system

Abstract

Provide a system. A means for collecting sales data; A means for using a generating AI to predict surplus food based on the sales data; means for generating a message notifying information about the surplus food; means for transmitting said message to a user terminal; a means for awarding points when a user purchases the surplus food using an electronic payment means; A system including:

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] In modern society, food waste and excess inventory in stores have become serious problems. These problems increase the burden on the environment and also lead to increased costs for stores. In addition, efficient inventory management is difficult because stores have limited ways to quickly dispose of excess inventory. To solve these issues, a system is needed that can predict surplus food and quickly notify consumers. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting sales data, a means for using a generation AI to predict surplus food based on the sales data, a means for generating a message notifying the user of information about the surplus food, a means for sending the message to a user's terminal, and a means for awarding points when the user purchases the surplus food using an electronic payment method. This allows stores to efficiently predict surplus inventory and quickly provide consumers with special sale information. Furthermore, consumers can obtain economic benefits by purchasing special sale items. As a result, it is expected that food waste will be reduced and store inventory management efficiency will be improved.

[0006] "Sales data" refers to information regarding the quantity and price of merchandise sold at a store.

[0007] "Generative AI" is a system that uses artificial intelligence technology to analyze past data and make future predictions.

[0008] "Surplus food" is food that remains unsold as a result of excess supply relative to demand.

[0009] "Notification Message" means information, including text and graphics, intended to communicate information to users about a predicted food surplus.

[0010] "User device" refers to an electronic device that can be operated by a user, such as a smartphone, tablet, or PC.

[0011] "Electronic payment instruments" refer to means of making payments electronically without using cash, such as credit cards, debit cards, and mobile payment apps.

[0012] A "means of awarding points" is a system that provides points as an incentive when a user meets certain conditions. [Brief explanation of the drawings]

[0013] [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 illustrating 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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention provides a generation AI that collects sales data and predicts surplus food based on that data, a system that generates a message notifying the user of the prediction result and sends it to the user's terminal, and a system that awards points when the user makes a purchase using an electronic payment method.

[0035] Data collection and prediction processing

[0036] Server: Periodically collects data from the store's sales database, including the type, quantity, price, and date and time of the sale of the product.

[0037] Server: Collected sales data is stored in an intermediate database, and based on that data, a generation AI is used to predict surplus food. This generation AI analyzes past sales and inventory data to identify foods that are likely to become surplus in the future.

[0038] As a specific example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0039] Generate and send notification messages

[0040] Server: Based on the prediction results of the generation AI, a list of special sale items is created and a LINE notification message is generated. This message includes the names of the special sale items, their prices, and details on how to purchase them.

[0041] Server: Uses the LINE OA API to send notification messages to the user's device via the LINE bot.

[0042] As a specific example, a notification is generated containing the content "Milk will be sold at a special price due to surplus milk."

[0043] User purchases and points awarded

[0044] User: Receives the notification message and purchases the specified special offer item at the store, using an electronic payment method such as PayPay.

[0045] Terminal: When a purchase is completed, additional points are automatically credited to the user's account. This points crediting process is integrated into the electronic payment system, so users can receive points without any additional procedures.

[0046] For example, when a user purchases milk on sale, they pay with PayPay, and as a result, they automatically receive additional points in addition to the usual points.

[0047] Specific operation of the system

[0048] The server periodically acquires store sales data using a data collection means and stores the information in an intermediate database.

[0049] The generative AI uses the collected data to predict future food surpluses.

[0050] Based on the prediction results, a list of special offers is created and a notification message is generated.

[0051] The server uses the LINE OA API to send a notification message to the user's device.

[0052] Users will receive a notification, purchase special items in the store, and receive additional Purchase Points.

[0053] This will reduce food waste and enable efficient inventory management. The system also encourages consumption by providing incentives to users.

[0054] The processing flow will be explained below.

[0055] Step 1: Data collection

[0056] Server: Periodically collects sales data from the store's sales database. The server queries the database to retrieve sales data for the past week. This sales data includes the product type, quantity, price, and date and time of the sale.

[0057] Step 2: Saving to an intermediate database

[0058] Server: Stores collected sales data in an intermediate database, allowing for the organization and retention of data required for subsequent processing.

[0059] Step 3: Generative AI predictions

[0060] Server: Obtains sales data from the intermediate database and inputs it into the generation AI. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. A list of surplus foods is created as a prediction result and saved in the prediction result database.

[0061] Step 4: Create a Special Offer List

[0062] Server: Retrieves surplus food information from the prediction result database and creates a special sale product list based on that information. The special sale product list includes details such as product name, discount price, and sale period.

[0063] Step 5: Generate a notification message

[0064] Server: Generates notification messages to send to users based on the special offer list. These messages include information about the special offer, how to purchase it, and where it is sold.

[0065] Step 6: Sending notifications

[0066] Server: Using the LINE OA API, the generated notification message is sent to the user's device via a LINE bot. For example, it sends a message such as "Milk is in surplus, so it will be sold at a special price."

[0067] Step 7: Receive and confirm notifications

[0068] Device: Users will receive a notification message on their device to check the special offer information. A notification alert will be displayed on their device to ensure users do not miss the notification.

[0069] Step 8: Shop the specials

[0070] User: After checking the notification message, the user goes to the store and purchases the specified special offer. At this point, the user knows what the special offer is and how to purchase it.

[0071] Step 9: Making an electronic payment

[0072] User: When purchasing special offer items, users pay using electronic payment methods such as PayPay. Users can complete the payment by scanning a QR code (registered trademark) at the store or using the app.

[0073] Step 10: Points awarded

[0074] Server: After the user completes the electronic payment, the server receives a notification from the payment system and automatically credits the additional points to the user's account, allowing the user to receive incentives through points in addition to purchasing special offers.

[0075] In this way, the system efficiently executes a series of processes, from collecting sales data to forecasting, notification, and purchasing and awarding points, thereby reducing food waste and promoting consumption.

[0076] Example 1

[0077] 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."

[0078] Currently, the generation of surplus food has become a serious problem in the food industry. This has led to increased food waste, raising concerns about economic losses and environmental impacts. Furthermore, there is a lack of efficient provision of special sale product information to consumers, making it difficult to promote consumption. Conventional methods have made it difficult to offer surplus food at special prices at the appropriate time and notify consumers.

[0079] 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.

[0080] In this invention, the server includes a means for collecting sales data, a means for using a generation AI to predict surplus food based on the sales data, a means for generating a message notifying the user of information about the surplus food, a means for sending the message to a user's terminal via the Internet, a means for awarding points to a user who receives the notification message when purchasing the surplus food, and a means for the user to purchase the surplus food using an electronic payment method. This makes it possible to efficiently identify surplus food and provide timely discount information to consumers. It also promotes consumption and reduces food waste.

[0081] "Sales data" refers to information about the sales activities of a store, such as the type, quantity, price, and date and time of sales of products sold.

[0082] "Surplus food" is food that may remain unsold to consumers and is expected to be wasted.

[0083] "Generative AI" is a type of artificial intelligence used to predict future situations based on past data, and in this invention is specifically used to predict food surpluses.

[0084] "Notification Message" means a text message generated to inform a consumer about a special offer.

[0085] "User terminal" refers to a device carried by a consumer for receiving notification messages, such as a smartphone, tablet, or computer.

[0086] "Means for transmitting through the Internet" refers to a method for transmitting and receiving information through a network, and is particularly used to send notification messages to users' terminals.

[0087] "Electronic payment instruments" are methods for making payments digitally without using cash, including credit cards, electronic money, and mobile payment apps.

[0088] "Points" refers to bonus points that are given to consumers when they purchase specially priced items, and can be used for future purchases.

[0089] A "special sale product list" is a list generated based on predicted surplus food, which contains detailed information such as products to be sold at special prices, their prices, and the sales period.

[0090] This system uses a generative AI model to collect sales data and predict food surpluses based on that data. It also generates notification messages based on the prediction results and sends them to users' devices. Furthermore, it provides a mechanism for rewarding users with points when they purchase specially priced items using electronic payment methods.

[0091] Data collection and intermediate database storage

[0092] The server periodically collects data from the store's sales database. This data includes information such as the type, quantity, price, and date and time of the sale of the product sold. For example, a periodic batch process is performed every day at midnight to collect hourly sales data. This data is then saved in an intermediate database. When saving, the data is checked for consistency to ensure that no invalid data is mixed in.

[0093] Food surplus forecast

[0094] The server formats the sales data stored in the intermediate database into a format that is easy for the generative AI model to handle. For example, it formats the sales data for the past week as time series data. It then inputs the formatted data into the generative AI model. It sends a prompt request saying, "Based on the sales data for the past week, please predict which foods are most likely to become surplus next." The prediction results from the generative AI model include a list of foods that are likely to become surplus and the probability of this happening.

[0095] Example prompt: "Based on sales data from the past week, please predict which foods are likely to be in surplus in the future. The sales data is as follows: (data content)."

[0096] Generate and send notification messages

[0097] The server creates a list of special sale items based on the surplus food prediction results. This list includes the product name, special price, and sale period. For example, a list containing information such as "Milk - Special price 100 yen - Sale period: This weekend" is created. Next, a LINE notification message is generated based on this list. The LINE OA API is used to send the notification message to the user's device. For example, a message such as "Milk will be in surplus! On sale this weekend for a special price of 100 yen" is generated and sent by the LINE bot.

[0098] User purchases and points awarded

[0099] The user receives the notification message in the LINE app. For example, "Check the notification about the milk special sale on LINE." After that, the user visits the store and purchases the special sale item. At this time, the user uses an electronic payment method. For example, "Purchase milk with PayPay." After the purchase is completed on the device, points are automatically added to the user's account via the electronic payment system. For example, "Additional points will be automatically added after payment is completed with PayPay."

[0100] This system can carry out an integrated process from collecting sales data to predicting surplus food, notifying consumers of special offers, and encouraging them to purchase and receive points. This makes it possible to efficiently identify surplus food and provide timely special offer information to consumers. It is also a system that can encourage consumption and reduce food waste.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] Step 1:

[0103] The server periodically collects data from the store's sales database. The input data includes information on the type, quantity, price, and date and time of the sale of the product sold. Specifically, a batch process is executed at midnight every day to collect hourly sales data. This batch process uses SQL queries to extract specified data from the sales database and saves the data in an intermediate database.

[0104] Step 2:

[0105] The server saves the collected sales data in an intermediate database. The input data is the sales data collected in step 1. Specifically, it performs an insert operation into the database and performs a data consistency check. For example, it checks whether the product code and quantity are valid. This saved data is used in subsequent analysis processing.

[0106] Step 3:

[0107] The server formats the sales data stored in the intermediate database. The input data is the sales data stored in the intermediate database, and the output data is data converted into a format that is easy for the generative AI model to handle. Specifically, the server formats the sales data for the past week as time-series data to create a dataset for input to the generative AI model. This includes sales volume by date and time and aggregated data by product category.

[0108] Step 4:

[0109] The server inputs the formatted data into the generative AI model. The input data is the dataset created in step 3. The request is sent as a prompt: "Based on sales data from the past week, please predict the foods that are most likely to become surplus next." The output data is the prediction result from the generative AI model, which includes a list of surplus foods and their probabilities. In this prediction process, the generative AI model analyzes past sales trends and inventory data and returns specific prediction results.

[0110] Step 5:

[0111] The server creates a list of special sale items based on the prediction results of the generative AI model. The input data is the prediction results from step 4, and a list of items to be sold at a special price is created. This list includes the product name, special price, and sale period. For example, a list such as "Milk - Special price 100 yen - Sale period: this weekend" is generated. This list is used to generate subsequent notification messages.

[0112] Step 6:

[0113] The server generates a message for LINE notification based on the special sale item list. The input data is the special sale item list created in step 5, and the output data is the notification message. For example, it generates a message with the content "We have a surplus of milk! It will be on sale this weekend for 100 yen." This message includes the name of the special sale item, its price, and details on how to purchase it.

[0114] Step 7:

[0115] The server uses the LINE OA API to send a notification message to the user's device. The input data is the notification message generated in step 6, and the output data is the message sent to the user's device. The notification message is sent to User A's device via the LINE bot, and a confirmation message is received. This step allows the user to receive information about special offers in real time.

[0116] Step 8:

[0117] The user receives the sent notification message in the LINE app. The input data is the notification message sent in step 7, and the output data is the message displayed in the user's LINE app. For example, "Check LINE for notifications about milk special sale."

[0118] Step 9:

[0119] The user visits the store and purchases the special sale item that was notified to them. At this time, they use an electronic payment method. The input data is the information in the notification message, and the output data is the special sale item that was purchased. For example, "Purchase milk with PayPay."

[0120] Step 10:

[0121] After the purchase is completed, the terminal automatically adds points to the user's account via the electronic payment system. The input data is the purchase completion information, and the output data is the points added to the user's account. For example, "After completing payment with PayPay, additional points will be automatically added."

[0122] (Application example 1)

[0123] 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."

[0124] The present invention relates to a system that uses sales data to predict surplus food, notifies customers of special offers, and encourages them to purchase in order to improve the efficiency of inventory management and consumer marketing methods in food delivery services. Conventional methods have made it difficult to predict surplus food, leading to insufficient inventory management and food waste reduction. Furthermore, they have not been effective in notifying customers of special offers and providing incentives to purchase.

[0125] 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.

[0126] In this invention, the server includes a means for collecting sales data, a means for using a generation AI to predict surplus food, a means for notifying users of special offers, a means for sending messages to users' devices, and a means for selling special offers. The server first predicts surplus food based on sales data and notifies users of the information as special offers. This makes it possible to improve the efficiency of inventory management and reduce food waste in food delivery services. Furthermore, by notifying users of special offers and providing incentives for purchases, the server can encourage consumers to purchase and improve the efficiency of the entire service.

[0127] "Sales data" refers to information related to the sale of products, and specifically includes information on the type, quantity, price, and date and time of the sale of the product.

[0128] "Generative AI" is an artificial intelligence technique that uses machine learning algorithms to analyze past data and predict specific future outcomes.

[0129] "Surplus food" refers to food that has been produced or stocked in excess of projected sales, is nearing its expiration date, or is not expected to be sold.

[0130] "Message" means an electronic communication that notifies you of special offers or other important information and may contain text, images, or links.

[0131] A "user device" is an electronic device, such as a smartphone, tablet, or computer, that is capable of connecting to the Internet and receiving communications.

[0132] An "electronic payment instrument" is a method by which a user can pay for goods or services digitally, and specifically uses electronic money, credit cards, debit cards, etc.

[0133] A "means of awarding points" is a system in which points are added to a user's account as a reward when the user meets certain conditions, and the points can be used for discounts or special offers at a later date.

[0134] "Special price items" are items offered at a lower price than the regular selling price, and are set up to promote the sale of surplus food and other items.

[0135] "Communications Network" means the Internet or other digital communications infrastructure used to transmit and receive data and to move information between users and systems.

[0136] This invention relates to a system for improving the efficiency of inventory management and supporting marketing activities in food delivery services. The system program and its processing will be described in detail below.

[0137] System Program

[0138] The system consists of a server, a user's device, and a generative AI model. The server collects and analyzes sales data and predicts surplus food. The user's device receives notifications and is used to purchase special offers. The generative AI model predicts surplus food based on past sales and inventory data.

[0139] Data collection and prediction processing

[0140] The server periodically collects store sales data from the database. This collected data includes the type, quantity, price, and sales date and time of the products sold. The collected sales data is stored in an intermediate database, and a generative AI is used to predict surplus food based on that data. The generative AI model uses a machine learning algorithm to analyze PastData and StockData to identify foods that are likely to become surplus next.

[0141] Generate and send notification messages

[0142] The server creates a list of special sale items based on the predictions made by the AI ​​and generates a notification message containing the names of the special sale items, their prices, and details on how to purchase them. The server then sends the notification message to the user's device via a communications network.

[0143] User purchases and points awarded

[0144] The user receives a notification message and uses their device to check the displayed special offers. They then select the special offer and complete the purchase using an electronic payment method. Once the purchase is complete, additional points are automatically credited to the user's account. This process is integrated into electronic payment systems such as electronic money and credit cards, so users can receive points without any special procedures.

[0145] Specific examples

[0146] For example, if the server collects a week's worth of sales data and, after analyzing it, predicts that milk is likely to become a surplus food item, a list of special sale items is created. A notification message stating, "Milk will be sold at a special price due to surplus milk," is sent to the user's device. The user receives the notification, uses their smartphone to purchase the special sale items, and pays with an electronic payment method. As a result, additional points are automatically awarded in addition to the usual points.

[0147] Prompt Sentence Examples

[0148] As a concrete example, the following prompt sentence is input to the generative AI model:

[0149] "Based on sandwich sales data from the past week, please predict which foods are likely to be in surplus the next day. Based on your prediction, please briefly explain why you think there is a high probability that sandwiches will be in surplus tomorrow."

[0150] This allows the server to efficiently execute a series of processes, from data collection to generating and sending notification messages, and from users making purchases to awarding points. By having the entire system work together, it becomes possible to streamline inventory management for food delivery services and significantly reduce food waste.

[0151] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0152] Step 1:

[0153] The server collects store sales data from the database. Specifically, it obtains information such as the type of product sold, quantity, price, and sales date and time, and stores this in an intermediate database. The inputs are database connection information and queries, and the output is the obtained sales data. This data collection operation accumulates the necessary analysis data.

[0154] Step 2:

[0155] The server inputs the collected sales data into the generative AI model, which then analyzes past sales and inventory data to predict surplus food. The inputs are sales and inventory data, and the output is a predicted surplus food list. The generative AI model uses machine learning algorithms to process and calculate the data and generate a specific surplus food list.

[0156] Step 3:

[0157] The server generates a list of special sale items based on the prediction results of the generative AI model. It lists the predicted surplus food items as special sale items and creates a notification message containing detailed information about them. The input is the predicted surplus food list, and the output is a notification message about the special sale items. Specifically, the message content is constructed using a notification message generation algorithm.

[0158] Step 4:

[0159] The server sends a special offer notification message to the user's device. Since the message is sent via a communication network, an internet connection is required. The input is the special offer notification message and the user's device information, and the output is the sent notification message. Specifically, the message is sent using a communication API.

[0160] Step 5:

[0161] The user checks the received notification message on their device and selects a special offer. The input is the notification message, and the output is confirmation of the user's intention to purchase. Specifically, this involves the user operating their device to select a special offer and pressing the purchase button.

[0162] Step 6:

[0163] The user uses a terminal to complete the purchase of a special offer item using an electronic payment method. The inputs are special offer item information and payment information, and the output is purchase completion information and point award information. In specific operations, payment is made using an electronic payment system (e.g., electronic money, credit card), and points are automatically awarded at that time.

[0164] Step 7:

[0165] The server receives the payment completion information and awards additional points to the user. The input is the user's payment completion information and the point awarding rules, and the output is the updated user point information. Specifically, it updates the point management system and awards additional points to the user's account.

[0166] This series of processing steps is expected to improve the efficiency of inventory management for food delivery services, reduce food waste, and increase purchasing incentives for consumers.

[0167] 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.

[0168] The present invention provides a system that predicts surplus food based on sales data and notifies users of this information, and combines it with an emotion engine that recognizes the user's emotional state and optimizes the content and timing of notifications based on that.

[0169] Data collection and prediction processing

[0170] Server: Periodically collects data from the store's sales database. The server queries the database to retrieve sales data for the past week, including product type, quantity, price, and sales date and time.

[0171] Server: Collected sales data is stored in an intermediate database, and based on that data, a generation AI is used to predict surplus food. The generation AI analyzes past sales and inventory data to identify foods that are likely to become surplus in the future.

[0172] As a specific example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0173] Emotion recognition by emotion engine

[0174] Device: When a user receives a notification message, the emotion engine on the user's device recognizes the user's emotional state through camera and voice input. During this process, the device analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger).

[0175] Device: The recognized emotion data is sent to the server in real time, and the content and urgency of the notification message are adjusted. Based on this information, the server generates a message appropriate to the user's emotional state.

[0176] As a specific example, if the emotion engine determines that the user is tired, it will adjust the content of the notification message to something like, "Help us if you're tired! Refresh yourself with milk at a special price."

[0177] Generate and send notification messages

[0178] Server: Based on the prediction results of the generative AI and the emotional data from the emotion engine, the server creates a list of special sale items and generates appropriate notification messages. These messages include information about the special sale items, recommended phrases based on the user's emotional state, how to purchase, and where to purchase.

[0179] Server: Using the LINE OA API, the generated notification message is sent to the user's device via the LINE bot, adjusting the timing to ensure that the notification is sent at the appropriate time.

[0180] User purchases and points awarded

[0181] User: Receives the notification message and purchases the specified special offer item at the store, using an electronic payment method (e.g., PayPay).

[0182] Terminal: When a purchase is completed, additional points will be automatically credited to the user's account. The points crediting process is integrated with the electronic payment system, so users can receive points without any special procedures.

[0183] For example, when a user purchases milk on sale, they pay with PayPay, and as a result, they automatically receive additional points in addition to the usual points.

[0184] Specific operation of the entire system

[0185] Server: Collects sales data, predicts surplus food using generative AI, recognizes user emotions using an emotion engine, and generates and sends notification messages.

[0186] Device: Recognizes the user's emotional state in real time and sends that information to the server, allowing the user to receive notifications at the appropriate time and with the right content, and purchase special offers in stores.

[0187] User: Purchase special offer items and complete electronic payment at the same time to receive additional points.

[0188] As a result, the present invention realizes a food waste reduction system that takes user emotions into consideration, enabling more efficient inventory management and improved consumer satisfaction.

[0189] The processing flow will be explained below.

[0190] Step 1: Data collection

[0191] Server: Periodically collects data from the store's sales database. The server queries the database to retrieve sales data for the past week, including product type, quantity, price, and sales date and time.

[0192] Step 2: Saving to an intermediate database

[0193] Server: Stores collected sales data in an intermediate database, allowing for the organization and retention of data required for subsequent processing.

[0194] Step 3: Generative AI predictions

[0195] Server: Obtains sales data from the intermediate database and inputs it into the generation AI. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. A list of surplus foods is created as a prediction result and saved in the prediction result database.

[0196] For example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0197] Step 4: Create a Special Offer List

[0198] Server: Retrieves surplus food information from the prediction result database and creates a special sale product list based on that information. The special sale product list includes details such as product name, discount price, and sale period.

[0199] Step 5: Obtaining emotion recognition data

[0200] On your device: When receiving a notification message, your device will use the camera and microphone to recognize your emotions. Your device will analyze your facial expressions and tone of voice to determine your current emotional state.

[0201] Step 6: Sending Emotion Data

[0202] Device: Recognized emotion data is sent to the server in real time, and the server uses the emotion data as a basis for optimizing notification messages.

[0203] Step 7: Generate a notification message

[0204] Server: Based on the prediction results of the generation AI and the emotion data sent from the emotion engine, a notification message for the special sale is generated. This message contains information about the special sale, recommended phrases based on the user's emotional state, and details on how to purchase.

[0205] For example, if the emotion engine determines that the user is tired, it will adjust the content of the notification message to something like, "Help us if you're tired! Refresh yourself with milk at a special price."

[0206] Step 8: Sending notifications

[0207] Server: Uses the LINE OA API to send the generated notification message to the user's device via a LINE bot.

[0208] Step 9: Receive and review notifications

[0209] On the device: The user receives a notification message to view the special offer and recommendations. The notification message is displayed on the device, immediately alerting the user.

[0210] Step 10: Shop the specials

[0211] User: After checking the notification message, the user goes to the store and purchases the specified special offer item. The user checks the shelves for special offers at the store and picks up the item.

[0212] Step 11: Making an electronic payment

[0213] User: When purchasing special offers, the user pays using an electronic payment method (e.g., PayPay). The user scans the QR code or completes the payment using the app.

[0214] Step 12: Awarding points

[0215] Server: After the user completes the electronic payment, the server receives a notification from the payment system and automatically adds additional points to the user's account. The user can receive the points without taking any special steps.

[0216] In this way, the present invention is a system that collects sales data, uses AI to generate and predict surplus food, notifies users of special offers based on that data, and also customizes the system by recognizing users' emotions, as well as the final purchase and point awarding process, thereby achieving efficient inventory management, reducing food waste, and providing a purchasing experience that highly satisfies consumers.

[0217] Example 2

[0218] 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."

[0219] Conventional food waste reduction systems predict surplus food based on sales data, but do not optimize notifications to take into account the user's emotional state. This can make it difficult for users to properly receive notifications and take action at the appropriate time, making it difficult to achieve effective food waste reduction. Furthermore, because emotion recognition technology is not applied to increase users' purchasing motivation, there is also the issue of not being able to sufficiently improve consumer satisfaction.

[0220] 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.

[0221] In this invention, the server includes a means for collecting sales data, a means for using artificial intelligence to predict surplus food based on the sales data, and a means for generating a message notifying the user of information about the surplus food. It also includes a means for recognizing the user's emotional state, a means for optimizing the content and timing of the notification message based on the recognized emotional state, and a means for awarding points when the user purchases the surplus food using an electronic payment method. This enables appropriate notifications that take the user's emotions into consideration, thereby enabling effective food waste reduction and improved consumer satisfaction.

[0222] "Sales data" is a record of product sales in a store, and includes product type, quantity, price, sales date and time, etc.

[0223] "Artificial intelligence" is a technology that allows computers to mimic human intelligence to analyze data and make predictions, and includes machine learning and deep learning.

[0224] A "notification message" is information sent to a user, and includes information about special offers and purchase recommendations.

[0225] "User's device" refers to a communication device owned by the user, such as a smartphone or tablet.

[0226] "Emotional state" refers to the user's psychological and emotional state, including states such as joy, sadness, fatigue, and anger.

[0227] "Electronic payment instruments" are payment methods made using digital technology, including credit cards, debit cards, and smartphone payment apps.

[0228] "Points" refers to bonuses or benefits added to a user's account based on certain conditions when the user purchases special offers.

[0229] This invention provides a system that predicts surplus food based on sales data and notifies users of this information, recognizing the emotional state of the user and optimizing the content and timing of notifications based on that. This system operates in cooperation with the server, terminal, and user components.

[0230] Server-based sales data collection and forecasting

[0231] The server periodically collects data from the store's sales database. Specifically, the server sends a query to the database to obtain sales data (product type, quantity, price, and sales date and time) for the past week. This data is stored in the intermediate database.

[0232] The server then runs a generative AI (artificial intelligence) based on this data to predict surplus food. The generative AI uses machine learning algorithms to analyze past sales and inventory data to identify foods that are likely to become surplus in the future. For example, the server can analyze a week's worth of sales data and predict that "milk is likely to become a surplus food."

[0233] Device-based emotional state recognition

[0234] When a user receives a notification message, the device recognizes the user's emotional state through camera or voice input. During this process, the device analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger, fatigue).

[0235] The recognized emotion data is sent to the server in real time. This allows the server to adjust the content and urgency of the notification message. For example, if the emotion engine determines that the user is tired, it can change the content of the notification message to something like, "Help us if you're tired! Refresh yourself with special price milk."

[0236] Server generation and sending of notification messages

[0237] The server creates a list of special sale items based on the predictions of the AI ​​and the emotional data sent from the device, and generates an appropriate notification message, which includes information about the special sale items, recommended phrases based on the user's emotional state, how to purchase them, and where they are sold.

[0238] The server uses the LINE OA API to generate notification messages, which are then sent to the user's device via a LINE bot, with the notification time adjusted accordingly.

[0239] User purchases and points awarded

[0240] The user receives the notification message and purchases the specified special offer item at the store using an electronic payment method (for example, a smartphone payment app).

[0241] Once a purchase is completed, the terminal automatically adds points to the user's account. The point adding process is integrated with the electronic payment system, so users can receive points without any special procedures. For example, when a user purchases milk on sale, they pay with an electronic payment app. As a result, additional points are automatically added to the usual points.

[0242] Specific prompt examples

[0243] Analyze sales data from the past week (e.g., 20 bottles of milk, 50 loaves of bread) to predict food surpluses. Also, adjust notification messages based on the user's emotional state (tiredness, joy, etc.).

[0244] This will enable the realization of a notification system that takes user emotions into consideration, effectively reducing food waste and improving consumer satisfaction.

[0245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0246] Step 1:

[0247] The server collects sales data

[0248] The server queries the store's sales database to retrieve sales data for the past week.

[0249] Input: Sales database

[0250] Output: Sales data for the past week (product type, quantity, price, sales date and time)

[0251] As a specific example, collect data such as "Milk: 20 bottles, Bread: 50 pieces."

[0252] Step 2:

[0253] The server stores the data in an intermediate database

[0254] The server stores the collected data in an intermediate database.

[0255] Input: Collected sales data

[0256] Output: Sales data stored in an intermediate database

[0257] As a concrete example, the collected data of "Milk: 20 bottles, Bread: 50 pieces" is stored in an intermediate database.

[0258] Step 3:

[0259] Server generates AI to predict surplus food

[0260] The server runs the AI ​​based on the data stored in the intermediate database. The AI ​​uses machine learning algorithms to analyze past sales and inventory data to identify foods that are likely to become surplus in the future.

[0261] Input: Sales data stored in the intermediate database

[0262] Output: Predicted food surplus

[0263] As a specific example, the generative AI predicts that "milk is likely to become a surplus food."

[0264] Step 4:

[0265] The device recognizes the user's emotional state

[0266] When a user receives a notification message, the device uses a camera and voice input to recognize the user's emotional state. The device analyzes facial expressions and tone of voice to identify emotions.

[0267] Input: User's facial expression, tone of voice

[0268] Output: User emotion data (happiness, sadness, anger, tiredness, etc.)

[0269] For example, if a user says, "I'm tired today," the device will recognize this as "tired."

[0270] Step 5:

[0271] The device sends emotion data to the server.

[0272] The device transmits the recognized emotion data to the server in real time.

[0273] Input: User emotion data

[0274] Output: Emotion data sent to the server

[0275] As a specific example, emotion data such as "tired" is sent to the server.

[0276] Step 6:

[0277] The server generates a notification message

[0278] The server creates a list of special offers based on the predictions made by the generation AI and the emotional data sent from the device, and generates appropriate notification messages.

[0279] Input: Generative AI prediction results, emotion data from the device

[0280] Output: Notification message

[0281] As a specific example, it generates a message such as "Help us if you're tired! Refresh yourself with special price milk."

[0282] Step 7:

[0283] The server uses the LINE OA API to send a notification message.

[0284] The server generates a notification message using the LINE OA API and sends it to the user's device via a LINE bot.

[0285] Input: Notification message

[0286] Output: Notification message sent to the user's terminal

[0287] As a specific example, the message "Help us if you're tired! Refresh with special price milk" can be sent through a LINE bot.

[0288] Step 8:

[0289] User receives notification message and purchases special offer

[0290] The user receives the notification message on the terminal and purchases the specified special offer item at the store. At this time, the user uses an electronic payment method (for example, a smartphone payment app).

[0291] Input: Notification message

[0292] Output: Special offer purchase and payment data

[0293] As a specific example, a user who receives a notification can purchase milk at a discount at a store using smartphone payment.

[0294] Step 9:

[0295] The terminal awards points

[0296] Once the purchase is complete, the device automatically credits the points to the user's account.

[0297] Input: Purchase and payment data

[0298] Output: Points awarded to the user's account

[0299] For example, after a user purchases milk, additional points are automatically awarded.

[0300] This will enable a notification system that takes user emotions into account through consecutive processing steps, effectively reducing food waste and improving consumer satisfaction.

[0301] (Application example 2)

[0302] 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."

[0303] Current inventory management systems often lack the ability to efficiently predict surplus food and appropriately notify users of this information. Furthermore, uniform notifications that do not take into account the user's emotional state can reduce engagement and reduce purchasing intent. Furthermore, the timing and content of notifications are not optimized, resulting in a poor user experience. As a result, food waste reduction and efficient inventory management are not fully achieved, and consumer satisfaction is declining.

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting sales data, means for using a generation AI to predict surplus food based on past sales data and inventory data, means for using an emotion engine to recognize the user's emotional state, means for optimizing the content and timing of notifications based on data from the emotion engine, means for generating messages notifying users of information about surplus food and sending them to the user's terminal via the Internet, and means for awarding points when the user purchases surplus food using an electronic payment method. This enables a consistent process from predicting surplus food to optimally notifying users, actual purchases, and providing incentives. This reduces food waste and streamlines inventory management, further improving user satisfaction and purchasing motivation.

[0305] "Sales data" refers to data that includes information about the sale of products in a store, including the type, quantity, price, and date and time of the sale of the product.

[0306] "Generative AI" is an artificial intelligence that analyzes past sales and inventory data to predict foods that are likely to become surplus in the future.

[0307] "Surplus food" is food that may remain in excess inventory in the future based on sales and inventory data.

[0308] A "notification message" is a message containing information about surplus food that is sent to inform users of the content.

[0309] An "emotion engine" is a technology for recognizing a user's emotional state and identifying the type of emotion the user is feeling through camera or voice input.

[0310] "User device" refers to an electronic device owned by a user, including a smartphone, tablet, computer, etc.

[0311] "Electronic payment instruments" are instruments for making payments electronically, including credit cards, debit cards, electronic money, etc.

[0312] A "means of awarding points" is a system that adds points to a user's account as an incentive when the user performs a specific action.

[0313] This invention combines a system that collects sales data, predicts surplus food based on that data, and notifies users of that information with an emotion engine that recognizes the user's emotional state and optimizes the content and timing of notifications based on that.

[0314] Data collection and prediction processing

[0315] The server periodically collects data from the store's sales database. This data includes product type, quantity, price, and sales date and time, and obtains sales data for the past week or other periods. The collected sales data is stored in an intermediate database, and the server uses a generation AI to predict surplus food. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. Specifically, based on trends shown in the sales data, it can predict, for example, that milk is likely to become a surplus food.

[0316] Emotion recognition by emotion engine

[0317] When a user receives a notification message, the device uses the built-in emotion engine to recognize the user's emotional state through camera and voice input. The emotion engine analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger). The recognized emotion data is sent to the server in real time, and the content and urgency of the notification message are adjusted based on the emotion data. For example, if the emotion engine determines that the user is tired, it generates a message such as "Help us! Refresh yourself with special price milk."

[0318] Generate and send notification messages

[0319] The server creates a list of special sale items based on the prediction results of the generation AI and the emotional data from the emotion engine, and generates appropriate notification messages. These messages include information about the special sale items, recommended phrases based on the user's emotional state, how to purchase, and where to purchase. The generated notification messages are sent to the user's device via the Internet, with the timing optimally set based on the emotional data.

[0320] User purchases and points awarded

[0321] The user receives the notification message and purchases the specified special offer item at the store using an electronic payment method (e.g., electronic money or credit card). Once the purchase is completed, additional points are automatically credited to the user's account. The point crediting process is integrated with the electronic payment system, so the user does not need to take any special steps.

[0322] As a result, the server can collect sales data, predict surplus food using generative AI, recognize user emotions using an emotion engine, and generate and send notification messages in a single process. Users can receive notifications at the appropriate time, complete electronic payments at the same time as purchasing special offers, and receive additional points.

[0323] Specific hardware and software names to be used

[0324] Hardware: Smartphones, tablets, webcams

[0325] Software: Python, Pandas, Request, OpenCV, Generative AI library (pseudonym), Emotion recognition library (pseudonym), LINE Official Account API

[0326] Prompt Sentence Examples

[0327] Sales Data:

[0328] Date, product, quantity, price

[0329] Based on past sales data, please forecast next week's food surplus. Please include product names and estimated quantities in your forecast.

[0330] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0331] Step 1:

[0332] The server periodically collects sales data from the store's sales database. This collection is done by sending queries to the database, with the store's sales database used as input. The server saves the retrieved data (product name, quantity, price, sales date and time, etc.) in an intermediate database. The output is sales data for the past week.

[0333] Step 2:

[0334] The server analyzes the sales data stored in the intermediate database and uses the generation AI to predict surplus food. The input for this step is the sales data collected in step 1. The generation AI performs a time series analysis of the sales data to identify foods that are likely to become surplus in the future. The output is a list of predicted surplus foods.

[0335] Step 3:

[0336] When the user receives a notification message, the device uses an emotion engine to recognize the user's emotional state. The input in this step includes the user's facial expression data and voice data. The device inputs this data into the emotion engine to identify the user's emotional state (such as joy, sadness, or anger). The output is emotion data.

[0337] Step 4:

[0338] The server receives the prediction results from the generation AI and the emotion data sent from the device, and generates a notification message based on them. The input for this step is the predicted list of surplus foods and the user's emotion data. The server adjusts the content and urgency of the notification message according to the emotion data. For example, for a tired user, a message such as "Help us out! Refresh yourself with special price milk" is generated. The output is a notification message.

[0339] Step 5:

[0340] The server sends the generated notification message to the user's device via the Internet. The input for this step is the notification message, and the output is the status of the message being sent to the user's device. Specifically, the message is sent to the user using the LINE Official Account API.

[0341] Step 6:

[0342] The user receives the notification message on their terminal and purchases the specified special offer item at the store. The user uses an electronic payment method to do so. The inputs for this step are the notification message and electronic payment information, and data confirming that the user has purchased the special offer item is output.

[0343] Step 7:

[0344] The terminal automatically adds additional points to the user's account when the user completes the purchase. The input of this step is the purchase completion information, and the output is the points added to the user's account. This allows the point adding process to be integrated with the electronic payment system.

[0345] 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.

[0346] 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.

[0347] 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.

[0348] [Second embodiment]

[0349] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0350] 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.

[0351] 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).

[0352] 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.

[0353] 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.

[0354] 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).

[0355] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] 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.

[0360] 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."

[0361] The present invention provides a generation AI that collects sales data and predicts surplus food based on that data, a system that generates a message notifying the user of the prediction result and sends it to the user's terminal, and a system that awards points when the user makes a purchase using an electronic payment method.

[0362] Data collection and prediction processing

[0363] Server: Periodically collects data from the store's sales database, including the type, quantity, price, and date and time of the sale of the product.

[0364] Server: Collected sales data is stored in an intermediate database, and based on that data, a generation AI is used to predict surplus food. This generation AI analyzes past sales and inventory data to identify foods that are likely to become surplus in the future.

[0365] As a specific example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0366] Generate and send notification messages

[0367] Server: Based on the prediction results of the generation AI, a list of special sale items is created and a LINE notification message is generated. This message includes the names of the special sale items, their prices, and details on how to purchase them.

[0368] Server: Uses the LINE OA API to send notification messages to the user's device via the LINE bot.

[0369] As a specific example, a notification is generated containing the content "Milk will be sold at a special price due to surplus milk."

[0370] User purchases and points awarded

[0371] User: Receives the notification message and purchases the specified special offer item at the store, using an electronic payment method such as PayPay.

[0372] Terminal: When a purchase is completed, additional points are automatically credited to the user's account. This points crediting process is integrated into the electronic payment system, so users can receive points without any additional procedures.

[0373] For example, when a user purchases milk on sale, they pay with PayPay, and as a result, they automatically receive additional points in addition to the usual points.

[0374] Specific operation of the system

[0375] The server periodically acquires store sales data using a data collection means and stores the information in an intermediate database.

[0376] The generative AI uses the collected data to predict future food surpluses.

[0377] Based on the prediction results, a list of special offers is created and a notification message is generated.

[0378] The server uses the LINE OA API to send a notification message to the user's device.

[0379] Users will receive a notification, purchase special items in the store, and receive additional Purchase Points.

[0380] This will reduce food waste and enable efficient inventory management. The system also encourages consumption by providing incentives to users.

[0381] The processing flow will be explained below.

[0382] Step 1: Data collection

[0383] Server: Periodically collects sales data from the store's sales database. The server queries the database to retrieve sales data for the past week. This sales data includes the product type, quantity, price, and date and time of the sale.

[0384] Step 2: Saving to an intermediate database

[0385] Server: Stores collected sales data in an intermediate database, allowing for the organization and retention of data required for subsequent processing.

[0386] Step 3: Generative AI predictions

[0387] Server: Obtains sales data from the intermediate database and inputs it into the generation AI. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. A list of surplus foods is created as a prediction result and saved in the prediction result database.

[0388] Step 4: Create a Special Offer List

[0389] Server: Retrieves surplus food information from the prediction result database and creates a special sale product list based on that information. The special sale product list includes details such as product name, discount price, and sale period.

[0390] Step 5: Generate a notification message

[0391] Server: Generates notification messages to send to users based on the special offer list. These messages include information about the special offer, how to purchase it, and where it is sold.

[0392] Step 6: Sending notifications

[0393] Server: Using the LINE OA API, the generated notification message is sent to the user's device via a LINE bot. For example, it sends a message such as "Milk is in surplus, so it will be sold at a special price."

[0394] Step 7: Receive and confirm notifications

[0395] Device: Users will receive a notification message on their device to check the special offer information. A notification alert will be displayed on their device to ensure users do not miss the notification.

[0396] Step 8: Shop the specials

[0397] User: After checking the notification message, the user goes to the store and purchases the specified special offer. At this point, the user knows what the special offer is and how to purchase it.

[0398] Step 9: Making an electronic payment

[0399] User: When purchasing special offers, the user pays using an electronic payment method such as PayPay. The user can scan a QR code in the store or complete the payment using the app.

[0400] Step 10: Points awarded

[0401] Server: After the user completes the electronic payment, the server receives a notification from the payment system and automatically credits the additional points to the user's account, allowing the user to receive incentives through points in addition to purchasing special offers.

[0402] In this way, the system efficiently executes a series of processes, from collecting sales data to forecasting, notification, and purchasing and awarding points, thereby reducing food waste and promoting consumption.

[0403] Example 1

[0404] 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."

[0405] Currently, the generation of surplus food has become a serious problem in the food industry. This has led to increased food waste, raising concerns about economic losses and environmental impacts. Furthermore, there is a lack of efficient provision of special sale product information to consumers, making it difficult to promote consumption. Conventional methods have made it difficult to offer surplus food at special prices at the appropriate time and notify consumers.

[0406] 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.

[0407] In this invention, the server includes a means for collecting sales data, a means for using a generation AI to predict surplus food based on the sales data, a means for generating a message notifying the user of information about the surplus food, a means for sending the message to a user's terminal via the Internet, a means for awarding points to a user who receives the notification message when purchasing the surplus food, and a means for the user to purchase the surplus food using an electronic payment method. This makes it possible to efficiently identify surplus food and provide timely discount information to consumers. It also promotes consumption and reduces food waste.

[0408] "Sales data" refers to information about the sales activities of a store, such as the type, quantity, price, and date and time of sales of products sold.

[0409] "Surplus food" is food that may remain unsold to consumers and is expected to be wasted.

[0410] "Generative AI" is a type of artificial intelligence used to predict future situations based on past data, and in this invention is specifically used to predict food surpluses.

[0411] "Notification Message" means a text message generated to inform a consumer about a special offer.

[0412] "User terminal" refers to a device carried by a consumer for receiving notification messages, such as a smartphone, tablet, or computer.

[0413] "Means for transmitting through the Internet" refers to a method for transmitting and receiving information through a network, and is particularly used to send notification messages to users' terminals.

[0414] "Electronic payment instruments" are methods for making payments digitally without using cash, including credit cards, electronic money, and mobile payment apps.

[0415] "Points" refers to bonus points that are given to consumers when they purchase specially priced items, and can be used for future purchases.

[0416] A "special sale product list" is a list generated based on predicted surplus food, which contains detailed information such as products to be sold at special prices, their prices, and the sales period.

[0417] This system uses a generative AI model to collect sales data and predict food surpluses based on that data. It also generates notification messages based on the prediction results and sends them to users' devices. Furthermore, it provides a mechanism for rewarding users with points when they purchase specially priced items using electronic payment methods.

[0418] Data collection and intermediate database storage

[0419] The server periodically collects data from the store's sales database. This data includes information such as the type, quantity, price, and date and time of the sale of the product sold. For example, a periodic batch process is performed every day at midnight to collect hourly sales data. This data is then saved in an intermediate database. When saving, the data is checked for consistency to ensure that no invalid data is mixed in.

[0420] Food surplus forecast

[0421] The server formats the sales data stored in the intermediate database into a format that is easy for the generative AI model to handle. For example, it formats the sales data for the past week as time series data. It then inputs the formatted data into the generative AI model. It sends a prompt request saying, "Based on the sales data for the past week, please predict which foods are most likely to become surplus next." The prediction results from the generative AI model include a list of foods that are likely to become surplus and the probability of this happening.

[0422] Example prompt: "Based on sales data from the past week, please predict which foods are likely to be in surplus in the future. The sales data is as follows: (data content)."

[0423] Generate and send notification messages

[0424] The server creates a list of special sale items based on the surplus food prediction results. This list includes the product name, special price, and sale period. For example, a list containing information such as "Milk - Special price 100 yen - Sale period: This weekend" is created. Next, a LINE notification message is generated based on this list. The LINE OA API is used to send the notification message to the user's device. For example, a message such as "Milk will be in surplus! On sale this weekend for a special price of 100 yen" is generated and sent by the LINE bot.

[0425] User purchases and points awarded

[0426] The user receives the notification message in the LINE app. For example, "Check the notification about the milk special sale on LINE." After that, the user visits the store and purchases the special sale item. At this time, the user uses an electronic payment method. For example, "Purchase milk with PayPay." After the purchase is completed on the device, points are automatically added to the user's account via the electronic payment system. For example, "Additional points will be automatically added after payment is completed with PayPay."

[0427] This system can carry out an integrated process from collecting sales data to predicting surplus food, notifying consumers of special offers, and encouraging them to purchase and receive points. This makes it possible to efficiently identify surplus food and provide timely special offer information to consumers. It is also a system that can encourage consumption and reduce food waste.

[0428] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0429] Step 1:

[0430] The server periodically collects data from the store's sales database. The input data includes information on the type, quantity, price, and date and time of the sale of the product sold. Specifically, a batch process is executed at midnight every day to collect hourly sales data. This batch process uses SQL queries to extract specified data from the sales database and saves the data in an intermediate database.

[0431] Step 2:

[0432] The server saves the collected sales data in an intermediate database. The input data is the sales data collected in step 1. Specifically, it performs an insert operation into the database and performs a data consistency check. For example, it checks whether the product code and quantity are valid. This saved data is used in subsequent analysis processing.

[0433] Step 3:

[0434] The server formats the sales data stored in the intermediate database. The input data is the sales data stored in the intermediate database, and the output data is data converted into a format that is easy for the generative AI model to handle. Specifically, the server formats the sales data for the past week as time-series data to create a dataset for input to the generative AI model. This includes sales volume by date and time and aggregated data by product category.

[0435] Step 4:

[0436] The server inputs the formatted data into the generative AI model. The input data is the dataset created in step 3. The request is sent as a prompt: "Based on sales data from the past week, please predict the foods that are most likely to become surplus next." The output data is the prediction result from the generative AI model, which includes a list of surplus foods and their probabilities. In this prediction process, the generative AI model analyzes past sales trends and inventory data and returns specific prediction results.

[0437] Step 5:

[0438] The server creates a list of special sale items based on the prediction results of the generative AI model. The input data is the prediction results from step 4, and a list of items to be sold at a special price is created. This list includes the product name, special price, and sale period. For example, a list such as "Milk - Special price 100 yen - Sale period: this weekend" is generated. This list is used to generate subsequent notification messages.

[0439] Step 6:

[0440] The server generates a message for LINE notification based on the special sale item list. The input data is the special sale item list created in step 5, and the output data is the notification message. For example, it generates a message with the content "We have a surplus of milk! It will be on sale this weekend for 100 yen." This message includes the name of the special sale item, its price, and details on how to purchase it.

[0441] Step 7:

[0442] The server uses the LINE OA API to send a notification message to the user's device. The input data is the notification message generated in step 6, and the output data is the message sent to the user's device. The notification message is sent to User A's device via the LINE bot, and a confirmation message is received. This step allows the user to receive information about special offers in real time.

[0443] Step 8:

[0444] The user receives the sent notification message in the LINE app. The input data is the notification message sent in step 7, and the output data is the message displayed in the user's LINE app. For example, "Check LINE for notifications about milk special sale."

[0445] Step 9:

[0446] The user visits the store and purchases the special sale item that was notified to them. At this time, they use an electronic payment method. The input data is the information in the notification message, and the output data is the special sale item that was purchased. For example, "Purchase milk with PayPay."

[0447] Step 10:

[0448] After the purchase is completed, the terminal automatically adds points to the user's account via the electronic payment system. The input data is the purchase completion information, and the output data is the points added to the user's account. For example, "After completing payment with PayPay, additional points will be automatically added."

[0449] (Application example 1)

[0450] 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."

[0451] The present invention relates to a system that uses sales data to predict surplus food, notifies customers of special offers, and encourages them to purchase in order to improve the efficiency of inventory management and consumer marketing methods in food delivery services. Conventional methods have made it difficult to predict surplus food, leading to insufficient inventory management and food waste reduction. Furthermore, they have not been effective in notifying customers of special offers and providing incentives to purchase.

[0452] 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.

[0453] In this invention, the server includes a means for collecting sales data, a means for using a generation AI to predict surplus food, a means for notifying users of special offers, a means for sending messages to users' devices, and a means for selling special offers. The server first predicts surplus food based on sales data and notifies users of the information as special offers. This makes it possible to improve the efficiency of inventory management and reduce food waste in food delivery services. Furthermore, by notifying users of special offers and providing incentives for purchases, the server can encourage consumers to purchase and improve the efficiency of the entire service.

[0454] "Sales data" refers to information related to the sale of products, and specifically includes information on the type, quantity, price, and date and time of the sale of the product.

[0455] "Generative AI" is an artificial intelligence technique that uses machine learning algorithms to analyze past data and predict specific future outcomes.

[0456] "Surplus food" refers to food that has been produced or stocked in excess of projected sales, is nearing its expiration date, or is not expected to be sold.

[0457] "Message" means an electronic communication that notifies you of special offers or other important information and may contain text, images, or links.

[0458] A "user device" is an electronic device, such as a smartphone, tablet, or computer, that is capable of connecting to the Internet and receiving communications.

[0459] An "electronic payment instrument" is a method by which a user can pay for goods or services digitally, and specifically uses electronic money, credit cards, debit cards, etc.

[0460] A "means of awarding points" is a system in which points are added to a user's account as a reward when the user meets certain conditions, and the points can be used for discounts or special offers at a later date.

[0461] "Special price items" are items offered at a lower price than the regular selling price, and are set up to promote the sale of surplus food and other items.

[0462] "Communications Network" means the Internet or other digital communications infrastructure used to transmit and receive data and to move information between users and systems.

[0463] This invention relates to a system for improving the efficiency of inventory management and supporting marketing activities in food delivery services. The system program and its processing will be described in detail below.

[0464] System Program

[0465] The system consists of a server, a user's device, and a generative AI model. The server collects and analyzes sales data and predicts surplus food. The user's device receives notifications and is used to purchase special offers. The generative AI model predicts surplus food based on past sales and inventory data.

[0466] Data collection and prediction processing

[0467] The server periodically collects store sales data from the database. This collected data includes the type, quantity, price, and sales date and time of the products sold. The collected sales data is stored in an intermediate database, and a generative AI is used to predict surplus food based on that data. The generative AI model uses a machine learning algorithm to analyze PastData and StockData to identify foods that are likely to become surplus next.

[0468] Generate and send notification messages

[0469] The server creates a list of special sale items based on the predictions made by the AI ​​and generates a notification message containing the names of the special sale items, their prices, and details on how to purchase them. The server then sends the notification message to the user's device via a communications network.

[0470] User purchases and points awarded

[0471] The user receives a notification message and uses their device to check the displayed special offers. They then select the special offer and complete the purchase using an electronic payment method. Once the purchase is complete, additional points are automatically credited to the user's account. This process is integrated into electronic payment systems such as electronic money and credit cards, so users can receive points without any special procedures.

[0472] Specific examples

[0473] For example, if the server collects a week's worth of sales data and, after analyzing it, predicts that milk is likely to become a surplus food item, a list of special sale items is created. A notification message stating, "Milk will be sold at a special price due to surplus milk," is sent to the user's device. The user receives the notification, uses their smartphone to purchase the special sale items, and pays with an electronic payment method. As a result, additional points are automatically awarded in addition to the usual points.

[0474] Prompt Sentence Examples

[0475] As a concrete example, the following prompt sentence is input to the generative AI model:

[0476] "Based on sandwich sales data from the past week, please predict which foods are likely to be in surplus the next day. Based on your prediction, please briefly explain why you think there is a high probability that sandwiches will be in surplus tomorrow."

[0477] This allows the server to efficiently execute a series of processes, from data collection to generating and sending notification messages, and from users making purchases to awarding points. By having the entire system work together, it becomes possible to streamline inventory management for food delivery services and significantly reduce food waste.

[0478] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0479] Step 1:

[0480] The server collects store sales data from the database. Specifically, it obtains information such as the type of product sold, quantity, price, and sales date and time, and stores this in an intermediate database. The inputs are database connection information and queries, and the output is the obtained sales data. This data collection operation accumulates the necessary analysis data.

[0481] Step 2:

[0482] The server inputs the collected sales data into the generative AI model, which then analyzes past sales and inventory data to predict surplus food. The inputs are sales and inventory data, and the output is a predicted surplus food list. The generative AI model uses machine learning algorithms to process and calculate the data and generate a specific surplus food list.

[0483] Step 3:

[0484] The server generates a list of special sale items based on the prediction results of the generative AI model. It lists the predicted surplus food items as special sale items and creates a notification message containing detailed information about them. The input is the predicted surplus food list, and the output is a notification message about the special sale items. Specifically, the message content is constructed using a notification message generation algorithm.

[0485] Step 4:

[0486] The server sends a special offer notification message to the user's device. Since the message is sent via a communication network, an internet connection is required. The input is the special offer notification message and the user's device information, and the output is the sent notification message. Specifically, the message is sent using a communication API.

[0487] Step 5:

[0488] The user checks the received notification message on their device and selects a special offer. The input is the notification message, and the output is confirmation of the user's intention to purchase. Specifically, this involves the user operating their device to select a special offer and pressing the purchase button.

[0489] Step 6:

[0490] The user uses a terminal to complete the purchase of a special offer item using an electronic payment method. The inputs are special offer item information and payment information, and the output is purchase completion information and point award information. In specific operations, payment is made using an electronic payment system (e.g., electronic money, credit card), and points are automatically awarded at that time.

[0491] Step 7:

[0492] The server receives the payment completion information and awards additional points to the user. The input is the user's payment completion information and the point awarding rules, and the output is the updated user point information. Specifically, it updates the point management system and awards additional points to the user's account.

[0493] This series of processing steps is expected to improve the efficiency of inventory management for food delivery services, reduce food waste, and increase purchasing incentives for consumers.

[0494] 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.

[0495] The present invention provides a system that predicts surplus food based on sales data and notifies users of this information, and combines it with an emotion engine that recognizes the user's emotional state and optimizes the content and timing of notifications based on that.

[0496] Data collection and prediction processing

[0497] Server: Periodically collects data from the store's sales database. The server queries the database to retrieve sales data for the past week, including product type, quantity, price, and sales date and time.

[0498] Server: Collected sales data is stored in an intermediate database, and based on that data, a generation AI is used to predict surplus food. The generation AI analyzes past sales and inventory data to identify foods that are likely to become surplus in the future.

[0499] As a specific example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0500] Emotion recognition by emotion engine

[0501] Device: When a user receives a notification message, the emotion engine on the user's device recognizes the user's emotional state through camera and voice input. During this process, the device analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger).

[0502] Device: The recognized emotion data is sent to the server in real time, and the content and urgency of the notification message are adjusted. Based on this information, the server generates a message appropriate to the user's emotional state.

[0503] As a specific example, if the emotion engine determines that the user is tired, it will adjust the content of the notification message to something like, "Help us if you're tired! Refresh yourself with milk at a special price."

[0504] Generate and send notification messages

[0505] Server: Based on the prediction results of the generative AI and the emotional data from the emotion engine, the server creates a list of special sale items and generates appropriate notification messages. These messages include information about the special sale items, recommended phrases based on the user's emotional state, how to purchase, and where to purchase.

[0506] Server: Using the LINE OA API, the generated notification message is sent to the user's device via the LINE bot, adjusting the timing to ensure that the notification is sent at the appropriate time.

[0507] User purchases and points awarded

[0508] User: Receives the notification message and purchases the specified special offer item at the store, using an electronic payment method (e.g., PayPay).

[0509] Terminal: When a purchase is completed, additional points will be automatically credited to the user's account. The points crediting process is integrated with the electronic payment system, so users can receive points without any special procedures.

[0510] For example, when a user purchases milk on sale, they pay with PayPay, and as a result, they automatically receive additional points in addition to the usual points.

[0511] Specific operation of the entire system

[0512] Server: Collects sales data, predicts surplus food using generative AI, recognizes user emotions using an emotion engine, and generates and sends notification messages.

[0513] Device: Recognizes the user's emotional state in real time and sends that information to the server, allowing the user to receive notifications at the appropriate time and with the right content, and purchase special offers in stores.

[0514] User: Purchase special offer items and complete electronic payment at the same time to receive additional points.

[0515] As a result, the present invention realizes a food waste reduction system that takes user emotions into consideration, enabling more efficient inventory management and improved consumer satisfaction.

[0516] The processing flow will be explained below.

[0517] Step 1: Data collection

[0518] Server: Periodically collects data from the store's sales database. The server queries the database to retrieve sales data for the past week, including product type, quantity, price, and sales date and time.

[0519] Step 2: Saving to an intermediate database

[0520] Server: Stores collected sales data in an intermediate database, allowing for the organization and retention of data required for subsequent processing.

[0521] Step 3: Generative AI predictions

[0522] Server: Obtains sales data from the intermediate database and inputs it into the generation AI. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. A list of surplus foods is created as a prediction result and saved in the prediction result database.

[0523] For example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0524] Step 4: Create a Special Offer List

[0525] Server: Retrieves surplus food information from the prediction result database and creates a special sale product list based on that information. The special sale product list includes details such as product name, discount price, and sale period.

[0526] Step 5: Obtaining emotion recognition data

[0527] On your device: When receiving a notification message, your device will use the camera and microphone to recognize your emotions. Your device will analyze your facial expressions and tone of voice to determine your current emotional state.

[0528] Step 6: Sending Emotion Data

[0529] Device: Recognized emotion data is sent to the server in real time, and the server uses the emotion data as a basis for optimizing notification messages.

[0530] Step 7: Generate a notification message

[0531] Server: Based on the prediction results of the generation AI and the emotion data sent from the emotion engine, a notification message for the special sale is generated. This message contains information about the special sale, recommended phrases based on the user's emotional state, and details on how to purchase.

[0532] For example, if the emotion engine determines that the user is tired, it will adjust the content of the notification message to something like, "Help us if you're tired! Refresh yourself with milk at a special price."

[0533] Step 8: Sending notifications

[0534] Server: Uses the LINE OA API to send the generated notification message to the user's device via a LINE bot.

[0535] Step 9: Receive and review notifications

[0536] On the device: The user receives a notification message to view the special offer and recommendations. The notification message is displayed on the device, immediately alerting the user.

[0537] Step 10: Shop the specials

[0538] User: After checking the notification message, the user goes to the store and purchases the specified special offer item. The user checks the shelves for special offers at the store and picks up the item.

[0539] Step 11: Making an electronic payment

[0540] User: When purchasing special offers, the user pays using an electronic payment method (e.g., PayPay). The user scans the QR code or completes the payment using the app.

[0541] Step 12: Awarding points

[0542] Server: After the user completes the electronic payment, the server receives a notification from the payment system and automatically adds additional points to the user's account. The user can receive the points without taking any special steps.

[0543] In this way, the present invention is a system that collects sales data, uses AI to generate and predict surplus food, notifies users of special offers based on that data, and also customizes the system by recognizing users' emotions, as well as the final purchase and point awarding process, thereby achieving efficient inventory management, reducing food waste, and providing a purchasing experience that highly satisfies consumers.

[0544] Example 2

[0545] 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."

[0546] Conventional food waste reduction systems predict surplus food based on sales data, but do not optimize notifications to take into account the user's emotional state. This can make it difficult for users to properly receive notifications and take action at the appropriate time, making it difficult to achieve effective food waste reduction. Furthermore, because emotion recognition technology is not applied to increase users' purchasing motivation, there is also the issue of not being able to sufficiently improve consumer satisfaction.

[0547] 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.

[0548] In this invention, the server includes a means for collecting sales data, a means for using artificial intelligence to predict surplus food based on the sales data, and a means for generating a message notifying the user of information about the surplus food. It also includes a means for recognizing the user's emotional state, a means for optimizing the content and timing of the notification message based on the recognized emotional state, and a means for awarding points when the user purchases the surplus food using an electronic payment method. This enables appropriate notifications that take the user's emotions into consideration, thereby enabling effective food waste reduction and improved consumer satisfaction.

[0549] "Sales data" is a record of product sales in a store, and includes product type, quantity, price, sales date and time, etc.

[0550] "Artificial intelligence" is a technology that allows computers to mimic human intelligence to analyze data and make predictions, and includes machine learning and deep learning.

[0551] A "notification message" is information sent to a user, and includes information about special offers and purchase recommendations.

[0552] "User's device" refers to a communication device owned by the user, such as a smartphone or tablet.

[0553] "Emotional state" refers to the user's psychological and emotional state, including states such as joy, sadness, fatigue, and anger.

[0554] "Electronic payment instruments" are payment methods made using digital technology, including credit cards, debit cards, and smartphone payment apps.

[0555] "Points" refers to bonuses or benefits added to a user's account based on certain conditions when the user purchases special offers.

[0556] This invention provides a system that predicts surplus food based on sales data and notifies users of this information, recognizing the emotional state of the user and optimizing the content and timing of notifications based on that. This system operates in cooperation with the server, terminal, and user components.

[0557] Server-based sales data collection and forecasting

[0558] The server periodically collects data from the store's sales database. Specifically, the server sends a query to the database to obtain sales data (product type, quantity, price, and sales date and time) for the past week. This data is stored in the intermediate database.

[0559] The server then runs a generative AI (artificial intelligence) based on this data to predict surplus food. The generative AI uses machine learning algorithms to analyze past sales and inventory data to identify foods that are likely to become surplus in the future. For example, the server can analyze a week's worth of sales data and predict that "milk is likely to become a surplus food."

[0560] Device-based emotional state recognition

[0561] When a user receives a notification message, the device recognizes the user's emotional state through camera or voice input. During this process, the device analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger, fatigue).

[0562] The recognized emotion data is sent to the server in real time. This allows the server to adjust the content and urgency of the notification message. For example, if the emotion engine determines that the user is tired, it can change the content of the notification message to something like, "Help us if you're tired! Refresh yourself with special price milk."

[0563] Server generation and sending of notification messages

[0564] The server creates a list of special sale items based on the predictions of the AI ​​and the emotional data sent from the device, and generates an appropriate notification message, which includes information about the special sale items, recommended phrases based on the user's emotional state, how to purchase them, and where they are sold.

[0565] The server uses the LINE OA API to generate notification messages, which are then sent to the user's device via a LINE bot, with the notification time adjusted accordingly.

[0566] User purchases and points awarded

[0567] The user receives the notification message and purchases the specified special offer item at the store using an electronic payment method (for example, a smartphone payment app).

[0568] Once a purchase is completed, the terminal automatically adds points to the user's account. The point adding process is integrated with the electronic payment system, so users can receive points without any special procedures. For example, when a user purchases milk on sale, they pay with an electronic payment app. As a result, additional points are automatically added to the usual points.

[0569] Specific prompt examples

[0570] Analyze sales data from the past week (e.g., 20 bottles of milk, 50 loaves of bread) to predict food surpluses. Also, adjust notification messages based on the user's emotional state (tiredness, joy, etc.).

[0571] This will enable the realization of a notification system that takes user emotions into consideration, effectively reducing food waste and improving consumer satisfaction.

[0572] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0573] Step 1:

[0574] The server collects sales data

[0575] The server queries the store's sales database to retrieve sales data for the past week.

[0576] Input: Sales database

[0577] Output: Sales data for the past week (product type, quantity, price, sales date and time)

[0578] As a specific example, collect data such as "Milk: 20 bottles, Bread: 50 pieces."

[0579] Step 2:

[0580] The server stores the data in an intermediate database

[0581] The server stores the collected data in an intermediate database.

[0582] Input: Collected sales data

[0583] Output: Sales data stored in an intermediate database

[0584] As a concrete example, the collected data of "Milk: 20 bottles, Bread: 50 pieces" is stored in an intermediate database.

[0585] Step 3:

[0586] Server generates AI to predict surplus food

[0587] The server runs the AI ​​based on the data stored in the intermediate database. The AI ​​uses machine learning algorithms to analyze past sales and inventory data to identify foods that are likely to become surplus in the future.

[0588] Input: Sales data stored in the intermediate database

[0589] Output: Predicted food surplus

[0590] As a specific example, the generative AI predicts that "milk is likely to become a surplus food."

[0591] Step 4:

[0592] The device recognizes the user's emotional state

[0593] When a user receives a notification message, the device uses a camera and voice input to recognize the user's emotional state. The device analyzes facial expressions and tone of voice to identify emotions.

[0594] Input: User's facial expression, tone of voice

[0595] Output: User emotion data (happiness, sadness, anger, tiredness, etc.)

[0596] For example, if a user says, "I'm tired today," the device will recognize this as "tired."

[0597] Step 5:

[0598] The device sends emotion data to the server.

[0599] The device transmits the recognized emotion data to the server in real time.

[0600] Input: User emotion data

[0601] Output: Emotion data sent to the server

[0602] As a specific example, emotion data such as "tired" is sent to the server.

[0603] Step 6:

[0604] The server generates a notification message

[0605] The server creates a list of special offers based on the predictions made by the generation AI and the emotional data sent from the device, and generates appropriate notification messages.

[0606] Input: Generative AI prediction results, emotion data from the device

[0607] Output: Notification message

[0608] As a specific example, it generates a message such as "Help us if you're tired! Refresh yourself with special price milk."

[0609] Step 7:

[0610] The server uses the LINE OA API to send a notification message.

[0611] The server generates a notification message using the LINE OA API and sends it to the user's device via a LINE bot.

[0612] Input: Notification message

[0613] Output: Notification message sent to the user's terminal

[0614] As a specific example, the message "Help us if you're tired! Refresh with special price milk" can be sent through a LINE bot.

[0615] Step 8:

[0616] User receives notification message and purchases special offer

[0617] The user receives the notification message on the terminal and purchases the specified special offer item at the store. At this time, the user uses an electronic payment method (for example, a smartphone payment app).

[0618] Input: Notification message

[0619] Output: Special offer purchase and payment data

[0620] As a specific example, a user who receives a notification can purchase milk at a discount at a store using smartphone payment.

[0621] Step 9:

[0622] The terminal awards points

[0623] Once the purchase is complete, the device automatically credits the points to the user's account.

[0624] Input: Purchase and payment data

[0625] Output: Points awarded to the user's account

[0626] For example, after a user purchases milk, additional points are automatically awarded.

[0627] This will enable a notification system that takes user emotions into account through consecutive processing steps, effectively reducing food waste and improving consumer satisfaction.

[0628] (Application example 2)

[0629] 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."

[0630] Current inventory management systems often lack the ability to efficiently predict surplus food and appropriately notify users of this information. Furthermore, uniform notifications that do not take into account the user's emotional state can reduce engagement and reduce purchasing intent. Furthermore, the timing and content of notifications are not optimized, resulting in a poor user experience. As a result, food waste reduction and efficient inventory management are not fully achieved, and consumer satisfaction is declining.

[0631] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting sales data, means for using a generation AI to predict surplus food based on past sales data and inventory data, means for using an emotion engine to recognize the user's emotional state, means for optimizing the content and timing of notifications based on data from the emotion engine, means for generating messages notifying users of information about surplus food and sending them to the user's terminal via the Internet, and means for awarding points when the user purchases surplus food using an electronic payment method. This enables a consistent process from predicting surplus food to optimally notifying users, actual purchases, and providing incentives. This reduces food waste and streamlines inventory management, further improving user satisfaction and purchasing motivation.

[0632] "Sales data" refers to data that includes information about the sale of products in a store, including the type, quantity, price, and date and time of the sale of the product.

[0633] "Generative AI" is an artificial intelligence that analyzes past sales and inventory data to predict foods that are likely to become surplus in the future.

[0634] "Surplus food" is food that may remain in excess inventory in the future based on sales and inventory data.

[0635] A "notification message" is a message containing information about surplus food that is sent to inform users of the content.

[0636] An "emotion engine" is a technology for recognizing a user's emotional state and identifying the type of emotion the user is feeling through camera or voice input.

[0637] "User device" refers to an electronic device owned by a user, including a smartphone, tablet, computer, etc.

[0638] "Electronic payment instruments" are instruments for making payments electronically, including credit cards, debit cards, electronic money, etc.

[0639] A "means of awarding points" is a system that adds points to a user's account as an incentive when the user performs a specific action.

[0640] This invention combines a system that collects sales data, predicts surplus food based on that data, and notifies users of that information with an emotion engine that recognizes the user's emotional state and optimizes the content and timing of notifications based on that.

[0641] Data collection and prediction processing

[0642] The server periodically collects data from the store's sales database. This data includes product type, quantity, price, and sales date and time, and obtains sales data for the past week or other periods. The collected sales data is stored in an intermediate database, and the server uses a generation AI to predict surplus food. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. Specifically, based on trends shown in the sales data, it can predict, for example, that milk is likely to become a surplus food.

[0643] Emotion recognition by emotion engine

[0644] When a user receives a notification message, the device uses the built-in emotion engine to recognize the user's emotional state through camera and voice input. The emotion engine analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger). The recognized emotion data is sent to the server in real time, and the content and urgency of the notification message are adjusted based on the emotion data. For example, if the emotion engine determines that the user is tired, it generates a message such as "Help us! Refresh yourself with special price milk."

[0645] Generate and send notification messages

[0646] The server creates a list of special sale items based on the prediction results of the generation AI and the emotional data from the emotion engine, and generates appropriate notification messages. These messages include information about the special sale items, recommended phrases based on the user's emotional state, how to purchase, and where to purchase. The generated notification messages are sent to the user's device via the Internet, with the timing optimally set based on the emotional data.

[0647] User purchases and points awarded

[0648] The user receives the notification message and purchases the specified special offer item at the store using an electronic payment method (e.g., electronic money or credit card). Once the purchase is completed, additional points are automatically credited to the user's account. The point crediting process is integrated with the electronic payment system, so the user does not need to take any special steps.

[0649] As a result, the server can collect sales data, predict surplus food using generative AI, recognize user emotions using an emotion engine, and generate and send notification messages in a single process. Users can receive notifications at the appropriate time, complete electronic payments at the same time as purchasing special offers, and receive additional points.

[0650] Specific hardware and software names to be used

[0651] Hardware: Smartphones, tablets, webcams

[0652] Software: Python, Pandas, Request, OpenCV, Generative AI library (pseudonym), Emotion recognition library (pseudonym), LINE Official Account API

[0653] Prompt Sentence Examples

[0654] Sales Data:

[0655] Date, product, quantity, price

[0656] Based on past sales data, please forecast next week's food surplus. Please include product names and estimated quantities in your forecast.

[0657] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0658] Step 1:

[0659] The server periodically collects sales data from the store's sales database. This collection is done by sending queries to the database, with the store's sales database used as input. The server saves the retrieved data (product name, quantity, price, sales date and time, etc.) in an intermediate database. The output is sales data for the past week.

[0660] Step 2:

[0661] The server analyzes the sales data stored in the intermediate database and uses the generation AI to predict surplus food. The input for this step is the sales data collected in step 1. The generation AI performs a time series analysis of the sales data to identify foods that are likely to become surplus in the future. The output is a list of predicted surplus foods.

[0662] Step 3:

[0663] When the user receives a notification message, the device uses an emotion engine to recognize the user's emotional state. The input in this step includes the user's facial expression data and voice data. The device inputs this data into the emotion engine to identify the user's emotional state (such as joy, sadness, or anger). The output is emotion data.

[0664] Step 4:

[0665] The server receives the prediction results from the generation AI and the emotion data sent from the device, and generates a notification message based on them. The input for this step is the predicted list of surplus foods and the user's emotion data. The server adjusts the content and urgency of the notification message according to the emotion data. For example, for a tired user, a message such as "Help us out! Refresh yourself with special price milk" is generated. The output is a notification message.

[0666] Step 5:

[0667] The server sends the generated notification message to the user's device via the Internet. The input for this step is the notification message, and the output is the status of the message being sent to the user's device. Specifically, the message is sent to the user using the LINE Official Account API.

[0668] Step 6:

[0669] The user receives the notification message on their terminal and purchases the specified special offer item at the store. The user uses an electronic payment method to do so. The inputs for this step are the notification message and electronic payment information, and data confirming that the user has purchased the special offer item is output.

[0670] Step 7:

[0671] The terminal automatically adds additional points to the user's account when the user completes the purchase. The input of this step is the purchase completion information, and the output is the points added to the user's account. This allows the point adding process to be integrated with the electronic payment system.

[0672] 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.

[0673] 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.

[0674] 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.

[0675] [Third embodiment]

[0676] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0677] 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.

[0678] 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).

[0679] 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.

[0680] 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.

[0681] 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).

[0682] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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."

[0688] The present invention provides a generation AI that collects sales data and predicts surplus food based on that data, a system that generates a message notifying the user of the prediction result and sends it to the user's terminal, and a system that awards points when the user makes a purchase using an electronic payment method.

[0689] Data collection and prediction processing

[0690] Server: Periodically collects data from the store's sales database, including the type, quantity, price, and date and time of the sale of the product.

[0691] Server: Collected sales data is stored in an intermediate database, and based on that data, a generation AI is used to predict surplus food. This generation AI analyzes past sales and inventory data to identify foods that are likely to become surplus in the future.

[0692] As a specific example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0693] Generate and send notification messages

[0694] Server: Based on the prediction results of the generation AI, a list of special sale items is created and a LINE notification message is generated. This message includes the names of the special sale items, their prices, and details on how to purchase them.

[0695] Server: Uses the LINE OA API to send notification messages to the user's device via the LINE bot.

[0696] As a specific example, a notification is generated containing the content "Milk will be sold at a special price due to surplus milk."

[0697] User purchases and points awarded

[0698] User: Receives the notification message and purchases the specified special offer item at the store, using an electronic payment method such as PayPay.

[0699] Terminal: When a purchase is completed, additional points are automatically credited to the user's account. This points crediting process is integrated into the electronic payment system, so users can receive points without any additional procedures.

[0700] For example, when a user purchases milk on sale, they pay with PayPay, and as a result, they automatically receive additional points in addition to the usual points.

[0701] Specific operation of the system

[0702] The server periodically acquires store sales data using a data collection means and stores the information in an intermediate database.

[0703] The generative AI uses the collected data to predict future food surpluses.

[0704] Based on the prediction results, a list of special offers is created and a notification message is generated.

[0705] The server uses the LINE OA API to send a notification message to the user's device.

[0706] Users will receive a notification, purchase special items in the store, and receive additional Purchase Points.

[0707] This will reduce food waste and enable efficient inventory management. The system also encourages consumption by providing incentives to users.

[0708] The processing flow will be explained below.

[0709] Step 1: Data collection

[0710] Server: Periodically collects sales data from the store's sales database. The server queries the database to retrieve sales data for the past week. This sales data includes the product type, quantity, price, and date and time of the sale.

[0711] Step 2: Saving to an intermediate database

[0712] Server: Stores collected sales data in an intermediate database, allowing for the organization and retention of data required for subsequent processing.

[0713] Step 3: Generative AI predictions

[0714] Server: Obtains sales data from the intermediate database and inputs it into the generation AI. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. A list of surplus foods is created as a prediction result and saved in the prediction result database.

[0715] Step 4: Create a Special Offer List

[0716] Server: Retrieves surplus food information from the prediction result database and creates a special sale product list based on that information. The special sale product list includes details such as product name, discount price, and sale period.

[0717] Step 5: Generate a notification message

[0718] Server: Generates notification messages to send to users based on the special offer list. These messages include information about the special offer, how to purchase it, and where it is sold.

[0719] Step 6: Sending notifications

[0720] Server: Using the LINE OA API, the generated notification message is sent to the user's device via a LINE bot. For example, it sends a message such as "Milk is in surplus, so it will be sold at a special price."

[0721] Step 7: Receive and confirm notifications

[0722] Device: Users will receive a notification message on their device to check the special offer information. A notification alert will be displayed on their device to ensure users do not miss the notification.

[0723] Step 8: Shop the specials

[0724] User: After checking the notification message, the user goes to the store and purchases the specified special offer. At this point, the user knows what the special offer is and how to purchase it.

[0725] Step 9: Making an electronic payment

[0726] User: When purchasing special offers, the user pays using an electronic payment method such as PayPay. The user can scan a QR code in the store or complete the payment using the app.

[0727] Step 10: Points awarded

[0728] Server: After the user completes the electronic payment, the server receives a notification from the payment system and automatically credits the additional points to the user's account, allowing the user to receive incentives through points in addition to purchasing special offers.

[0729] In this way, the system efficiently executes a series of processes, from collecting sales data to forecasting, notification, and purchasing and awarding points, thereby reducing food waste and promoting consumption.

[0730] Example 1

[0731] 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."

[0732] Currently, the generation of surplus food has become a serious problem in the food industry. This has led to increased food waste, raising concerns about economic losses and environmental impacts. Furthermore, there is a lack of efficient provision of special sale product information to consumers, making it difficult to promote consumption. Conventional methods have made it difficult to offer surplus food at special prices at the appropriate time and notify consumers.

[0733] 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.

[0734] In this invention, the server includes a means for collecting sales data, a means for using a generation AI to predict surplus food based on the sales data, a means for generating a message notifying the user of information about the surplus food, a means for sending the message to a user's terminal via the Internet, a means for awarding points to a user who receives the notification message when purchasing the surplus food, and a means for the user to purchase the surplus food using an electronic payment method. This makes it possible to efficiently identify surplus food and provide timely discount information to consumers. It also promotes consumption and reduces food waste.

[0735] "Sales data" refers to information about the sales activities of a store, such as the type, quantity, price, and date and time of sales of products sold.

[0736] "Surplus food" is food that may remain unsold to consumers and is expected to be wasted.

[0737] "Generative AI" is a type of artificial intelligence used to predict future situations based on past data, and in this invention is specifically used to predict food surpluses.

[0738] "Notification Message" means a text message generated to inform a consumer about a special offer.

[0739] "User terminal" refers to a device carried by a consumer for receiving notification messages, such as a smartphone, tablet, or computer.

[0740] "Means for transmitting through the Internet" refers to a method for transmitting and receiving information through a network, and is particularly used to send notification messages to users' terminals.

[0741] "Electronic payment instruments" are methods for making payments digitally without using cash, including credit cards, electronic money, and mobile payment apps.

[0742] "Points" refers to bonus points that are given to consumers when they purchase specially priced items, and can be used for future purchases.

[0743] A "special sale product list" is a list generated based on predicted surplus food, which contains detailed information such as products to be sold at special prices, their prices, and the sales period.

[0744] This system uses a generative AI model to collect sales data and predict food surpluses based on that data. It also generates notification messages based on the prediction results and sends them to users' devices. Furthermore, it provides a mechanism for rewarding users with points when they purchase specially priced items using electronic payment methods.

[0745] Data collection and intermediate database storage

[0746] The server periodically collects data from the store's sales database. This data includes information such as the type, quantity, price, and date and time of the sale of the product sold. For example, a periodic batch process is performed every day at midnight to collect hourly sales data. This data is then saved in an intermediate database. When saving, the data is checked for consistency to ensure that no invalid data is mixed in.

[0747] Food surplus forecast

[0748] The server formats the sales data stored in the intermediate database into a format that is easy for the generative AI model to handle. For example, it formats the sales data for the past week as time series data. It then inputs the formatted data into the generative AI model. It sends a prompt request saying, "Based on the sales data for the past week, please predict which foods are most likely to become surplus next." The prediction results from the generative AI model include a list of foods that are likely to become surplus and the probability of this happening.

[0749] Example prompt: "Based on sales data from the past week, please predict which foods are likely to be in surplus in the future. The sales data is as follows: (data content)."

[0750] Generate and send notification messages

[0751] The server creates a list of special sale items based on the surplus food prediction results. This list includes the product name, special price, and sale period. For example, a list containing information such as "Milk - Special price 100 yen - Sale period: This weekend" is created. Next, a LINE notification message is generated based on this list. The LINE OA API is used to send the notification message to the user's device. For example, a message such as "Milk will be in surplus! On sale this weekend for a special price of 100 yen" is generated and sent by the LINE bot.

[0752] User purchases and points awarded

[0753] The user receives the notification message in the LINE app. For example, "Check the notification about the milk special sale on LINE." After that, the user visits the store and purchases the special sale item. At this time, the user uses an electronic payment method. For example, "Purchase milk with PayPay." After the purchase is completed on the device, points are automatically added to the user's account via the electronic payment system. For example, "Additional points will be automatically added after payment is completed with PayPay."

[0754] This system can carry out an integrated process from collecting sales data to predicting surplus food, notifying consumers of special offers, and encouraging them to purchase and receive points. This makes it possible to efficiently identify surplus food and provide timely special offer information to consumers. It is also a system that can encourage consumption and reduce food waste.

[0755] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0756] Step 1:

[0757] The server periodically collects data from the store's sales database. The input data includes information on the type, quantity, price, and date and time of the sale of the product sold. Specifically, a batch process is executed at midnight every day to collect hourly sales data. This batch process uses SQL queries to extract specified data from the sales database and saves the data in an intermediate database.

[0758] Step 2:

[0759] The server saves the collected sales data in an intermediate database. The input data is the sales data collected in step 1. Specifically, it performs an insert operation into the database and performs a data consistency check. For example, it checks whether the product code and quantity are valid. This saved data is used in subsequent analysis processing.

[0760] Step 3:

[0761] The server formats the sales data stored in the intermediate database. The input data is the sales data stored in the intermediate database, and the output data is data converted into a format that is easy for the generative AI model to handle. Specifically, the server formats the sales data for the past week as time-series data to create a dataset for input to the generative AI model. This includes sales volume by date and time and aggregated data by product category.

[0762] Step 4:

[0763] The server inputs the formatted data into the generative AI model. The input data is the dataset created in step 3. The request is sent as a prompt: "Based on sales data from the past week, please predict the foods that are most likely to become surplus next." The output data is the prediction result from the generative AI model, which includes a list of surplus foods and their probabilities. In this prediction process, the generative AI model analyzes past sales trends and inventory data and returns specific prediction results.

[0764] Step 5:

[0765] The server creates a list of special sale items based on the prediction results of the generative AI model. The input data is the prediction results from step 4, and a list of items to be sold at a special price is created. This list includes the product name, special price, and sale period. For example, a list such as "Milk - Special price 100 yen - Sale period: this weekend" is generated. This list is used to generate subsequent notification messages.

[0766] Step 6:

[0767] The server generates a message for LINE notification based on the special sale item list. The input data is the special sale item list created in step 5, and the output data is the notification message. For example, it generates a message with the content "We have a surplus of milk! It will be on sale this weekend for 100 yen." This message includes the name of the special sale item, its price, and details on how to purchase it.

[0768] Step 7:

[0769] The server uses the LINE OA API to send a notification message to the user's device. The input data is the notification message generated in step 6, and the output data is the message sent to the user's device. The notification message is sent to User A's device via the LINE bot, and a confirmation message is received. This step allows the user to receive information about special offers in real time.

[0770] Step 8:

[0771] The user receives the sent notification message in the LINE app. The input data is the notification message sent in step 7, and the output data is the message displayed in the user's LINE app. For example, "Check LINE for notifications about milk special sale."

[0772] Step 9:

[0773] The user visits the store and purchases the special sale item that was notified to them. At this time, they use an electronic payment method. The input data is the information in the notification message, and the output data is the special sale item that was purchased. For example, "Purchase milk with PayPay."

[0774] Step 10:

[0775] After the purchase is completed, the terminal automatically adds points to the user's account via the electronic payment system. The input data is the purchase completion information, and the output data is the points added to the user's account. For example, "After completing payment with PayPay, additional points will be automatically added."

[0776] (Application example 1)

[0777] 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."

[0778] The present invention relates to a system that uses sales data to predict surplus food, notifies customers of special offers, and encourages them to purchase in order to improve the efficiency of inventory management and consumer marketing methods in food delivery services. Conventional methods have made it difficult to predict surplus food, leading to insufficient inventory management and food waste reduction. Furthermore, they have not been effective in notifying customers of special offers and providing incentives to purchase.

[0779] 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.

[0780] In this invention, the server includes a means for collecting sales data, a means for using a generation AI to predict surplus food, a means for notifying users of special offers, a means for sending messages to users' devices, and a means for selling special offers. The server first predicts surplus food based on sales data and notifies users of the information as special offers. This makes it possible to improve the efficiency of inventory management and reduce food waste in food delivery services. Furthermore, by notifying users of special offers and providing incentives for purchases, the server can encourage consumers to purchase and improve the efficiency of the entire service.

[0781] "Sales data" refers to information related to the sale of products, and specifically includes information on the type, quantity, price, and date and time of the sale of the product.

[0782] "Generative AI" is an artificial intelligence technique that uses machine learning algorithms to analyze past data and predict specific future outcomes.

[0783] "Surplus food" refers to food that has been produced or stocked in excess of projected sales, is nearing its expiration date, or is not expected to be sold.

[0784] "Message" means an electronic communication that notifies you of special offers or other important information and may contain text, images, or links.

[0785] A "user device" is an electronic device, such as a smartphone, tablet, or computer, that is capable of connecting to the Internet and receiving communications.

[0786] An "electronic payment instrument" is a method by which a user can pay for goods or services digitally, and specifically uses electronic money, credit cards, debit cards, etc.

[0787] A "means of awarding points" is a system in which points are added to a user's account as a reward when the user meets certain conditions, and the points can be used for discounts or special offers at a later date.

[0788] "Special price items" are items offered at a lower price than the regular selling price, and are set up to promote the sale of surplus food and other items.

[0789] "Communications Network" means the Internet or other digital communications infrastructure used to transmit and receive data and to move information between users and systems.

[0790] This invention relates to a system for improving the efficiency of inventory management and supporting marketing activities in food delivery services. The system program and its processing will be described in detail below.

[0791] System Program

[0792] The system consists of a server, a user's device, and a generative AI model. The server collects and analyzes sales data and predicts surplus food. The user's device receives notifications and is used to purchase special offers. The generative AI model predicts surplus food based on past sales and inventory data.

[0793] Data collection and prediction processing

[0794] The server periodically collects store sales data from the database. This collected data includes the type, quantity, price, and sales date and time of the products sold. The collected sales data is stored in an intermediate database, and a generative AI is used to predict surplus food based on that data. The generative AI model uses a machine learning algorithm to analyze PastData and StockData to identify foods that are likely to become surplus next.

[0795] Generate and send notification messages

[0796] The server creates a list of special sale items based on the predictions made by the AI ​​and generates a notification message containing the names of the special sale items, their prices, and details on how to purchase them. The server then sends the notification message to the user's device via a communications network.

[0797] User purchases and points awarded

[0798] The user receives a notification message and uses their device to check the displayed special offers. They then select the special offer and complete the purchase using an electronic payment method. Once the purchase is complete, additional points are automatically credited to the user's account. This process is integrated into electronic payment systems such as electronic money and credit cards, so users can receive points without any special procedures.

[0799] Specific examples

[0800] For example, if the server collects a week's worth of sales data and, after analyzing it, predicts that milk is likely to become a surplus food item, a list of special sale items is created. A notification message stating, "Milk will be sold at a special price due to surplus milk," is sent to the user's device. The user receives the notification, uses their smartphone to purchase the special sale items, and pays with an electronic payment method. As a result, additional points are automatically awarded in addition to the usual points.

[0801] Prompt Sentence Examples

[0802] As a concrete example, the following prompt sentence is input to the generative AI model:

[0803] "Based on sandwich sales data from the past week, please predict which foods are likely to be in surplus the next day. Based on your prediction, please briefly explain why you think there is a high probability that sandwiches will be in surplus tomorrow."

[0804] This allows the server to efficiently execute a series of processes, from data collection to generating and sending notification messages, and from users making purchases to awarding points. By having the entire system work together, it becomes possible to streamline inventory management for food delivery services and significantly reduce food waste.

[0805] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0806] Step 1:

[0807] The server collects store sales data from the database. Specifically, it obtains information such as the type of product sold, quantity, price, and sales date and time, and stores this in an intermediate database. The inputs are database connection information and queries, and the output is the obtained sales data. This data collection operation accumulates the necessary analysis data.

[0808] Step 2:

[0809] The server inputs the collected sales data into the generative AI model, which then analyzes past sales and inventory data to predict surplus food. The inputs are sales and inventory data, and the output is a predicted surplus food list. The generative AI model uses machine learning algorithms to process and calculate the data and generate a specific surplus food list.

[0810] Step 3:

[0811] The server generates a list of special sale items based on the prediction results of the generative AI model. It lists the predicted surplus food items as special sale items and creates a notification message containing detailed information about them. The input is the predicted surplus food list, and the output is a notification message about the special sale items. Specifically, the message content is constructed using a notification message generation algorithm.

[0812] Step 4:

[0813] The server sends a special offer notification message to the user's device. Since the message is sent via a communication network, an internet connection is required. The input is the special offer notification message and the user's device information, and the output is the sent notification message. Specifically, the message is sent using a communication API.

[0814] Step 5:

[0815] The user checks the received notification message on their device and selects a special offer. The input is the notification message, and the output is confirmation of the user's intention to purchase. Specifically, this involves the user operating their device to select a special offer and pressing the purchase button.

[0816] Step 6:

[0817] The user uses a terminal to complete the purchase of a special offer item using an electronic payment method. The inputs are special offer item information and payment information, and the output is purchase completion information and point award information. In specific operations, payment is made using an electronic payment system (e.g., electronic money, credit card), and points are automatically awarded at that time.

[0818] Step 7:

[0819] The server receives the payment completion information and awards additional points to the user. The input is the user's payment completion information and the point awarding rules, and the output is the updated user point information. Specifically, it updates the point management system and awards additional points to the user's account.

[0820] This series of processing steps is expected to improve the efficiency of inventory management for food delivery services, reduce food waste, and increase purchasing incentives for consumers.

[0821] 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.

[0822] The present invention provides a system that predicts surplus food based on sales data and notifies users of this information, and combines it with an emotion engine that recognizes the user's emotional state and optimizes the content and timing of notifications based on that.

[0823] Data collection and prediction processing

[0824] Server: Periodically collects data from the store's sales database. The server queries the database to retrieve sales data for the past week, including product type, quantity, price, and sales date and time.

[0825] Server: Collected sales data is stored in an intermediate database, and based on that data, a generation AI is used to predict surplus food. The generation AI analyzes past sales and inventory data to identify foods that are likely to become surplus in the future.

[0826] As a specific example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0827] Emotion recognition by emotion engine

[0828] Device: When a user receives a notification message, the emotion engine on the user's device recognizes the user's emotional state through camera and voice input. During this process, the device analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger).

[0829] Device: The recognized emotion data is sent to the server in real time, and the content and urgency of the notification message are adjusted. Based on this information, the server generates a message appropriate to the user's emotional state.

[0830] As a specific example, if the emotion engine determines that the user is tired, it will adjust the content of the notification message to something like, "Help us if you're tired! Refresh yourself with milk at a special price."

[0831] Generate and send notification messages

[0832] Server: Based on the prediction results of the generative AI and the emotional data from the emotion engine, the server creates a list of special sale items and generates appropriate notification messages. These messages include information about the special sale items, recommended phrases based on the user's emotional state, how to purchase, and where to purchase.

[0833] Server: Using the LINE OA API, the generated notification message is sent to the user's device via the LINE bot, adjusting the timing to ensure that the notification is sent at the appropriate time.

[0834] User purchases and points awarded

[0835] User: Receives the notification message and purchases the specified special offer item at the store, using an electronic payment method (e.g., PayPay).

[0836] Terminal: When a purchase is completed, additional points will be automatically credited to the user's account. The points crediting process is integrated with the electronic payment system, so users can receive points without any special procedures.

[0837] For example, when a user purchases milk on sale, they pay with PayPay, and as a result, they automatically receive additional points in addition to the usual points.

[0838] Specific operation of the entire system

[0839] Server: Collects sales data, predicts surplus food using generative AI, recognizes user emotions using an emotion engine, and generates and sends notification messages.

[0840] Device: Recognizes the user's emotional state in real time and sends that information to the server, allowing the user to receive notifications at the appropriate time and with the right content, and purchase special offers in stores.

[0841] User: Purchase special offer items and complete electronic payment at the same time to receive additional points.

[0842] As a result, the present invention realizes a food waste reduction system that takes user emotions into consideration, enabling more efficient inventory management and improved consumer satisfaction.

[0843] The processing flow will be explained below.

[0844] Step 1: Data collection

[0845] Server: Periodically collects data from the store's sales database. The server queries the database to retrieve sales data for the past week, including product type, quantity, price, and sales date and time.

[0846] Step 2: Saving to an intermediate database

[0847] Server: Stores collected sales data in an intermediate database, allowing for the organization and retention of data required for subsequent processing.

[0848] Step 3: Generative AI predictions

[0849] Server: Obtains sales data from the intermediate database and inputs it into the generation AI. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. A list of surplus foods is created as a prediction result and saved in the prediction result database.

[0850] For example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[0851] Step 4: Create a Special Offer List

[0852] Server: Retrieves surplus food information from the prediction result database and creates a special sale product list based on that information. The special sale product list includes details such as product name, discount price, and sale period.

[0853] Step 5: Obtaining emotion recognition data

[0854] On your device: When receiving a notification message, your device will use the camera and microphone to recognize your emotions. Your device will analyze your facial expressions and tone of voice to determine your current emotional state.

[0855] Step 6: Sending Emotion Data

[0856] Device: Recognized emotion data is sent to the server in real time, and the server uses the emotion data as a basis for optimizing notification messages.

[0857] Step 7: Generate a notification message

[0858] Server: Based on the prediction results of the generation AI and the emotion data sent from the emotion engine, a notification message for the special sale is generated. This message contains information about the special sale, recommended phrases based on the user's emotional state, and details on how to purchase.

[0859] For example, if the emotion engine determines that the user is tired, it will adjust the content of the notification message to something like, "Help us if you're tired! Refresh yourself with milk at a special price."

[0860] Step 8: Sending notifications

[0861] Server: Uses the LINE OA API to send the generated notification message to the user's device via a LINE bot.

[0862] Step 9: Receive and review notifications

[0863] On the device: The user receives a notification message to view the special offer and recommendations. The notification message is displayed on the device, immediately alerting the user.

[0864] Step 10: Shop the specials

[0865] User: After checking the notification message, the user goes to the store and purchases the specified special offer item. The user checks the shelves for special offers at the store and picks up the item.

[0866] Step 11: Making an electronic payment

[0867] User: When purchasing special offers, the user pays using an electronic payment method (e.g., PayPay). The user scans the QR code or completes the payment using the app.

[0868] Step 12: Awarding points

[0869] Server: After the user completes the electronic payment, the server receives a notification from the payment system and automatically adds additional points to the user's account. The user can receive the points without taking any special steps.

[0870] In this way, the present invention is a system that collects sales data, uses AI to generate and predict surplus food, notifies users of special offers based on that data, and also customizes the system by recognizing users' emotions, as well as the final purchase and point awarding process, thereby achieving efficient inventory management, reducing food waste, and providing a purchasing experience that highly satisfies consumers.

[0871] Example 2

[0872] 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."

[0873] Conventional food waste reduction systems predict surplus food based on sales data, but do not optimize notifications to take into account the user's emotional state. This can make it difficult for users to properly receive notifications and take action at the appropriate time, making it difficult to achieve effective food waste reduction. Furthermore, because emotion recognition technology is not applied to increase users' purchasing motivation, there is also the issue of not being able to sufficiently improve consumer satisfaction.

[0874] 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.

[0875] In this invention, the server includes a means for collecting sales data, a means for using artificial intelligence to predict surplus food based on the sales data, and a means for generating a message notifying the user of information about the surplus food. It also includes a means for recognizing the user's emotional state, a means for optimizing the content and timing of the notification message based on the recognized emotional state, and a means for awarding points when the user purchases the surplus food using an electronic payment method. This enables appropriate notifications that take the user's emotions into consideration, thereby enabling effective food waste reduction and improved consumer satisfaction.

[0876] "Sales data" is a record of product sales in a store, and includes product type, quantity, price, sales date and time, etc.

[0877] "Artificial intelligence" is a technology that allows computers to mimic human intelligence to analyze data and make predictions, and includes machine learning and deep learning.

[0878] A "notification message" is information sent to a user, and includes information about special offers and purchase recommendations.

[0879] "User's device" refers to a communication device owned by the user, such as a smartphone or tablet.

[0880] "Emotional state" refers to the user's psychological and emotional state, including states such as joy, sadness, fatigue, and anger.

[0881] "Electronic payment instruments" are payment methods made using digital technology, including credit cards, debit cards, and smartphone payment apps.

[0882] "Points" refers to bonuses or benefits added to a user's account based on certain conditions when the user purchases special offers.

[0883] This invention provides a system that predicts surplus food based on sales data and notifies users of this information, recognizing the emotional state of the user and optimizing the content and timing of notifications based on that. This system operates in cooperation with the server, terminal, and user components.

[0884] Server-based sales data collection and forecasting

[0885] The server periodically collects data from the store's sales database. Specifically, the server sends a query to the database to obtain sales data (product type, quantity, price, and sales date and time) for the past week. This data is stored in the intermediate database.

[0886] The server then runs a generative AI (artificial intelligence) based on this data to predict surplus food. The generative AI uses machine learning algorithms to analyze past sales and inventory data to identify foods that are likely to become surplus in the future. For example, the server can analyze a week's worth of sales data and predict that "milk is likely to become a surplus food."

[0887] Device-based emotional state recognition

[0888] When a user receives a notification message, the device recognizes the user's emotional state through camera or voice input. During this process, the device analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger, fatigue).

[0889] The recognized emotion data is sent to the server in real time. This allows the server to adjust the content and urgency of the notification message. For example, if the emotion engine determines that the user is tired, it can change the content of the notification message to something like, "Help us if you're tired! Refresh yourself with special price milk."

[0890] Server generation and sending of notification messages

[0891] The server creates a list of special sale items based on the predictions of the AI ​​and the emotional data sent from the device, and generates an appropriate notification message, which includes information about the special sale items, recommended phrases based on the user's emotional state, how to purchase them, and where they are sold.

[0892] The server uses the LINE OA API to generate notification messages, which are then sent to the user's device via a LINE bot, with the notification time adjusted accordingly.

[0893] User purchases and points awarded

[0894] The user receives the notification message and purchases the specified special offer item at the store using an electronic payment method (for example, a smartphone payment app).

[0895] Once a purchase is completed, the terminal automatically adds points to the user's account. The point adding process is integrated with the electronic payment system, so users can receive points without any special procedures. For example, when a user purchases milk on sale, they pay with an electronic payment app. As a result, additional points are automatically added to the usual points.

[0896] Specific prompt examples

[0897] Analyze sales data from the past week (e.g., 20 bottles of milk, 50 loaves of bread) to predict food surpluses. Also, adjust notification messages based on the user's emotional state (tiredness, joy, etc.).

[0898] This will enable the realization of a notification system that takes user emotions into consideration, effectively reducing food waste and improving consumer satisfaction.

[0899] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0900] Step 1:

[0901] The server collects sales data

[0902] The server queries the store's sales database to retrieve sales data for the past week.

[0903] Input: Sales database

[0904] Output: Sales data for the past week (product type, quantity, price, sales date and time)

[0905] As a specific example, collect data such as "Milk: 20 bottles, Bread: 50 pieces."

[0906] Step 2:

[0907] The server stores the data in an intermediate database

[0908] The server stores the collected data in an intermediate database.

[0909] Input: Collected sales data

[0910] Output: Sales data stored in an intermediate database

[0911] As a concrete example, the collected data of "Milk: 20 bottles, Bread: 50 pieces" is stored in an intermediate database.

[0912] Step 3:

[0913] Server generates AI to predict surplus food

[0914] The server runs the AI ​​based on the data stored in the intermediate database. The AI ​​uses machine learning algorithms to analyze past sales and inventory data to identify foods that are likely to become surplus in the future.

[0915] Input: Sales data stored in the intermediate database

[0916] Output: Predicted food surplus

[0917] As a specific example, the generative AI predicts that "milk is likely to become a surplus food."

[0918] Step 4:

[0919] The device recognizes the user's emotional state

[0920] When a user receives a notification message, the device uses a camera and voice input to recognize the user's emotional state. The device analyzes facial expressions and tone of voice to identify emotions.

[0921] Input: User's facial expression, tone of voice

[0922] Output: User emotion data (happiness, sadness, anger, tiredness, etc.)

[0923] For example, if a user says, "I'm tired today," the device will recognize this as "tired."

[0924] Step 5:

[0925] The device sends emotion data to the server.

[0926] The device transmits the recognized emotion data to the server in real time.

[0927] Input: User emotion data

[0928] Output: Emotion data sent to the server

[0929] As a specific example, emotion data such as "tired" is sent to the server.

[0930] Step 6:

[0931] The server generates a notification message

[0932] The server creates a list of special offers based on the predictions made by the generation AI and the emotional data sent from the device, and generates appropriate notification messages.

[0933] Input: Generative AI prediction results, emotion data from the device

[0934] Output: Notification message

[0935] As a specific example, it generates a message such as "Help us if you're tired! Refresh yourself with special price milk."

[0936] Step 7:

[0937] The server uses the LINE OA API to send a notification message.

[0938] The server generates a notification message using the LINE OA API and sends it to the user's device via a LINE bot.

[0939] Input: Notification message

[0940] Output: Notification message sent to the user's terminal

[0941] As a specific example, the message "Help us if you're tired! Refresh with special price milk" can be sent through a LINE bot.

[0942] Step 8:

[0943] User receives notification message and purchases special offer

[0944] The user receives the notification message on the terminal and purchases the specified special offer item at the store. At this time, the user uses an electronic payment method (for example, a smartphone payment app).

[0945] Input: Notification message

[0946] Output: Special offer purchase and payment data

[0947] As a specific example, a user who receives a notification can purchase milk at a discount at a store using smartphone payment.

[0948] Step 9:

[0949] The terminal awards points

[0950] Once the purchase is complete, the device automatically credits the points to the user's account.

[0951] Input: Purchase and payment data

[0952] Output: Points awarded to the user's account

[0953] For example, after a user purchases milk, additional points are automatically awarded.

[0954] This will enable a notification system that takes user emotions into account through consecutive processing steps, effectively reducing food waste and improving consumer satisfaction.

[0955] (Application example 2)

[0956] 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."

[0957] Current inventory management systems often lack the ability to efficiently predict surplus food and appropriately notify users of this information. Furthermore, uniform notifications that do not take into account the user's emotional state can reduce engagement and reduce purchasing intent. Furthermore, the timing and content of notifications are not optimized, resulting in a poor user experience. As a result, food waste reduction and efficient inventory management are not fully achieved, and consumer satisfaction is declining.

[0958] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting sales data, means for using a generation AI to predict surplus food based on past sales data and inventory data, means for using an emotion engine to recognize the user's emotional state, means for optimizing the content and timing of notifications based on data from the emotion engine, means for generating messages notifying users of information about surplus food and sending them to the user's terminal via the Internet, and means for awarding points when the user purchases surplus food using an electronic payment method. This enables a consistent process from predicting surplus food to optimally notifying users, actual purchases, and providing incentives. This reduces food waste and streamlines inventory management, further improving user satisfaction and purchasing motivation.

[0959] "Sales data" refers to data that includes information about the sale of products in a store, including the type, quantity, price, and date and time of the sale of the product.

[0960] "Generative AI" is an artificial intelligence that analyzes past sales and inventory data to predict foods that are likely to become surplus in the future.

[0961] "Surplus food" is food that may remain in excess inventory in the future based on sales and inventory data.

[0962] A "notification message" is a message containing information about surplus food that is sent to inform users of the content.

[0963] An "emotion engine" is a technology for recognizing a user's emotional state and identifying the type of emotion the user is feeling through camera or voice input.

[0964] "User device" refers to an electronic device owned by a user, including a smartphone, tablet, computer, etc.

[0965] "Electronic payment instruments" are instruments for making payments electronically, including credit cards, debit cards, electronic money, etc.

[0966] A "means of awarding points" is a system that adds points to a user's account as an incentive when the user performs a specific action.

[0967] This invention combines a system that collects sales data, predicts surplus food based on that data, and notifies users of that information with an emotion engine that recognizes the user's emotional state and optimizes the content and timing of notifications based on that.

[0968] Data collection and prediction processing

[0969] The server periodically collects data from the store's sales database. This data includes product type, quantity, price, and sales date and time, and obtains sales data for the past week or other periods. The collected sales data is stored in an intermediate database, and the server uses a generation AI to predict surplus food. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. Specifically, based on trends shown in the sales data, it can predict, for example, that milk is likely to become a surplus food.

[0970] Emotion recognition by emotion engine

[0971] When a user receives a notification message, the device uses the built-in emotion engine to recognize the user's emotional state through camera and voice input. The emotion engine analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger). The recognized emotion data is sent to the server in real time, and the content and urgency of the notification message are adjusted based on the emotion data. For example, if the emotion engine determines that the user is tired, it generates a message such as "Help us! Refresh yourself with special price milk."

[0972] Generate and send notification messages

[0973] The server creates a list of special sale items based on the prediction results of the generation AI and the emotional data from the emotion engine, and generates appropriate notification messages. These messages include information about the special sale items, recommended phrases based on the user's emotional state, how to purchase, and where to purchase. The generated notification messages are sent to the user's device via the Internet, with the timing optimally set based on the emotional data.

[0974] User purchases and points awarded

[0975] The user receives the notification message and purchases the specified special offer item at the store using an electronic payment method (e.g., electronic money or credit card). Once the purchase is completed, additional points are automatically credited to the user's account. The point crediting process is integrated with the electronic payment system, so the user does not need to take any special steps.

[0976] As a result, the server can collect sales data, predict surplus food using generative AI, recognize user emotions using an emotion engine, and generate and send notification messages in a single process. Users can receive notifications at the appropriate time, complete electronic payments at the same time as purchasing special offers, and receive additional points.

[0977] Specific hardware and software names to be used

[0978] Hardware: Smartphones, tablets, webcams

[0979] Software: Python, Pandas, Request, OpenCV, Generative AI library (pseudonym), Emotion recognition library (pseudonym), LINE Official Account API

[0980] Prompt Sentence Examples

[0981] Sales Data:

[0982] Date, product, quantity, price

[0983] Based on past sales data, please forecast next week's food surplus. Please include product names and estimated quantities in your forecast.

[0984] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0985] Step 1:

[0986] The server periodically collects sales data from the store's sales database. This collection is done by sending queries to the database, with the store's sales database used as input. The server saves the retrieved data (product name, quantity, price, sales date and time, etc.) in an intermediate database. The output is sales data for the past week.

[0987] Step 2:

[0988] The server analyzes the sales data stored in the intermediate database and uses the generation AI to predict surplus food. The input for this step is the sales data collected in step 1. The generation AI performs a time series analysis of the sales data to identify foods that are likely to become surplus in the future. The output is a list of predicted surplus foods.

[0989] Step 3:

[0990] When the user receives a notification message, the device uses an emotion engine to recognize the user's emotional state. The input in this step includes the user's facial expression data and voice data. The device inputs this data into the emotion engine to identify the user's emotional state (such as joy, sadness, or anger). The output is emotion data.

[0991] Step 4:

[0992] The server receives the prediction results from the generation AI and the emotion data sent from the device, and generates a notification message based on them. The input for this step is the predicted list of surplus foods and the user's emotion data. The server adjusts the content and urgency of the notification message according to the emotion data. For example, for a tired user, a message such as "Help us out! Refresh yourself with special price milk" is generated. The output is a notification message.

[0993] Step 5:

[0994] The server sends the generated notification message to the user's device via the Internet. The input for this step is the notification message, and the output is the status of the message being sent to the user's device. Specifically, the message is sent to the user using the LINE Official Account API.

[0995] Step 6:

[0996] The user receives the notification message on their terminal and purchases the specified special offer item at the store. The user uses an electronic payment method to do so. The inputs for this step are the notification message and electronic payment information, and data confirming that the user has purchased the special offer item is output.

[0997] Step 7:

[0998] The terminal automatically adds additional points to the user's account when the user completes the purchase. The input of this step is the purchase completion information, and the output is the points added to the user's account. This allows the point adding process to be integrated with the electronic payment system.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] [Fourth embodiment]

[1003] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1004] 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.

[1005] 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).

[1006] 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.

[1007] 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.

[1008] 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).

[1009] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1010] 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.

[1011] 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.

[1012] 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.

[1013] 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.

[1014] 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.

[1015] 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."

[1016] The present invention provides a generation AI that collects sales data and predicts surplus food based on that data, a system that generates a message notifying the user of the prediction result and sends it to the user's terminal, and a system that awards points when the user makes a purchase using an electronic payment method.

[1017] Data collection and prediction processing

[1018] Server: Periodically collects data from the store's sales database, including the type, quantity, price, and date and time of the sale of the product.

[1019] Server: Collected sales data is stored in an intermediate database, and based on that data, a generation AI is used to predict surplus food. This generation AI analyzes past sales and inventory data to identify foods that are likely to become surplus in the future.

[1020] As a specific example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[1021] Generate and send notification messages

[1022] Server: Based on the prediction results of the generation AI, a list of special sale items is created and a LINE notification message is generated. This message includes the names of the special sale items, their prices, and details on how to purchase them.

[1023] Server: Uses the LINE OA API to send notification messages to the user's device via the LINE bot.

[1024] As a specific example, a notification is generated containing the content "Milk will be sold at a special price due to surplus milk."

[1025] User purchases and points awarded

[1026] User: Receives the notification message and purchases the specified special offer item at the store, using an electronic payment method such as PayPay.

[1027] Terminal: When a purchase is completed, additional points are automatically credited to the user's account. This points crediting process is integrated into the electronic payment system, so users can receive points without any additional procedures.

[1028] For example, when a user purchases milk on sale, they pay with PayPay, and as a result, they automatically receive additional points in addition to the usual points.

[1029] Specific operation of the system

[1030] The server periodically acquires store sales data using a data collection means and stores the information in an intermediate database.

[1031] The generative AI uses the collected data to predict future food surpluses.

[1032] Based on the prediction results, a list of special offers is created and a notification message is generated.

[1033] The server uses the LINE OA API to send a notification message to the user's device.

[1034] Users will receive a notification, purchase special items in the store, and receive additional Purchase Points.

[1035] This will reduce food waste and enable efficient inventory management. The system also encourages consumption by providing incentives to users.

[1036] The processing flow will be explained below.

[1037] Step 1: Data collection

[1038] Server: Periodically collects sales data from the store's sales database. The server queries the database to retrieve sales data for the past week. This sales data includes the product type, quantity, price, and date and time of the sale.

[1039] Step 2: Saving to an intermediate database

[1040] Server: Stores collected sales data in an intermediate database, allowing for the organization and retention of data required for subsequent processing.

[1041] Step 3: Generative AI predictions

[1042] Server: Obtains sales data from the intermediate database and inputs it into the generation AI. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. A list of surplus foods is created as a prediction result and saved in the prediction result database.

[1043] Step 4: Create a Special Offer List

[1044] Server: Retrieves surplus food information from the prediction result database and creates a special sale product list based on that information. The special sale product list includes details such as product name, discount price, and sale period.

[1045] Step 5: Generate a notification message

[1046] Server: Generates notification messages to send to users based on the special offer list. These messages include information about the special offer, how to purchase it, and where it is sold.

[1047] Step 6: Sending notifications

[1048] Server: Using the LINE OA API, the generated notification message is sent to the user's device via a LINE bot. For example, it sends a message such as "Milk is in surplus, so it will be sold at a special price."

[1049] Step 7: Receive and confirm notifications

[1050] Device: Users will receive a notification message on their device to check the special offer information. A notification alert will be displayed on their device to ensure users do not miss the notification.

[1051] Step 8: Shop the specials

[1052] User: After checking the notification message, the user goes to the store and purchases the specified special offer. At this point, the user knows what the special offer is and how to purchase it.

[1053] Step 9: Making an electronic payment

[1054] User: When purchasing special offers, the user pays using an electronic payment method such as PayPay. The user can scan a QR code in the store or complete the payment using the app.

[1055] Step 10: Points awarded

[1056] Server: After the user completes the electronic payment, the server receives a notification from the payment system and automatically credits the additional points to the user's account, allowing the user to receive incentives through points in addition to purchasing special offers.

[1057] In this way, the system efficiently executes a series of processes, from collecting sales data to forecasting, notification, and purchasing and awarding points, thereby reducing food waste and promoting consumption.

[1058] Example 1

[1059] 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."

[1060] Currently, the generation of surplus food has become a serious problem in the food industry. This has led to increased food waste, raising concerns about economic losses and environmental impacts. Furthermore, there is a lack of efficient provision of special sale product information to consumers, making it difficult to promote consumption. Conventional methods have made it difficult to offer surplus food at special prices at the appropriate time and notify consumers.

[1061] 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.

[1062] In this invention, the server includes a means for collecting sales data, a means for using a generation AI to predict surplus food based on the sales data, a means for generating a message notifying the user of information about the surplus food, a means for sending the message to a user's terminal via the Internet, a means for awarding points to a user who receives the notification message when purchasing the surplus food, and a means for the user to purchase the surplus food using an electronic payment method. This makes it possible to efficiently identify surplus food and provide timely discount information to consumers. It also promotes consumption and reduces food waste.

[1063] "Sales data" refers to information about the sales activities of a store, such as the type, quantity, price, and date and time of sales of products sold.

[1064] "Surplus food" is food that may remain unsold to consumers and is expected to be wasted.

[1065] "Generative AI" is a type of artificial intelligence used to predict future situations based on past data, and in this invention is specifically used to predict food surpluses.

[1066] "Notification Message" means a text message generated to inform a consumer about a special offer.

[1067] "User terminal" refers to a device carried by a consumer for receiving notification messages, such as a smartphone, tablet, or computer.

[1068] "Means for transmitting through the Internet" refers to a method for transmitting and receiving information through a network, and is particularly used to send notification messages to users' terminals.

[1069] "Electronic payment instruments" are methods for making payments digitally without using cash, including credit cards, electronic money, and mobile payment apps.

[1070] "Points" refers to bonus points that are given to consumers when they purchase specially priced items, and can be used for future purchases.

[1071] A "special sale product list" is a list generated based on predicted surplus food, which contains detailed information such as products to be sold at special prices, their prices, and the sales period.

[1072] This system uses a generative AI model to collect sales data and predict food surpluses based on that data. It also generates notification messages based on the prediction results and sends them to users' devices. Furthermore, it provides a mechanism for rewarding users with points when they purchase specially priced items using electronic payment methods.

[1073] Data collection and intermediate database storage

[1074] The server periodically collects data from the store's sales database. This data includes information such as the type, quantity, price, and date and time of the sale of the product sold. For example, a periodic batch process is performed every day at midnight to collect hourly sales data. This data is then saved in an intermediate database. When saving, the data is checked for consistency to ensure that no invalid data is mixed in.

[1075] Food surplus forecast

[1076] The server formats the sales data stored in the intermediate database into a format that is easy for the generative AI model to handle. For example, it formats the sales data for the past week as time series data. It then inputs the formatted data into the generative AI model. It sends a prompt request saying, "Based on the sales data for the past week, please predict which foods are most likely to become surplus next." The prediction results from the generative AI model include a list of foods that are likely to become surplus and the probability of this happening.

[1077] Example prompt: "Based on sales data from the past week, please predict which foods are likely to be in surplus in the future. The sales data is as follows: (data content)."

[1078] Generate and send notification messages

[1079] The server creates a list of special sale items based on the surplus food prediction results. This list includes the product name, special price, and sale period. For example, a list containing information such as "Milk - Special price 100 yen - Sale period: This weekend" is created. Next, a LINE notification message is generated based on this list. The LINE OA API is used to send the notification message to the user's device. For example, a message such as "Milk will be in surplus! On sale this weekend for a special price of 100 yen" is generated and sent by the LINE bot.

[1080] User purchases and points awarded

[1081] The user receives the notification message in the LINE app. For example, "Check the notification about the milk special sale on LINE." After that, the user visits the store and purchases the special sale item. At this time, the user uses an electronic payment method. For example, "Purchase milk with PayPay." After the purchase is completed on the device, points are automatically added to the user's account via the electronic payment system. For example, "Additional points will be automatically added after payment is completed with PayPay."

[1082] This system can carry out an integrated process from collecting sales data to predicting surplus food, notifying consumers of special offers, and encouraging them to purchase and receive points. This makes it possible to efficiently identify surplus food and provide timely special offer information to consumers. It is also a system that can encourage consumption and reduce food waste.

[1083] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1084] Step 1:

[1085] The server periodically collects data from the store's sales database. The input data includes information on the type, quantity, price, and date and time of the sale of the product sold. Specifically, a batch process is executed at midnight every day to collect hourly sales data. This batch process uses SQL queries to extract specified data from the sales database and saves the data in an intermediate database.

[1086] Step 2:

[1087] The server saves the collected sales data in an intermediate database. The input data is the sales data collected in step 1. Specifically, it performs an insert operation into the database and performs a data consistency check. For example, it checks whether the product code and quantity are valid. This saved data is used in subsequent analysis processing.

[1088] Step 3:

[1089] The server formats the sales data stored in the intermediate database. The input data is the sales data stored in the intermediate database, and the output data is data converted into a format that is easy for the generative AI model to handle. Specifically, the server formats the sales data for the past week as time-series data to create a dataset for input to the generative AI model. This includes sales volume by date and time and aggregated data by product category.

[1090] Step 4:

[1091] The server inputs the formatted data into the generative AI model. The input data is the dataset created in step 3. The request is sent as a prompt: "Based on sales data from the past week, please predict the foods that are most likely to become surplus next." The output data is the prediction result from the generative AI model, which includes a list of surplus foods and their probabilities. In this prediction process, the generative AI model analyzes past sales trends and inventory data and returns specific prediction results.

[1092] Step 5:

[1093] The server creates a list of special sale items based on the prediction results of the generative AI model. The input data is the prediction results from step 4, and a list of items to be sold at a special price is created. This list includes the product name, special price, and sale period. For example, a list such as "Milk - Special price 100 yen - Sale period: this weekend" is generated. This list is used to generate subsequent notification messages.

[1094] Step 6:

[1095] The server generates a message for LINE notification based on the special sale item list. The input data is the special sale item list created in step 5, and the output data is the notification message. For example, it generates a message with the content "We have a surplus of milk! It will be on sale this weekend for 100 yen." This message includes the name of the special sale item, its price, and details on how to purchase it.

[1096] Step 7:

[1097] The server uses the LINE OA API to send a notification message to the user's device. The input data is the notification message generated in step 6, and the output data is the message sent to the user's device. The notification message is sent to User A's device via the LINE bot, and a confirmation message is received. This step allows the user to receive information about special offers in real time.

[1098] Step 8:

[1099] The user receives the sent notification message in the LINE app. The input data is the notification message sent in step 7, and the output data is the message displayed in the user's LINE app. For example, "Check LINE for notifications about milk special sale."

[1100] Step 9:

[1101] The user visits the store and purchases the special sale item that was notified to them. At this time, they use an electronic payment method. The input data is the information in the notification message, and the output data is the special sale item that was purchased. For example, "Purchase milk with PayPay."

[1102] Step 10:

[1103] After the purchase is completed, the terminal automatically adds points to the user's account via the electronic payment system. The input data is the purchase completion information, and the output data is the points added to the user's account. For example, "After completing payment with PayPay, additional points will be automatically added."

[1104] (Application example 1)

[1105] 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."

[1106] The present invention relates to a system that uses sales data to predict surplus food, notifies customers of special offers, and encourages them to purchase in order to improve the efficiency of inventory management and consumer marketing methods in food delivery services. Conventional methods have made it difficult to predict surplus food, leading to insufficient inventory management and food waste reduction. Furthermore, they have not been effective in notifying customers of special offers and providing incentives to purchase.

[1107] 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.

[1108] In this invention, the server includes a means for collecting sales data, a means for using a generation AI to predict surplus food, a means for notifying users of special offers, a means for sending messages to users' devices, and a means for selling special offers. The server first predicts surplus food based on sales data and notifies users of the information as special offers. This makes it possible to improve the efficiency of inventory management and reduce food waste in food delivery services. Furthermore, by notifying users of special offers and providing incentives for purchases, the server can encourage consumers to purchase and improve the efficiency of the entire service.

[1109] "Sales data" refers to information related to the sale of products, and specifically includes information on the type, quantity, price, and date and time of the sale of the product.

[1110] "Generative AI" is an artificial intelligence technique that uses machine learning algorithms to analyze past data and predict specific future outcomes.

[1111] "Surplus food" refers to food that has been produced or stocked in excess of projected sales, is nearing its expiration date, or is not expected to be sold.

[1112] "Message" means an electronic communication that notifies you of special offers or other important information and may contain text, images, or links.

[1113] A "user device" is an electronic device, such as a smartphone, tablet, or computer, that is capable of connecting to the Internet and receiving communications.

[1114] An "electronic payment instrument" is a method by which a user can pay for goods or services digitally, and specifically uses electronic money, credit cards, debit cards, etc.

[1115] A "means of awarding points" is a system in which points are added to a user's account as a reward when the user meets certain conditions, and the points can be used for discounts or special offers at a later date.

[1116] "Special price items" are items offered at a lower price than the regular selling price, and are set up to promote the sale of surplus food and other items.

[1117] "Communications Network" means the Internet or other digital communications infrastructure used to transmit and receive data and to move information between users and systems.

[1118] This invention relates to a system for improving the efficiency of inventory management and supporting marketing activities in food delivery services. The system program and its processing will be described in detail below.

[1119] System Program

[1120] The system consists of a server, a user's device, and a generative AI model. The server collects and analyzes sales data and predicts surplus food. The user's device receives notifications and is used to purchase special offers. The generative AI model predicts surplus food based on past sales and inventory data.

[1121] Data collection and prediction processing

[1122] The server periodically collects store sales data from the database. This collected data includes the type, quantity, price, and sales date and time of the products sold. The collected sales data is stored in an intermediate database, and a generative AI is used to predict surplus food based on that data. The generative AI model uses a machine learning algorithm to analyze PastData and StockData to identify foods that are likely to become surplus next.

[1123] Generate and send notification messages

[1124] The server creates a list of special sale items based on the predictions made by the AI ​​and generates a notification message containing the names of the special sale items, their prices, and details on how to purchase them. The server then sends the notification message to the user's device via a communications network.

[1125] User purchases and points awarded

[1126] The user receives a notification message and uses their device to check the displayed special offers. They then select the special offer and complete the purchase using an electronic payment method. Once the purchase is complete, additional points are automatically credited to the user's account. This process is integrated into electronic payment systems such as electronic money and credit cards, so users can receive points without any special procedures.

[1127] Specific examples

[1128] For example, if the server collects a week's worth of sales data and, after analyzing it, predicts that milk is likely to become a surplus food item, a list of special sale items is created. A notification message stating, "Milk will be sold at a special price due to surplus milk," is sent to the user's device. The user receives the notification, uses their smartphone to purchase the special sale items, and pays with an electronic payment method. As a result, additional points are automatically awarded in addition to the usual points.

[1129] Prompt Sentence Examples

[1130] As a concrete example, the following prompt sentence is input to the generative AI model:

[1131] "Based on sandwich sales data from the past week, please predict which foods are likely to be in surplus the next day. Based on your prediction, please briefly explain why you think there is a high probability that sandwiches will be in surplus tomorrow."

[1132] This allows the server to efficiently execute a series of processes, from data collection to generating and sending notification messages, and from users making purchases to awarding points. By having the entire system work together, it becomes possible to streamline inventory management for food delivery services and significantly reduce food waste.

[1133] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1134] Step 1:

[1135] The server collects store sales data from the database. Specifically, it obtains information such as the type of product sold, quantity, price, and sales date and time, and stores this in an intermediate database. The inputs are database connection information and queries, and the output is the obtained sales data. This data collection operation accumulates the necessary analysis data.

[1136] Step 2:

[1137] The server inputs the collected sales data into the generative AI model, which then analyzes past sales and inventory data to predict surplus food. The inputs are sales and inventory data, and the output is a predicted surplus food list. The generative AI model uses machine learning algorithms to process and calculate the data and generate a specific surplus food list.

[1138] Step 3:

[1139] The server generates a list of special sale items based on the prediction results of the generative AI model. It lists the predicted surplus food items as special sale items and creates a notification message containing detailed information about them. The input is the predicted surplus food list, and the output is a notification message about the special sale items. Specifically, the message content is constructed using a notification message generation algorithm.

[1140] Step 4:

[1141] The server sends a special offer notification message to the user's device. Since the message is sent via a communication network, an internet connection is required. The input is the special offer notification message and the user's device information, and the output is the sent notification message. Specifically, the message is sent using a communication API.

[1142] Step 5:

[1143] The user checks the received notification message on their device and selects a special offer. The input is the notification message, and the output is confirmation of the user's intention to purchase. Specifically, this involves the user operating their device to select a special offer and pressing the purchase button.

[1144] Step 6:

[1145] The user uses a terminal to complete the purchase of a special offer item using an electronic payment method. The inputs are special offer item information and payment information, and the output is purchase completion information and point award information. In specific operations, payment is made using an electronic payment system (e.g., electronic money, credit card), and points are automatically awarded at that time.

[1146] Step 7:

[1147] The server receives the payment completion information and awards additional points to the user. The input is the user's payment completion information and the point awarding rules, and the output is the updated user point information. Specifically, it updates the point management system and awards additional points to the user's account.

[1148] This series of processing steps is expected to improve the efficiency of inventory management for food delivery services, reduce food waste, and increase purchasing incentives for consumers.

[1149] 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.

[1150] The present invention provides a system that predicts surplus food based on sales data and notifies users of this information, and combines it with an emotion engine that recognizes the user's emotional state and optimizes the content and timing of notifications based on that.

[1151] Data collection and prediction processing

[1152] Server: Periodically collects data from the store's sales database. The server queries the database to retrieve sales data for the past week, including product type, quantity, price, and sales date and time.

[1153] Server: Collected sales data is stored in an intermediate database, and based on that data, a generation AI is used to predict surplus food. The generation AI analyzes past sales and inventory data to identify foods that are likely to become surplus in the future.

[1154] As a specific example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[1155] Emotion recognition by emotion engine

[1156] Device: When a user receives a notification message, the emotion engine on the user's device recognizes the user's emotional state through camera and voice input. During this process, the device analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger).

[1157] Device: The recognized emotion data is sent to the server in real time, and the content and urgency of the notification message are adjusted. Based on this information, the server generates a message appropriate to the user's emotional state.

[1158] As a specific example, if the emotion engine determines that the user is tired, it will adjust the content of the notification message to something like, "Help us if you're tired! Refresh yourself with milk at a special price."

[1159] Generate and send notification messages

[1160] Server: Based on the prediction results of the generative AI and the emotional data from the emotion engine, the server creates a list of special sale items and generates appropriate notification messages. These messages include information about the special sale items, recommended phrases based on the user's emotional state, how to purchase, and where to purchase.

[1161] Server: Using the LINE OA API, the generated notification message is sent to the user's device via the LINE bot, adjusting the timing to ensure that the notification is sent at the appropriate time.

[1162] User purchases and points awarded

[1163] User: Receives the notification message and purchases the specified special offer item at the store, using an electronic payment method (e.g., PayPay).

[1164] Terminal: When a purchase is completed, additional points will be automatically credited to the user's account. The points crediting process is integrated with the electronic payment system, so users can receive points without any special procedures.

[1165] For example, when a user purchases milk on sale, they pay with PayPay, and as a result, they automatically receive additional points in addition to the usual points.

[1166] Specific operation of the entire system

[1167] Server: Collects sales data, predicts surplus food using generative AI, recognizes user emotions using an emotion engine, and generates and sends notification messages.

[1168] Device: Recognizes the user's emotional state in real time and sends that information to the server, allowing the user to receive notifications at the appropriate time and with the right content, and purchase special offers in stores.

[1169] User: Purchase special offer items and complete electronic payment at the same time to receive additional points.

[1170] As a result, the present invention realizes a food waste reduction system that takes user emotions into consideration, enabling more efficient inventory management and improved consumer satisfaction.

[1171] The processing flow will be explained below.

[1172] Step 1: Data collection

[1173] Server: Periodically collects data from the store's sales database. The server queries the database to retrieve sales data for the past week, including product type, quantity, price, and sales date and time.

[1174] Step 2: Saving to an intermediate database

[1175] Server: Stores collected sales data in an intermediate database, allowing for the organization and retention of data required for subsequent processing.

[1176] Step 3: Generative AI predictions

[1177] Server: Obtains sales data from the intermediate database and inputs it into the generation AI. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. A list of surplus foods is created as a prediction result and saved in the prediction result database.

[1178] For example, a server can collect a week's worth of sales data, analyze it, and predict that milk is likely to become a surplus food item.

[1179] Step 4: Create a Special Offer List

[1180] Server: Retrieves surplus food information from the prediction result database and creates a special sale product list based on that information. The special sale product list includes details such as product name, discount price, and sale period.

[1181] Step 5: Obtaining emotion recognition data

[1182] On your device: When receiving a notification message, your device will use the camera and microphone to recognize your emotions. Your device will analyze your facial expressions and tone of voice to determine your current emotional state.

[1183] Step 6: Sending Emotion Data

[1184] Device: Recognized emotion data is sent to the server in real time, and the server uses the emotion data as a basis for optimizing notification messages.

[1185] Step 7: Generate a notification message

[1186] Server: Based on the prediction results of the generation AI and the emotion data sent from the emotion engine, a notification message for the special sale is generated. This message contains information about the special sale, recommended phrases based on the user's emotional state, and details on how to purchase.

[1187] For example, if the emotion engine determines that the user is tired, it will adjust the content of the notification message to something like, "Help us if you're tired! Refresh yourself with milk at a special price."

[1188] Step 8: Sending notifications

[1189] Server: Uses the LINE OA API to send the generated notification message to the user's device via a LINE bot.

[1190] Step 9: Receive and review notifications

[1191] On the device: The user receives a notification message to view the special offer and recommendations. The notification message is displayed on the device, immediately alerting the user.

[1192] Step 10: Shop the specials

[1193] User: After checking the notification message, the user goes to the store and purchases the specified special offer item. The user checks the shelves for special offers at the store and picks up the item.

[1194] Step 11: Making an electronic payment

[1195] User: When purchasing special offers, the user pays using an electronic payment method (e.g., PayPay). The user scans the QR code or completes the payment using the app.

[1196] Step 12: Awarding points

[1197] Server: After the user completes the electronic payment, the server receives a notification from the payment system and automatically adds additional points to the user's account. The user can receive the points without taking any special steps.

[1198] In this way, the present invention is a system that collects sales data, uses AI to generate and predict surplus food, notifies users of special offers based on that data, and also customizes the system by recognizing users' emotions, as well as the final purchase and point awarding process, thereby achieving efficient inventory management, reducing food waste, and providing a purchasing experience that highly satisfies consumers.

[1199] Example 2

[1200] 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."

[1201] Conventional food waste reduction systems predict surplus food based on sales data, but do not optimize notifications to take into account the user's emotional state. This can make it difficult for users to properly receive notifications and take action at the appropriate time, making it difficult to achieve effective food waste reduction. Furthermore, because emotion recognition technology is not applied to increase users' purchasing motivation, there is also the issue of not being able to sufficiently improve consumer satisfaction.

[1202] 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.

[1203] In this invention, the server includes a means for collecting sales data, a means for using artificial intelligence to predict surplus food based on the sales data, and a means for generating a message notifying the user of information about the surplus food. It also includes a means for recognizing the user's emotional state, a means for optimizing the content and timing of the notification message based on the recognized emotional state, and a means for awarding points when the user purchases the surplus food using an electronic payment method. This enables appropriate notifications that take the user's emotions into consideration, thereby enabling effective food waste reduction and improved consumer satisfaction.

[1204] "Sales data" is a record of product sales in a store, and includes product type, quantity, price, sales date and time, etc.

[1205] "Artificial intelligence" is a technology that allows computers to mimic human intelligence to analyze data and make predictions, and includes machine learning and deep learning.

[1206] A "notification message" is information sent to a user, and includes information about special offers and purchase recommendations.

[1207] "User's device" refers to a communication device owned by the user, such as a smartphone or tablet.

[1208] "Emotional state" refers to the user's psychological and emotional state, including states such as joy, sadness, fatigue, and anger.

[1209] "Electronic payment instruments" are payment methods made using digital technology, including credit cards, debit cards, and smartphone payment apps.

[1210] "Points" refers to bonuses or benefits added to a user's account based on certain conditions when the user purchases special offers.

[1211] This invention provides a system that predicts surplus food based on sales data and notifies users of this information, recognizing the emotional state of the user and optimizing the content and timing of notifications based on that. This system operates in cooperation with the server, terminal, and user components.

[1212] Server-based sales data collection and forecasting

[1213] The server periodically collects data from the store's sales database. Specifically, the server sends a query to the database to obtain sales data (product type, quantity, price, and sales date and time) for the past week. This data is stored in the intermediate database.

[1214] The server then runs a generative AI (artificial intelligence) based on this data to predict surplus food. The generative AI uses machine learning algorithms to analyze past sales and inventory data to identify foods that are likely to become surplus in the future. For example, the server can analyze a week's worth of sales data and predict that "milk is likely to become a surplus food."

[1215] Device-based emotional state recognition

[1216] When a user receives a notification message, the device recognizes the user's emotional state through camera or voice input. During this process, the device analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger, fatigue).

[1217] The recognized emotion data is sent to the server in real time. This allows the server to adjust the content and urgency of the notification message. For example, if the emotion engine determines that the user is tired, it can change the content of the notification message to something like, "Help us if you're tired! Refresh yourself with special price milk."

[1218] Server generation and sending of notification messages

[1219] The server creates a list of special sale items based on the predictions of the AI ​​and the emotional data sent from the device, and generates an appropriate notification message, which includes information about the special sale items, recommended phrases based on the user's emotional state, how to purchase them, and where they are sold.

[1220] The server uses the LINE OA API to generate notification messages, which are then sent to the user's device via a LINE bot, with the notification time adjusted accordingly.

[1221] User purchases and points awarded

[1222] The user receives the notification message and purchases the specified special offer item at the store using an electronic payment method (for example, a smartphone payment app).

[1223] Once a purchase is completed, the terminal automatically adds points to the user's account. The point adding process is integrated with the electronic payment system, so users can receive points without any special procedures. For example, when a user purchases milk on sale, they pay with an electronic payment app. As a result, additional points are automatically added to the usual points.

[1224] Specific prompt examples

[1225] Analyze sales data from the past week (e.g., 20 bottles of milk, 50 loaves of bread) to predict food surpluses. Also, adjust notification messages based on the user's emotional state (tiredness, joy, etc.).

[1226] This will enable the realization of a notification system that takes user emotions into consideration, effectively reducing food waste and improving consumer satisfaction.

[1227] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1228] Step 1:

[1229] The server collects sales data

[1230] The server queries the store's sales database to retrieve sales data for the past week.

[1231] Input: Sales database

[1232] Output: Sales data for the past week (product type, quantity, price, sales date and time)

[1233] As a specific example, collect data such as "Milk: 20 bottles, Bread: 50 pieces."

[1234] Step 2:

[1235] The server stores the data in an intermediate database

[1236] The server stores the collected data in an intermediate database.

[1237] Input: Collected sales data

[1238] Output: Sales data stored in an intermediate database

[1239] As a concrete example, the collected data of "Milk: 20 bottles, Bread: 50 pieces" is stored in an intermediate database.

[1240] Step 3:

[1241] Server generates AI to predict surplus food

[1242] The server runs the AI ​​based on the data stored in the intermediate database. The AI ​​uses machine learning algorithms to analyze past sales and inventory data to identify foods that are likely to become surplus in the future.

[1243] Input: Sales data stored in the intermediate database

[1244] Output: Predicted food surplus

[1245] As a specific example, the generative AI predicts that "milk is likely to become a surplus food."

[1246] Step 4:

[1247] The device recognizes the user's emotional state

[1248] When a user receives a notification message, the device uses a camera and voice input to recognize the user's emotional state. The device analyzes facial expressions and tone of voice to identify emotions.

[1249] Input: User's facial expression, tone of voice

[1250] Output: User emotion data (happiness, sadness, anger, tiredness, etc.)

[1251] For example, if a user says, "I'm tired today," the device will recognize this as "tired."

[1252] Step 5:

[1253] The device sends emotion data to the server.

[1254] The device transmits the recognized emotion data to the server in real time.

[1255] Input: User emotion data

[1256] Output: Emotion data sent to the server

[1257] As a specific example, emotion data such as "tired" is sent to the server.

[1258] Step 6:

[1259] The server generates a notification message

[1260] The server creates a list of special offers based on the predictions made by the generation AI and the emotional data sent from the device, and generates appropriate notification messages.

[1261] Input: Generative AI prediction results, emotion data from the device

[1262] Output: Notification message

[1263] As a specific example, it generates a message such as "Help us if you're tired! Refresh yourself with special price milk."

[1264] Step 7:

[1265] The server uses the LINE OA API to send a notification message.

[1266] The server generates a notification message using the LINE OA API and sends it to the user's device via a LINE bot.

[1267] Input: Notification message

[1268] Output: Notification message sent to the user's terminal

[1269] As a specific example, the message "Help us if you're tired! Refresh with special price milk" can be sent through a LINE bot.

[1270] Step 8:

[1271] User receives notification message and purchases special offer

[1272] The user receives the notification message on the terminal and purchases the specified special offer item at the store. At this time, the user uses an electronic payment method (for example, a smartphone payment app).

[1273] Input: Notification message

[1274] Output: Special offer purchase and payment data

[1275] As a specific example, a user who receives a notification can purchase milk at a discount at a store using smartphone payment.

[1276] Step 9:

[1277] The terminal awards points

[1278] Once the purchase is complete, the device automatically credits the points to the user's account.

[1279] Input: Purchase and payment data

[1280] Output: Points awarded to the user's account

[1281] For example, after a user purchases milk, additional points are automatically awarded.

[1282] This will enable a notification system that takes user emotions into account through consecutive processing steps, effectively reducing food waste and improving consumer satisfaction.

[1283] (Application example 2)

[1284] 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."

[1285] Current inventory management systems often lack the ability to efficiently predict surplus food and appropriately notify users of this information. Furthermore, uniform notifications that do not take into account the user's emotional state can reduce engagement and reduce purchasing intent. Furthermore, the timing and content of notifications are not optimized, resulting in a poor user experience. As a result, food waste reduction and efficient inventory management are not fully achieved, and consumer satisfaction is declining.

[1286] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting sales data, means for using a generation AI to predict surplus food based on past sales data and inventory data, means for using an emotion engine to recognize the user's emotional state, means for optimizing the content and timing of notifications based on data from the emotion engine, means for generating messages notifying users of information about surplus food and sending them to the user's terminal via the Internet, and means for awarding points when the user purchases surplus food using an electronic payment method. This enables a consistent process from predicting surplus food to optimally notifying users, actual purchases, and providing incentives. This reduces food waste and streamlines inventory management, further improving user satisfaction and purchasing motivation.

[1287] "Sales data" refers to data that includes information about the sale of products in a store, including the type, quantity, price, and date and time of the sale of the product.

[1288] "Generative AI" is an artificial intelligence that analyzes past sales and inventory data to predict foods that are likely to become surplus in the future.

[1289] "Surplus food" is food that may remain in excess inventory in the future based on sales and inventory data.

[1290] A "notification message" is a message containing information about surplus food that is sent to inform users of the content.

[1291] An "emotion engine" is a technology for recognizing a user's emotional state and identifying the type of emotion the user is feeling through camera or voice input.

[1292] "User device" refers to an electronic device owned by a user, including a smartphone, tablet, computer, etc.

[1293] "Electronic payment instruments" are instruments for making payments electronically, including credit cards, debit cards, electronic money, etc.

[1294] A "means of awarding points" is a system that adds points to a user's account as an incentive when the user performs a specific action.

[1295] This invention combines a system that collects sales data, predicts surplus food based on that data, and notifies users of that information with an emotion engine that recognizes the user's emotional state and optimizes the content and timing of notifications based on that.

[1296] Data collection and prediction processing

[1297] The server periodically collects data from the store's sales database. This data includes product type, quantity, price, and sales date and time, and obtains sales data for the past week or other periods. The collected sales data is stored in an intermediate database, and the server uses a generation AI to predict surplus food. The generation AI analyzes past sales data and inventory data to identify foods that are likely to become surplus in the future. Specifically, based on trends shown in the sales data, it can predict, for example, that milk is likely to become a surplus food.

[1298] Emotion recognition by emotion engine

[1299] When a user receives a notification message, the device uses the built-in emotion engine to recognize the user's emotional state through camera and voice input. The emotion engine analyzes the user's facial expressions and tone of voice to identify the type of emotion (e.g., joy, sadness, anger). The recognized emotion data is sent to the server in real time, and the content and urgency of the notification message are adjusted based on the emotion data. For example, if the emotion engine determines that the user is tired, it generates a message such as "Help us! Refresh yourself with special price milk."

[1300] Generate and send notification messages

[1301] The server creates a list of special sale items based on the prediction results of the generation AI and the emotional data from the emotion engine, and generates appropriate notification messages. These messages include information about the special sale items, recommended phrases based on the user's emotional state, how to purchase, and where to purchase. The generated notification messages are sent to the user's device via the Internet, with the timing optimally set based on the emotional data.

[1302] User purchases and points awarded

[1303] The user receives the notification message and purchases the specified special offer item at the store using an electronic payment method (e.g., electronic money or credit card). Once the purchase is completed, additional points are automatically credited to the user's account. The point crediting process is integrated with the electronic payment system, so the user does not need to take any special steps.

[1304] As a result, the server can collect sales data, predict surplus food using generative AI, recognize user emotions using an emotion engine, and generate and send notification messages in a single process. Users can receive notifications at the appropriate time, complete electronic payments at the same time as purchasing special offers, and receive additional points.

[1305] Specific hardware and software names to be used

[1306] Hardware: Smartphones, tablets, webcams

[1307] Software: Python, Pandas, Request, OpenCV, Generative AI library (pseudonym), Emotion recognition library (pseudonym), LINE Official Account API

[1308] Prompt Sentence Examples

[1309] Sales Data:

[1310] Date, product, quantity, price

[1311] Based on past sales data, please forecast next week's food surplus. Please include product names and estimated quantities in your forecast.

[1312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1313] Step 1:

[1314] The server periodically collects sales data from the store's sales database. This collection is done by sending queries to the database, with the store's sales database used as input. The server saves the retrieved data (product name, quantity, price, sales date and time, etc.) in an intermediate database. The output is sales data for the past week.

[1315] Step 2:

[1316] The server analyzes the sales data stored in the intermediate database and uses the generation AI to predict surplus food. The input for this step is the sales data collected in step 1. The generation AI performs a time series analysis of the sales data to identify foods that are likely to become surplus in the future. The output is a list of predicted surplus foods.

[1317] Step 3:

[1318] When the user receives a notification message, the device uses an emotion engine to recognize the user's emotional state. The input in this step includes the user's facial expression data and voice data. The device inputs this data into the emotion engine to identify the user's emotional state (such as joy, sadness, or anger). The output is emotion data.

[1319] Step 4:

[1320] The server receives the prediction results from the generation AI and the emotion data sent from the device, and generates a notification message based on them. The input for this step is the predicted list of surplus foods and the user's emotion data. The server adjusts the content and urgency of the notification message according to the emotion data. For example, for a tired user, a message such as "Help us out! Refresh yourself with special price milk" is generated. The output is a notification message.

[1321] Step 5:

[1322] The server sends the generated notification message to the user's device via the Internet. The input for this step is the notification message, and the output is the status of the message being sent to the user's device. Specifically, the message is sent to the user using the LINE Official Account API.

[1323] Step 6:

[1324] The user receives the notification message on their terminal and purchases the specified special offer item at the store. The user uses an electronic payment method to do so. The inputs for this step are the notification message and electronic payment information, and data confirming that the user has purchased the special offer item is output.

[1325] Step 7:

[1326] The terminal automatically adds additional points to the user's account when the user completes the purchase. The input of this step is the purchase completion information, and the output is the points added to the user's account. This allows the point adding process to be integrated with the electronic payment system.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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.

[1331] 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.

[1332] 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.

[1333] 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).

[1334] 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.

[1335] 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."

[1336] 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.

[1337] 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).

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] The following is further disclosed regarding the above embodiment.

[1349] (Claim 1)

[1350] a means of collecting sales data;

[1351] A means for using a generating AI to predict surplus food based on the sales data;

[1352] means for generating a message notifying information about the surplus food;

[1353] means for transmitting said message to a user terminal;

[1354] a means for awarding points when a user purchases the surplus food using an electronic payment means;

[1355] A system including:

[1356] (Claim 2)

[1357] 2. The system according to claim 1, wherein the means for sending the notification message sends the notification message to the user's terminal via the Internet.

[1358] (Claim 3)

[1359] The system of claim 1, wherein the generating AI includes means for predicting surplus food based on past sales data and inventory data.

[1360] "Example 1"

[1361] (Claim 1)

[1362] a means of collecting sales data;

[1363] A means for using a generating AI to predict surplus food based on the sales data;

[1364] means for generating a message notifying information about the surplus food;

[1365] means for transmitting said message to a user terminal over the Internet;

[1366] a means for awarding points to a user who receives the notification message when the user purchases the surplus food;

[1367] a means for a user to purchase said surplus food using an electronic payment means;

[1368] A system including:

[1369] (Claim 2)

[1370] 10. The system of claim 1, further comprising means for generating a special offer list based on sales data and forecast results to generate notification messages.

[1371] (Claim 3)

[1372] The system of claim 1, wherein the generating AI includes means for predicting surplus food based on past sales data and inventory data.

[1373] "Application Example 1"

[1374] (Claim 1)

[1375] a means of collecting sales data;

[1376] A means for using a generating AI to predict surplus food based on the sales data;

[1377] means for generating a message notifying information about the surplus food;

[1378] means for transmitting said message to a user terminal;

[1379] a means for awarding points when a user purchases the surplus food using an electronic payment means;

[1380] means for notifying said user of special offers;

[1381] means for selling special sale items over a communication network using the sales data;

[1382] A system including:

[1383] (Claim 2)

[1384] 2. The system according to claim 1, wherein the means for sending the notification message sends the notification message to the user's terminal via the Internet.

[1385] (Claim 3)

[1386] The system of claim 1, wherein the generating AI includes means for predicting surplus food based on past sales data and inventory data.

[1387] "Example 2: Combining Emotion Engines"

[1388] (Claim 1)

[1389] a means of collecting sales data;

[1390] A means for using artificial intelligence to predict surplus food based on the sales data;

[1391] means for generating a message notifying information about the surplus food;

[1392] means for transmitting said message to a user terminal;

[1393] a means for recognizing the emotional state of a user;

[1394] means for optimizing the content and timing of notification messages based on the perceived emotional state;

[1395] a means for awarding points when a user purchases the surplus food using an electronic payment means;

[1396] A system including:

[1397] (Claim 2)

[1398] 2. The system according to claim 1, wherein the means for sending the notification message sends the notification message to the user's terminal via the Internet.

[1399] (Claim 3)

[1400] 10. The system of claim 1, wherein the artificial intelligence includes means for predicting surplus food based on historical sales data and inventory data.

[1401] (Claim 4)

[1402] 10. The system of claim 1, further comprising means for recognizing the user's emotional state from facial expressions and tone of voice.

[1403] (Claim 5)

[1404] 10. The system of claim 1, further comprising means for transmitting the recognized emotional state to a server in real time to optimize the content and timing of notification messages.

[1405] "Application example 2 when combining emotion engines"

[1406] (Claim 1)

[1407] a means of collecting sales data;

[1408] A means for using a generating AI to predict surplus food based on the sales data;

[1409] means for generating a message notifying information about the surplus food;

[1410] means for using an emotion engine to recognize the emotional state of a user;

[1411] means for optimizing notification content and timing based on data from the emotion engine;

[1412] means for transmitting said message to a user terminal;

[1413] a means for awarding points when a user purchases the surplus food using an electronic payment means;

[1414] A system including:

[1415] (Claim 2)

[1416] 2. The system according to claim 1, wherein the means for sending the notification message sends the notification message to the user's terminal via the Internet.

[1417] (Claim 3)

[1418] The system of claim 1, wherein the generating AI includes means for predicting surplus food based on past sales data and inventory data. [Explanation of symbols]

[1419] 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. a means of collecting sales data; A means for using a generating AI to predict surplus food based on the sales data; means for generating a message notifying information about the surplus food; means for transmitting said message to a user terminal; a means for awarding points when a user purchases the surplus food using an electronic payment means; A system including:

2. 2. The system according to claim 1, wherein the means for sending the notification message sends the notification message to the user's terminal via the Internet.

3. The system of claim 1, wherein the generating AI includes means for predicting surplus food based on past sales data and inventory data.

Images