind it (e.g., recognizing two orders: "cheeseburger" and "fries").

[0332] Step 9:

[0333] The server receives the analysis results from the generative AI model and converts them into a store-specific order format (e.g., "one cheeseburger and one fries").

[0334] Step 10:

[0335] The server translates the converted order into the user's language of choice (e.g., English) (e.g., "Order 1 cheeseburger and 1 fries").

[0336] Step 11:

[0337] The emotion engine analyzes the text and voice data entered by the user to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[0338] Step 12:

[0339] The server generates personalized suggestions (e.g., "Would you like to add a chocolate shake?") based on the user's past order history and the results of sentiment analysis. Depending on the user's emotional state, it will make simple suggestions if the user is stressed, or suggest new products if the user is relaxed.

[0340] Step 13:

[0341] The server sends the converted order details and proposals to the user terminal.

[0342] Step 14:

[0343] The terminal displays the order and additional suggestions to the user.

[0344] Step 15:

[0345] The user checks the order details, corrects them if necessary, and finally presses the confirm button.

[0346] Step 16:

[0347] The terminal sends the final order details to the OrderBridge server.

[0348] Step 17:

[0349] The server receives the final order details and sends them to the store's system.

[0350] Step 18:

[0351] The store's system receives the order details and begins processing the order.

[0352] Step 19:

[0353] Store staff prepare the order and, once complete, send a confirmation message to the OrderBridge server.

[0354] Step 20:

[0355] The server receives a confirmation message from the store.

[0356] Step 21:

[0357] The server sends an order completion notification to the user's terminal.

[0358] Step 22:

[0359] The terminal will display a completed order and a redemption code to the user, who will then receive a notification that their order is ready for pickup at the store.

[0360] Example 2

[0361] 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."

[0362] In modern society, when users place orders at different stores, they often encounter barriers due to different ordering formats and languages. This makes ordering time-consuming and prone to misunderstandings. Furthermore, personalized suggestions that take into account the user's emotions and past order history are not provided, making it difficult to improve the user experience. There is a need for a system that can solve these problems and enable smooth ordering between users and stores.

[0363] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0364] In this invention, the server includes: means for accepting order details entered by a user; means for analyzing the order details using a generative AI model; means for converting the order details into an order format for each store based on the analysis results; means for presenting the converted order details to the user; means for transmitting the order details finally confirmed by the user to the store; means for receiving an order confirmation message from the store and notifying the user; means including an emotion analysis engine for analyzing emotions from the user's input text and voice data; and means for generating personalized suggestions based on the emotion analysis results and the user's past order history. This allows users to smoothly place orders at different stores, improving the user experience.

[0365] A "user terminal" is an electronic device used by a user to enter an order and communicate with the server.

[0366] The "server" is a central processing unit that communicates with the user terminal, analyzes and converts the order details, and transmits them to the store.

[0367] An "order support system" is a system in which a user terminal and a server are communicatively connected to support the user's ordering process.

[0368] A "generative AI model" is a system that uses machine learning algorithms to analyze the order details entered by the user and understand the intent behind the order.

[0369] "Order details" are specific requirements for an order that are input by the user through the terminal and analyzed by the server.

[0370] An "emotion analysis engine" is a device or program that analyzes a user's emotional state from input text and voice data.

[0371] "Personalized suggestions" are suggestions that are individually generated based on the user's past order history and sentiment analysis results.

[0372] A "store format" is a standard format for order details used at a particular store.

[0373] The "multilingual function" is a function capable of translating the order contents into an appropriate language according to the language selected by the user.

[0374] An "order confirmation message" is a message that the store sends to the server after confirming the order details it has received.

[0375] This invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other, allowing users to smoothly place orders at stores they visit for the first time. This system uses a generative AI model to analyze order details and convert them into an order format specific to each store. It also supports multiple languages, provides personalized suggestions, and includes an emotion analysis engine that recognizes user emotions.

[0376] To give an overview of the system, electronic devices such as smartphones, tablets, and PCs are used as user terminals. Users use these terminals to input order details, confirm, and finally confirm the order. Next, a server is connected to the user terminal so that it can communicate with it, and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, analyzing emotions, sending them to the store, and notifying the user.

[0377] The generative AI model is the core technology of this system and includes machine learning algorithms used to analyze order details and generate recommendations. Specifically, it uses natural language processing (NLP) technology to interpret the order details entered by the user and convert them into an appropriate format. In addition, the sentiment analysis engine analyzes emotions from the user's voice and text input and provides information and recommendations appropriate to the user based on the analysis results.

[0378] Next, we will explain in detail how the system works. The user launches the application on their device and selects the language they wish to use. The user then enters the order details, which are sent from the device to the server. The server passes the received order details to the generative AI model for analysis. After analyzing the order details, the generative AI model converts them into a format specific to each store. For example, an order in English such as "I want to order a cheeseburger and fries" is converted to "one cheeseburger and one french fries."

[0379] For multilingual support, the server translates the converted order into the appropriate language based on the language selected by the user. For example, the converted Japanese order might be translated into English as "Order 1 cheeseburger and 1 fries."

[0380] For emotion analysis, the emotion engine analyzes the user's input text and voice data to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[0381] Then, to generate personalized suggestions, the server suggests additional options based on the user's past order history and the results of sentiment analysis. For example, if the user is stressed, the server can suggest simple suggestions, and if the user is relaxed, it can suggest new products.

[0382] Finally, the converted order details are confirmed and confirmed. The server presents the converted order details and suggestions to the user and displays them on the terminal. The user confirms the details, makes any necessary corrections, and finally presses the confirm button, at which point the final order details are sent to the server. The server then sends the confirmed order details to the store, where the store staff processes the order and sends a confirmation message to the server once it is complete. Finally, the server receives the confirmation message from the store and sends an order completion notification to the user's terminal.

[0383] As a concrete example, let's look at the process of ordering at a restaurant. The user launches the OrderBridge app and selects English. Next, they enter "I want to order a cheeseburger and fries," and the device sends the order details to the server. The server analyzes the order using a generative AI model and converts the order to "1 cheeseburger and 1 fries." The server then translates the converted content into English, setting it to "Order 1 cheeseburger and 1 fries." The emotion engine analyzes the user's emotional state from their text and voice and determines that they are relaxed. The server takes into account the user's past history and asks, "Would you like to add a chocolate shake?" The user confirms and confirms the order details. The device sends the final order details to the server, which then sends the order details to the store. The store staff processes the order and, once complete, sends a confirmation message to the server. The server then sends a notification of order completion to the user's device.

[0384] This invention is expected to facilitate smoother communication between users and stores, significantly reducing troubles with orders, and also improve user satisfaction by providing services that correspond to the user's emotional state.

[0385] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0386] Specific explanation of processing steps

[0387] Step 1:

[0388] User input of order details

[0389] The user opens the OrderBridge app, selects the language they want to use (e.g., English), and then enters their order details: "I want to order a cheeseburger and fries." When the user presses the "Submit" button, the order details are sent to the terminal as input data.

[0390] Step 2:

[0391] Sending order details to the server via the terminal

[0392] The terminal sends the entered order details to the server. In this step, the user's order details are sent as input data from the terminal to the server via HTTPS. The server adds the received data to a queue for analysis.

[0393] Step 3:

[0394] Analysis of order details using a server-generated AI model

[0395] The server passes the received order details to the generative AI model for analysis. Specifically, the generative AI model analyzes the order details using natural language processing (NLP) technology and extracts the keywords "cheeseburger" and "fries." The input data is the user's order, and the output data is the extracted keywords and structured order information.

[0396] Step 4:

[0397] The server converts the order into store format.

[0398] The server converts the order details into the store's format based on the analysis results returned by the generative AI model. This conversion process uses pre-defined store format mapping rules. For example, "cheeseburger" and "fries" are converted into "1 cheeseburger, 1 french fries." The input data is the analysis results, and the output data is the converted order details.

[0399] Step 5:

[0400] Multilingual support for order details via the server

[0401] The server translates the converted order into the language selected by the user (e.g., English). In this step, a translation API (e.g., Google® Translate API) is used to translate the order. The input data is the converted order, and the output data is the translated order.

[0402] Step 6:

[0403] User emotion analysis by emotion engine on the server

[0404] The server uses an emotion engine to analyze the user's input text and voice data. The emotion engine determines the user's emotional state using, for example, IBM Watson® emotion analysis API. The input data is the user's text and voice data, and the output data is the user's emotional state.

[0405] Step 7:

[0406] Server-generated personalized suggestions

[0407] The server generates personalized suggestions based on the user's past order history and the results of emotion analysis. The suggestions suggest new products to relaxed users and simple suggestions to stressed users. The input data are the user's order history and emotional state, and the output data are personalized suggestions.

[0408] Step 8:

[0409] User confirms and confirms order details

[0410] The server presents the converted order details and proposals to the user and displays them on the terminal. The user checks the displayed details, makes any necessary corrections, and presses the "Confirm" button. The input data are the order details and proposals presented to the user, and the output data are the final order details confirmed by the user.

[0411] Step 9:

[0412] Sending the final order details to the server by the terminal

[0413] When the user confirms the order, the terminal sends the final order details to the server. Once this sending operation is complete, the order processing proceeds to the next step. The input data is the final order details confirmed by the user, and the output data is the final order details sent to the server.

[0414] Step 10:

[0415] The server sends the order to the store

[0416] The server sends the final order details to the store's system using a standard protocol (e.g., REST API). The input data is the final order details, and the output data is the order details sent to the store's system.

[0417] Step 11:

[0418] Order processing and confirmation by the store

[0419] The store staff prepares the product based on the received order details, and when the order is completed, the store's system sends a completion confirmation message to the server. The input data is the order details received by the store, and the output data is the completion confirmation message sent to the server.

[0420] Step 12:

[0421] The server sends a notification of order completion to the user's device.

[0422] The server receives a completion confirmation message from the store and sends an order completion notification to the user's terminal. This notification includes a redemption code and pickup time. The input data is the completion confirmation message from the store, and the output data is the order completion notification sent to the user's terminal.

[0423] In this way, this system realizes smooth communication between users and stores, significantly reducing ordering problems. It also improves user satisfaction by making suggestions based on the user's emotional state.

[0424] (Application example 2)

[0425] 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."

[0426] Conventional ordering support systems make it difficult for users to order smoothly at stores or services they visit for the first time. Furthermore, the lack of multilingual support and personalized suggestions based on the user's emotions often compromises the user experience. This leads to issues such as reduced ordering accuracy and user satisfaction.

[0427] The identification process 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 accepting order details entered by a user, means for analyzing the order details using a generative AI model, means for converting the order details into an order format for each request destination based on the analysis results, means for presenting the converted order details to the user, means for sending the order details finally confirmed by the user to the request destination, means for receiving a confirmation message from the request destination and notifying the user, means for analyzing the user's emotional state and generating personalized proposals based thereon, means for translating the order details into a language selected by the user with a multilingual function, and means for generating personalized proposals based on the user's past order history and preferences. This enables the user to smoothly place an order even when visiting a store or service for the first time, realizes a detailed response that reflects the user's emotions, and improves the accuracy of orders and user satisfaction.

[0428] A "user terminal" is a device through which a user inputs order details and communicates with the server.

[0429] "Server" refers to a central processing unit that receives and analyzes the order details sent from the user terminal and performs processes such as conversion, translation, and notification.

[0430] The "order support system" is a system that communicates between the user's terminal and a server, analyzes, converts, and translates the order details entered by the user, and makes appropriate suggestions.

[0431] A "generative AI model" is an artificial intelligence model that includes machine learning algorithms to analyze the order details entered by the user and understand the intent behind the order.

[0432] "Emotional State" means the user's psychological and emotional state as analyzed from the user's voice and text input.

[0433] "Emotion analysis" is the process of recognizing a user's emotional state from their vocabulary, tone, typing speed, etc.

[0434] "Personalized suggestions" is a feature that makes optimal suggestions to individual users based on their past order history and emotional state.

[0435] "Multilingual support" is a function that allows order details to be translated into various languages ​​for users who speak different languages.

[0436] The "request destination" refers to the store or service provider to which the user wishes to place an order.

[0437] "Order format" refers to the specific order entry format required by each requestor.

[0438] MODE FOR CARRYING OUT THE INVENTION

[0439] The present invention is an ordering support system in which a user terminal and a server are connected so that they can communicate with each other, and aims to enable users to smoothly place orders even in new locations. This system is particularly equipped with multilingual support and a personalized suggestion function using sentiment analysis, which significantly improves the user experience.

[0440] System Configuration

[0441] The system includes the following main components:

[0442] 1. User Device:

[0443] This is a device that users use to input order details. It is often a smartphone, tablet, or PC. Users use this device to input order details and send them to the server.

[0444] 2. Server:

[0445] The server receives the order content sent from the user terminal and processes it through analysis, conversion, suggestions, translation, etc. The server has the computing resources to run the generative AI model and emotion engine.

[0446] 3. Generative AI Model:

[0447] The generative AI model uses natural language processing (NLP) technology to analyze the order details entered by the user and understand the intent behind the order. The model also generates optimal suggestions based on the user's order history and sentiment analysis results.

[0448] 4. Emotion Engine:

[0449] The emotion engine analyzes the user's text and voice data to recognize their emotional state, determining whether they are relaxed or stressed.

[0450] Operation overview

[0451] The system operates as follows:

[0452] 1. Enter and submit your order:

[0453] The user starts the terminal application and enters the order details, for example, "I want to order a cheeseburger and fries." This input is sent to the server as a prompt.

[0454] 2. Order analysis and conversion:

[0455] The server uses a generative AI model to analyze the order and convert it into a custom order format, such as "one cheeseburger and one fries."

[0456] 3. Multilingual support:

[0457] The server translates the converted order into the user's language of choice, for example, "Order 1 cheeseburger and 1 fries."

[0458] 4. Sentiment analysis and suggestion generation:

[0459] The emotion engine analyzes the user's emotional state from their text or voice input, providing new suggestions if they are relaxed, or simple suggestions if they are stressed.

[0460] 5. Final confirmation and order submission:

[0461] The user sends the final order details to the server, which then sends them to the requested party. The order is completed when a confirmation message is received from the requested party and the user is notified.

[0462] Specific examples

[0463] When a user places an order using a smartphone, they enter the following prompt:

[0464] "I want to order a cheeseburger and fries"

[0465] The server analyzes this order, converts it into the appropriate format, translates it if necessary, analyzes the user's emotional state, and generates new suggestions based on that (e.g., "Would you like to add a chocolate shake?"). The user finally confirms and confirms the order, which is then sent to the destination.

[0466] As described above, the present invention enables users to smoothly place orders in different locations and language environments, and improves the ordering experience by providing personalized suggestions based on emotions.

[0467] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0468] Step 1:

[0469] The user starts the application on the terminal and selects the language to use. Next, the user inputs the order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the terminal to the server as a prompt. Based on the input (prompt), the server receives the order details.

[0470] Step 2:

[0471] The server passes the order details to the generative AI model for analysis. The generative AI model analyzes the input prompt (order details) and understands the intent of the order. Data processing involves tokenizing the order details using natural language processing technology and evaluating the context. Structured order data is generated as the output.

[0472] Step 3:

[0473] Based on the analysis results, the server converts the order details into an order format specific to the customer. Here, the output of the generative AI model is used to convert the data into a specific order format. For example, "I want to order a cheeseburger and fries" is converted to "1 cheeseburger and 1 french fries."

[0474] Step 4:

[0475] The server presents the converted order details to the user. At this time, the order details are translated according to the language selected by the user. For example, if English is selected, the order details will be translated as "Order 1 cheeseburger and 1 fries." A multilingual API is used for the translation.

[0476] Step 5:

[0477] The server uses an emotion engine to analyze the user's emotional state from the text and voice input. Data processing involves extracting emotional features from the input text and voice data and evaluating them with an emotion classification model. The output is the user's emotional state (relaxed, stressed, etc.).

[0478] Step 6:

[0479] The server generates personalized suggestions based on the user's past ordering history and emotional state, such as "Would you like to add a chocolate shake?". A recommendation system is used to make new suggestions using the emotional state and past ordering data.

[0480] Step 7:

[0481] The server presents the order details and proposals to the user for final confirmation and displays them on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button. Based on the input (user's final confirmation), the confirmed order details are sent to the server.

[0482] Step 8:

[0483] The server sends the confirmed order details to the requester. The requester's system receives and processes the order details. Once processing is complete, the requester's system sends a confirmation message to the server.

[0484] Step 9:

[0485] The server receives a confirmation message from the request destination and sends an order completion notification to the user's terminal. The user can check this notification and know that the order has been completed.

[0486] 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.

[0487] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0488] 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.

[0489] [Second embodiment]

[0490] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0491] 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.

[0492] 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).

[0493] 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.

[0494] 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.

[0495] 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).

[0496] 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. 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.

[0497] 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.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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."

[0502] This system, "OrderBridge," connects the user's device and server for communication, allowing the user to smoothly place orders at stores they visit for the first time. When the user enters their order details, the details are analyzed by a generative AI model and converted into a format suitable for the store. The system also supports multiple languages ​​and provides personalized suggestions.

[0503] System Overview

[0504] 1. User Device

[0505] User terminals include devices such as smartphones, tablets, and personal computers. Users use these terminals to input order details, confirm the order, and finalize it.

[0506] 2. Server

[0507] The server is communicatively connected to the user terminal and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, sending them to the store, and notifying the user.

[0508] 3. Generative AI Models

[0509] The generative AI model includes machine learning algorithms used to analyze order content and generate recommendations, allowing it to interpret and convert order content entered by users in natural language into an appropriate format.

[0510] Program processing explanation

[0511] 1. User Order Entry

[0512] The user launches the application on the device, selects a language, and then enters their order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the device to the server.

[0513] 2. Server analyzes the order

[0514] The server passes the received order details to the generative AI model for analysis. The generative AI model analyzes the input and understands the intent of the order.

[0515] 3. Order Conversion

[0516] The server then converts the order into a store-specific format based on the analysis results returned by the generative AI model, such as "one cheeseburger and one fries."

[0517] 4. Multilingual support

[0518] The server translates the converted order content into the appropriate language based on the language selected by the user.

[0519] 5. Generate personalized suggestions

[0520] The server considers the user's past ordering history and preferences and suggests additional options (e.g., "Would you like to add a chocolate shake?").

[0521] 6. Confirm and confirm the order details after conversion

[0522] The server presents the converted order details and suggestions to the user, which are displayed on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button, after which the final order details are sent to the server.

[0523] 7. Sending and confirming orders to the store

[0524] The server sends the confirmed order details to the store, which receives the order details. The store staff processes the order and sends a confirmation message to the server after completion.

[0525] 8. Order completion notification

[0526] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check the notification and find out the redemption code, pick-up time, etc.

[0527] Specific examples

[0528] Restaurant orders:

[0529] A user launches the OrderBridge app and selects English.

[0530] The user enters, "I want to order a cheeseburger and fries."

[0531] The terminal sends the order details to the server.

[0532] The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[0533] The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[0534] The server considers the user's past history and suggests, "Would you like to add a chocolate shake?"

[0535] The user checks and confirms the order.

[0536] The terminal sends the final order details to the server.

[0537] The server sends the final order details to the store.

[0538] Store staff processes the order and sends a confirmation message to the server once completed.

[0539] The server sends an order completion notification to the user's terminal.

[0540] The present invention is expected to facilitate smooth communication between users and stores, significantly reducing troubles with orders.

[0541] The processing flow will be explained below.

[0542] Step 1:

[0543] The user launches the OrderBridge app and the home screen appears.

[0544] Step 2:

[0545] Users select the language they want to use on their home screen.

[0546] Step 3:

[0547] The terminal sends the selected language information to the OrderBridge server.

[0548] Step 4:

[0549] The server records the received language information and loads the corresponding language resource.

[0550] Step 5:

[0551] The user opens an order entry screen on their device and enters what they want to order (e.g., "I want to order a cheeseburger and fries").

[0552] Step 6:

[0553] The terminal sends the entered order details in text format to the OrderBridge server.

[0554] Step 7:

[0555] The server receives the order details and passes them to the generative AI model.

[0556] Step 8:

[0557] A generative AI model analyzes the order and extracts the intent behind it (e.g., recognizing two orders: "cheeseburger" and "fries").

[0558] Step 9:

[0559] The server receives the analysis results from the generative AI model and converts them into a store-specific order format (e.g., "one cheeseburger and one fries").

[0560] Step 10:

[0561] The server translates the converted order into the user's language of choice (e.g., English) (e.g., "Order 1 cheeseburger and 1 fries").

[0562] Step 11:

[0563] The server considers the user's past ordering history and preferences and suggests additional options (e.g., "Would you like to add a chocolate shake?").

[0564] Step 12:

[0565] The server sends the converted order details and proposals to the user terminal.

[0566] Step 13:

[0567] The terminal displays the order and additional suggestions to the user.

[0568] Step 14:

[0569] The user checks the order details, corrects them if necessary, and finally presses the confirm button.

[0570] Step 15:

[0571] The terminal sends the final order details to the OrderBridge server.

[0572] Step 16:

[0573] The server receives the final order details and sends them to the store's system.

[0574] Step 17:

[0575] The store's system receives the order and begins processing it.

[0576] Step 18:

[0577] Store staff prepare the order and, once complete, send a confirmation message to the OrderBridge server.

[0578] Step 19:

[0579] The server receives a confirmation message from the store.

[0580] Step 20:

[0581] The server sends an order completion notification to the user's terminal.

[0582] Step 21:

[0583] The terminal will display a code to the user to complete the order and redeem it.

[0584] Example 1

[0585] 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."

[0586] Conventional ordering support systems have problems such as difficulty in ordering at stores visited for the first time or in communicating in a foreign language, which can easily lead to problems. Furthermore, they often lack personalized suggestions based on the user's past preferences and order history, resulting in a poor user experience. To solve these problems, a new ordering support system with multilingual support and personalized suggestion functionality is needed.

[0587] 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.

[0588] In this invention, the server includes means for accepting order details entered by a user, means for analyzing the order details using a generative AI model, means for converting the order details into a format for each information system based on the analysis results, means for presenting the converted order details to the user, means for transmitting the order details finally confirmed by the user to the information processing device, means for receiving an order confirmation message from the information processing device and notifying the user, means for generating personalized suggestions based on the user's past order history and preferences, and means for appropriately translating the order details based on the selected language. This allows users to smoothly place orders even at stores they visit for the first time, and is expected to improve the user experience through multilingual support and personalized suggestions.

[0589] A "user terminal" is a computer device that allows a user to input, confirm, and finalize an order, and specifically includes a smartphone, tablet, PC, etc.

[0590] A "server" is a computer device that is communicatively connected to a user terminal and performs processes such as receiving order details, analyzing, converting, translating, generating suggestions, sending to stores, and notifying users.

[0591] A "generative AI model" is a model that uses machine learning algorithms to analyze input order details and convert the order details into a format specific to each store.

[0592] "Order details" refers to information about the product or service that the user wishes to purchase, which is input into the terminal.

[0593] The "order format" is a format that has been converted and formatted to make the analyzed order content easier for stores and information systems to process.

[0594] "Multilingual support" is a function that translates and displays order details based on the different languages ​​selected by the user when entering an order.

[0595] "Personalized Offers" refers to additional offers or options that are individually provided to a user based on the user's past order history and preference data.

[0596] An "order confirmation message" is a message that a store sends to a server after accepting a user's order and confirming its contents.

[0597] This invention is a system that allows users to input order details using a terminal, and a server analyzes and converts the details and transmits the order to the store in an appropriate format. This system uses the user terminal, server, and generative AI model to smoothly perform the entire process from order input to confirmation, confirmation, and notification, and also has multilingual support and personalized suggestion functions.

[0598] User terminal

[0599] A user terminal is a device that is directly operated by a user, and includes a smartphone, tablet, PC, etc. A dedicated application is installed on these devices, and the user launches this application to place an order.

[0600] server

[0601] The server is connected to the user's device and performs a series of processes, from receiving the order details to analyzing, converting, translating, generating suggestions, and sending them to the store. The server is equipped with a generative AI model and properly analyzes the user's natural language input.

[0602] Generative AI Models

[0603] The generative AI model is used to analyze orders using machine learning algorithms and convert them into store-specific order formats. The model also has multilingual support and can translate orders based on the language selected by the user.

[0604] Specific examples

[0605] Here's a sample order at a restaurant:

[0606] 1. The user launches the OrderBridge app and selects English.

[0607] 2. The user enters, "I want to order a cheeseburger and fries."

[0608] 3. The terminal sends the order details to the server.

[0609] 4. The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[0610] 5. The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[0611] 6. The server considers the user's past history and suggests, "Would you like to add a chocolate shake?"

[0612] 7. The user confirms and confirms the order.

[0613] 8. The terminal sends the final order details to the server.

[0614] 9. The server sends the final order details to the store.

[0615] 10. The store staff processes the order and sends a confirmation message to the server once completed.

[0616] 11. The server sends an order completion notification to the user's device.

[0617] This system allows users to place orders smoothly, regardless of language barriers, and allows stores to receive accurate orders. Furthermore, personalized suggestions are expected to improve the user experience.

[0618] Example prompt sentence:

[0619] "I want to order a cheeseburger and fries"

[0620] "Can I get a vegetarian pizza with extra cheese?"

[0621] "I would like to add a large coffee to my order"

[0622] The system of the present invention is expected to streamline the entire ordering process and strengthen communication between users and stores.

[0623] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0624] Step 1:

[0625] User order entry

[0626] The user launches the OrderBridge app on their device (smartphone, tablet, or PC) and selects the language they wish to use. Next, the user enters the order details in natural language and presses the submit button. The order details entered by the user are then saved as text data on the device. For example, the user might enter "I want to order a cheeseburger and fries." This text data is sent to the server.

[0627] Input: User's natural language order details

[0628] Output: Text data of the order details sent to the server

[0629] Step 2:

[0630] Server parsing of order details

[0631] The server passes the text data received from the device to the generative AI model, which uses natural language processing technology to analyze the user's input. As a result of the analysis, the model extracts the ordering intent (e.g., "I would like to order a cheeseburger and fries") and generates semantic data in digital form.

[0632] Input: Text data of order details from the terminal

[0633] Output: Digital data of parsed order details

[0634] Step 3:

[0635] Order conversion

[0636] The server receives the analysis results from the generative AI model and converts the order content into a store-specific format based on the analysis results. For example, "I want to order a cheeseburger and fries" is converted into "1 cheeseburger and 1 fries."

[0637] Input: Analyzed digital data of order details

[0638] Output: Order details converted into a store-friendly format

[0639] Step 4:

[0640] Multilingual support

[0641] The server translates the converted order into the appropriate language based on the user's language selection: if the user selects English, the converted order will be translated as "Order 1 cheeseburger and 1 fries."

[0642] Input: Order details converted into store-appropriate format, user's preferred language setting

[0643] Output: Order details translated into the selected language

[0644] Step 5:

[0645] Generate personalized suggestions

[0646] The server will refer to the user's past order history and preference data to generate appropriate additional suggestions. For example, if a user has previously ordered a chocolate shake, the server will generate the suggestion "Would you like to add a chocolate shake?"

[0647] Input: User's past order history, preference data

[0648] Output: Personalized suggestions

[0649] Step 6:

[0650] Confirm and confirm the order details after conversion

[0651] The server presents the converted order and personalized suggestions to the user, who can then review the order on their device and make any necessary corrections. Finally, when the user presses the confirm button, the final order is sent to the server.

[0652] Input: translated order, personalized suggestions

[0653] Output: Order details and proposals presented to the user, and final order details

[0654] Step 7:

[0655] Sending and confirming orders to the store

[0656] The server sends the order details confirmed by the user to the store. The store's system receives the order details and begins processing the order. Once the order is processed, the store's system sends a confirmation message to the server.

[0657] Input: Final order details

[0658] Output: Order details sent to the store, confirmation message from the store

[0659] Step 8:

[0660] Order completion notification

[0661] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check information such as the redemption code and pickup time.

[0662] Input: Confirmation message from the store

[0663] Output: Order completion notification sent to the user

[0664] The above processing flow allows the user to place an order smoothly and the store to receive the order accurately.

[0665] (Application example 1)

[0666] 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."

[0667] In the modern restaurant and food delivery industry, ordering is often difficult when users are visiting a new restaurant or using a new platform. Meanwhile, there is a need to improve the user experience due to issues with translation between different languages ​​and a lack of appropriate suggestions based on user preferences. Furthermore, the lack of personalized suggestions based on past ordering history makes it difficult for users to efficiently order what suits their preferences.

[0668] 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.

[0669] In this invention, the server includes: means for being communicatively connected to a user terminal; means for accepting order details entered by a user; means for analyzing the order details using a generative AI model; means for converting the order details into an order format for each store based on the analysis results; means for presenting the converted order details to the user; means for sending the order details finally confirmed by the user to the store; means for receiving an order confirmation message from the store and notifying the user; means for translating the order details into a language selected by the user with a multilingual function; means for generating personalized suggestions based on the user's past ordering history and preferences; and means for transmitting the order details to affiliated restaurants. This allows users to smoothly order at stores or platforms they are using for the first time through appropriate suggestions based on translation issues between different languages ​​and user preferences, as well as personalized suggestions.

[0670] "User terminal" refers to a device used by a user to input order details, such as a smartphone, tablet, or PC.

[0671] "Server" refers to a computer system that is communicatively connected to a user terminal and performs processes such as receiving, analyzing, converting, translating, generating suggestions, sending to the restaurant, and notifying the user.

[0672] A "generative AI model" refers to a model that includes machine learning algorithms to interpret order details entered in natural language and convert them into an appropriate format.

[0673] "Multilingual support" refers to the ability to automatically translate orders based on the language selected by the user.

[0674] "Personalized suggestions" refers to the ability to generate additional options and suggestions based on a user's past ordering history and preferences.

[0675] "Food delivery service" refers to a service that allows users to order food and drinks from restaurants using their smartphones and have them delivered.

[0676] An "order confirmation message" refers to a message that confirms that the restaurant has accepted the order details confirmed by the user.

[0677] MODE FOR CARRYING OUT THE INVENTION

[0678] The present invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other. Below, the processing of a program for realizing this system and a specific example thereof will be described.

[0679] System Configuration

[0680] The system mainly consists of the following components:

[0681] 1. User Device

[0682] Smartphone (iOS or Android)

[0683] tablet

[0684] PC

[0685] 2. Server

[0686] Cloud hosting (e.g. AWS)

[0687] Database (e.g. MongoDB)

[0688] Machine learning models (e.g., generative AI models using GPT-3)

[0689] 3. Software

[0690] Frontend: React Native

[0691] Backend: Node.js, Express.js

[0692] Program processing explanation

[0693] 1. User Order Entry

[0694] A user launches a smartphone application, selects their preferred language, and then enters their order details in natural language into the application's input field. For example, they might enter, "I'd like to order a pizza and a cola."

[0695] 2. Server analyzes the order

[0696] The terminal sends the entered order details to the server. The server passes the order details to the generative AI model for analysis. The generative AI model analyzes the order details and understands the user's intentions.

[0697] 3. Order Conversion

[0698] Based on the analysis results, the server converts the order details into a format specific to the partner restaurant, such as "one pizza and one bottle of coke."

[0699] 4. Multilingual support

[0700] The server automatically translates the order based on the language selected by the user.

[0701] 5. Generate personalized suggestions

[0702] The server takes into account the user's past ordering history and preferences to make further recommendations, such as "Would you like some garlic bread as a side?"

[0703] 6. Confirm and confirm the order details after conversion

[0704] The server presents the converted order details and suggestions to the user. When the user confirms the details and finally presses the confirm button, the confirmed order details are sent to the server.

[0705] 7. Sending and confirming orders to restaurants

[0706] The server sends the confirmed order to the partner restaurant, which receives the order, and the restaurant's system receives it. The restaurant staff processes the order and sends a confirmation message to the server once it is complete.

[0707] 8. Order completion notification

[0708] The server receives a confirmation message from the restaurant and sends a completed order notification to the user's smartphone, along with information such as a redemption code and pickup time.

[0709] Specific examples

[0710] For example, a user launches the FoodEase app and selects English. Then, they enter, "I want to order a Hawaiian pizza and a coke." The input is sent to the server and analyzed by the generative AI model. The analysis results in "One Hawaiian pizza and one bottle of Coca-Cola." The model then suggests, "Would you like to add garlic bread to your order?" Once the user confirms and places the order, the server sends the final order details to the partner restaurant. The restaurant processes the order and sends a confirmation message to the server, which then sends the user a notification that the order is complete.

[0711] Prompt Sentence Examples

[0712] User order: "I want to order a cheeseburger and fries"

[0713] Response: "Your order was recognized as '1 cheeseburger, 1 fries'. Additional suggestion: 'Would you like to add a chocolate shake?'"

[0714] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0715] Step 1:

[0716] The user starts up the device (smartphone) and launches the FoodEase application. The user selects their preferred language before entering their order. The input at this stage is the language setting of the application. There is no output to the server.

[0717] Step 2:

[0718] A user enters their order in natural language into an application's input field, for example, "I want to order a Hawaiian pizza and a coke." This input is sent from the device to the server, where it is forwarded to the server and prepared for analysis.

[0719] Step 3:

[0720] The server sends the received natural language order content to the generative AI model for analysis. The input for analysis is "I want to order a Hawaiian pizza and a coke." The generative AI model understands the order content and outputs formatted order data (e.g., "One Hawaiian pizza and one bottle of Coca-Cola").

[0721] Step 4:

[0722] The server converts the order details into a format specific to the partner restaurant based on the analysis results of the generative AI model. The input is the analyzed order data, and the output is the converted order data (e.g., "One Hawaiian pizza and one bottle of Coca-Cola"). The server then prepares this to be presented to the user.

[0723] Step 5:

[0724] The server translates the order based on the language selected by the user. For example, if the parsing result is "1 Hawaiian pizza and 1 Coca-Cola," it translates it into the selected language. In this case, the input is the parsing result, and the output is the translated order (e.g., "Order 1 Hawaiian pizza and 1 coke").

[0725] Step 6:

[0726] The server considers the user's past order history and preferences and suggests additional options. The input is the user's order history data and current order details, and the output is a recommendation (e.g., "Would you like to add garlic bread to your order?").

[0727] Step 7:

[0728] The server sends the converted and translated order details and suggestions to the user terminal. The user checks the details and finally presses the confirm button. The input is the suggested order details and additional suggestions, and the output is the user's final confirmation action.

[0729] Step 8:

[0730] When the user's final confirmation action is sent to the server, the server sends the confirmed order details to the partner restaurant. The input is the final confirmed order details, and the output is the order data for the restaurant. The restaurant accepts the order and starts processing it.

[0731] Step 9:

[0732] Once the restaurant has processed the order, it sends a confirmation message to the server. The server receives the confirmation message and sends a notification of order completion to the user's smartphone. The input is the confirmation message from the restaurant, and the output is a notification of order completion to the user's device.

[0733] This series of processing steps allows users to smoothly input and confirm order details even when using a store or platform for the first time.

[0734] 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.

[0735] This invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other, allowing users to smoothly place orders at stores they visit for the first time. This system uses a generative AI model to analyze order details and convert them into an order format specific to each store. It also supports multiple languages, provides personalized suggestions, and is equipped with an emotion engine that recognizes user emotions.

[0736] System Overview

[0737] 1. User Device

[0738] User terminals include devices such as smartphones, tablets, and personal computers. Users use these terminals to input order details, confirm the order, and finalize it.

[0739] 2. Server

[0740] The server is communicatively connected to the user terminal and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, analyzing emotions, sending to the store, and notifying the user.

[0741] 3. Generative AI Models

[0742] The generative AI model includes machine learning algorithms used to analyze order content and generate recommendations, allowing it to interpret and convert order content entered by users in natural language into an appropriate format.

[0743] 4. Emotion Engine

[0744] The emotion engine analyzes the user's emotions from their voice and text input, and provides information and suggestions appropriate to the user based on the analysis results, enabling appropriate responses to be made according to the user's emotions.

[0745] Program processing explanation

[0746] 1. User Order Entry

[0747] The user launches the application on the device, selects the language they want to use, and then enters their order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the device to the server.

[0748] 2. Server analyzes the order

[0749] The server passes the received order details to the generative AI model for analysis. The generative AI model analyzes the input and understands the intent of the order.

[0750] 3. Order Conversion

[0751] The server then converts the order into a store-specific format based on the analysis results returned by the generative AI model, such as "one cheeseburger and one fries."

[0752] 4. Multilingual support

[0753] The server translates the converted order into the appropriate language based on the user's language selection (e.g., "Order 1 cheeseburger and 1 fries").

[0754] 5. User sentiment analysis

[0755] The emotion engine analyzes the text and voice data entered by the user to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[0756] 6. Generating personalized suggestions

[0757] The server suggests additional options (e.g., "Would you like to add a chocolate shake?") based on the user's past order history and the results of emotional analysis. Depending on the user's emotional state, it can respond by suggesting simple suggestions if the user is stressed, or new products if the user is relaxed.

[0758] 7. Confirm and confirm the converted order details

[0759] The server presents the converted order details and suggestions to the user, which are displayed on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button, after which the final order details are sent to the server.

[0760] 8. Sending and confirming orders to the store

[0761] The server sends the confirmed order details to the store, which receives the order details. The store staff processes the order and sends a confirmation message to the server after completion.

[0762] 9. Order completion notification

[0763] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check the notification and find out the redemption code, pick-up time, etc.

[0764] Specific examples

[0765] Restaurant orders:

[0766] A user launches the OrderBridge app and selects English.

[0767] The user enters, "I want to order a cheeseburger and fries."

[0768] The terminal sends the order details to the server.

[0769] The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[0770] The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[0771] The emotion engine analyzes the user's emotional state from their text and voice and determines that they are relaxed.

[0772] The server considers the user's past history and presents "Would you like to add a chocolate shake?" as a new suggestion suitable for relaxation.

[0773] The user checks and confirms the order.

[0774] The terminal sends the final order details to the server.

[0775] The server sends the final order details to the store.

[0776] Store staff processes the order and sends a confirmation message to the server once completed.

[0777] The server sends an order completion notification to the user's terminal.

[0778] The present invention is expected to facilitate smoother communication between users and stores, significantly reducing ordering problems, and improve user satisfaction by providing services tailored to the user's emotional state.

[0779] The processing flow will be explained below.

[0780] Step 1:

[0781] The user launches the OrderBridge app and the home screen appears.

[0782] Step 2:

[0783] Users select the language they want to use on their home screen.

[0784] Step 3:

[0785] The terminal sends the selected language information to the OrderBridge server.

[0786] Step 4:

[0787] The server records the received language information and loads the corresponding language resource.

[0788] Step 5:

[0789] The user opens an order entry screen on their device and enters what they want to order (e.g., "I want to order a cheeseburger and fries").

[0790] Step 6:

[0791] The terminal sends the entered order details in text format to the OrderBridge server.

[0792] Step 7:

[0793] The server receives the order details and passes them to the generative AI model.

[0794] Step 8:

[0795] A generative AI model analyzes the order and extracts the intent behind it (e.g., recognizing two orders: "cheeseburger" and "fries").

[0796] Step 9:

[0797] The server receives the analysis results from the generative AI model and converts them into a store-specific order format (e.g., "one cheeseburger and one fries").

[0798] Step 10:

[0799] The server translates the converted order into the user's language of choice (e.g., English) (e.g., "Order 1 cheeseburger and 1 fries").

[0800] Step 11:

[0801] The emotion engine analyzes the text and voice data entered by the user to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[0802] Step 12:

[0803] The server generates personalized suggestions (e.g., "Would you like to add a chocolate shake?") based on the user's past order history and the results of sentiment analysis. Depending on the user's emotional state, it will make simple suggestions if the user is stressed, or suggest new products if the user is relaxed.

[0804] Step 13:

[0805] The server sends the converted order details and proposals to the user terminal.

[0806] Step 14:

[0807] The terminal displays the order and additional suggestions to the user.

[0808] Step 15:

[0809] The user checks the order details, corrects them if necessary, and finally presses the confirm button.

[0810] Step 16:

[0811] The terminal sends the final order details to the OrderBridge server.

[0812] Step 17:

[0813] The server receives the final order details and sends them to the store's system.

[0814] Step 18:

[0815] The store's system receives the order details and begins processing the order.

[0816] Step 19:

[0817] Store staff prepare the order and, once complete, send a confirmation message to the OrderBridge server.

[0818] Step 20:

[0819] The server receives a confirmation message from the store.

[0820] Step 21:

[0821] The server sends an order completion notification to the user's terminal.

[0822] Step 22:

[0823] The terminal will display a completed order and a redemption code to the user, who will then receive a notification that their order is ready for pickup at the store.

[0824] Example 2

[0825] 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."

[0826] In modern society, when users place orders at different stores, they often encounter barriers due to different ordering formats and languages. This makes ordering time-consuming and prone to misunderstandings. Furthermore, personalized suggestions that take into account the user's emotions and past order history are not provided, making it difficult to improve the user experience. There is a need for a system that can solve these problems and enable smooth ordering between users and stores.

[0827] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0828] In this invention, the server includes: means for accepting order details entered by a user; means for analyzing the order details using a generative AI model; means for converting the order details into an order format for each store based on the analysis results; means for presenting the converted order details to the user; means for transmitting the order details finally confirmed by the user to the store; means for receiving an order confirmation message from the store and notifying the user; means including an emotion analysis engine for analyzing emotions from the user's input text and voice data; and means for generating personalized suggestions based on the emotion analysis results and the user's past order history. This allows users to smoothly place orders at different stores, improving the user experience.

[0829] A "user terminal" is an electronic device used by a user to enter an order and communicate with the server.

[0830] The "server" is a central processing unit that communicates with the user terminal, analyzes and converts the order details, and transmits them to the store.

[0831] An "order support system" is a system in which a user terminal and a server are communicatively connected to support the user's ordering process.

[0832] A "generative AI model" is a system that uses machine learning algorithms to analyze the order details entered by the user and understand the intent behind the order.

[0833] "Order details" are specific requirements for an order that are input by the user through the terminal and analyzed by the server.

[0834] An "emotion analysis engine" is a device or program that analyzes a user's emotional state from input text and voice data.

[0835] "Personalized suggestions" are suggestions that are individually generated based on the user's past order history and sentiment analysis results.

[0836] A "store format" is a standard format for order details used at a particular store.

[0837] The "multilingual function" is a function capable of translating the order contents into an appropriate language according to the language selected by the user.

[0838] An "order confirmation message" is a message that the store sends to the server after confirming the order details it has received.

[0839] This invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other, allowing users to smoothly place orders at stores they visit for the first time. This system uses a generative AI model to analyze order details and convert them into an order format specific to each store. It also supports multiple languages, provides personalized suggestions, and includes an emotion analysis engine that recognizes user emotions.

[0840] To give an overview of the system, electronic devices such as smartphones, tablets, and PCs are used as user terminals. Users use these terminals to input order details, confirm, and finally confirm the order. Next, a server is connected to the user terminal so that it can communicate with it, and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, analyzing emotions, sending them to the store, and notifying the user.

[0841] The generative AI model is the core technology of this system and includes machine learning algorithms used to analyze order details and generate recommendations. Specifically, it uses natural language processing (NLP) technology to interpret the order details entered by the user and convert them into an appropriate format. In addition, the sentiment analysis engine analyzes emotions from the user's voice and text input and provides information and recommendations appropriate to the user based on the analysis results.

[0842] Next, we will explain in detail how the system works. The user launches the application on their device and selects the language they wish to use. The user then enters the order details, which are sent from the device to the server. The server passes the received order details to the generative AI model for analysis. After analyzing the order details, the generative AI model converts them into a format specific to each store. For example, an order in English such as "I want to order a cheeseburger and fries" is converted to "one cheeseburger and one french fries."

[0843] For multilingual support, the server translates the converted order into the appropriate language based on the language selected by the user. For example, the converted Japanese order might be translated into English as "Order 1 cheeseburger and 1 fries."

[0844] For emotion analysis, the emotion engine analyzes the user's input text and voice data to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[0845] Then, to generate personalized suggestions, the server suggests additional options based on the user's past order history and the results of sentiment analysis. For example, if the user is stressed, the server can suggest simple suggestions, and if the user is relaxed, it can suggest new products.

[0846] Finally, the converted order details are confirmed and confirmed. The server presents the converted order details and suggestions to the user and displays them on the terminal. The user confirms the details, makes any necessary corrections, and finally presses the confirm button, at which point the final order details are sent to the server. The server then sends the confirmed order details to the store, where the store staff processes the order and sends a confirmation message to the server once it is complete. Finally, the server receives the confirmation message from the store and sends an order completion notification to the user's terminal.

[0847] As a concrete example, let's look at the process of ordering at a restaurant. The user launches the OrderBridge app and selects English. Next, they enter "I want to order a cheeseburger and fries," and the device sends the order details to the server. The server analyzes the order using a generative AI model and converts the order to "1 cheeseburger and 1 fries." The server then translates the converted content into English, setting it to "Order 1 cheeseburger and 1 fries." The emotion engine analyzes the user's emotional state from their text and voice and determines that they are relaxed. The server takes into account the user's past history and asks, "Would you like to add a chocolate shake?" The user confirms and confirms the order details. The device sends the final order details to the server, which then sends the order details to the store. The store staff processes the order and, once complete, sends a confirmation message to the server. The server then sends a notification of order completion to the user's device.

[0848] This invention is expected to facilitate smoother communication between users and stores, significantly reducing troubles with orders, and also improve user satisfaction by providing services that correspond to the user's emotional state.

[0849] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0850] Specific explanation of processing steps

[0851] Step 1:

[0852] User input of order details

[0853] The user opens the OrderBridge app, selects the language they want to use (e.g., English), and then enters their order details: "I want to order a cheeseburger and fries." When the user presses the "Submit" button, the order details are sent to the terminal as input data.

[0854] Step 2:

[0855] Sending order details to the server via the terminal

[0856] The terminal sends the entered order details to the server. In this step, the user's order details are sent as input data from the terminal to the server via HTTPS. The server adds the received data to a queue for analysis.

[0857] Step 3:

[0858] Analysis of order details using a server-generated AI model

[0859] The server passes the received order details to the generative AI model for analysis. Specifically, the generative AI model analyzes the order details using natural language processing (NLP) technology and extracts the keywords "cheeseburger" and "fries." The input data is the user's order, and the output data is the extracted keywords and structured order information.

[0860] Step 4:

[0861] The server converts the order into store format.

[0862] The server converts the order details into the store's format based on the analysis results returned by the generative AI model. This conversion process uses pre-defined store format mapping rules. For example, "cheeseburger" and "fries" are converted into "1 cheeseburger, 1 french fries." The input data is the analysis results, and the output data is the converted order details.

[0863] Step 5:

[0864] Multilingual support for order details via the server

[0865] The server translates the converted order into the language selected by the user (e.g., English). In this step, the order is translated using a translation API (e.g., Google Translate API). The input data is the converted order, and the output data is the translated order.

[0866] Step 6:

[0867] User emotion analysis by emotion engine on the server

[0868] The server uses an emotion engine to analyze the user's input text and voice data. The emotion engine determines the user's emotional state using, for example, IBM Watson's emotion analysis API. The input data is the user's text and voice data, and the output data is the user's emotional state.

[0869] Step 7:

[0870] Server-generated personalized suggestions

[0871] The server generates personalized suggestions based on the user's past order history and the results of emotion analysis. The suggestions suggest new products to relaxed users and simple suggestions to stressed users. The input data are the user's order history and emotional state, and the output data are personalized suggestions.

[0872] Step 8:

[0873] User confirms and confirms order details

[0874] The server presents the converted order details and proposals to the user and displays them on the terminal. The user checks the displayed details, makes any necessary corrections, and presses the "Confirm" button. The input data are the order details and proposals presented to the user, and the output data are the final order details confirmed by the user.

[0875] Step 9:

[0876] Sending the final order details to the server by the terminal

[0877] When the user confirms the order, the terminal sends the final order details to the server. Once this sending operation is complete, the order processing proceeds to the next step. The input data is the final order details confirmed by the user, and the output data is the final order details sent to the server.

[0878] Step 10:

[0879] The server sends the order to the store

[0880] The server sends the final order details to the store's system using a standard protocol (e.g., REST API). The input data is the final order details, and the output data is the order details sent to the store's system.

[0881] Step 11:

[0882] Order processing and confirmation by the store

[0883] The store staff prepares the product based on the received order details, and when the order is completed, the store's system sends a completion confirmation message to the server. The input data is the order details received by the store, and the output data is the completion confirmation message sent to the server.

[0884] Step 12:

[0885] The server sends a notification of order completion to the user's device.

[0886] The server receives a completion confirmation message from the store and sends an order completion notification to the user's terminal. This notification includes a redemption code and pickup time. The input data is the completion confirmation message from the store, and the output data is the order completion notification sent to the user's terminal.

[0887] In this way, this system realizes smooth communication between users and stores, significantly reducing ordering problems. It also improves user satisfaction by making suggestions based on the user's emotional state.

[0888] (Application example 2)

[0889] 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."

[0890] Conventional ordering support systems make it difficult for users to order smoothly at stores or services they visit for the first time. Furthermore, the lack of multilingual support and personalized suggestions based on the user's emotions often compromises the user experience. This leads to issues such as reduced ordering accuracy and user satisfaction.

[0891] The identification process 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 accepting order details entered by a user, means for analyzing the order details using a generative AI model, means for converting the order details into an order format for each request destination based on the analysis results, means for presenting the converted order details to the user, means for sending the order details finally confirmed by the user to the request destination, means for receiving a confirmation message from the request destination and notifying the user, means for analyzing the user's emotional state and generating personalized proposals based thereon, means for translating the order details into a language selected by the user with a multilingual function, and means for generating personalized proposals based on the user's past order history and preferences. This enables the user to smoothly place an order even when visiting a store or service for the first time, realizes a detailed response that reflects the user's emotions, and improves the accuracy of orders and user satisfaction.

[0892] A "user terminal" is a device through which a user inputs order details and communicates with the server.

[0893] "Server" refers to a central processing unit that receives and analyzes the order details sent from the user terminal and performs processes such as conversion, translation, and notification.

[0894] The "order support system" is a system that communicates between the user's terminal and a server, analyzes, converts, and translates the order details entered by the user, and makes appropriate suggestions.

[0895] A "generative AI model" is an artificial intelligence model that includes machine learning algorithms to analyze the order details entered by the user and understand the intent behind the order.

[0896] "Emotional State" means the user's psychological and emotional state as analyzed from the user's voice and text input.

[0897] "Emotion analysis" is the process of recognizing a user's emotional state from their vocabulary, tone, typing speed, etc.

[0898] "Personalized suggestions" is a feature that makes optimal suggestions to individual users based on their past order history and emotional state.

[0899] "Multilingual support" is a function that allows order details to be translated into various languages ​​for users who speak different languages.

[0900] The "request destination" refers to the store or service provider to which the user wishes to place an order.

[0901] "Order format" refers to the specific order entry format required by each requestor.

[0902] MODE FOR CARRYING OUT THE INVENTION

[0903] The present invention is an ordering support system in which a user terminal and a server are connected so that they can communicate with each other, and aims to enable users to smoothly place orders even in new locations. This system is particularly equipped with multilingual support and a personalized suggestion function using sentiment analysis, which significantly improves the user experience.

[0904] System Configuration

[0905] The system includes the following main components:

[0906] 1. User Device:

[0907] This is a device that users use to input order details. It is often a smartphone, tablet, or PC. Users use this device to input order details and send them to the server.

[0908] 2. Server:

[0909] The server receives the order content sent from the user terminal and processes it through analysis, conversion, suggestions, translation, etc. The server has the computing resources to run the generative AI model and emotion engine.

[0910] 3. Generative AI Model:

[0911] The generative AI model uses natural language processing (NLP) technology to analyze the order details entered by the user and understand the intent behind the order. The model also generates optimal suggestions based on the user's order history and sentiment analysis results.

[0912] 4. Emotion Engine:

[0913] The emotion engine analyzes the user's text and voice data to recognize their emotional state, determining whether they are relaxed or stressed.

[0914] Operation overview

[0915] The system operates as follows:

[0916] 1. Enter and submit your order:

[0917] The user starts the terminal application and enters the order details, for example, "I want to order a cheeseburger and fries." This input is sent to the server as a prompt.

[0918] 2. Order analysis and conversion:

[0919] The server uses a generative AI model to analyze the order and convert it into a custom order format, such as "one cheeseburger and one fries."

[0920] 3. Multilingual support:

[0921] The server translates the converted order into the user's language of choice, for example, "Order 1 cheeseburger and 1 fries."

[0922] 4. Sentiment analysis and suggestion generation:

[0923] The emotion engine analyzes the user's emotional state from their text or voice input, providing new suggestions if they are relaxed, or simple suggestions if they are stressed.

[0924] 5. Final confirmation and order submission:

[0925] The user sends the final order details to the server, which then sends them to the requested party. The order is completed when a confirmation message is received from the requested party and the user is notified.

[0926] Specific examples

[0927] When a user places an order using a smartphone, they enter the following prompt:

[0928] "I want to order a cheeseburger and fries"

[0929] The server analyzes this order, converts it into the appropriate format, translates it if necessary, analyzes the user's emotional state, and generates new suggestions based on that (e.g., "Would you like to add a chocolate shake?"). The user finally confirms and confirms the order, which is then sent to the destination.

[0930] As described above, the present invention enables users to smoothly place orders in different locations and language environments, and improves the ordering experience by providing personalized suggestions based on emotions.

[0931] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0932] Step 1:

[0933] The user starts the application on the terminal and selects the language to use. Next, the user inputs the order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the terminal to the server as a prompt. Based on the input (prompt), the server receives the order details.

[0934] Step 2:

[0935] The server passes the order details to the generative AI model for analysis. The generative AI model analyzes the input prompt (order details) and understands the intent of the order. Data processing involves tokenizing the order details using natural language processing technology and evaluating the context. Structured order data is generated as the output.

[0936] Step 3:

[0937] Based on the analysis results, the server converts the order details into an order format specific to the customer. Here, the output of the generative AI model is used to convert the data into a specific order format. For example, "I want to order a cheeseburger and fries" is converted to "1 cheeseburger and 1 french fries."

[0938] Step 4:

[0939] The server presents the converted order details to the user. At this time, the order details are translated according to the language selected by the user. For example, if English is selected, the order details will be translated as "Order 1 cheeseburger and 1 fries." A multilingual API is used for the translation.

[0940] Step 5:

[0941] The server uses an emotion engine to analyze the user's emotional state from the text and voice input. Data processing involves extracting emotional features from the input text and voice data and evaluating them with an emotion classification model. The output is the user's emotional state (relaxed, stressed, etc.).

[0942] Step 6:

[0943] The server generates personalized suggestions based on the user's past ordering history and emotional state, such as "Would you like to add a chocolate shake?". A recommendation system is used to make new suggestions using the emotional state and past ordering data.

[0944] Step 7:

[0945] The server presents the order details and proposals to the user for final confirmation and displays them on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button. Based on the input (user's final confirmation), the confirmed order details are sent to the server.

[0946] Step 8:

[0947] The server sends the confirmed order details to the requester. The requester's system receives and processes the order details. Once processing is complete, the requester's system sends a confirmation message to the server.

[0948] Step 9:

[0949] The server receives a confirmation message from the request destination and sends an order completion notification to the user's terminal. The user can check this notification and know that the order has been completed.

[0950] 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.

[0951] 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.

[0952] 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.

[0953] [Third embodiment]

[0954] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0955] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0956] 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).

[0957] 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.

[0958] 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.

[0959] 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).

[0960] 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. 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.

[0961] 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.

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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."

[0966] This system, "OrderBridge," connects the user's device and server for communication, allowing the user to smoothly place orders at stores they visit for the first time. When the user enters their order details, the details are analyzed by a generative AI model and converted into a format suitable for the store. The system also supports multiple languages ​​and provides personalized suggestions.

[0967] System Overview

[0968] 1. User Device

[0969] User terminals include devices such as smartphones, tablets, and personal computers. Users use these terminals to input order details, confirm the order, and finalize it.

[0970] 2. Server

[0971] The server is communicatively connected to the user terminal and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, sending them to the store, and notifying the user.

[0972] 3. Generative AI Models

[0973] The generative AI model includes machine learning algorithms used to analyze order content and generate recommendations, allowing it to interpret and convert order content entered by users in natural language into an appropriate format.

[0974] Program processing explanation

[0975] 1. User Order Entry

[0976] The user launches the application on the device, selects a language, and then enters their order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the device to the server.

[0977] 2. Server analyzes the order

[0978] The server passes the received order details to the generative AI model for analysis. The generative AI model analyzes the input and understands the intent of the order.

[0979] 3. Order Conversion

[0980] The server then converts the order into a store-specific format based on the analysis results returned by the generative AI model, such as "one cheeseburger and one fries."

[0981] 4. Multilingual support

[0982] The server translates the converted order content into the appropriate language based on the language selected by the user.

[0983] 5. Generate personalized suggestions

[0984] The server considers the user's past ordering history and preferences and suggests additional options (e.g., "Would you like to add a chocolate shake?").

[0985] 6. Confirm and confirm the order details after conversion

[0986] The server presents the converted order details and suggestions to the user, which are displayed on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button, after which the final order details are sent to the server.

[0987] 7. Sending and confirming orders to the store

[0988] The server sends the confirmed order details to the store, which receives the order details. The store staff processes the order and sends a confirmation message to the server after completion.

[0989] 8. Order completion notification

[0990] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check the notification and find out the redemption code, pick-up time, etc.

[0991] Specific examples

[0992] Restaurant orders:

[0993] A user launches the OrderBridge app and selects English.

[0994] The user enters, "I want to order a cheeseburger and fries."

[0995] The terminal sends the order details to the server.

[0996] The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[0997] The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[0998] The server considers the user's past history and suggests, "Would you like to add a chocolate shake?"

[0999] The user checks and confirms the order.

[1000] The terminal sends the final order details to the server.

[1001] The server sends the final order details to the store.

[1002] Store staff processes the order and sends a confirmation message to the server once completed.

[1003] The server sends an order completion notification to the user's terminal.

[1004] The present invention is expected to facilitate smooth communication between users and stores, significantly reducing troubles with orders.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] The user launches the OrderBridge app and the home screen appears.

[1008] Step 2:

[1009] Users select the language they want to use on their home screen.

[1010] Step 3:

[1011] The terminal sends the selected language information to the OrderBridge server.

[1012] Step 4:

[1013] The server records the received language information and loads the corresponding language resource.

[1014] Step 5:

[1015] The user opens an order entry screen on their device and enters what they want to order (e.g., "I want to order a cheeseburger and fries").

[1016] Step 6:

[1017] The terminal sends the entered order details in text format to the OrderBridge server.

[1018] Step 7:

[1019] The server receives the order details and passes them to the generative AI model.

[1020] Step 8:

[1021] A generative AI model analyzes the order and extracts the intent behind it (e.g., recognizing two orders: "cheeseburger" and "fries").

[1022] Step 9:

[1023] The server receives the analysis results from the generative AI model and converts them into a store-specific order format (e.g., "one cheeseburger and one fries").

[1024] Step 10:

[1025] The server translates the converted order into the user's language of choice (e.g., English) (e.g., "Order 1 cheeseburger and 1 fries").

[1026] Step 11:

[1027] The server considers the user's past ordering history and preferences and suggests additional options (e.g., "Would you like to add a chocolate shake?").

[1028] Step 12:

[1029] The server sends the converted order details and proposals to the user terminal.

[1030] Step 13:

[1031] The terminal displays the order and additional suggestions to the user.

[1032] Step 14:

[1033] The user checks the order details, corrects them if necessary, and finally presses the confirm button.

[1034] Step 15:

[1035] The terminal sends the final order details to the OrderBridge server.

[1036] Step 16:

[1037] The server receives the final order details and sends them to the store's system.

[1038] Step 17:

[1039] The store's system receives the order and begins processing it.

[1040] Step 18:

[1041] Store staff prepare the order and, once complete, send a confirmation message to the OrderBridge server.

[1042] Step 19:

[1043] The server receives a confirmation message from the store.

[1044] Step 20:

[1045] The server sends an order completion notification to the user's terminal.

[1046] Step 21:

[1047] The terminal will display a code to the user to complete the order and redeem it.

[1048] Example 1

[1049] 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."

[1050] Conventional ordering support systems have problems such as difficulty in ordering at stores visited for the first time or in communicating in a foreign language, which can easily lead to problems. Furthermore, they often lack personalized suggestions based on the user's past preferences and order history, resulting in a poor user experience. To solve these problems, a new ordering support system with multilingual support and personalized suggestion functionality is needed.

[1051] 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.

[1052] In this invention, the server includes means for accepting order details entered by a user, means for analyzing the order details using a generative AI model, means for converting the order details into a format for each information system based on the analysis results, means for presenting the converted order details to the user, means for transmitting the order details finally confirmed by the user to the information processing device, means for receiving an order confirmation message from the information processing device and notifying the user, means for generating personalized suggestions based on the user's past order history and preferences, and means for appropriately translating the order details based on the selected language. This allows users to smoothly place orders even at stores they visit for the first time, and is expected to improve the user experience through multilingual support and personalized suggestions.

[1053] A "user terminal" is a computer device that allows a user to input, confirm, and finalize an order, and specifically includes a smartphone, tablet, PC, etc.

[1054] A "server" is a computer device that is communicatively connected to a user terminal and performs processes such as receiving order details, analyzing, converting, translating, generating suggestions, sending to stores, and notifying users.

[1055] A "generative AI model" is a model that uses machine learning algorithms to analyze input order details and convert the order details into a format specific to each store.

[1056] "Order details" refers to information about the product or service that the user wishes to purchase, which is input into the terminal.

[1057] The "order format" is a format that has been converted and formatted to make the analyzed order content easier for stores and information systems to process.

[1058] "Multilingual support" is a function that translates and displays order details based on the different languages ​​selected by the user when entering an order.

[1059] "Personalized Offers" refers to additional offers or options that are individually provided to a user based on the user's past order history and preference data.

[1060] An "order confirmation message" is a message that a store sends to a server after accepting a user's order and confirming its contents.

[1061] This invention is a system that allows users to input order details using a terminal, and a server analyzes and converts the details and transmits the order to the store in an appropriate format. This system uses the user terminal, server, and generative AI model to smoothly perform the entire process from order input to confirmation, confirmation, and notification, and also has multilingual support and personalized suggestion functions.

[1062] User terminal

[1063] A user terminal is a device that is directly operated by a user, and includes a smartphone, tablet, PC, etc. A dedicated application is installed on these devices, and the user launches this application to place an order.

[1064] server

[1065] The server is connected to the user's device and performs a series of processes, from receiving the order details to analyzing, converting, translating, generating suggestions, and sending them to the store. The server is equipped with a generative AI model and properly analyzes the user's natural language input.

[1066] Generative AI Models

[1067] The generative AI model is used to analyze orders using machine learning algorithms and convert them into store-specific order formats. The model also has multilingual support and can translate orders based on the language selected by the user.

[1068] Specific examples

[1069] Here's a sample order at a restaurant:

[1070] 1. The user launches the OrderBridge app and selects English.

[1071] 2. The user enters, "I want to order a cheeseburger and fries."

[1072] 3. The terminal sends the order details to the server.

[1073] 4. The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[1074] 5. The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[1075] 6. The server considers the user's past history and suggests, "Would you like to add a chocolate shake?"

[1076] 7. The user confirms and confirms the order.

[1077] 8. The terminal sends the final order details to the server.

[1078] 9. The server sends the final order details to the store.

[1079] 10. The store staff processes the order and sends a confirmation message to the server once completed.

[1080] 11. The server sends an order completion notification to the user's device.

[1081] This system allows users to place orders smoothly, regardless of language barriers, and allows stores to receive accurate orders. Furthermore, personalized suggestions are expected to improve the user experience.

[1082] Example prompt sentence:

[1083] "I want to order a cheeseburger and fries"

[1084] "Can I get a vegetarian pizza with extra cheese?"

[1085] "I would like to add a large coffee to my order"

[1086] The system of the present invention is expected to streamline the entire ordering process and strengthen communication between users and stores.

[1087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1088] Step 1:

[1089] User order entry

[1090] The user launches the OrderBridge app on their device (smartphone, tablet, or PC) and selects the language they wish to use. Next, the user enters the order details in natural language and presses the submit button. The order details entered by the user are then saved as text data on the device. For example, the user might enter "I want to order a cheeseburger and fries." This text data is sent to the server.

[1091] Input: User's natural language order details

[1092] Output: Text data of the order details sent to the server

[1093] Step 2:

[1094] Server parsing of order details

[1095] The server passes the text data received from the device to the generative AI model, which uses natural language processing technology to analyze the user's input. As a result of the analysis, the model extracts the ordering intent (e.g., "I would like to order a cheeseburger and fries") and generates semantic data in digital form.

[1096] Input: Text data of order details from the terminal

[1097] Output: Digital data of parsed order details

[1098] Step 3:

[1099] Order conversion

[1100] The server receives the analysis results from the generative AI model and converts the order content into a store-specific format based on the analysis results. For example, "I want to order a cheeseburger and fries" is converted into "1 cheeseburger and 1 fries."

[1101] Input: Analyzed digital data of order details

[1102] Output: Order details converted into a store-friendly format

[1103] Step 4:

[1104] Multilingual support

[1105] The server translates the converted order into the appropriate language based on the user's language selection: if the user selects English, the converted order will be translated as "Order 1 cheeseburger and 1 fries."

[1106] Input: Order details converted into store-appropriate format, user's preferred language setting

[1107] Output: Order details translated into the selected language

[1108] Step 5:

[1109] Generate personalized suggestions

[1110] The server will refer to the user's past order history and preference data to generate appropriate additional suggestions. For example, if a user has previously ordered a chocolate shake, the server will generate the suggestion "Would you like to add a chocolate shake?"

[1111] Input: User's past order history, preference data

[1112] Output: Personalized suggestions

[1113] Step 6:

[1114] Confirm and confirm the order details after conversion

[1115] The server presents the converted order and personalized suggestions to the user, who can then review the order on their device and make any necessary corrections. Finally, when the user presses the confirm button, the final order is sent to the server.

[1116] Input: translated order, personalized suggestions

[1117] Output: Order details and proposals presented to the user, and final order details

[1118] Step 7:

[1119] Sending and confirming orders to the store

[1120] The server sends the order details confirmed by the user to the store. The store's system receives the order details and begins processing the order. Once the order is processed, the store's system sends a confirmation message to the server.

[1121] Input: Final order details

[1122] Output: Order details sent to the store, confirmation message from the store

[1123] Step 8:

[1124] Order completion notification

[1125] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check information such as the redemption code and pickup time.

[1126] Input: Confirmation message from the store

[1127] Output: Order completion notification sent to the user

[1128] The above processing flow allows the user to place an order smoothly and the store to receive the order accurately.

[1129] (Application example 1)

[1130] 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."

[1131] In the modern restaurant and food delivery industry, ordering is often difficult when users are visiting a new restaurant or using a new platform. Meanwhile, there is a need to improve the user experience due to issues with translation between different languages ​​and a lack of appropriate suggestions based on user preferences. Furthermore, the lack of personalized suggestions based on past ordering history makes it difficult for users to efficiently order what suits their preferences.

[1132] 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.

[1133] In this invention, the server includes: means for being communicatively connected to a user terminal; means for accepting order details entered by a user; means for analyzing the order details using a generative AI model; means for converting the order details into an order format for each store based on the analysis results; means for presenting the converted order details to the user; means for sending the order details finally confirmed by the user to the store; means for receiving an order confirmation message from the store and notifying the user; means for translating the order details into a language selected by the user with a multilingual function; means for generating personalized suggestions based on the user's past ordering history and preferences; and means for transmitting the order details to affiliated restaurants. This allows users to smoothly order at stores or platforms they are using for the first time through appropriate suggestions based on translation issues between different languages ​​and user preferences, as well as personalized suggestions.

[1134] "User terminal" refers to a device used by a user to input order details, such as a smartphone, tablet, or PC.

[1135] "Server" refers to a computer system that is communicatively connected to a user terminal and performs processes such as receiving, analyzing, converting, translating, generating suggestions, sending to the restaurant, and notifying the user.

[1136] A "generative AI model" refers to a model that includes machine learning algorithms to interpret order details entered in natural language and convert them into an appropriate format.

[1137] "Multilingual support" refers to the ability to automatically translate orders based on the language selected by the user.

[1138] "Personalized suggestions" refers to the ability to generate additional options and suggestions based on a user's past ordering history and preferences.

[1139] "Food delivery service" refers to a service that allows users to order food and drinks from restaurants using their smartphones and have them delivered.

[1140] An "order confirmation message" refers to a message that confirms that the restaurant has accepted the order details confirmed by the user.

[1141] MODE FOR CARRYING OUT THE INVENTION

[1142] The present invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other. Below, the processing of a program for realizing this system and a specific example thereof will be described.

[1143] System Configuration

[1144] The system mainly consists of the following components:

[1145] 1. User Device

[1146] Smartphone (iOS or Android)

[1147] tablet

[1148] PC

[1149] 2. Server

[1150] Cloud hosting (e.g. AWS)

[1151] Database (e.g. MongoDB)

[1152] Machine learning models (e.g., generative AI models using GPT-3)

[1153] 3. Software

[1154] Frontend: React Native

[1155] Backend: Node.js, Express.js

[1156] Program processing explanation

[1157] 1. User Order Entry

[1158] A user launches a smartphone application, selects their preferred language, and then enters their order details in natural language into the application's input field. For example, they might enter, "I'd like to order a pizza and a cola."

[1159] 2. Server analyzes the order

[1160] The terminal sends the entered order details to the server. The server passes the order details to the generative AI model for analysis. The generative AI model analyzes the order details and understands the user's intentions.

[1161] 3. Order Conversion

[1162] Based on the analysis results, the server converts the order details into a format specific to the partner restaurant, such as "one pizza and one bottle of coke."

[1163] 4. Multilingual support

[1164] The server automatically translates the order based on the language selected by the user.

[1165] 5. Generate personalized suggestions

[1166] The server takes into account the user's past ordering history and preferences to make further recommendations, such as "Would you like some garlic bread as a side?"

[1167] 6. Confirm and confirm the order details after conversion

[1168] The server presents the converted order details and suggestions to the user. When the user confirms the details and finally presses the confirm button, the confirmed order details are sent to the server.

[1169] 7. Sending and confirming orders to restaurants

[1170] The server sends the confirmed order to the partner restaurant, which receives the order, and the restaurant's system receives it. The restaurant staff processes the order and sends a confirmation message to the server once it is complete.

[1171] 8. Order completion notification

[1172] The server receives a confirmation message from the restaurant and sends a completed order notification to the user's smartphone, along with information such as a redemption code and pickup time.

[1173] Specific examples

[1174] For example, a user launches the FoodEase app and selects English. Then, they enter, "I want to order a Hawaiian pizza and a coke." The input is sent to the server and analyzed by the generative AI model. The analysis results in "One Hawaiian pizza and one bottle of Coca-Cola." The model then suggests, "Would you like to add garlic bread to your order?" Once the user confirms and places the order, the server sends the final order details to the partner restaurant. The restaurant processes the order and sends a confirmation message to the server, which then sends the user a notification that the order is complete.

[1175] Prompt Sentence Examples

[1176] User order: "I want to order a cheeseburger and fries"

[1177] Response: "Your order was recognized as '1 cheeseburger, 1 fries'. Additional suggestion: 'Would you like to add a chocolate shake?'"

[1178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1179] Step 1:

[1180] The user starts up the device (smartphone) and launches the FoodEase application. The user selects their preferred language before entering their order. The input at this stage is the language setting of the application. There is no output to the server.

[1181] Step 2:

[1182] A user enters their order in natural language into an application's input field, for example, "I want to order a Hawaiian pizza and a coke." This input is sent from the device to the server, where it is forwarded to the server and prepared for analysis.

[1183] Step 3:

[1184] The server sends the received natural language order content to the generative AI model for analysis. The input for analysis is "I want to order a Hawaiian pizza and a coke." The generative AI model understands the order content and outputs formatted order data (e.g., "One Hawaiian pizza and one bottle of Coca-Cola").

[1185] Step 4:

[1186] The server converts the order details into a format specific to the partner restaurant based on the analysis results of the generative AI model. The input is the analyzed order data, and the output is the converted order data (e.g., "One Hawaiian pizza and one bottle of Coca-Cola"). The server then prepares this to be presented to the user.

[1187] Step 5:

[1188] The server translates the order based on the language selected by the user. For example, if the parsing result is "1 Hawaiian pizza and 1 Coca-Cola," it translates it into the selected language. In this case, the input is the parsing result, and the output is the translated order (e.g., "Order 1 Hawaiian pizza and 1 coke").

[1189] Step 6:

[1190] The server considers the user's past order history and preferences and suggests additional options. The input is the user's order history data and current order details, and the output is a recommendation (e.g., "Would you like to add garlic bread to your order?").

[1191] Step 7:

[1192] The server sends the converted and translated order details and suggestions to the user terminal. The user checks the details and finally presses the confirm button. The input is the suggested order details and additional suggestions, and the output is the user's final confirmation action.

[1193] Step 8:

[1194] When the user's final confirmation action is sent to the server, the server sends the confirmed order details to the partner restaurant. The input is the final confirmed order details, and the output is the order data for the restaurant. The restaurant accepts the order and starts processing it.

[1195] Step 9:

[1196] Once the restaurant has processed the order, it sends a confirmation message to the server. The server receives the confirmation message and sends a notification of order completion to the user's smartphone. The input is the confirmation message from the restaurant, and the output is a notification of order completion to the user's device.

[1197] This series of processing steps allows users to smoothly input and confirm order details even when using a store or platform for the first time.

[1198] 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.

[1199] This invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other, allowing users to smoothly place orders at stores they visit for the first time. This system uses a generative AI model to analyze order details and convert them into an order format specific to each store. It also supports multiple languages, provides personalized suggestions, and is equipped with an emotion engine that recognizes user emotions.

[1200] System Overview

[1201] 1. User Device

[1202] User terminals include devices such as smartphones, tablets, and personal computers. Users use these terminals to input order details, confirm the order, and finalize it.

[1203] 2. Server

[1204] The server is communicatively connected to the user terminal and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, analyzing emotions, sending to the store, and notifying the user.

[1205] 3. Generative AI Models

[1206] The generative AI model includes machine learning algorithms used to analyze order content and generate recommendations, allowing it to interpret and convert order content entered by users in natural language into an appropriate format.

[1207] 4. Emotion Engine

[1208] The emotion engine analyzes the user's emotions from their voice and text input, and provides information and suggestions appropriate to the user based on the analysis results, enabling appropriate responses to be made according to the user's emotions.

[1209] Program processing explanation

[1210] 1. User Order Entry

[1211] The user launches the application on the device, selects the language they want to use, and then enters their order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the device to the server.

[1212] 2. Server analyzes the order

[1213] The server passes the received order details to the generative AI model for analysis. The generative AI model analyzes the input and understands the intent of the order.

[1214] 3. Order Conversion

[1215] The server then converts the order into a store-specific format based on the analysis results returned by the generative AI model, such as "one cheeseburger and one fries."

[1216] 4. Multilingual support

[1217] The server translates the converted order into the appropriate language based on the user's language selection (e.g., "Order 1 cheeseburger and 1 fries").

[1218] 5. User sentiment analysis

[1219] The emotion engine analyzes the text and voice data entered by the user to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[1220] 6. Generating personalized suggestions

[1221] The server suggests additional options (e.g., "Would you like to add a chocolate shake?") based on the user's past order history and the results of emotional analysis. Depending on the user's emotional state, it can respond by suggesting simple suggestions if the user is stressed, or new products if the user is relaxed.

[1222] 7. Confirm and confirm the converted order details

[1223] The server presents the converted order details and suggestions to the user, which are displayed on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button, after which the final order details are sent to the server.

[1224] 8. Sending and confirming orders to the store

[1225] The server sends the confirmed order details to the store, which receives the order details. The store staff processes the order and sends a confirmation message to the server after completion.

[1226] 9. Order completion notification

[1227] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check the notification and find out the redemption code, pick-up time, etc.

[1228] Specific examples

[1229] Restaurant orders:

[1230] A user launches the OrderBridge app and selects English.

[1231] The user enters, "I want to order a cheeseburger and fries."

[1232] The terminal sends the order details to the server.

[1233] The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[1234] The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[1235] The emotion engine analyzes the user's emotional state from their text and voice and determines that they are relaxed.

[1236] The server considers the user's past history and presents "Would you like to add a chocolate shake?" as a new suggestion suitable for relaxation.

[1237] The user checks and confirms the order.

[1238] The terminal sends the final order details to the server.

[1239] The server sends the final order details to the store.

[1240] Store staff processes the order and sends a confirmation message to the server once completed.

[1241] The server sends an order completion notification to the user's terminal.

[1242] The present invention is expected to facilitate smoother communication between users and stores, significantly reducing ordering problems, and improve user satisfaction by providing services tailored to the user's emotional state.

[1243] The processing flow will be explained below.

[1244] Step 1:

[1245] The user launches the OrderBridge app and the home screen appears.

[1246] Step 2:

[1247] Users select the language they want to use on their home screen.

[1248] Step 3:

[1249] The terminal sends the selected language information to the OrderBridge server.

[1250] Step 4:

[1251] The server records the received language information and loads the corresponding language resource.

[1252] Step 5:

[1253] The user opens an order entry screen on their device and enters what they want to order (e.g., "I want to order a cheeseburger and fries").

[1254] Step 6:

[1255] The terminal sends the entered order details in text format to the OrderBridge server.

[1256] Step 7:

[1257] The server receives the order details and passes them to the generative AI model.

[1258] Step 8:

[1259] A generative AI model analyzes the order and extracts the intent behind it (e.g., recognizing two orders: "cheeseburger" and "fries").

[1260] Step 9:

[1261] The server receives the analysis results from the generative AI model and converts them into a store-specific order format (e.g., "one cheeseburger and one fries").

[1262] Step 10:

[1263] The server translates the converted order into the user's language of choice (e.g., English) (e.g., "Order 1 cheeseburger and 1 fries").

[1264] Step 11:

[1265] The emotion engine analyzes the text and voice data entered by the user to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[1266] Step 12:

[1267] The server generates personalized suggestions (e.g., "Would you like to add a chocolate shake?") based on the user's past order history and the results of sentiment analysis. Depending on the user's emotional state, it will make simple suggestions if the user is stressed, or suggest new products if the user is relaxed.

[1268] Step 13:

[1269] The server sends the converted order details and proposals to the user terminal.

[1270] Step 14:

[1271] The terminal displays the order and additional suggestions to the user.

[1272] Step 15:

[1273] The user checks the order details, corrects them if necessary, and finally presses the confirm button.

[1274] Step 16:

[1275] The terminal sends the final order details to the OrderBridge server.

[1276] Step 17:

[1277] The server receives the final order details and sends them to the store's system.

[1278] Step 18:

[1279] The store's system receives the order details and begins processing the order.

[1280] Step 19:

[1281] Store staff prepare the order and, once complete, send a confirmation message to the OrderBridge server.

[1282] Step 20:

[1283] The server receives a confirmation message from the store.

[1284] Step 21:

[1285] The server sends an order completion notification to the user's terminal.

[1286] Step 22:

[1287] The terminal will display a completed order and a redemption code to the user, who will then receive a notification that their order is ready for pickup at the store.

[1288] Example 2

[1289] 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."

[1290] In modern society, when users place orders at different stores, they often encounter barriers due to different ordering formats and languages. This makes ordering time-consuming and prone to misunderstandings. Furthermore, personalized suggestions that take into account the user's emotions and past order history are not provided, making it difficult to improve the user experience. There is a need for a system that can solve these problems and enable smooth ordering between users and stores.

[1291] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1292] In this invention, the server includes: means for accepting order details entered by a user; means for analyzing the order details using a generative AI model; means for converting the order details into an order format for each store based on the analysis results; means for presenting the converted order details to the user; means for transmitting the order details finally confirmed by the user to the store; means for receiving an order confirmation message from the store and notifying the user; means including an emotion analysis engine for analyzing emotions from the user's input text and voice data; and means for generating personalized suggestions based on the emotion analysis results and the user's past order history. This allows users to smoothly place orders at different stores, improving the user experience.

[1293] A "user terminal" is an electronic device used by a user to enter an order and communicate with the server.

[1294] The "server" is a central processing unit that communicates with the user terminal, analyzes and converts the order details, and transmits them to the store.

[1295] An "order support system" is a system in which a user terminal and a server are communicatively connected to support the user's ordering process.

[1296] A "generative AI model" is a system that uses machine learning algorithms to analyze the order details entered by the user and understand the intent behind the order.

[1297] "Order details" are specific requirements for an order that are input by the user through the terminal and analyzed by the server.

[1298] An "emotion analysis engine" is a device or program that analyzes a user's emotional state from input text and voice data.

[1299] "Personalized suggestions" are suggestions that are individually generated based on the user's past order history and sentiment analysis results.

[1300] A "store format" is a standard format for order details used at a particular store.

[1301] The "multilingual function" is a function capable of translating the order contents into an appropriate language according to the language selected by the user.

[1302] An "order confirmation message" is a message that the store sends to the server after confirming the order details it has received.

[1303] This invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other, allowing users to smoothly place orders at stores they visit for the first time. This system uses a generative AI model to analyze order details and convert them into an order format specific to each store. It also supports multiple languages, provides personalized suggestions, and includes an emotion analysis engine that recognizes user emotions.

[1304] To give an overview of the system, electronic devices such as smartphones, tablets, and PCs are used as user terminals. Users use these terminals to input order details, confirm, and finally confirm the order. Next, a server is connected to the user terminal so that it can communicate with it, and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, analyzing emotions, sending them to the store, and notifying the user.

[1305] The generative AI model is the core technology of this system and includes machine learning algorithms used to analyze order details and generate recommendations. Specifically, it uses natural language processing (NLP) technology to interpret the order details entered by the user and convert them into an appropriate format. In addition, the sentiment analysis engine analyzes emotions from the user's voice and text input and provides information and recommendations appropriate to the user based on the analysis results.

[1306] Next, we will explain in detail how the system works. The user launches the application on their device and selects the language they wish to use. The user then enters the order details, which are sent from the device to the server. The server passes the received order details to the generative AI model for analysis. After analyzing the order details, the generative AI model converts them into a format specific to each store. For example, an order in English such as "I want to order a cheeseburger and fries" is converted to "one cheeseburger and one french fries."

[1307] For multilingual support, the server translates the converted order into the appropriate language based on the language selected by the user. For example, the converted Japanese order might be translated into English as "Order 1 cheeseburger and 1 fries."

[1308] For emotion analysis, the emotion engine analyzes the user's input text and voice data to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[1309] Then, to generate personalized suggestions, the server suggests additional options based on the user's past order history and the results of sentiment analysis. For example, if the user is stressed, the server can suggest simple suggestions, and if the user is relaxed, it can suggest new products.

[1310] Finally, the converted order details are confirmed and confirmed. The server presents the converted order details and suggestions to the user and displays them on the terminal. The user confirms the details, makes any necessary corrections, and finally presses the confirm button, at which point the final order details are sent to the server. The server then sends the confirmed order details to the store, where the store staff processes the order and sends a confirmation message to the server once it is complete. Finally, the server receives the confirmation message from the store and sends an order completion notification to the user's terminal.

[1311] As a concrete example, let's look at the process of ordering at a restaurant. The user launches the OrderBridge app and selects English. Next, they enter "I want to order a cheeseburger and fries," and the device sends the order details to the server. The server analyzes the order using a generative AI model and converts the order to "1 cheeseburger and 1 fries." The server then translates the converted content into English, setting it to "Order 1 cheeseburger and 1 fries." The emotion engine analyzes the user's emotional state from their text and voice and determines that they are relaxed. The server takes into account the user's past history and asks, "Would you like to add a chocolate shake?" The user confirms and confirms the order details. The device sends the final order details to the server, which then sends the order details to the store. The store staff processes the order and, once complete, sends a confirmation message to the server. The server then sends a notification of order completion to the user's device.

[1312] This invention is expected to facilitate smoother communication between users and stores, significantly reducing troubles with orders, and also improve user satisfaction by providing services that correspond to the user's emotional state.

[1313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1314] Specific explanation of processing steps

[1315] Step 1:

[1316] User input of order details

[1317] The user opens the OrderBridge app, selects the language they want to use (e.g., English), and then enters their order details: "I want to order a cheeseburger and fries." When the user presses the "Submit" button, the order details are sent to the terminal as input data.

[1318] Step 2:

[1319] Sending order details to the server via the terminal

[1320] The terminal sends the entered order details to the server. In this step, the user's order details are sent as input data from the terminal to the server via HTTPS. The server adds the received data to a queue for analysis.

[1321] Step 3:

[1322] Analysis of order details using a server-generated AI model

[1323] The server passes the received order details to the generative AI model for analysis. Specifically, the generative AI model analyzes the order details using natural language processing (NLP) technology and extracts the keywords "cheeseburger" and "fries." The input data is the user's order, and the output data is the extracted keywords and structured order information.

[1324] Step 4:

[1325] The server converts the order into store format.

[1326] The server converts the order details into the store's format based on the analysis results returned by the generative AI model. This conversion process uses pre-defined store format mapping rules. For example, "cheeseburger" and "fries" are converted into "1 cheeseburger, 1 french fries." The input data is the analysis results, and the output data is the converted order details.

[1327] Step 5:

[1328] Multilingual support for order details via the server

[1329] The server translates the converted order into the language selected by the user (e.g., English). In this step, the order is translated using a translation API (e.g., Google Translate API). The input data is the converted order, and the output data is the translated order.

[1330] Step 6:

[1331] User emotion analysis by emotion engine on the server

[1332] The server uses an emotion engine to analyze the user's input text and voice data. The emotion engine determines the user's emotional state using, for example, IBM Watson's emotion analysis API. The input data is the user's text and voice data, and the output data is the user's emotional state.

[1333] Step 7:

[1334] Server-generated personalized suggestions

[1335] The server generates personalized suggestions based on the user's past order history and the results of emotion analysis. The suggestions suggest new products to relaxed users and simple suggestions to stressed users. The input data are the user's order history and emotional state, and the output data are personalized suggestions.

[1336] Step 8:

[1337] User confirms and confirms order details

[1338] The server presents the converted order details and proposals to the user and displays them on the terminal. The user checks the displayed details, makes any necessary corrections, and presses the "Confirm" button. The input data are the order details and proposals presented to the user, and the output data are the final order details confirmed by the user.

[1339] Step 9:

[1340] Sending the final order details to the server by the terminal

[1341] When the user confirms the order, the terminal sends the final order details to the server. Once this sending operation is complete, the order processing proceeds to the next step. The input data is the final order details confirmed by the user, and the output data is the final order details sent to the server.

[1342] Step 10:

[1343] The server sends the order to the store

[1344] The server sends the final order details to the store's system using a standard protocol (e.g., REST API). The input data is the final order details, and the output data is the order details sent to the store's system.

[1345] Step 11:

[1346] Order processing and confirmation by the store

[1347] The store staff prepares the product based on the received order details, and when the order is completed, the store's system sends a completion confirmation message to the server. The input data is the order details received by the store, and the output data is the completion confirmation message sent to the server.

[1348] Step 12:

[1349] The server sends a notification of order completion to the user's device.

[1350] The server receives a completion confirmation message from the store and sends an order completion notification to the user's terminal. This notification includes a redemption code and pickup time. The input data is the completion confirmation message from the store, and the output data is the order completion notification sent to the user's terminal.

[1351] In this way, this system realizes smooth communication between users and stores, significantly reducing ordering problems. It also improves user satisfaction by making suggestions based on the user's emotional state.

[1352] (Application example 2)

[1353] 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."

[1354] Conventional ordering support systems make it difficult for users to order smoothly at stores or services they visit for the first time. Furthermore, the lack of multilingual support and personalized suggestions based on the user's emotions often compromises the user experience. This leads to issues such as reduced ordering accuracy and user satisfaction.

[1355] The identification process 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 accepting order details entered by a user, means for analyzing the order details using a generative AI model, means for converting the order details into an order format for each request destination based on the analysis results, means for presenting the converted order details to the user, means for sending the order details finally confirmed by the user to the request destination, means for receiving a confirmation message from the request destination and notifying the user, means for analyzing the user's emotional state and generating personalized proposals based thereon, means for translating the order details into a language selected by the user with a multilingual function, and means for generating personalized proposals based on the user's past order history and preferences. This enables the user to smoothly place an order even when visiting a store or service for the first time, realizes a detailed response that reflects the user's emotions, and improves the accuracy of orders and user satisfaction.

[1356] A "user terminal" is a device through which a user inputs order details and communicates with the server.

[1357] "Server" refers to a central processing unit that receives and analyzes the order details sent from the user terminal and performs processes such as conversion, translation, and notification.

[1358] The "order support system" is a system that communicates between the user's terminal and a server, analyzes, converts, and translates the order details entered by the user, and makes appropriate suggestions.

[1359] A "generative AI model" is an artificial intelligence model that includes machine learning algorithms to analyze the order details entered by the user and understand the intent behind the order.

[1360] "Emotional State" means the user's psychological and emotional state as analyzed from the user's voice and text input.

[1361] "Emotion analysis" is the process of recognizing a user's emotional state from their vocabulary, tone, typing speed, etc.

[1362] "Personalized suggestions" is a feature that makes optimal suggestions to individual users based on their past order history and emotional state.

[1363] "Multilingual support" is a function that allows order details to be translated into various languages ​​for users who speak different languages.

[1364] The "request destination" refers to the store or service provider to which the user wishes to place an order.

[1365] "Order format" refers to the specific order entry format required by each requestor.

[1366] MODE FOR CARRYING OUT THE INVENTION

[1367] The present invention is an ordering support system in which a user terminal and a server are connected so that they can communicate with each other, and aims to enable users to smoothly place orders even in new locations. This system is particularly equipped with multilingual support and a personalized suggestion function using sentiment analysis, which significantly improves the user experience.

[1368] System Configuration

[1369] The system includes the following main components:

[1370] 1. User Device:

[1371] This is a device that users use to input order details. It is often a smartphone, tablet, or PC. Users use this device to input order details and send them to the server.

[1372] 2. Server:

[1373] The server receives the order content sent from the user terminal and processes it through analysis, conversion, suggestions, translation, etc. The server has the computing resources to run the generative AI model and emotion engine.

[1374] 3. Generative AI Model:

[1375] The generative AI model uses natural language processing (NLP) technology to analyze the order details entered by the user and understand the intent behind the order. The model also generates optimal suggestions based on the user's order history and sentiment analysis results.

[1376] 4. Emotion Engine:

[1377] The emotion engine analyzes the user's text and voice data to recognize their emotional state, determining whether they are relaxed or stressed.

[1378] Operation overview

[1379] The system operates as follows:

[1380] 1. Enter and submit your order:

[1381] The user starts the terminal application and enters the order details, for example, "I want to order a cheeseburger and fries." This input is sent to the server as a prompt.

[1382] 2. Order analysis and conversion:

[1383] The server uses a generative AI model to analyze the order and convert it into a custom order format, such as "one cheeseburger and one fries."

[1384] 3. Multilingual support:

[1385] The server translates the converted order into the user's language of choice, for example, "Order 1 cheeseburger and 1 fries."

[1386] 4. Sentiment analysis and suggestion generation:

[1387] The emotion engine analyzes the user's emotional state from their text or voice input, providing new suggestions if they are relaxed, or simple suggestions if they are stressed.

[1388] 5. Final confirmation and order submission:

[1389] The user sends the final order details to the server, which then sends them to the requested party. The order is completed when a confirmation message is received from the requested party and the user is notified.

[1390] Specific examples

[1391] When a user places an order using a smartphone, they enter the following prompt:

[1392] "I want to order a cheeseburger and fries"

[1393] The server analyzes this order, converts it into the appropriate format, translates it if necessary, analyzes the user's emotional state, and generates new suggestions based on that (e.g., "Would you like to add a chocolate shake?"). The user finally confirms and confirms the order, which is then sent to the destination.

[1394] As described above, the present invention enables users to smoothly place orders in different locations and language environments, and improves the ordering experience by providing personalized suggestions based on emotions.

[1395] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1396] Step 1:

[1397] The user starts the application on the terminal and selects the language to use. Next, the user inputs the order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the terminal to the server as a prompt. Based on the input (prompt), the server receives the order details.

[1398] Step 2:

[1399] The server passes the order details to the generative AI model for analysis. The generative AI model analyzes the input prompt (order details) and understands the intent of the order. Data processing involves tokenizing the order details using natural language processing technology and evaluating the context. Structured order data is generated as the output.

[1400] Step 3:

[1401] Based on the analysis results, the server converts the order details into an order format specific to the customer. Here, the output of the generative AI model is used to convert the data into a specific order format. For example, "I want to order a cheeseburger and fries" is converted to "1 cheeseburger and 1 french fries."

[1402] Step 4:

[1403] The server presents the converted order details to the user. At this time, the order details are translated according to the language selected by the user. For example, if English is selected, the order details will be translated as "Order 1 cheeseburger and 1 fries." A multilingual API is used for the translation.

[1404] Step 5:

[1405] The server uses an emotion engine to analyze the user's emotional state from the text and voice input. Data processing involves extracting emotional features from the input text and voice data and evaluating them with an emotion classification model. The output is the user's emotional state (relaxed, stressed, etc.).

[1406] Step 6:

[1407] The server generates personalized suggestions based on the user's past ordering history and emotional state, such as "Would you like to add a chocolate shake?". A recommendation system is used to make new suggestions using the emotional state and past ordering data.

[1408] Step 7:

[1409] The server presents the order details and proposals to the user for final confirmation and displays them on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button. Based on the input (user's final confirmation), the confirmed order details are sent to the server.

[1410] Step 8:

[1411] The server sends the confirmed order details to the requester. The requester's system receives and processes the order details. Once processing is complete, the requester's system sends a confirmation message to the server.

[1412] Step 9:

[1413] The server receives a confirmation message from the request destination and sends an order completion notification to the user's terminal. The user can check this notification and know that the order has been completed.

[1414] 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.

[1415] 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.

[1416] 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.

[1417] [Fourth embodiment]

[1418] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1419] 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.

[1420] 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).

[1421] 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.

[1422] 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.

[1423] 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).

[1424] 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. 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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."

[1431] This system, "OrderBridge," connects the user's device and server for communication, allowing the user to smoothly place orders at stores they visit for the first time. When the user enters their order details, the details are analyzed by a generative AI model and converted into a format suitable for the store. The system also supports multiple languages ​​and provides personalized suggestions.

[1432] System Overview

[1433] 1. User Device

[1434] User terminals include devices such as smartphones, tablets, and personal computers. Users use these terminals to input order details, confirm the order, and finalize it.

[1435] 2. Server

[1436] The server is communicatively connected to the user terminal and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, sending them to the store, and notifying the user.

[1437] 3. Generative AI Models

[1438] The generative AI model includes machine learning algorithms used to analyze order content and generate recommendations, allowing it to interpret and convert order content entered by users in natural language into an appropriate format.

[1439] Program processing explanation

[1440] 1. User Order Entry

[1441] The user launches the application on the device, selects a language, and then enters their order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the device to the server.

[1442] 2. Server analyzes the order

[1443] The server passes the received order details to the generative AI model for analysis. The generative AI model analyzes the input and understands the intent of the order.

[1444] 3. Order Conversion

[1445] The server then converts the order into a store-specific format based on the analysis results returned by the generative AI model, such as "one cheeseburger and one fries."

[1446] 4. Multilingual support

[1447] The server translates the converted order content into the appropriate language based on the language selected by the user.

[1448] 5. Generate personalized suggestions

[1449] The server considers the user's past ordering history and preferences and suggests additional options (e.g., "Would you like to add a chocolate shake?").

[1450] 6. Confirm and confirm the order details after conversion

[1451] The server presents the converted order details and suggestions to the user, which are displayed on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button, after which the final order details are sent to the server.

[1452] 7. Sending and confirming orders to the store

[1453] The server sends the confirmed order details to the store, which receives the order details. The store staff processes the order and sends a confirmation message to the server after completion.

[1454] 8. Order completion notification

[1455] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check the notification and find out the redemption code, pick-up time, etc.

[1456] Specific examples

[1457] Restaurant orders:

[1458] A user launches the OrderBridge app and selects English.

[1459] The user enters, "I want to order a cheeseburger and fries."

[1460] The terminal sends the order details to the server.

[1461] The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[1462] The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[1463] The server considers the user's past history and suggests, "Would you like to add a chocolate shake?"

[1464] The user checks and confirms the order.

[1465] The terminal sends the final order details to the server.

[1466] The server sends the final order details to the store.

[1467] Store staff processes the order and sends a confirmation message to the server once completed.

[1468] The server sends an order completion notification to the user's terminal.

[1469] The present invention is expected to facilitate smooth communication between users and stores, significantly reducing troubles with orders.

[1470] The processing flow will be explained below.

[1471] Step 1:

[1472] The user launches the OrderBridge app and the home screen appears.

[1473] Step 2:

[1474] Users select the language they want to use on their home screen.

[1475] Step 3:

[1476] The terminal sends the selected language information to the OrderBridge server.

[1477] Step 4:

[1478] The server records the received language information and loads the corresponding language resource.

[1479] Step 5:

[1480] The user opens an order entry screen on their device and enters what they want to order (e.g., "I want to order a cheeseburger and fries").

[1481] Step 6:

[1482] The terminal sends the entered order details in text format to the OrderBridge server.

[1483] Step 7:

[1484] The server receives the order details and passes them to the generative AI model.

[1485] Step 8:

[1486] A generative AI model analyzes the order and extracts the intent behind it (e.g., recognizing two orders: "cheeseburger" and "fries").

[1487] Step 9:

[1488] The server receives the analysis results from the generative AI model and converts them into a store-specific order format (e.g., "one cheeseburger and one fries").

[1489] Step 10:

[1490] The server translates the converted order into the user's language of choice (e.g., English) (e.g., "Order 1 cheeseburger and 1 fries").

[1491] Step 11:

[1492] The server considers the user's past ordering history and preferences and suggests additional options (e.g., "Would you like to add a chocolate shake?").

[1493] Step 12:

[1494] The server sends the converted order details and proposals to the user terminal.

[1495] Step 13:

[1496] The terminal displays the order and additional suggestions to the user.

[1497] Step 14:

[1498] The user checks the order details, corrects them if necessary, and finally presses the confirm button.

[1499] Step 15:

[1500] The terminal sends the final order details to the OrderBridge server.

[1501] Step 16:

[1502] The server receives the final order details and sends them to the store's system.

[1503] Step 17:

[1504] The store's system receives the order and begins processing it.

[1505] Step 18:

[1506] Store staff prepare the order and, once complete, send a confirmation message to the OrderBridge server.

[1507] Step 19:

[1508] The server receives a confirmation message from the store.

[1509] Step 20:

[1510] The server sends an order completion notification to the user's terminal.

[1511] Step 21:

[1512] The terminal will display a code to the user to complete the order and redeem it.

[1513] Example 1

[1514] 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."

[1515] Conventional ordering support systems have problems such as difficulty in ordering at stores visited for the first time or in communicating in a foreign language, which can easily lead to problems. Furthermore, they often lack personalized suggestions based on the user's past preferences and order history, resulting in a poor user experience. To solve these problems, a new ordering support system with multilingual support and personalized suggestion functionality is needed.

[1516] 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.

[1517] In this invention, the server includes means for accepting order details entered by a user, means for analyzing the order details using a generative AI model, means for converting the order details into a format for each information system based on the analysis results, means for presenting the converted order details to the user, means for transmitting the order details finally confirmed by the user to the information processing device, means for receiving an order confirmation message from the information processing device and notifying the user, means for generating personalized suggestions based on the user's past order history and preferences, and means for appropriately translating the order details based on the selected language. This allows users to smoothly place orders even at stores they visit for the first time, and is expected to improve the user experience through multilingual support and personalized suggestions.

[1518] A "user terminal" is a computer device that allows a user to input, confirm, and finalize an order, and specifically includes a smartphone, tablet, PC, etc.

[1519] A "server" is a computer device that is communicatively connected to a user terminal and performs processes such as receiving order details, analyzing, converting, translating, generating suggestions, sending to stores, and notifying users.

[1520] A "generative AI model" is a model that uses machine learning algorithms to analyze input order details and convert the order details into a format specific to each store.

[1521] "Order details" refers to information about the product or service that the user wishes to purchase, which is input into the terminal.

[1522] The "order format" is a format that has been converted and formatted to make the analyzed order content easier for stores and information systems to process.

[1523] "Multilingual support" is a function that translates and displays order details based on the different languages ​​selected by the user when entering an order.

[1524] "Personalized Offers" refers to additional offers or options that are individually provided to a user based on the user's past order history and preference data.

[1525] An "order confirmation message" is a message that a store sends to a server after accepting a user's order and confirming its contents.

[1526] This invention is a system that allows users to input order details using a terminal, and a server analyzes and converts the details and transmits the order to the store in an appropriate format. This system uses the user terminal, server, and generative AI model to smoothly perform the entire process from order input to confirmation, confirmation, and notification, and also has multilingual support and personalized suggestion functions.

[1527] User terminal

[1528] A user terminal is a device that is directly operated by a user, and includes a smartphone, tablet, PC, etc. A dedicated application is installed on these devices, and the user launches this application to place an order.

[1529] server

[1530] The server is connected to the user's device and performs a series of processes, from receiving the order details to analyzing, converting, translating, generating suggestions, and sending them to the store. The server is equipped with a generative AI model and properly analyzes the user's natural language input.

[1531] Generative AI Models

[1532] The generative AI model is used to analyze orders using machine learning algorithms and convert them into store-specific order formats. The model also has multilingual support and can translate orders based on the language selected by the user.

[1533] Specific examples

[1534] Here's a sample order at a restaurant:

[1535] 1. The user launches the OrderBridge app and selects English.

[1536] 2. The user enters, "I want to order a cheeseburger and fries."

[1537] 3. The terminal sends the order details to the server.

[1538] 4. The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[1539] 5. The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[1540] 6. The server considers the user's past history and suggests, "Would you like to add a chocolate shake?"

[1541] 7. The user confirms and confirms the order.

[1542] 8. The terminal sends the final order details to the server.

[1543] 9. The server sends the final order details to the store.

[1544] 10. The store staff processes the order and sends a confirmation message to the server once completed.

[1545] 11. The server sends an order completion notification to the user's device.

[1546] This system allows users to place orders smoothly, regardless of language barriers, and allows stores to receive accurate orders. Furthermore, personalized suggestions are expected to improve the user experience.

[1547] Example prompt sentence:

[1548] "I want to order a cheeseburger and fries"

[1549] "Can I get a vegetarian pizza with extra cheese?"

[1550] "I would like to add a large coffee to my order"

[1551] The system of the present invention is expected to streamline the entire ordering process and strengthen communication between users and stores.

[1552] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1553] Step 1:

[1554] User order entry

[1555] The user launches the OrderBridge app on their device (smartphone, tablet, or PC) and selects the language they wish to use. Next, the user enters the order details in natural language and presses the submit button. The order details entered by the user are then saved as text data on the device. For example, the user might enter "I want to order a cheeseburger and fries." This text data is sent to the server.

[1556] Input: User's natural language order details

[1557] Output: Text data of the order details sent to the server

[1558] Step 2:

[1559] Server parsing of order details

[1560] The server passes the text data received from the device to the generative AI model, which uses natural language processing technology to analyze the user's input. As a result of the analysis, the model extracts the ordering intent (e.g., "I would like to order a cheeseburger and fries") and generates semantic data in digital form.

[1561] Input: Text data of order details from the terminal

[1562] Output: Digital data of parsed order details

[1563] Step 3:

[1564] Order conversion

[1565] The server receives the analysis results from the generative AI model and converts the order content into a store-specific format based on the analysis results. For example, "I want to order a cheeseburger and fries" is converted into "1 cheeseburger and 1 fries."

[1566] Input: Analyzed digital data of order details

[1567] Output: Order details converted into a store-friendly format

[1568] Step 4:

[1569] Multilingual support

[1570] The server translates the converted order into the appropriate language based on the user's language selection: if the user selects English, the converted order will be translated as "Order 1 cheeseburger and 1 fries."

[1571] Input: Order details converted into store-appropriate format, user's preferred language setting

[1572] Output: Order details translated into the selected language

[1573] Step 5:

[1574] Generate personalized suggestions

[1575] The server will refer to the user's past order history and preference data to generate appropriate additional suggestions. For example, if a user has previously ordered a chocolate shake, the server will generate the suggestion "Would you like to add a chocolate shake?"

[1576] Input: User's past order history, preference data

[1577] Output: Personalized suggestions

[1578] Step 6:

[1579] Confirm and confirm the order details after conversion

[1580] The server presents the converted order and personalized suggestions to the user, who can then review the order on their device and make any necessary corrections. Finally, when the user presses the confirm button, the final order is sent to the server.

[1581] Input: translated order, personalized suggestions

[1582] Output: Order details and proposals presented to the user, and final order details

[1583] Step 7:

[1584] Sending and confirming orders to the store

[1585] The server sends the order details confirmed by the user to the store. The store's system receives the order details and begins processing the order. Once the order is processed, the store's system sends a confirmation message to the server.

[1586] Input: Final order details

[1587] Output: Order details sent to the store, confirmation message from the store

[1588] Step 8:

[1589] Order completion notification

[1590] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check information such as the redemption code and pickup time.

[1591] Input: Confirmation message from the store

[1592] Output: Order completion notification sent to the user

[1593] The above processing flow allows the user to place an order smoothly and the store to receive the order accurately.

[1594] (Application example 1)

[1595] 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."

[1596] In the modern restaurant and food delivery industry, ordering is often difficult when users are visiting a new restaurant or using a new platform. Meanwhile, there is a need to improve the user experience due to issues with translation between different languages ​​and a lack of appropriate suggestions based on user preferences. Furthermore, the lack of personalized suggestions based on past ordering history makes it difficult for users to efficiently order what suits their preferences.

[1597] 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.

[1598] In this invention, the server includes: means for being communicatively connected to a user terminal; means for accepting order details entered by a user; means for analyzing the order details using a generative AI model; means for converting the order details into an order format for each store based on the analysis results; means for presenting the converted order details to the user; means for sending the order details finally confirmed by the user to the store; means for receiving an order confirmation message from the store and notifying the user; means for translating the order details into a language selected by the user with a multilingual function; means for generating personalized suggestions based on the user's past ordering history and preferences; and means for transmitting the order details to affiliated restaurants. This allows users to smoothly order at stores or platforms they are using for the first time through appropriate suggestions based on translation issues between different languages ​​and user preferences, as well as personalized suggestions.

[1599] "User terminal" refers to a device used by a user to input order details, such as a smartphone, tablet, or PC.

[1600] "Server" refers to a computer system that is communicatively connected to a user terminal and performs processes such as receiving, analyzing, converting, translating, generating suggestions, sending to the restaurant, and notifying the user.

[1601] A "generative AI model" refers to a model that includes machine learning algorithms to interpret order details entered in natural language and convert them into an appropriate format.

[1602] "Multilingual support" refers to the ability to automatically translate orders based on the language selected by the user.

[1603] "Personalized suggestions" refers to the ability to generate additional options and suggestions based on a user's past ordering history and preferences.

[1604] "Food delivery service" refers to a service that allows users to order food and drinks from restaurants using their smartphones and have them delivered.

[1605] An "order confirmation message" refers to a message that confirms that the restaurant has accepted the order details confirmed by the user.

[1606] MODE FOR CARRYING OUT THE INVENTION

[1607] The present invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other. Below, the processing of a program for realizing this system and a specific example thereof will be described.

[1608] System Configuration

[1609] The system mainly consists of the following components:

[1610] 1. User Device

[1611] Smartphone (iOS or Android)

[1612] tablet

[1613] PC

[1614] 2. Server

[1615] Cloud hosting (e.g. AWS)

[1616] Database (e.g. MongoDB)

[1617] Machine learning models (e.g., generative AI models using GPT-3)

[1618] 3. Software

[1619] Frontend: React Native

[1620] Backend: Node.js, Express.js

[1621] Program processing explanation

[1622] 1. User Order Entry

[1623] A user launches a smartphone application, selects their preferred language, and then enters their order details in natural language into the application's input field. For example, they might enter, "I'd like to order a pizza and a cola."

[1624] 2. Server analyzes the order

[1625] The terminal sends the entered order details to the server. The server passes the order details to the generative AI model for analysis. The generative AI model analyzes the order details and understands the user's intentions.

[1626] 3. Order Conversion

[1627] Based on the analysis results, the server converts the order details into a format specific to the partner restaurant, such as "one pizza and one bottle of coke."

[1628] 4. Multilingual support

[1629] The server automatically translates the order based on the language selected by the user.

[1630] 5. Generate personalized suggestions

[1631] The server takes into account the user's past ordering history and preferences to make further recommendations, such as "Would you like some garlic bread as a side?"

[1632] 6. Confirm and confirm the order details after conversion

[1633] The server presents the converted order details and suggestions to the user. When the user confirms the details and finally presses the confirm button, the confirmed order details are sent to the server.

[1634] 7. Sending and confirming orders to restaurants

[1635] The server sends the confirmed order to the partner restaurant, which receives the order, and the restaurant's system receives it. The restaurant staff processes the order and sends a confirmation message to the server once it is complete.

[1636] 8. Order completion notification

[1637] The server receives a confirmation message from the restaurant and sends a completed order notification to the user's smartphone, along with information such as a redemption code and pickup time.

[1638] Specific examples

[1639] For example, a user launches the FoodEase app and selects English. Then, they enter, "I want to order a Hawaiian pizza and a coke." The input is sent to the server and analyzed by the generative AI model. The analysis results in "One Hawaiian pizza and one bottle of Coca-Cola." The model then suggests, "Would you like to add garlic bread to your order?" Once the user confirms and places the order, the server sends the final order details to the partner restaurant. The restaurant processes the order and sends a confirmation message to the server, which then sends the user a notification that the order is complete.

[1640] Prompt Sentence Examples

[1641] User order: "I want to order a cheeseburger and fries"

[1642] Response: "Your order was recognized as '1 cheeseburger, 1 fries'. Additional suggestion: 'Would you like to add a chocolate shake?'"

[1643] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1644] Step 1:

[1645] The user starts up the device (smartphone) and launches the FoodEase application. The user selects their preferred language before entering their order. The input at this stage is the language setting of the application. There is no output to the server.

[1646] Step 2:

[1647] A user enters their order in natural language into an application's input field, for example, "I want to order a Hawaiian pizza and a coke." This input is sent from the device to the server, where it is forwarded to the server and prepared for analysis.

[1648] Step 3:

[1649] The server sends the received natural language order content to the generative AI model for analysis. The input for analysis is "I want to order a Hawaiian pizza and a coke." The generative AI model understands the order content and outputs formatted order data (e.g., "One Hawaiian pizza and one bottle of Coca-Cola").

[1650] Step 4:

[1651] The server converts the order details into a format specific to the partner restaurant based on the analysis results of the generative AI model. The input is the analyzed order data, and the output is the converted order data (e.g., "One Hawaiian pizza and one bottle of Coca-Cola"). The server then prepares this to be presented to the user.

[1652] Step 5:

[1653] The server translates the order based on the language selected by the user. For example, if the parsing result is "1 Hawaiian pizza and 1 Coca-Cola," it translates it into the selected language. In this case, the input is the parsing result, and the output is the translated order (e.g., "Order 1 Hawaiian pizza and 1 coke").

[1654] Step 6:

[1655] The server considers the user's past order history and preferences and suggests additional options. The input is the user's order history data and current order details, and the output is a recommendation (e.g., "Would you like to add garlic bread to your order?").

[1656] Step 7:

[1657] The server sends the converted and translated order details and suggestions to the user terminal. The user checks the details and finally presses the confirm button. The input is the suggested order details and additional suggestions, and the output is the user's final confirmation action.

[1658] Step 8:

[1659] When the user's final confirmation action is sent to the server, the server sends the confirmed order details to the partner restaurant. The input is the final confirmed order details, and the output is the order data for the restaurant. The restaurant accepts the order and starts processing it.

[1660] Step 9:

[1661] Once the restaurant has processed the order, it sends a confirmation message to the server. The server receives the confirmation message and sends a notification of order completion to the user's smartphone. The input is the confirmation message from the restaurant, and the output is a notification of order completion to the user's device.

[1662] This series of processing steps allows users to smoothly input and confirm order details even when using a store or platform for the first time.

[1663] 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.

[1664] This invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other, allowing users to smoothly place orders at stores they visit for the first time. This system uses a generative AI model to analyze order details and convert them into an order format specific to each store. It also supports multiple languages, provides personalized suggestions, and is equipped with an emotion engine that recognizes user emotions.

[1665] System Overview

[1666] 1. User Device

[1667] User terminals include devices such as smartphones, tablets, and personal computers. Users use these terminals to input order details, confirm the order, and finalize it.

[1668] 2. Server

[1669] The server is communicatively connected to the user terminal and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, analyzing emotions, sending to the store, and notifying the user.

[1670] 3. Generative AI Models

[1671] The generative AI model includes machine learning algorithms used to analyze order content and generate recommendations, allowing it to interpret and convert order content entered by users in natural language into an appropriate format.

[1672] 4. Emotion Engine

[1673] The emotion engine analyzes the user's emotions from their voice and text input, and provides information and suggestions appropriate to the user based on the analysis results, enabling appropriate responses to be made according to the user's emotions.

[1674] Program processing explanation

[1675] 1. User Order Entry

[1676] The user launches the application on the device, selects the language they want to use, and then enters their order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the device to the server.

[1677] 2. Server analyzes the order

[1678] The server passes the received order details to the generative AI model for analysis. The generative AI model analyzes the input and understands the intent of the order.

[1679] 3. Order Conversion

[1680] The server then converts the order into a store-specific format based on the analysis results returned by the generative AI model, such as "one cheeseburger and one fries."

[1681] 4. Multilingual support

[1682] The server translates the converted order into the appropriate language based on the user's language selection (e.g., "Order 1 cheeseburger and 1 fries").

[1683] 5. User sentiment analysis

[1684] The emotion engine analyzes the text and voice data entered by the user to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[1685] 6. Generating personalized suggestions

[1686] The server suggests additional options (e.g., "Would you like to add a chocolate shake?") based on the user's past order history and the results of emotional analysis. Depending on the user's emotional state, it can respond by suggesting simple suggestions if the user is stressed, or new products if the user is relaxed.

[1687] 7. Confirm and confirm the converted order details

[1688] The server presents the converted order details and suggestions to the user, which are displayed on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button, after which the final order details are sent to the server.

[1689] 8. Sending and confirming orders to the store

[1690] The server sends the confirmed order details to the store, which receives the order details. The store staff processes the order and sends a confirmation message to the server after completion.

[1691] 9. Order completion notification

[1692] The server receives a confirmation message from the store and sends an order completion notification to the user's device, where the user can check the notification and find out the redemption code, pick-up time, etc.

[1693] Specific examples

[1694] Restaurant orders:

[1695] A user launches the OrderBridge app and selects English.

[1696] The user enters, "I want to order a cheeseburger and fries."

[1697] The terminal sends the order details to the server.

[1698] The server analyzes the order using a generative AI model and converts it into "one cheeseburger and one fries."

[1699] The server translates the converted content into English, resulting in "Order 1 cheeseburger and 1 fries."

[1700] The emotion engine analyzes the user's emotional state from their text and voice and determines that they are relaxed.

[1701] The server considers the user's past history and presents "Would you like to add a chocolate shake?" as a new suggestion suitable for relaxation.

[1702] The user checks and confirms the order.

[1703] The terminal sends the final order details to the server.

[1704] The server sends the final order details to the store.

[1705] Store staff processes the order and sends a confirmation message to the server once completed.

[1706] The server sends an order completion notification to the user's terminal.

[1707] The present invention is expected to facilitate smoother communication between users and stores, significantly reducing ordering problems, and improve user satisfaction by providing services tailored to the user's emotional state.

[1708] The processing flow will be explained below.

[1709] Step 1:

[1710] The user launches the OrderBridge app and the home screen appears.

[1711] Step 2:

[1712] Users select the language they want to use on their home screen.

[1713] Step 3:

[1714] The terminal sends the selected language information to the OrderBridge server.

[1715] Step 4:

[1716] The server records the received language information and loads the corresponding language resource.

[1717] Step 5:

[1718] The user opens an order entry screen on their device and enters what they want to order (e.g., "I want to order a cheeseburger and fries").

[1719] Step 6:

[1720] The terminal sends the entered order details in text format to the OrderBridge server.

[1721] Step 7:

[1722] The server receives the order details and passes them to the generative AI model.

[1723] Step 8:

[1724] A generative AI model analyzes the order and extracts the intent behind it (e.g., recognizing two orders: "cheeseburger" and "fries").

[1725] Step 9:

[1726] The server receives the analysis results from the generative AI model and converts them into a store-specific order format (e.g., "one cheeseburger and one fries").

[1727] Step 10:

[1728] The server translates the converted order into the user's language of choice (e.g., English) (e.g., "Order 1 cheeseburger and 1 fries").

[1729] Step 11:

[1730] The emotion engine analyzes the text and voice data entered by the user to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[1731] Step 12:

[1732] The server generates personalized suggestions (e.g., "Would you like to add a chocolate shake?") based on the user's past order history and the results of sentiment analysis. Depending on the user's emotional state, it will make simple suggestions if the user is stressed, or suggest new products if the user is relaxed.

[1733] Step 13:

[1734] The server sends the converted order details and proposals to the user terminal.

[1735] Step 14:

[1736] The terminal displays the order and additional suggestions to the user.

[1737] Step 15:

[1738] The user checks the order details, corrects them if necessary, and finally presses the confirm button.

[1739] Step 16:

[1740] The terminal sends the final order details to the OrderBridge server.

[1741] Step 17:

[1742] The server receives the final order details and sends them to the store's system.

[1743] Step 18:

[1744] The store's system receives the order details and begins processing the order.

[1745] Step 19:

[1746] Store staff prepare the order and, once complete, send a confirmation message to the OrderBridge server.

[1747] Step 20:

[1748] The server receives a confirmation message from the store.

[1749] Step 21:

[1750] The server sends an order completion notification to the user's terminal.

[1751] Step 22:

[1752] The terminal will display a completed order and a redemption code to the user, who will then receive a notification that their order is ready for pickup at the store.

[1753] Example 2

[1754] 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."

[1755] In modern society, when users place orders at different stores, they often encounter barriers due to different ordering formats and languages. This makes ordering time-consuming and prone to misunderstandings. Furthermore, personalized suggestions that take into account the user's emotions and past order history are not provided, making it difficult to improve the user experience. There is a need for a system that can solve these problems and enable smooth ordering between users and stores.

[1756] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1757] In this invention, the server includes: means for accepting order details entered by a user; means for analyzing the order details using a generative AI model; means for converting the order details into an order format for each store based on the analysis results; means for presenting the converted order details to the user; means for transmitting the order details finally confirmed by the user to the store; means for receiving an order confirmation message from the store and notifying the user; means including an emotion analysis engine for analyzing emotions from the user's input text and voice data; and means for generating personalized suggestions based on the emotion analysis results and the user's past order history. This allows users to smoothly place orders at different stores, improving the user experience.

[1758] A "user terminal" is an electronic device used by a user to enter an order and communicate with the server.

[1759] The "server" is a central processing unit that communicates with the user terminal, analyzes and converts the order details, and transmits them to the store.

[1760] An "order support system" is a system in which a user terminal and a server are communicatively connected to support the user's ordering process.

[1761] A "generative AI model" is a system that uses machine learning algorithms to analyze the order details entered by the user and understand the intent behind the order.

[1762] "Order details" are specific requirements for an order that are input by the user through the terminal and analyzed by the server.

[1763] An "emotion analysis engine" is a device or program that analyzes a user's emotional state from input text and voice data.

[1764] "Personalized suggestions" are suggestions that are individually generated based on the user's past order history and sentiment analysis results.

[1765] A "store format" is a standard format for order details used at a particular store.

[1766] The "multilingual function" is a function capable of translating the order contents into an appropriate language according to the language selected by the user.

[1767] An "order confirmation message" is a message that the store sends to the server after confirming the order details it has received.

[1768] This invention is an order support system in which a user terminal and a server are connected so that they can communicate with each other, allowing users to smoothly place orders at stores they visit for the first time. This system uses a generative AI model to analyze order details and convert them into an order format specific to each store. It also supports multiple languages, provides personalized suggestions, and includes an emotion analysis engine that recognizes user emotions.

[1769] To give an overview of the system, electronic devices such as smartphones, tablets, and PCs are used as user terminals. Users use these terminals to input order details, confirm, and finally confirm the order. Next, a server is connected to the user terminal so that it can communicate with it, and performs processes such as receiving the order details, analyzing, converting, translating, generating suggestions, analyzing emotions, sending them to the store, and notifying the user.

[1770] The generative AI model is the core technology of this system and includes machine learning algorithms used to analyze order details and generate recommendations. Specifically, it uses natural language processing (NLP) technology to interpret the order details entered by the user and convert them into an appropriate format. In addition, the sentiment analysis engine analyzes emotions from the user's voice and text input and provides information and recommendations appropriate to the user based on the analysis results.

[1771] Next, we will explain in detail how the system works. The user launches the application on their device and selects the language they wish to use. The user then enters the order details, which are sent from the device to the server. The server passes the received order details to the generative AI model for analysis. After analyzing the order details, the generative AI model converts them into a format specific to each store. For example, an order in English such as "I want to order a cheeseburger and fries" is converted to "one cheeseburger and one french fries."

[1772] For multilingual support, the server translates the converted order into the appropriate language based on the language selected by the user. For example, the converted Japanese order might be translated into English as "Order 1 cheeseburger and 1 fries."

[1773] For emotion analysis, the emotion engine analyzes the user's input text and voice data to understand the user's emotional state, for example, recognizing emotions from the user's vocabulary, tone, and typing speed.

[1774] Then, to generate personalized suggestions, the server suggests additional options based on the user's past order history and the results of sentiment analysis. For example, if the user is stressed, the server can suggest simple suggestions, and if the user is relaxed, it can suggest new products.

[1775] Finally, the converted order details are confirmed and confirmed. The server presents the converted order details and suggestions to the user and displays them on the terminal. The user confirms the details, makes any necessary corrections, and finally presses the confirm button, at which point the final order details are sent to the server. The server then sends the confirmed order details to the store, where the store staff processes the order and sends a confirmation message to the server once it is complete. Finally, the server receives the confirmation message from the store and sends an order completion notification to the user's terminal.

[1776] As a concrete example, let's look at the process of ordering at a restaurant. The user launches the OrderBridge app and selects English. Next, they enter "I want to order a cheeseburger and fries," and the device sends the order details to the server. The server analyzes the order using a generative AI model and converts the order to "1 cheeseburger and 1 fries." The server then translates the converted content into English, setting it to "Order 1 cheeseburger and 1 fries." The emotion engine analyzes the user's emotional state from their text and voice and determines that they are relaxed. The server takes into account the user's past history and asks, "Would you like to add a chocolate shake?" The user confirms and confirms the order details. The device sends the final order details to the server, which then sends the order details to the store. The store staff processes the order and, once complete, sends a confirmation message to the server. The server then sends a notification of order completion to the user's device.

[1777] This invention is expected to facilitate smoother communication between users and stores, significantly reducing troubles with orders, and also improve user satisfaction by providing services that correspond to the user's emotional state.

[1778] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1779] Specific explanation of processing steps

[1780] Step 1:

[1781] User input of order details

[1782] The user opens the OrderBridge app, selects the language they want to use (e.g., English), and then enters their order details: "I want to order a cheeseburger and fries." When the user presses the "Submit" button, the order details are sent to the terminal as input data.

[1783] Step 2:

[1784] Sending order details to the server via the terminal

[1785] The terminal sends the entered order details to the server. In this step, the user's order details are sent as input data from the terminal to the server via HTTPS. The server adds the received data to a queue for analysis.

[1786] Step 3:

[1787] Analysis of order details using a server-generated AI model

[1788] The server passes the received order details to the generative AI model for analysis. Specifically, the generative AI model analyzes the order details using natural language processing (NLP) technology and extracts the keywords "cheeseburger" and "fries." The input data is the user's order, and the output data is the extracted keywords and structured order information.

[1789] Step 4:

[1790] The server converts the order into store format.

[1791] The server converts the order details into the store's format based on the analysis results returned by the generative AI model. This conversion process uses pre-defined store format mapping rules. For example, "cheeseburger" and "fries" are converted into "1 cheeseburger, 1 french fries." The input data is the analysis results, and the output data is the converted order details.

[1792] Step 5:

[1793] Multilingual support for order details via the server

[1794] The server translates the converted order into the language selected by the user (e.g., English). In this step, the order is translated using a translation API (e.g., Google Translate API). The input data is the converted order, and the output data is the translated order.

[1795] Step 6:

[1796] User emotion analysis by emotion engine on the server

[1797] The server uses an emotion engine to analyze the user's input text and voice data. The emotion engine determines the user's emotional state using, for example, IBM Watson's emotion analysis API. The input data is the user's text and voice data, and the output data is the user's emotional state.

[1798] Step 7:

[1799] Server-generated personalized suggestions

[1800] The server generates personalized suggestions based on the user's past order history and the results of emotion analysis. The suggestions suggest new products to relaxed users and simple suggestions to stressed users. The input data are the user's order history and emotional state, and the output data are personalized suggestions.

[1801] Step 8:

[1802] User confirms and confirms order details

[1803] The server presents the converted order details and proposals to the user and displays them on the terminal. The user checks the displayed details, makes any necessary corrections, and presses the "Confirm" button. The input data are the order details and proposals presented to the user, and the output data are the final order details confirmed by the user.

[1804] Step 9:

[1805] Sending the final order details to the server by the terminal

[1806] When the user confirms the order, the terminal sends the final order details to the server. Once this sending operation is complete, the order processing proceeds to the next step. The input data is the final order details confirmed by the user, and the output data is the final order details sent to the server.

[1807] Step 10:

[1808] The server sends the order to the store

[1809] The server sends the final order details to the store's system using a standard protocol (e.g., REST API). The input data is the final order details, and the output data is the order details sent to the store's system.

[1810] Step 11:

[1811] Order processing and confirmation by the store

[1812] The store staff prepares the product based on the received order details, and when the order is completed, the store's system sends a completion confirmation message to the server. The input data is the order details received by the store, and the output data is the completion confirmation message sent to the server.

[1813] Step 12:

[1814] The server sends a notification of order completion to the user's device.

[1815] The server receives a completion confirmation message from the store and sends an order completion notification to the user's terminal. This notification includes a redemption code and pickup time. The input data is the completion confirmation message from the store, and the output data is the order completion notification sent to the user's terminal.

[1816] In this way, this system realizes smooth communication between users and stores, significantly reducing ordering problems. It also improves user satisfaction by making suggestions based on the user's emotional state.

[1817] (Application example 2)

[1818] 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."

[1819] Conventional ordering support systems make it difficult for users to order smoothly at stores or services they visit for the first time. Furthermore, the lack of multilingual support and personalized suggestions based on the user's emotions often compromises the user experience. This leads to issues such as reduced ordering accuracy and user satisfaction.

[1820] The identification process 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 accepting order details entered by a user, means for analyzing the order details using a generative AI model, means for converting the order details into an order format for each request destination based on the analysis results, means for presenting the converted order details to the user, means for sending the order details finally confirmed by the user to the request destination, means for receiving a confirmation message from the request destination and notifying the user, means for analyzing the user's emotional state and generating personalized proposals based thereon, means for translating the order details into a language selected by the user with a multilingual function, and means for generating personalized proposals based on the user's past order history and preferences. This enables the user to smoothly place an order even when visiting a store or service for the first time, realizes a detailed response that reflects the user's emotions, and improves the accuracy of orders and user satisfaction.

[1821] A "user terminal" is a device through which a user inputs order details and communicates with the server.

[1822] "Server" refers to a central processing unit that receives and analyzes the order details sent from the user terminal and performs processes such as conversion, translation, and notification.

[1823] The "order support system" is a system that communicates between the user's terminal and a server, analyzes, converts, and translates the order details entered by the user, and makes appropriate suggestions.

[1824] A "generative AI model" is an artificial intelligence model that includes machine learning algorithms to analyze the order details entered by the user and understand the intent behind the order.

[1825] "Emotional State" means the user's psychological and emotional state as analyzed from the user's voice and text input.

[1826] "Emotion analysis" is the process of recognizing a user's emotional state from their vocabulary, tone, typing speed, etc.

[1827] "Personalized suggestions" is a feature that makes optimal suggestions to individual users based on their past order history and emotional state.

[1828] "Multilingual support" is a function that allows order details to be translated into various languages ​​for users who speak different languages.

[1829] The "request destination" refers to the store or service provider to which the user wishes to place an order.

[1830] "Order format" refers to the specific order entry format required by each requestor.

[1831] MODE FOR CARRYING OUT THE INVENTION

[1832] The present invention is an ordering support system in which a user terminal and a server are connected so that they can communicate with each other, and aims to enable users to smoothly place orders even in new locations. This system is particularly equipped with multilingual support and a personalized suggestion function using sentiment analysis, which significantly improves the user experience.

[1833] System Configuration

[1834] The system includes the following main components:

[1835] 1. User Device:

[1836] This is a device that users use to input order details. It is often a smartphone, tablet, or PC. Users use this device to input order details and send them to the server.

[1837] 2. Server:

[1838] The server receives the order content sent from the user terminal and processes it through analysis, conversion, suggestions, translation, etc. The server has the computing resources to run the generative AI model and emotion engine.

[1839] 3. Generative AI Model:

[1840] The generative AI model uses natural language processing (NLP) technology to analyze the order details entered by the user and understand the intent behind the order. The model also generates optimal suggestions based on the user's order history and sentiment analysis results.

[1841] 4. Emotion Engine:

[1842] The emotion engine analyzes the user's text and voice data to recognize their emotional state, determining whether they are relaxed or stressed.

[1843] Operation overview

[1844] The system operates as follows:

[1845] 1. Enter and submit your order:

[1846] The user starts the terminal application and enters the order details, for example, "I want to order a cheeseburger and fries." This input is sent to the server as a prompt.

[1847] 2. Order analysis and conversion:

[1848] The server uses a generative AI model to analyze the order and convert it into a custom order format, such as "one cheeseburger and one fries."

[1849] 3. Multilingual support:

[1850] The server translates the converted order into the user's language of choice, for example, "Order 1 cheeseburger and 1 fries."

[1851] 4. Sentiment analysis and suggestion generation:

[1852] The emotion engine analyzes the user's emotional state from their text or voice input, providing new suggestions if they are relaxed, or simple suggestions if they are stressed.

[1853] 5. Final confirmation and order submission:

[1854] The user sends the final order details to the server, which then sends them to the requested party. The order is completed when a confirmation message is received from the requested party and the user is notified.

[1855] Specific examples

[1856] When a user places an order using a smartphone, they enter the following prompt:

[1857] "I want to order a cheeseburger and fries"

[1858] The server analyzes this order, converts it into the appropriate format, translates it if necessary, analyzes the user's emotional state, and generates new suggestions based on that (e.g., "Would you like to add a chocolate shake?"). The user finally confirms and confirms the order, which is then sent to the destination.

[1859] As described above, the present invention enables users to smoothly place orders in different locations and language environments, and improves the ordering experience by providing personalized suggestions based on emotions.

[1860] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1861] Step 1:

[1862] The user starts the application on the terminal and selects the language to use. Next, the user inputs the order details (e.g., "I want to order a cheeseburger and fries"), which are then sent from the terminal to the server as a prompt. Based on the input (prompt), the server receives the order details.

[1863] Step 2:

[1864] The server passes the order details to the generative AI model for analysis. The generative AI model analyzes the input prompt (order details) and understands the intent of the order. Data processing involves tokenizing the order details using natural language processing technology and evaluating the context. Structured order data is generated as the output.

[1865] Step 3:

[1866] Based on the analysis results, the server converts the order details into an order format specific to the customer. Here, the output of the generative AI model is used to convert the data into a specific order format. For example, "I want to order a cheeseburger and fries" is converted to "1 cheeseburger and 1 french fries."

[1867] Step 4:

[1868] The server presents the converted order details to the user. At this time, the order details are translated according to the language selected by the user. For example, if English is selected, the order details will be translated as "Order 1 cheeseburger and 1 fries." A multilingual API is used for the translation.

[1869] Step 5:

[1870] The server uses an emotion engine to analyze the user's emotional state from the text and voice input. Data processing involves extracting emotional features from the input text and voice data and evaluating them with an emotion classification model. The output is the user's emotional state (relaxed, stressed, etc.).

[1871] Step 6:

[1872] The server generates personalized suggestions based on the user's past ordering history and emotional state, such as "Would you like to add a chocolate shake?". A recommendation system is used to make new suggestions using the emotional state and past ordering data.

[1873] Step 7:

[1874] The server presents the order details and proposals to the user for final confirmation and displays them on the terminal. The user checks the details, makes any necessary corrections, and finally presses the confirm button. Based on the input (user's final confirmation), the confirmed order details are sent to the server.

[1875] Step 8:

[1876] The server sends the confirmed order details to the requester. The requester's system receives and processes the order details. Once processing is complete, the requester's system sends a confirmation message to the server.

[1877] Step 9:

[1878] The server receives a confirmation message from the request destination and sends an order completion notification to the user's terminal. The user can check this notification and know that the order has been completed.

[1879] 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.

[1880] 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.

[1881] 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 robot 414.

[1882] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1883] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1884] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1885] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1886] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1887] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1888] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1889] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1890] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1891] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1892] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1893] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1894] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1895] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1896] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1897] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1898] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1899] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1900] The following is further disclosed regarding the above embodiment.

[1901] (Claim 1)

[1902] An order support system in which a user terminal and a server are communicably connected,

[1903] A means for accepting order details input by a user;

[1904] A means for analyzing the order content using a generative AI model;

[1905] A means for converting the order content into an order format for each store based on the analysis result;

[1906] means for presenting the converted order details to the user;

[1907] A means for transmitting the order details finally confirmed by the user to the store;

[1908] A means of receiving order confirmation messages from stores and notifying users.

[1909] A system including:

[1910] (Claim 2)

[1911] 10. The system of claim 1,

[1912] It has multilingual functionality,

[1913] The system further includes means for translating the order according to a language selected by the user.

[1914] (Claim 3)

[1915] 10. The system of claim 1,

[1916] The system further includes means for generating personalized suggestions based on the user's past ordering history and preferences.

[1917] "Example 1"

[1918] (Claim 1)

[1919] A means for accepting order details input by a user;

[1920] A means for analyzing the order content using a generative AI model;

[1921] A means for converting the order contents into a format for each information system based on the analysis results;

[1922] means for presenting the converted order details to a user;

[1923] means for transmitting the order details finally confirmed by the user to the information processing device;

[1924] means for receiving an order confirmation message from the information processing device and notifying the user;

[1925] means for generating personalized offers based on the user's past ordering history and preferences;

[1926] A means to properly translate your order based on your selected language;

[1927] A system including:

[1928] (Claim 2)

[1929] 10. The system according to claim 1, characterized in that it has a multilingual function and translates the order contents according to the language selected by the user.

[1930] (Claim 3)

[1931] 10. The system of claim 1, wherein the system generates personalized offers based on a user's ordering history and preferences.

[1932] "Application Example 1"

[1933] (Claim 1)

[1934] An order support system in which a user terminal and a server are communicably connected,

[1935] A means for accepting order details input by a user;

[1936] A means for analyzing the order content using a generative AI model;

[1937] A means for converting the order content into an order format for each store based on the analysis result;

[1938] means for presenting the converted order details to the user;

[1939] A means for transmitting the order details finally confirmed by the user to the store;

[1940] a means for receiving an order confirmation message from the store and notifying the user;

[1941] a means for translating the order contents according to the language selected by the user, with a multilingual function;

[1942] means for generating personalized recommendations based on the user's past ordering history and preferences;

[1943] A means for transmitting order details to affiliated dining establishments;

[1944] A system including:

[1945] (Claim 2)

[1946] 2. The system according to claim 1, characterized in that it is applied to a mobile terminal including a smartphone.

[1947] (Claim 3)

[1948] 2. The system according to claim 1, characterized in that it is applied to a food delivery service.

[1949] "Example 2: Combining Emotion Engines"

[1950] (Claim 1)

[1951] An order support system in which a user terminal and a server are communicably connected,

[1952] A means for accepting order details input by a user;

[1953] A means for analyzing the order content using a generative AI model;

[1954] A means for converting the order content into an order format for each store based on the analysis result;

[1955] means for presenting the converted order details to the user;

[1956] A means for transmitting the order details finally confirmed by the user to the store;

[1957] a means for receiving an order confirmation message from the store and notifying the user;

[1958] means including a sentiment analysis engine for analyzing sentiment from user input text and voice data;

[1959] means for generating personalized recommendations based on the user's sentiment analysis and past order history;

[1960] A system including:

[1961] (Claim 2)

[1962] It has multilingual functionality,

[1963] 10. The system of claim 1, further comprising means for translating the order according to a language selected by the user.

[1964] (Claim 3)

[1965] 10. The system of claim 1, further comprising means for generating personalized suggestions based on the user's past ordering history and preferences.

[1966] "Application example 2 when combining emotion engines"

[1967] (Claim 1)

[1968] An order support system in which a user terminal and a server are communicably connected,

[1969] A means for accepting order details input by a user;

[1970] A means for analyzing the order content using a generative AI model;

[1971] A means for converting the order content into an order format for each request destination based on the analysis result;

[1972] means for presenting the converted order details to the user;

[1973] A means for transmitting the order details finally confirmed by the user to the requested destination;

[1974] a means for receiving a confirmation message from the request destination and notifying the user;

[1975] means for analyzing a user's emotional state and generating personalized suggestions based thereon;

[1976] A system including:

[1977] (Claim 2)

[1978] 10. The system of claim 1, further comprising means for translating the order contents according to a language selected by the user, the system having a multilingual function.

[1979] (Claim 3)

[1980] 10. The system of claim 1, further comprising means for generating personalized suggestions based on the user's past ordering history and preferences. [Explanation of symbols]

[1981] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. An order support system in which a user terminal and a server are communicably connected, A means for accepting order details input by a user; A means for analyzing the order content using a generative AI model; A means for converting the order content into an order format for each store based on the analysis result; means for presenting the converted order details to the user; A means for transmitting the order details finally confirmed by the user to the store; A means of receiving order confirmation messages from stores and notifying users. A system including:

2. 10. The system of claim 1, It has multilingual functionality, The system further includes means for translating the order according to a language selected by the user.

3. 10. The system of claim 1, The system further includes means for generating personalized suggestions based on the user's past ordering history and preferences.

Images