System

Abstract

A system is provided.SOLUTION: The system further includes means for storing the analyzed results in the database and making the analyzed results accessible to a user, means for generating an alert for an ingredient approaching an expiration date, means for displaying the analyzed results of food loss in a form of a graph or a report on a dashboard of the user, and means for logging in a training platform of the user to view and learn educational materials and training videos. AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the restaurant industry, food waste due to over-preparation, over-purchasing, and expired ingredients has become a serious problem. Such food waste not only results in wasted food costs, but also places a significant burden on the environment. Furthermore, the recent rise in prices has led to rising ingredient costs, putting unnecessary costs on restaurant management. Conventional systems make it difficult to properly manage inventory and predict purchase quantities, preventing efficient management. Therefore, the present invention aims to provide a system that solves the above-mentioned problems and enables appropriate adjustment of purchase quantities and reduction of food waste. [Means for solving the problem]

[0005] This invention provides a means for collecting a restaurant's past sales data, purchasing data, and food waste data and storing this data in a database. It also provides a means for preprocessing the collected data, a means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item, a means for saving the analysis results in a database and making them accessible to users, and a means for generating alerts for food items approaching their expiration date. It also provides a means for users to use a dashboard to view the food waste analysis results in graphs and reports, and a means for users to log in to a training platform and view and learn from educational materials and training videos.

[0006] This system will enable restaurants to properly manage inventory and predict purchasing quantities, reducing food waste. This will reduce operating costs, enable sustainable operations, and is also expected to contribute to environmental protection.

[0007] "Past restaurant sales data" is information about the sales amount and quantity of each menu item sold in the past at the restaurant.

[0008] "Purchase data" refers to information about the quantity, price, purchase date, etc. of ingredients and raw materials purchased by a restaurant.

[0009] "Food waste data" is information regarding the quantity and reasons for the disposal of unused or unused food ingredients.

[0010] A "database" is a digital data warehouse that organizes and stores data collected by the system so that it can be searched and analyzed later.

[0011] "Preprocessing" is the process of organizing and formatting collected data so that it can be analyzed appropriately, such as by filling in missing values ​​and correcting outliers.

[0012] An "AI model" is an artificial intelligence algorithm used to analyze patterns and trends based on collected data and make predictions and decisions.

[0013] "Causes of food waste" refers to the factors and reasons why food ingredients are wasted, including over-purchasing and over-preparing.

[0014] An "alert" is a warning message or notification issued by the system when food ingredients are approaching their expiration date.

[0015] A "dashboard" is an interface that allows users to visually check various data and analysis results.

[0016] "Training Platform" means an online system for employees to learn through educational materials and training videos.

[0017] "Weather Data API" means an application programming interface for obtaining external weather data.

[0018] "Visit history" refers to data related to the number of times a customer has visited a restaurant in the past, the date and time, and the details of their orders.

[0019] A "predictive algorithm" is a mathematical method for predicting future events and figures based on past data.

[0020] A "reservation system" is a system that allows customers to reserve seats and food in advance at restaurants.

[0021] "Adjusting purchasing quantities" is a management operation that increases or decreases the quantity of ingredients needed based on forecast data and alert information. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The present invention is a system for collecting data on restaurant sales, purchasing, and food waste from restaurants and effectively utilizing this data to reduce food waste. An embodiment of the present invention will be described in detail below.

[0044] 1. Food waste data collection and analysis

[0045] Data collection

[0046] Server: Works in conjunction with the restaurant's POS system to collect past sales data, purchasing data, and food waste data, and stores this data in a database.

[0047] Example: After closing time each day, the server automatically retrieves sales data from the restaurant's POS system and stores it in a database.

[0048] Data Preprocessing

[0049] Server: Complements missing values ​​and corrects outliers in the collected data, and prepares it in a format suitable for analysis.

[0050] Example: The server complements missing data with data from the previous day and corrects any abnormal values ​​to bring them within the normal range.

[0051] Analysis by AI model

[0052] Server: Inputs the preprocessed data into the AI ​​model to identify the causes of food waste for each menu item.

[0053] Example: The AI ​​model uses statistical methods based on data from the past three months to identify the main causes of food waste and their impact.

[0054] Save and notify results

[0055] Server: Stores the analysis results in a database for user access, and generates alerts for ingredients approaching their expiration date.

[0056] Example: The saved analysis results are visualized on a dashboard, and an alert is sent immediately if there is food that has a shelf life of two days.

[0057] 2. Customer Data Predictions

[0058] Collection of store visit history data

[0059] Server: Collects customer visit history and stores it in a database.

[0060] Example: The server retrieves data on customer repeat visits and the number of new customers from the POS system and stores it in a database.

[0061] Analysis of store visit patterns

[0062] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[0063] Example: The server uses visitor data from the past year to analyze visitor trends for specific days of the week and time periods, and predicts the number of customers to visit next week.

[0064] Sales forecast and purchase quantity proposals

[0065] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[0066] Example: The server predicts sales for each menu item based on the predicted number of customers for the next week, and calculates the amount of ingredients needed to purchase to achieve this.

[0067] Proposal Notification

[0068] Terminal: Notifies the user of the forecast results and recommended purchase quantities.

[0069] Example: The terminal displays a pop-up message with suggested purchases for next week (e.g. 10 kg of chicken, 20 kg of vegetables).

[0070] 3. Weather data forecasting

[0071] Obtaining weather data

[0072] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[0073] Example: Every morning, the server calls a weather data API to retrieve the weather forecast data for that day.

[0074] Correlation analysis between weather and customer numbers

[0075] Server: Compares past weather data with store visit data and analyzes correlations.

[0076] Example: The server cross-analyzes weather data and store visit data from the past year to determine the impact of weather on store visits.

[0077] Weather-based customer traffic forecast

[0078] Server: Predict the number of customers based on the weather forecast for the next day.

[0079] Example: Based on the analysis result that "the number of customers decreases by about 20% on rainy days," the server predicts the number of customers if rain is forecast for the next day, taking that impact into account.

[0080] System Notifications

[0081] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[0082] Example: On days when rain is forecast, the terminal will display a pop-up suggesting, "Reduce purchases due to predicted decline in customer numbers."

[0083] 4. Best before date management

[0084] Input of food ingredient data

[0085] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[0086] Example: When new ingredients are purchased, the server registers their expiration date data in the database.

[0087] Best before date monitoring

[0088] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[0089] Example: The server checks the database every morning and generates an alert for ingredients that are due within the next 3 days.

[0090] Alerting and Notifications

[0091] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests recipes to use them in.

[0092] Example: The device notifies the user, "The expiration date of the chicken is approaching in two days. We have some suggestions for new dishes using this chicken."

[0093] 5. Reservation system integration

[0094] Retrieving reservation data

[0095] Server: Obtains the most recent reservation data in real time from the restaurant reservation system and stores it in a database.

[0096] Example: The server checks the reservation system every morning and stores the reservation status for that day in a database.

[0097] Reservation data analysis

[0098] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[0099] Example: The server calculates the cancellation rate of reservations based on historical reservation data from the past few months.

[0100] Adjustment of purchase quantity

[0101] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[0102] Example: The server makes a suggestion such as, "Because the cancellation rate is high on this day, we will reduce the amount of purchases by 10% compared to normal."

[0103] Proposal Notification

[0104] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[0105] Example: The terminal displays the message, "We have a suggested purchase adjustment based on this week's reservation status," and provides detailed recommended quantities.

[0106] The above is a specific embodiment of the system, which allows restaurants to appropriately manage inventory and adjust purchasing, reducing food waste and improving cost efficiency.

[0107] The processing flow will be explained below.

[0108] 1. Food waste data collection and analysis

[0109] Step 1: Data collection

[0110] Server: Works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data, and stores this data in a database.

[0111] Step 2: Data Preprocessing

[0112] Server: Checks the collected data for missing or outlier values, and performs imputation or correction as necessary.

[0113] Step 3: Analysis by AI model

[0114] Server: Preprocessed data is input into the AI ​​model and analyzed to identify the causes of food waste for each menu item.

[0115] Step 4: Save the results

[0116] Server: Stores the analysis results in a database and makes them later accessible via the dashboard.

[0117] Step 5: View the dashboard

[0118] Device: The food waste analysis results are displayed in graph and report format on the user's dashboard.

[0119] Step 6: User Verification

[0120] Users: See the top causes of food waste on the dashboard.

[0121] 2. Customer Data Predictions

[0122] Step 1: Collect store visit history data

[0123] Server: Collects customer visit history and stores it in a database.

[0124] Step 2: Analyze store visit patterns

[0125] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[0126] Step 3: Sales forecast

[0127] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[0128] Step 4: Viewing Proposals

[0129] Terminal: Displays forecast results and recommended purchase quantities.

[0130] Step 5: Confirm instructions

[0131] User: Places an order for the required amount based on the displayed proposal.

[0132] 3. Weather data forecasting

[0133] Step 1: Getting weather data

[0134] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[0135] Step 2: Correlation analysis between weather and customer traffic

[0136] Server: Compares past weather data with store visit data and analyzes correlations.

[0137] Step 3: Weather-based customer traffic forecast

[0138] Server: Predict the number of customers based on the weather forecast for the next day.

[0139] Step 4: System Notifications

[0140] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[0141] Step 5: Check the prediction

[0142] User: Review and adjust forecasts and purchasing suggestions based on weather forecasts.

[0143] 4. Best before date management

[0144] Step 1: Input food ingredients data

[0145] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[0146] Step 2: Monitor expiration dates

[0147] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[0148] Step 3: Alert Generation

[0149] Server: Generates alert messages about food items that are approaching their expiration date and sends them to the terminal.

[0150] Step 4: Displaying alerts

[0151] Device: Displays an alert message when ingredients are nearing their expiration date and suggests recipes to use them in.

[0152] Step 5: Recipe Ideation

[0153] User: Create and serve new menu items based on the suggested recipes.

[0154] 5. Reservation system integration

[0155] Step 1: Get reservation data

[0156] Server: Retrieves reservation status data in real time from the restaurant reservation system and stores it in a database.

[0157] Step 2: Analyze your booking data

[0158] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[0159] Step 3: Adjusting inventory by reservation

[0160] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[0161] Step 4: Proposal Notification

[0162] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[0163] Step 5: Proposal confirmation

[0164] User: Check the reservation status and place an order based on the suggested purchase amount.

[0165] The above is the processing flow according to a specific embodiment of the present system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste.

[0166] Example 1

[0167] 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."

[0168] Food waste in restaurants is a major issue, as it not only leads to economic losses but also increases environmental impact. It is also difficult to manage appropriate purchasing amounts due to fluctuations in customer numbers and weather, which can further increase food waste. Furthermore, it is difficult to effectively manage ingredients approaching their expiration date and adjust purchasing appropriately based on reservation status, so a system that can efficiently solve these issues is needed.

[0169] 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.

[0170] In this invention, the server includes means for collecting a restaurant's past sales data, purchasing data, and food waste data and storing them in a database, means for preprocessing the data, means for inputting the preprocessed data into a generative AI model to identify the causes of food waste for each menu item, means for saving the analysis results in a database and making them accessible to users, means for generating alerts for food items approaching their expiration dates, means for displaying the food waste analysis results in graphs and reports on the user's dashboard, means for logging into the user's training platform to view and study educational materials and training videos, means for collecting restaurant visit history data and storing it in a database, means for acquiring weather forecast information and storing it in a database, means for acquiring reservation data from a reservation system and storing it in a database, means for predicting the number of customers and sales based on the acquired data and calculating appropriate purchase amounts, and means for notifying the user of the calculated purchase amounts.This enables restaurants to achieve appropriate inventory management and purchase adjustments, significantly reducing food waste and improving cost efficiency.

[0171] "Sales data" refers to data that records transaction information when products or menu items are sold at a restaurant.

[0172] "Purchase data" is data that records transaction information when a restaurant purchases ingredients or products.

[0173] "Food waste data" refers to data that records information about food ingredients that are discarded without being used by restaurants.

[0174] A "database" is a system for organizing and storing collected data and efficiently retrieving necessary information.

[0175] "Data preprocessing" is the process of preparing data in a format suitable for analysis, such as by filling in missing values ​​and correcting outliers.

[0176] A "generative AI model" is an algorithm that recognizes patterns based on past data and makes predictions and classifications.

[0177] "Causes of food waste" refers to factors that cause food waste and disposal in restaurants.

[0178] "Analysis results" are information that represents findings and conclusions obtained from collected and analyzed data.

[0179] An "alert" is a message that notifies or warns you when a specific condition is met.

[0180] A "dashboard" is an interface that allows users to visualize data.

[0181] A "graph or report format" is a format for visually displaying data, making it easier to understand.

[0182] A "training platform" is an environment or system for users to learn or train.

[0183] "Educational materials" are content or materials for learning specific knowledge or skills.

[0184] A "training video" is a video that provides learning content visually.

[0185] "Visit history data" is recorded information when a customer visits a restaurant.

[0186] "Weather forecast information" is forecast data regarding future weather.

[0187] "Reservation data" is data that records information when a customer reserves a table at a restaurant.

[0188] "Inventory management" is the process of properly maintaining and managing inventory of goods and ingredients.

[0189] "Purchase adjustment" refers to making adjustments to purchase the appropriate amount of ingredients and products based on forecasts and actual results.

[0190] "Improving cost efficiency" refers to reducing costs and utilizing funds efficiently.

[0191] This invention is a system for reducing food waste through the collection and analysis of restaurant sales data, purchasing data, and food waste data. This system operates in cooperation with a server, terminals, and users.

[0192] The server connects to the restaurant's POS system and collects sales data, purchasing data, and food waste data. This data is then stored in a database. For example, after closing each day, the server automatically retrieves sales data from the POS system and stores it in the database. It also extracts and stores purchasing data and food waste data in the same way.

[0193] The server complements missing values ​​and corrects outliers in the collected data. This process improves the reliability of the data and increases the accuracy of analysis. For example, the server complements missing data with data from the previous day and corrects any outliers to bring them within the normal range. This results in a data format suitable for analysis.

[0194] The server then inputs the preprocessed data into a generative AI model, which uses that data to identify the causes of food waste for each menu item. The AI ​​model uses statistical methods based on data from the past few months to identify the main causes of food waste and their impact. For example, it can identify specific causes such as "ingredient B from dish A is frequently wasted."

[0195] The analysis results are stored in a database and displayed on a dashboard that users can access. This dashboard visualizes the data in graphs and reports, and is designed to make it easy for users to understand. For example, it visually displays the main causes of food waste and trends in waste volume.

[0196] In addition, the server generates an alert for food ingredients that are approaching their expiration date and notifies the user. For example, if there is food that has an expiration date of two days, an alert saying "Chicken expiration date is approaching" will be displayed on the terminal. This alert is an important measure to prevent food waste.

[0197] Store visit history data is also collected by the server and stored in a database. This data is analyzed and the next number of customers is predicted based on past patterns. The server uses the past year's store visit data to analyze store visit trends for specific days of the week and time periods, and predicts the number of customers for the following week. For example, based on a pattern of high customer numbers on Friday nights, the server predicts the number of customers for the following Friday.

[0198] Weather forecast information is also obtained by the server and stored in a database. The server calls a weather data API to obtain and store the weather forecast data for that day. This weather data is compared with past store visit data and correlations are analyzed. Based on the analysis results, the server concludes that "the number of customers decreases by approximately 20% on rainy days."

[0199] The server comprehensively analyzes this data and predicts the number of customers based on the weather forecast for the next day. For example, if rain is forecast for the next day, the server predicts that the number of customers will decrease. The server notifies the user of this prediction and a suggested amount of stock to be purchased. The terminal displays a message such as, "The forecast suggests that the number of customers may decrease tomorrow, so we suggest reducing the amount of stock to be purchased."

[0200] Furthermore, the system retrieves reservation data from the reservation system and stores it in a database. Based on this data, it generates a purchase adjustment proposal based on the reservation status and notifies the user. For example, the terminal may display a message saying, "We have a purchase adjustment proposal based on this week's reservation status," along with detailed recommendations for purchase quantities.

[0201] Examples of specific prompts include:

[0202] "Calculate the necessary inventory based on the most recent reservation data."

[0203] "Please identify the main causes of food waste based on sales data and food waste data from the past three months."

[0204] "Based on this week's weather forecast, please predict the number of customers we will have and suggest the amount of stock we should stock."

[0205] This will enable restaurants to properly manage their inventory and adjust their purchasing, significantly reducing food waste and improving cost efficiency.

[0206] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0207] Step 1:

[0208] The server works with the restaurant's POS system to collect sales data, purchasing data, and food waste data. This data is automatically acquired after closing time each day and stored in a database. The input is raw data acquired from the POS system, and the output is raw data stored in the database. Specifically, the server calls the API for the POS system and saves the acquired data in the database.

[0209] Step 2:

[0210] The server complements missing values ​​and corrects outliers in the collected data. This process results in a data format suitable for analysis. The input is raw data stored in the database, and the output is preprocessed data. Specifically, it complements missing values ​​with data from the previous day, and corrects any outliers to within an appropriate range.

[0211] Step 3:

[0212] The server inputs the preprocessed data into the generative AI model to identify the causes of food waste for each menu item. The input is the preprocessed data, and the output is the analysis results of the causes of food waste. Specifically, data from the past few months is input into the generative AI model, which analyzes it using statistical methods to identify the causes of food waste.

[0213] Step 4:

[0214] The server stores the analysis results generated by the AI ​​model in a database and displays them on a dashboard that users can access. The input is the analysis results of the causes of food waste, and the output is the visualized data displayed on the dashboard. Specifically, the analysis results are converted into graphs and reports and displayed in a format that is easy for users to access.

[0215] Step 5:

[0216] The server generates an alert for food ingredients approaching their expiration date and notifies the user. The input is the food ingredient data for which the expiration date is approaching, and the output is an alert message displayed on the terminal. Specifically, the server periodically checks the database, generates an alert for food ingredients approaching their expiration date, and notifies the user.

[0217] Step 6:

[0218] The server collects customer visit history data and stores it in a database. The input is the visit history data, and the output is the visit data stored in the database. Specifically, it obtains the visit history data from the POS system and saves it in the database.

[0219] Step 7:

[0220] The server analyzes the visit history data and predicts the next number of customers based on past patterns. The input is the past visit history data, and the output is the predicted number of customers. Specifically, it analyzes visit trends by day of the week and time of day based on data from the past year, and predicts the next number of customers.

[0221] Step 8:

[0222] The server obtains weather forecast information from the weather data API and stores it in a database. The input is the weather forecast information obtained from the weather data API, and the output is the weather forecast data stored in the database. Specifically, the server calls the weather data API, obtains the weather forecast data, and stores it in the database.

[0223] Step 9:

[0224] The server compares past weather data with store visit data and analyzes the correlation. The input is past weather data and store visit data, and the output is the correlation analysis results between weather and store visits. Specifically, it cross-analyzes both sets of data to identify the impact that weather has on the number of store visitors.

[0225] Step 10:

[0226] The server predicts the number of customers based on the weather forecast for the next day. The input is weather forecast data, and the output is the predicted number of customers for the next day. Specifically, the server predicts the number of customers based on the weather forecast data and calculates the appropriate amount of stock to be purchased.

[0227] Step 11:

[0228] The server obtains reservation data from the reservation system and stores it in a database. The input is the reservation data obtained from the reservation system, and the output is the reservation data stored in the database. Specifically, the server accesses the reservation system to obtain data and stores it in the database.

[0229] Step 12:

[0230] The server analyzes the seating rate and reservation cancellation rate based on the reservation data, and generates a purchase adjustment proposal according to the reservation situation. The input is reservation data, and the output is a purchase adjustment proposal. Specifically, it analyzes past reservation history and proposes appropriate purchase amounts based on the cancellation rate and seating rate.

[0231] Step 13:

[0232] The terminal notifies the user of the forecast results and recommended purchase quantities. The input is the recommended purchase data from the server, and the output is a message displayed to the user. Specifically, the terminal notifies the user of the purchase adjustment proposal using a pop-up message or notification function.

[0233] (Application example 1)

[0234] 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."

[0235] In restaurant operations, excessive food waste and lost sales opportunities due to shortages are problems. These problems arise because it is difficult to properly manage inventory and predict customer demand. Also, adjusting purchasing quantities based on fluctuations in weather and customer visit history is difficult, which contributes to waste. Furthermore, inadequate management of expiration dates also leads to food loss.

[0236] 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.

[0237] In this invention, the server includes means for collecting the restaurant's past sales data, purchasing data, and food waste data and storing them in a database, means for preprocessing the data, means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item, means for saving the analysis results in a database and making them accessible to users, means for generating alerts for food ingredients whose expiration dates are approaching, means for displaying the food waste analysis results in graphs and reports on the user's dashboard, means for sending alerts and prediction results via push notifications to the user's mobile device, and means for providing recommended purchase amounts based on the prediction results. This enables the reduction of food waste and efficient inventory management in restaurants.

[0238] "Past sales data of a restaurant" is information relating to the quantity and price of products sold in the past at a restaurant.

[0239] "Purchase data" refers to information about ingredients and other necessities purchased by a restaurant.

[0240] "Food waste data" is information on the amount and type of food that is discarded without being used.

[0241] A "database" is a system for centrally managing and storing collected data.

[0242] "Data preprocessing" is the process of filling in missing data values ​​and correcting outliers, preparing the data in a form that is easy to analyze.

[0243] An "AI model" is an algorithm that uses artificial intelligence to analyze data and make predictions and classifications.

[0244] "Causes of food waste" are the main reasons why food ingredients are discarded unnecessarily.

[0245] "Analysis results" refers to the information and insights obtained as a result of analyzing data.

[0246] An "alert" is a warning message that notifies the user of urgent information.

[0247] A "dashboard" is a tool that visually organizes information and displays it in a way that allows users to intuitively understand it.

[0248] A "mobile terminal" is a mobile device such as a smartphone or tablet.

[0249] "Push notifications" are a method of sending information to a user's device in real time.

[0250] "Recommended purchase quantities" are the appropriate amounts of ingredients to purchase suggested based on forecast data.

[0251] This invention is a system for streamlining restaurant operations and reducing food waste. This system collects sales data, purchasing data, food waste data, etc., and analyzes them using an AI model. It also notifies users of prediction results and alerts, supporting appropriate purchasing and inventory management.

[0252] Data collection and storage

[0253] The server connects to the restaurant's POS system and collects past sales data, purchasing data, and food waste data, storing it in a database. This data is automatically retrieved, organized, and saved after closing time each day.

[0254] Data Preprocessing

[0255] The server uses the Python pandas library to fill in missing values ​​and correct outliers in the collected data, and then formats it for analysis.

[0256] Analysis by AI model

[0257] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item. The AI ​​model uses scikit-learn's Linear Regression model to make highly accurate predictions based on past data.

[0258] Save and notify results

[0259] The analysis results are stored in a database and displayed on a dashboard for user access, and alerts are generated for ingredients approaching their expiration date and sent to users' mobile devices via push notifications.

[0260] User Dashboard

[0261] Users can visually check the results of food waste analysis in the form of graphs and reports through the dashboard, which is implemented using the Shiny package in the R programming language.

[0262] Providing prediction results

[0263] The server calculates sales forecasts and recommended stock quantities based on the predicted number of customers for the next week, and sends these to the user's mobile device via push notification.

[0264] Specific examples

[0265] For example, when a store manager opens the application on their smartphone, it displays next week's predicted sales, purchasing suggestions, and alerts for ingredients that are nearing their expiration date.

[0266] Prompt Sentence Examples

[0267] Examples of prompt sentences include:

[0268] "Please use the store's sales data, purchasing data, food waste data, and weather forecast data from the past month to identify causes of food waste and predict the number of customers visiting the store. Also, please make purchasing amount suggestions based on the results."

[0269] The above is an embodiment of the present invention.

[0270] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0271] Step 1:

[0272] The server connects to the restaurant's POS system and collects past sales data, purchasing data, and food waste data.

[0273] Input: Sales data, purchasing data, and food waste data from the POS system.

[0274] Output: The collected data is stored in a database.

[0275] Specifically, after closing time each day, the server accesses the POS system, automatically retrieves the necessary data via API, and stores it in a database.

[0276] Step 2:

[0277] The server performs data preprocessing by filling in missing values ​​and correcting outliers in the collected data.

[0278] Input: Raw sales data, purchasing data, and food waste data stored in the database.

[0279] Output: Preprocessed data.

[0280] Specifically, missing data is filled in with the previous day's values ​​using Python's pandas library, and outliers are corrected to within a statistically appropriate range.

[0281] Step 3:

[0282] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item.

[0283] Input: Preprocessed sales data, purchasing data, and food waste data.

[0284] Output: Analysis results of causes of food waste.

[0285] Specifically, we use scikit-learn's Linear Regression model to analyze correlations in the data and identify the main causes of food waste and their contribution.

[0286] Step 4:

[0287] The server stores the analysis results in a database and makes them accessible to users through a dashboard.

[0288] Input: Analysis results of causes of food waste.

[0289] Output: Analysis results stored in a database.

[0290] Specifically, the analysis results are stored in a database, and users can view the results by accessing a dashboard via a web interface.

[0291] Step 5:

[0292] The server generates an alert for food ingredients approaching their expiration date and sends a push notification to the user's mobile device.

[0293] Input: Best before information in the database.

[0294] Output: Alert notification.

[0295] Specifically, the database is checked periodically, and if the expiration date is approaching, an alert is sent to the user's email address using an SMTP server.

[0296] Step 6:

[0297] The server calculates sales forecasts and recommended stock quantities based on the predicted number of customers visiting the store next week, and sends these to the user's mobile device via push notification.

[0298] Input: Store visit history data and weather forecast data.

[0299] Output: Sales forecast and recommended purchase quantities.

[0300] Specifically, an AI model makes predictions based on store visit history and weather data, calculates the amount of stock to be purchased based on the results, and notifies the user's smartphone.

[0301] Step 7:

[0302] Users can check food waste analysis results, store visit predictions, purchasing suggestions, and more through the dashboard, and take appropriate action.

[0303] Input: Server-generated analysis results, forecast data, and purchasing recommendations.

[0304] Output: User confirmation and action.

[0305] Specifically, users access the dashboard through a web browser or a dedicated app, view information in the form of graphs and reports, and make adjustments to purchases and menus as needed.

[0306] 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.

[0307] This invention is a system that collects restaurant sales data, purchasing data, and food waste data and uses this data to reduce food waste. Furthermore, this invention achieves more effective operation by combining it with an emotion engine that recognizes user emotions. Below, we will explain in detail how each component works together and functions as an entire system.

[0308] 1. Food waste data collection and analysis

[0309] Data collection

[0310] Server: Works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data, and stores it in a database.

[0311] Example: The server automatically retrieves sales data from the POS system after closing each day and stores it in a database.

[0312] Data Preprocessing

[0313] Server: Complements missing values ​​and corrects outliers in the collected data, and prepares it in a format suitable for analysis.

[0314] Example: The server complements missing data with data from the previous day and corrects any abnormal values ​​to bring them within the normal range.

[0315] Analysis by AI model

[0316] Server: Preprocessed data is input into the AI ​​model and analyzed to identify the causes of food waste for each menu item.

[0317] Example: The AI ​​model uses statistical methods based on data from the past three months to identify the main causes of food waste and their impact.

[0318] Save and notify results

[0319] Server: Stores the analysis results in a database for user access, and generates alerts for ingredients approaching their expiration date.

[0320] Example: The saved analysis results are visualized on a dashboard, and an alert is sent immediately if there is food that has a shelf life of two days.

[0321] 2. Customer Data Predictions

[0322] Collection of store visit history data

[0323] Server: Periodically collects customer visit history and stores it in a database.

[0324] Example: The server retrieves data on customer repeat visits and the number of new customers from the POS system and stores it in a database.

[0325] Analysis of store visit patterns

[0326] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[0327] Example: The server uses visitor data from the past year to analyze visitor trends for specific days of the week and time periods, and predicts the number of customers to visit next week.

[0328] Sales forecast and purchase quantity proposals

[0329] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[0330] Example: The server predicts sales for each menu item based on the predicted number of customers for the next week, and calculates the amount of ingredients needed to purchase to achieve this.

[0331] Proposal Notification

[0332] Terminal: Notifies the user of the forecast results and recommended purchase quantities.

[0333] Example: The terminal displays a pop-up message with suggested purchases for next week (e.g. 10 kg of chicken, 20 kg of vegetables).

[0334] 3. Weather data forecasting

[0335] Obtaining weather data

[0336] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[0337] Example: Every morning, the server calls a weather data API to retrieve the weather forecast data for that day.

[0338] Correlation analysis between weather and customer numbers

[0339] Server: Compares past weather data with store visit data and analyzes correlations.

[0340] Example: The server cross-analyzes weather data and store visit data from the past year to determine the impact of weather on store visits.

[0341] Weather-based customer traffic forecast

[0342] Server: Predict the number of customers based on the weather forecast for the next day.

[0343] Example: Based on the analysis result that "the number of customers decreases by about 20% on rainy days," the server predicts the number of customers if rain is forecast for the next day, taking that impact into account.

[0344] System Notifications

[0345] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[0346] Example: On days when rain is forecast, the terminal will display a pop-up suggesting, "Reduce purchases due to predicted decline in customer numbers."

[0347] 4. Best before date management

[0348] Input of food ingredient data

[0349] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[0350] Example: When new ingredients are purchased, the server registers their expiration date data in the database.

[0351] Best before date monitoring

[0352] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[0353] Example: The server checks the database every morning and generates an alert for ingredients that are due within the next 3 days.

[0354] Alerting and Notifications

[0355] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests recipes to use them in.

[0356] Example: The device notifies the user, "The expiration date of the chicken is approaching in two days. We have some suggestions for new dishes using this chicken."

[0357] 5. Reservation system integration

[0358] Retrieving reservation data

[0359] Server: Obtains the most recent reservation data in real time from the restaurant reservation system and stores it in a database.

[0360] Example: The server checks the reservation system every morning and stores the reservation status for that day in a database.

[0361] Reservation data analysis

[0362] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[0363] Example: The server calculates the cancellation rate of reservations based on historical reservation data from the past few months.

[0364] Adjustment of purchase quantity

[0365] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[0366] Example: The server makes a suggestion such as, "Because the cancellation rate is high on this day, we will reduce the amount of purchases by 10% compared to normal."

[0367] Proposal Notification

[0368] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[0369] Example: The terminal displays the message, "We have a suggested purchase adjustment based on this week's reservation status," and provides detailed recommended quantities.

[0370] 6. Combining Emotion Engines

[0371] Emotion recognition by emotion engine

[0372] Server: Analyzes the user's voice and text input and recognizes emotions using an emotion engine.

[0373] Example: The server analyzes voice comments and feedback in real time as users operate the dashboard, and recognizes emotions using an emotion engine.

[0374] Customized display content based on emotions

[0375] Device: The content displayed on the dashboard is automatically customized based on the user's emotions recognized by the emotion engine.

[0376] Example: If the user is stressed, simplify the display and prioritize important information.

[0377] Changing information provision based on emotions

[0378] Device: Based on the user's emotions recognized by the emotion engine, the method of providing information on reducing food waste and purchasing suggestions is changed.

[0379] Example: If the user is not satisfied with the previous suggestion, switch to a more detailed and illustrated presentation.

[0380] Recording and analyzing emotional data

[0381] Server: The user's emotion data recognized by the emotion engine is stored in a database and used for later analysis.

[0382] Example: The server stores the user's usage history along with emotional data, and periodically analyzes this data to help improve the system.

[0383] The above is the processing flow of a specific embodiment of this system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste. Furthermore, by combining it with an emotion engine, the user experience can be improved and the effectiveness of the system can be further enhanced.

[0384] The processing flow will be explained below.

[0385] 1. Food waste data collection and analysis

[0386] Step 1: Data collection

[0387] Server: Connects to the restaurant's POS system via API, collects past sales data, purchasing data, and food waste data on a daily basis, and stores this data in a database.

[0388] Step 2: Data Preprocessing

[0389] Server: Preprocesses the collected data and performs missing value interpolation and outlier correction. For example, if some sales data is missing, the data from the previous day is used as a reference to complete the data.

[0390] Step 3: Analysis by AI model

[0391] Server: The preprocessed data is input into an AI model equipped with statistical methods, and analysis is performed to identify the causes of food waste for each menu item. The analysis results are then compiled into a report.

[0392] Step 4: Save the results

[0393] Server: The analysis results are stored in a database for later access by users. The stored data includes the causes and impact of food waste for each menu item.

[0394] Step 5: View the dashboard

[0395] Device: The results of food waste analysis are displayed visually in graphs and reports on the user's dedicated dashboard. The interface is optimized to make it intuitive for users.

[0396] Step 6: User Verification

[0397] Users: Access the dashboard to view the main causes of food waste and their associated data, identify problems, and consider solutions.

[0398] 2. Customer Data Predictions

[0399] Step 1: Collect store visit history data

[0400] Server: Periodically collects customer visit history from the restaurant's POS system and stores it in a database.

[0401] Step 2: Analyze store visit patterns

[0402] Server: Analyzes collected store visit history data and identifies patterns of store visits by day of the week, time of day, and season. For example, it extracts trends such as higher customer numbers on weekends compared to weekdays.

[0403] Step 3: Sales forecast

[0404] Server: Based on the analysis of customer visit patterns, it performs calculations to predict the next number of customers and sales. Based on the prediction results, it calculates the recommended stock amount.

[0405] Step 4: Viewing Proposals

[0406] Terminal: The forecast results and recommended purchase quantities are displayed on the interface. For example, the recommended purchase quantities (e.g., 10 kg of chicken and 20 kg of vegetables) based on the predicted number of customers for the next week are displayed.

[0407] Step 5: Confirm instructions

[0408] User: Checks the displayed forecast results and purchase proposals, decides on the actual purchase amount, and places an order with the supplier by pressing the approval button on the screen.

[0409] 3. Weather data forecasting

[0410] Step 1: Getting weather data

[0411] Server: Using the weather data API, the latest weather forecast information is obtained daily and stored in a database.

[0412] Step 2: Correlation analysis between weather and customer traffic

[0413] Server: Correlate historical weather data with store visit data to identify the impact of weather on store visits. For example, confirm that store visits on rainy days are lower than normal.

[0414] Step 3: Weather-based customer traffic forecast

[0415] Server: Based on the weather forecast for the next day, calculates the number of customers to visit. If the weather forecast predicts rain, it takes into account that the number of customers will be lower than usual.

[0416] Step 4: System Notifications

[0417] Terminal: Notifies the user of customer traffic predictions based on weather forecasts and suggests adjustments to purchasing quantities based on this. For example, on days when rain is predicted, a suggestion to reduce purchasing quantities by 20% is displayed.

[0418] Step 5: Check the prediction

[0419] User: Review forecasts and purchasing suggestions based on weather forecasts and make adjustments as needed.

[0420] 4. Best before date management

[0421] Step 1: Input food ingredients data

[0422] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database. Whenever new ingredients are purchased, the expiration date information is registered.

[0423] Step 2: Monitor expiration dates

[0424] Server: Periodically checks the expiration dates of ingredients in the database and identifies ingredients that are approaching their expiration date.

[0425] Step 3: Alert Generation

[0426] Server: Generates an alert message for food ingredients that are approaching their expiration date and notifies the terminal.

[0427] Step 4: Displaying alerts

[0428] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests new recipes using those ingredients. For example, it displays a message like, "Your chicken will expire in two days. How about making a special dish using this chicken?"

[0429] Step 5: Recipe Ideation

[0430] User: Create and serve new menu items based on the suggested recipes. Update the menu display as needed.

[0431] 5. Reservation system integration

[0432] Step 1: Get reservation data

[0433] Server: Obtains reservation data in real time from the restaurant reservation system and stores it in a database.

[0434] Step 2: Analyze your booking data

[0435] Server: Analyzes reservation cancellation rates, seating rates, etc. based on reservation data.

[0436] Step 3: Adjusting inventory by reservation

[0437] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[0438] Step 4: Proposal Notification

[0439] Terminal: Notify the user of a purchase quantity adjustment proposal based on the reservation status. For example, display "There is a purchase adjustment proposal based on this week's reservation status."

[0440] Step 5: Proposal confirmation

[0441] User: Checks the reservation status and places an actual order based on the suggested purchase amount.

[0442] 6. Combining Emotion Engines

[0443] Step 1: Emotion recognition by the emotion engine

[0444] Server: Analyzes the user's voice and text input in real time and recognizes emotions using an emotion engine. For example, if a user inputs a voice comment while operating the dashboard, the voice data is analyzed by the emotion engine.

[0445] Step 2: Customize your display based on emotions

[0446] Device: The dashboard display is automatically customized based on the user's emotions as recognized by the emotion engine. For example, if the user is feeling stressed, the display will be simplified and important information will be prioritized.

[0447] Step 3: Modify your information based on emotions

[0448] Device: Based on the user's emotions recognized by the emotion engine, the way information on food waste reduction and purchasing suggestions is presented is changed. For example, if the user is dissatisfied with the previous suggestion, the explanation is made more detailed and the display is switched to one that makes use of more illustrations.

[0449] Step 4: Record and analyze emotion data

[0450] Server: The user's emotional data recognized by the emotion engine is stored in a database and used for later analysis. The emotional data is used as a reference for periodic system improvements.

[0451] The above is the processing flow of a specific embodiment of this system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste. Furthermore, by combining it with an emotion engine, the user experience can be improved and the effectiveness of the system can be further enhanced.

[0452] Example 2

[0453] 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."

[0454] Appropriate inventory management and food waste reduction are important issues in modern restaurant management. Conventional methods involve manually analyzing sales and purchasing data to generate food waste data, but this method is inaccurate and makes effective food waste reduction and inventory management difficult. Furthermore, there is an insufficient system for integrating and utilizing weather data, restaurant visit forecast data, and reservation data, creating a need for more efficient food ingredient management and customer trend forecasts. Furthermore, there is a lack of information provided that takes user stress and satisfaction into consideration, making it difficult to provide an optimal user experience.

[0455] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting and storing the restaurant's past sales data, purchasing data, and food waste data in a database; means for preprocessing the data; means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item; means for saving the analysis results in a database and making them accessible to the user; means for generating alerts for food ingredients whose expiration dates are approaching; means for displaying the food waste analysis results in graphs and reports on the user's dashboard; means for customizing the display content using an emotion engine that recognizes the user's emotions; and means for recording and analyzing the user's emotion data. This enables efficient food waste reduction, appropriate inventory management, and highly accurate purchasing suggestions based on restaurant visit predictions. Furthermore, optimal information is provided according to the user's emotional state, improving the user experience.

[0456] "Food and beverage establishments" are establishments that serve food and beverages, including restaurants, cafes, and bars.

[0457] "Sales data" refers to information regarding the quantity and value of products sold by a restaurant during a specific period.

[0458] "Purchasing data" refers to information about ingredients, beverages, and other items purchased by a restaurant during a specific period.

[0459] "Food waste data" refers to information on the types and quantities of food ingredients that are discarded unused by restaurants.

[0460] "Database" refers to a system for organizing, storing, and managing collected data.

[0461] "Data preprocessing" refers to the process of performing operations such as filling in missing values ​​and correcting outliers in order to convert data into a format suitable for analysis.

[0462] An "AI model" is a program that uses artificial intelligence to analyze data and make predictions or classifications that are useful for a specific purpose.

[0463] "Causes of food waste" refers to the main factors and reasons why food is wasted.

[0464] "Analysis results" refers to conclusions and findings obtained through data analysis work.

[0465] "Alert" refers to a warning message sent to provide important information or caution.

[0466] A "dashboard" is an interface that visually displays important information, allowing users to understand the situation at a glance.

[0467] An "emotion engine" refers to a system for recognizing and analyzing emotions from a user's voice or text.

[0468] "Customizing the display content" refers to adjusting the display method and content of information according to the user's emotions and needs.

[0469] "Emotional Data" refers to information about a user's emotional state, including that recognized and recorded by the system.

[0470] "Visit history" refers to records of the date, time, and frequency of a customer's visits to a restaurant.

[0471] "Weather Forecast Information" means data regarding future weather conditions in a particular geographic area.

[0472] "Correlation" refers to a statistical association between two or more variables.

[0473] "Reservation data" refers to information regarding seat and service reservations made in advance by customers to restaurants.

[0474] The present invention is a system for reducing food waste and optimizing inventory management in restaurants. This system is built on the interaction between a server, a terminal, and a user, and the invention is implemented as follows.

[0475] Data collection and storage

[0476] The server works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data and store it in a database.

[0477] Example: After closing each day, the server automatically retrieves data from the POS system and stores it in a database.

[0478] Data Preprocessing

[0479] The server performs preprocessing such as filling in missing values ​​in the collected data with data from the previous day and correcting outliers to bring them within the normal range, and then converts the data into a format suitable for analysis.

[0480] Example: The server fills in any missing data with data from the previous day, and corrects any extremely outlying values.

[0481] Analysis by AI model

[0482] The server inputs the preprocessed data into an AI model and performs statistical analysis to identify the causes of food waste in restaurants.

[0483] Example: The server identifies the main causes of food waste based on data from the past three months and assesses their impact.

[0484] Save and notify results

[0485] The server stores the analysis results in a database and generates alerts based on the results for food ingredients approaching their expiration date.

[0486] Example: Food waste analysis results are saved in dashboard format, and an alert message is generated for food ingredients with a shelf life of less than two days.

[0487] User Interface

[0488] The device notifies the user of analysis results and alerts, and displays the food waste analysis results in graphs and reports on the dashboard.

[0489] Example: When users access the dashboard, the causes and impact of food waste for each ingredient are visualized, prompting them to take necessary action.

[0490] Customization with Emotion Engine

[0491] The server analyzes the user's voice and text input and uses an emotion engine to recognize the user's emotions.

[0492] Example: When a user interacts with a dashboard, they can enter feedback and comments, and the system can recognize their emotions from the content.

[0493] The terminal customizes the display content on the dashboard based on the user's emotions recognized by the emotion engine.

[0494] Example: If the user is stressed, simplify the display and prioritize the most important information.

[0495] Storing and analyzing emotional data

[0496] The server stores the recognized emotion data in a database for later analysis.

[0497] Example: Emotional data is stored along with the user's operation history and periodically analyzed to help improve the system.

[0498] Prompt Sentence Examples

[0499] Use the following prompt to instruct the generative AI model to identify the causes of food waste from food waste data:

[0500] "Based on data from the past three months, please identify the main causes of food waste and their impact."

[0501] The above is a specific example of an embodiment of the present invention. This invention enables restaurants to efficiently reduce food waste and achieve appropriate inventory management, thereby improving customer satisfaction.

[0502] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0503] Step 1: Collect and store data

[0504] The server periodically connects to the restaurant's POS system to obtain past sales data, purchasing data, and food waste data.

[0505] Input: Sales data, purchasing data, food waste data collected from POS systems

[0506] Output: Sales data, purchasing data, food waste data stored in a database

[0507] Specific operation: After closing time every day, the server automatically accesses the POS system, extracts the necessary data, and stores it in the database.

[0508] Step 2: Preprocessing the data

[0509] The server completes missing values ​​and corrects outliers in the collected data.

[0510] Input: Sales data, purchasing data, food waste data stored in the database

[0511] Output: Preprocessed data

[0512] Specific operation: The server identifies missing values ​​and fills them with data from the previous day. If an outlier is detected, it corrects it to an appropriate value.

[0513] Step 3: Identifying causes of food waste using an AI model

[0514] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item.

[0515] Input: Preprocessed data

[0516] Output: Report on causes of food waste and their impact

[0517] Specific operation: The server prompts the generative AI model, saying, "Based on data from the past three months, please identify the main causes of food waste and their impact," and analyzes the results.

[0518] Step 4: Save the analysis results and generate alerts

[0519] The server stores the analysis results obtained from the AI ​​model in a database and generates alerts for ingredients that are approaching their expiration date.

[0520] Input: Food waste cause report, food ingredient data

[0521] Output: Saved reports, generated alerts

[0522] Specific operation: The server stores the analysis results in a database in the form of a dashboard and generates an alert for ingredients whose expiration date is within two days.

[0523] Step 5: User interface notification

[0524] The terminal notifies the user of the analysis results and alerts and displays them on a dashboard.

[0525] Input: Analysis results and alerts stored in the database

[0526] Output: Graphs, reports, and popup alerts displayed on the user dashboard

[0527] Specific operation: When a user accesses the dashboard, the device visually displays the causes of food waste and their impact for each ingredient, and notifies them of expiration dates via a pop-up alert.

[0528] Step 6: Emotion Recognition and Customization with the Emotion Engine

[0529] The server analyzes the user's voice and text input using an emotion engine to recognize emotions.

[0530] Input: User voice commands and text feedback

[0531] Output: User emotion data

[0532] Specific operation: The server analyzes the voice comments and feedback provided by the user during operation, and recognizes and records emotions using an emotion engine.

[0533] The device will adjust the content displayed on the dashboard based on the recognized emotion.

[0534] Input: User emotion data

[0535] Output: Customized Dashboard View

[0536] Specific behavior: When the user is feeling stressed, the device simplifies the display and prioritizes displaying important information.

[0537] Step 7: Storing and analyzing sentiment data

[0538] The server stores the user's emotion data recognized by the emotion engine in a database and periodically analyzes it.

[0539] Input: User emotion data

[0540] Output: Sentiment analysis report

[0541] Specific operation: The server stores the user's emotional data along with their operation history in a database, and periodically analyzes the emotional data to improve the system.

[0542] The above are the specific processing steps of the program of this system.

[0543] (Application example 2)

[0544] 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."

[0545] Conventional restaurant inventory management systems often collect and analyze sales and purchasing data separately, making it difficult to reduce food waste and predict appropriate purchasing amounts. Furthermore, proposals did not take into account factors such as weather changes or consumer sentiment, resulting in a lack of concrete countermeasures. The food delivery industry, in particular, requires real-time inventory management and forecasting to respond to fluctuations in orders. A system that solves these problems and enables more efficient inventory management and food waste reduction is needed.

[0546] 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 the restaurant's past sales data, purchasing data, and food waste data and storing them in a database; means for preprocessing the data; means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item; means for saving the analysis results in a database and making them accessible to users; means for generating alerts for food ingredients whose expiration date is approaching; means for displaying the food waste analysis results in graphs and reports on the user's dashboard; means for logging into the user's training platform and viewing and studying educational materials and training videos; means for forecasting food delivery sales and recommending necessary inventory and purchasing; means for importing weather data, analyzing the impact of weather on delivery orders, and notifying the user of the results; and means for recognizing the emotions of delivery personnel and store staff and customizing operation methods and information presentation. This enables comprehensive, real-time inventory management and sales forecasting, further improving the user experience.

[0547] "Sales data" refers to information on the total revenue earned by a restaurant over a certain period of time.

[0548] "Purchasing data" is detailed information about when a restaurant purchases ingredients and products.

[0549] "Food waste data" is information on food ingredients that were discarded because they were not used.

[0550] A "database" is a system for efficiently managing, searching, and manipulating multiple pieces of data.

[0551] "Data preprocessing" is the process of converting collected raw data into a form suitable for analysis.

[0552] An "AI model" is a type of algorithm that uses artificial intelligence to analyze data and make predictions.

[0553] "Food loss" is the waste that occurs when food ingredients are discarded without being used.

[0554] An "alert" is a system that notifies a user of a warning when a specific condition occurs.

[0555] A "dashboard" is a user interface that allows various data to be visually displayed and manipulated.

[0556] "Training Platform" means a system for providing educational materials and training videos.

[0557] "Food delivery" is a service that delivers ordered meals to a designated location.

[0558] "Weather data" is data that includes various information about the weather.

[0559] The "emotion engine" is a function that recognizes and analyzes the user's emotions and adjusts the system's behavior based on the results.

[0560] This invention is a system that collects and analyzes past sales data, purchasing data, and food waste data from restaurants to reduce food waste and achieve efficient inventory management. The invention also aims to improve operability and user experience by incorporating an approach specialized for food delivery services and using an emotion engine that recognizes user emotions.

[0561] The server connects to the POS system to collect various data from the restaurant. Sales data, purchasing data, and food waste data are sent to the server after the end of business each day and stored in a database. The server also performs preprocessing such as filling in missing values ​​and correcting outliers.

[0562] The pre-processed data is then analyzed using a generative AI model. This AI model identifies causes of food waste based on historical data and supports efficient inventory management. It also generates sales forecasts for food delivery services. For example, by combining historical sales data with weather data, it can predict the impact of weather on delivery orders and adjust ingredient purchases accordingly.

[0563] Weather data is obtained from an external weather data API and stored on the server. This data is input into an AI model and used to predict customer numbers and make purchasing recommendations based on the next day's weather forecast. Users can view these predictions on a dashboard and receive specific alerts and purchasing recommendations.

[0564] Furthermore, the server uses an emotion engine to analyze the emotions of delivery personnel and store staff, and customizes the user interface operation method and information presentation. If the user feels stressed about a particular operation, the operation procedure is simplified and important information is prioritized.

[0565] For example, if the emotion engine detects that the user is stressed, it will provide detailed, visual information, or if the user is dissatisfied with the previous purchase suggestion, it will switch to a more detailed explanation and illustration-heavy display.

[0566] Specific prompts that are used include:

[0567] "Please demonstrate an application that uses sales data, purchase data, and waste data from the past three months to forecast sales for the next week and suggest optimal inventory levels. Also, please demonstrate how to take into account the effects of weather and adjust inventory levels on days with bad weather. Finally, please provide a concrete explanation of the forecast based on sales data and how to notify the results."

[0568] This enables comprehensive, real-time inventory management and sales forecasting, further enhancing the user experience.

[0569] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0570] Step 1:

[0571] The server connects to the restaurant's POS system and automatically collects past sales data, purchasing data, and food waste data after each day's business hours. This data is then stored in a database. The inputs are sales data, purchasing data, and waste data obtained from the POS system, and the output is stored in the database.

[0572] Step 2:

[0573] The server fills in missing values ​​and corrects outliers in the collected data to prepare it for analysis. This preprocessing includes, for example, filling in missing data with data from the previous day and correcting outliers to bring them within a normal range. The input is raw data, and the output is preprocessed data.

[0574] Step 3:

[0575] The server inputs the preprocessed data into the AI ​​model to identify the causes of food waste for each menu item. In this process, the AI ​​model performs statistical analysis of the data to identify the main causes of food waste and their impact. The input is the preprocessed data, and the output is the results of identifying the causes of food waste.

[0576] Step 4:

[0577] The server stores the analysis results of the AI ​​model in a database and makes them accessible to users. The analysis results are displayed in the form of graphs and reports on a dashboard. The input is the analysis results of the AI ​​model, and the output is the analysis results converted into an easy-to-read format.

[0578] Step 5:

[0579] The server generates an alert for food items approaching their expiration date. This alert is sent to the user's device as a notification to prompt further action. The input is expiration date data, and the output is an alert notification.

[0580] Step 6:

[0581] Users can check the food loss analysis results on the dashboard and take action as necessary. The user's input is access to the dashboard and the necessary operations, and the output is the displayed analysis results and a presentation of countermeasures.

[0582] Step 7:

[0583] The server obtains weather forecast information from an external weather data API and stores it in a database. The weather data is used to predict the number of customers and delivery orders. The input is the weather forecast information obtained from the weather data API, and the output is the weather data stored in the database.

[0584] Step 8:

[0585] The server predicts the number of delivery orders for the next day based on the weather forecast and calculates the necessary food ingredient stocking amounts. This allows for purchase suggestions that reflect the impact of weather on delivery orders. The inputs are weather data and past order data, and the output is a purchase suggestion.

[0586] Step 9:

[0587] The server uses an emotion engine to recognize the user's emotions and optimize operability. This includes analyzing the user's voice and text input and making adjustments such as simplifying the operation screen if the user is feeling stressed. The input is the user's voice and text data, and the output is an optimized operation screen and the presentation of information.

[0588] Step 10:

[0589] The server sends the notification results to the user, ensuring that important information is provided in a timely manner, such as purchasing suggestions and alert notifications. The inputs include food waste analysis results and suggestions based on weather forecasts, and the output is a notification sent to the user's device.

[0590] 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.

[0591] 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.

[0592] 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.

[0593] [Second embodiment]

[0594] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0595] 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.

[0596] 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).

[0597] 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.

[0598] 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.

[0599] 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).

[0600] 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.

[0601] 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.

[0602] 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.

[0603] 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.

[0604] 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.

[0605] 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."

[0606] The present invention is a system for collecting data on restaurant sales, purchasing, and food waste from restaurants and effectively utilizing this data to reduce food waste. An embodiment of the present invention will be described in detail below.

[0607] 1. Food waste data collection and analysis

[0608] Data collection

[0609] Server: Works in conjunction with the restaurant's POS system to collect past sales data, purchasing data, and food waste data, and stores this data in a database.

[0610] Example: After closing time each day, the server automatically retrieves sales data from the restaurant's POS system and stores it in a database.

[0611] Data Preprocessing

[0612] Server: Complements missing values ​​and corrects outliers in the collected data, and prepares it in a format suitable for analysis.

[0613] Example: The server complements missing data with data from the previous day and corrects any abnormal values ​​to bring them within the normal range.

[0614] Analysis by AI model

[0615] Server: Inputs the preprocessed data into the AI ​​model to identify the causes of food waste for each menu item.

[0616] Example: The AI ​​model uses statistical methods based on data from the past three months to identify the main causes of food waste and their impact.

[0617] Save and notify results

[0618] Server: Stores the analysis results in a database for user access, and generates alerts for ingredients approaching their expiration date.

[0619] Example: The saved analysis results are visualized on a dashboard, and an alert is sent immediately if there is food that has a shelf life of two days.

[0620] 2. Customer Data Predictions

[0621] Collection of store visit history data

[0622] Server: Collects customer visit history and stores it in a database.

[0623] Example: The server retrieves data on customer repeat visits and the number of new customers from the POS system and stores it in a database.

[0624] Analysis of store visit patterns

[0625] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[0626] Example: The server uses visitor data from the past year to analyze visitor trends for specific days of the week and time periods, and predicts the number of customers to visit next week.

[0627] Sales forecast and purchase quantity proposals

[0628] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[0629] Example: The server predicts sales for each menu item based on the predicted number of customers for the next week, and calculates the amount of ingredients needed to purchase to achieve this.

[0630] Proposal Notification

[0631] Terminal: Notifies the user of the forecast results and recommended purchase quantities.

[0632] Example: The terminal displays a pop-up message with suggested purchases for next week (e.g. 10 kg of chicken, 20 kg of vegetables).

[0633] 3. Weather data forecasting

[0634] Obtaining weather data

[0635] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[0636] Example: Every morning, the server calls a weather data API to retrieve the weather forecast data for that day.

[0637] Correlation analysis between weather and customer numbers

[0638] Server: Compares past weather data with store visit data and analyzes correlations.

[0639] Example: The server cross-analyzes weather data and store visit data from the past year to determine the impact of weather on store visits.

[0640] Weather-based customer traffic forecast

[0641] Server: Predict the number of customers based on the weather forecast for the next day.

[0642] Example: Based on the analysis result that "the number of customers decreases by about 20% on rainy days," the server predicts the number of customers if rain is forecast for the next day, taking that impact into account.

[0643] System Notifications

[0644] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[0645] Example: On days when rain is forecast, the terminal will display a pop-up suggesting, "Reduce purchases due to predicted decline in customer numbers."

[0646] 4. Best before date management

[0647] Input of food ingredient data

[0648] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[0649] Example: When new ingredients are purchased, the server registers their expiration date data in the database.

[0650] Best before date monitoring

[0651] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[0652] Example: The server checks the database every morning and generates an alert for ingredients that are due within the next 3 days.

[0653] Alerting and Notifications

[0654] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests recipes to use them in.

[0655] Example: The device notifies the user, "The expiration date of the chicken is approaching in two days. We have some suggestions for new dishes using this chicken."

[0656] 5. Reservation system integration

[0657] Retrieving reservation data

[0658] Server: Obtains the most recent reservation data in real time from the restaurant reservation system and stores it in a database.

[0659] Example: The server checks the reservation system every morning and stores the reservation status for that day in a database.

[0660] Reservation data analysis

[0661] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[0662] Example: The server calculates the cancellation rate of reservations based on historical reservation data from the past few months.

[0663] Adjustment of purchase quantity

[0664] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[0665] Example: The server makes a suggestion such as, "Because the cancellation rate is high on this day, we will reduce the amount of purchases by 10% compared to normal."

[0666] Proposal Notification

[0667] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[0668] Example: The terminal displays the message, "We have a suggested purchase adjustment based on this week's reservation status," and provides detailed recommended quantities.

[0669] The above is a specific embodiment of the system, which allows restaurants to appropriately manage inventory and adjust purchasing, reducing food waste and improving cost efficiency.

[0670] The processing flow will be explained below.

[0671] 1. Food waste data collection and analysis

[0672] Step 1: Data collection

[0673] Server: Works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data, and stores this data in a database.

[0674] Step 2: Data Preprocessing

[0675] Server: Checks the collected data for missing or outlier values, and performs imputation or correction as necessary.

[0676] Step 3: Analysis by AI model

[0677] Server: Preprocessed data is input into the AI ​​model and analyzed to identify the causes of food waste for each menu item.

[0678] Step 4: Save the results

[0679] Server: Stores the analysis results in a database and makes them later accessible via the dashboard.

[0680] Step 5: View the dashboard

[0681] Device: The food waste analysis results are displayed in graph and report format on the user's dashboard.

[0682] Step 6: User Verification

[0683] Users: See the top causes of food waste on the dashboard.

[0684] 2. Customer Data Predictions

[0685] Step 1: Collect store visit history data

[0686] Server: Collects customer visit history and stores it in a database.

[0687] Step 2: Analyze store visit patterns

[0688] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[0689] Step 3: Sales forecast

[0690] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[0691] Step 4: Viewing Proposals

[0692] Terminal: Displays forecast results and recommended purchase quantities.

[0693] Step 5: Confirm instructions

[0694] User: Places an order for the required amount based on the displayed proposal.

[0695] 3. Weather data forecasting

[0696] Step 1: Getting weather data

[0697] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[0698] Step 2: Correlation analysis between weather and customer traffic

[0699] Server: Compares past weather data with store visit data and analyzes correlations.

[0700] Step 3: Weather-based customer traffic forecast

[0701] Server: Predict the number of customers based on the weather forecast for the next day.

[0702] Step 4: System Notifications

[0703] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[0704] Step 5: Check the prediction

[0705] User: Review and adjust forecasts and purchasing suggestions based on weather forecasts.

[0706] 4. Best before date management

[0707] Step 1: Input food ingredients data

[0708] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[0709] Step 2: Monitor expiration dates

[0710] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[0711] Step 3: Alert Generation

[0712] Server: Generates alert messages about food items that are approaching their expiration date and sends them to the terminal.

[0713] Step 4: Displaying alerts

[0714] Device: Displays an alert message when ingredients are nearing their expiration date and suggests recipes to use them in.

[0715] Step 5: Recipe Ideation

[0716] User: Create and serve new menu items based on the suggested recipes.

[0717] 5. Reservation system integration

[0718] Step 1: Get reservation data

[0719] Server: Retrieves reservation status data in real time from the restaurant reservation system and stores it in a database.

[0720] Step 2: Analyze your booking data

[0721] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[0722] Step 3: Adjusting inventory by reservation

[0723] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[0724] Step 4: Proposal Notification

[0725] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[0726] Step 5: Proposal confirmation

[0727] User: Check the reservation status and place an order based on the suggested purchase amount.

[0728] The above is the processing flow according to a specific embodiment of the present system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste.

[0729] Example 1

[0730] 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."

[0731] Food waste in restaurants is a major issue, as it not only leads to economic losses but also increases environmental impact. It is also difficult to manage appropriate purchasing amounts due to fluctuations in customer numbers and weather, which can further increase food waste. Furthermore, it is difficult to effectively manage ingredients approaching their expiration date and adjust purchasing appropriately based on reservation status, so a system that can efficiently solve these issues is needed.

[0732] 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.

[0733] In this invention, the server includes means for collecting a restaurant's past sales data, purchasing data, and food waste data and storing them in a database, means for preprocessing the data, means for inputting the preprocessed data into a generative AI model to identify the causes of food waste for each menu item, means for saving the analysis results in a database and making them accessible to users, means for generating alerts for food items approaching their expiration dates, means for displaying the food waste analysis results in graphs and reports on the user's dashboard, means for logging into the user's training platform to view and study educational materials and training videos, means for collecting restaurant visit history data and storing it in a database, means for acquiring weather forecast information and storing it in a database, means for acquiring reservation data from a reservation system and storing it in a database, means for predicting the number of customers and sales based on the acquired data and calculating appropriate purchase amounts, and means for notifying the user of the calculated purchase amounts.This enables restaurants to achieve appropriate inventory management and purchase adjustments, significantly reducing food waste and improving cost efficiency.

[0734] "Sales data" refers to data that records transaction information when products or menu items are sold at a restaurant.

[0735] "Purchase data" is data that records transaction information when a restaurant purchases ingredients or products.

[0736] "Food waste data" refers to data that records information about food ingredients that are discarded without being used by restaurants.

[0737] A "database" is a system for organizing and storing collected data and efficiently retrieving necessary information.

[0738] "Data preprocessing" is the process of preparing data in a format suitable for analysis, such as by filling in missing values ​​and correcting outliers.

[0739] A "generative AI model" is an algorithm that recognizes patterns based on past data and makes predictions and classifications.

[0740] "Causes of food waste" refers to factors that cause food waste and disposal in restaurants.

[0741] "Analysis results" are information that represents findings and conclusions obtained from collected and analyzed data.

[0742] An "alert" is a message that notifies or warns you when a specific condition is met.

[0743] A "dashboard" is an interface that allows users to visualize data.

[0744] A "graph or report format" is a format for visually displaying data, making it easier to understand.

[0745] A "training platform" is an environment or system for users to learn or train.

[0746] "Educational materials" are content or materials for learning specific knowledge or skills.

[0747] A "training video" is a video that provides learning content visually.

[0748] "Visit history data" is recorded information when a customer visits a restaurant.

[0749] "Weather forecast information" is forecast data regarding future weather.

[0750] "Reservation data" is data that records information when a customer reserves a table at a restaurant.

[0751] "Inventory management" is the process of properly maintaining and managing inventory of goods and ingredients.

[0752] "Purchase adjustment" refers to making adjustments to purchase the appropriate amount of ingredients and products based on forecasts and actual results.

[0753] "Improving cost efficiency" refers to reducing costs and utilizing funds efficiently.

[0754] This invention is a system for reducing food waste through the collection and analysis of restaurant sales data, purchasing data, and food waste data. This system operates in cooperation with a server, terminals, and users.

[0755] The server connects to the restaurant's POS system and collects sales data, purchasing data, and food waste data. This data is then stored in a database. For example, after closing each day, the server automatically retrieves sales data from the POS system and stores it in the database. It also extracts and stores purchasing data and food waste data in the same way.

[0756] The server complements missing values ​​and corrects outliers in the collected data. This process improves the reliability of the data and increases the accuracy of analysis. For example, the server complements missing data with data from the previous day and corrects any outliers to bring them within the normal range. This results in a data format suitable for analysis.

[0757] The server then inputs the preprocessed data into a generative AI model, which uses that data to identify the causes of food waste for each menu item. The AI ​​model uses statistical methods based on data from the past few months to identify the main causes of food waste and their impact. For example, it can identify specific causes such as "ingredient B from dish A is frequently wasted."

[0758] The analysis results are stored in a database and displayed on a dashboard that users can access. This dashboard visualizes the data in graphs and reports, and is designed to make it easy for users to understand. For example, it visually displays the main causes of food waste and trends in waste volume.

[0759] In addition, the server generates an alert for food ingredients that are approaching their expiration date and notifies the user. For example, if there is food that has an expiration date of two days, an alert saying "Chicken expiration date is approaching" will be displayed on the terminal. This alert is an important measure to prevent food waste.

[0760] Store visit history data is also collected by the server and stored in a database. This data is analyzed and the next number of customers is predicted based on past patterns. The server uses the past year's store visit data to analyze store visit trends for specific days of the week and time periods, and predicts the number of customers for the following week. For example, based on a pattern of high customer numbers on Friday nights, the server predicts the number of customers for the following Friday.

[0761] Weather forecast information is also obtained by the server and stored in a database. The server calls a weather data API to obtain and store the weather forecast data for that day. This weather data is compared with past store visit data and correlations are analyzed. Based on the analysis results, the server concludes that "the number of customers decreases by approximately 20% on rainy days."

[0762] The server comprehensively analyzes this data and predicts the number of customers based on the weather forecast for the next day. For example, if rain is forecast for the next day, the server predicts that the number of customers will decrease. The server notifies the user of this prediction and a suggested amount of stock to be purchased. The terminal displays a message such as, "The forecast suggests that the number of customers may decrease tomorrow, so we suggest reducing the amount of stock to be purchased."

[0763] Furthermore, the system retrieves reservation data from the reservation system and stores it in a database. Based on this data, it generates a purchase adjustment proposal based on the reservation status and notifies the user. For example, the terminal may display a message saying, "We have a purchase adjustment proposal based on this week's reservation status," along with detailed recommendations for purchase quantities.

[0764] Examples of specific prompts include:

[0765] "Calculate the necessary inventory based on the most recent reservation data."

[0766] "Please identify the main causes of food waste based on sales data and food waste data from the past three months."

[0767] "Based on this week's weather forecast, please predict the number of customers we will have and suggest the amount of stock we should stock."

[0768] This will enable restaurants to properly manage their inventory and adjust their purchasing, significantly reducing food waste and improving cost efficiency.

[0769] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0770] Step 1:

[0771] The server works with the restaurant's POS system to collect sales data, purchasing data, and food waste data. This data is automatically acquired after closing time each day and stored in a database. The input is raw data acquired from the POS system, and the output is raw data stored in the database. Specifically, the server calls the API for the POS system and saves the acquired data in the database.

[0772] Step 2:

[0773] The server complements missing values ​​and corrects outliers in the collected data. This process results in a data format suitable for analysis. The input is raw data stored in the database, and the output is preprocessed data. Specifically, it complements missing values ​​with data from the previous day, and corrects any outliers to within an appropriate range.

[0774] Step 3:

[0775] The server inputs the preprocessed data into the generative AI model to identify the causes of food waste for each menu item. The input is the preprocessed data, and the output is the analysis results of the causes of food waste. Specifically, data from the past few months is input into the generative AI model, which analyzes it using statistical methods to identify the causes of food waste.

[0776] Step 4:

[0777] The server stores the analysis results generated by the AI ​​model in a database and displays them on a dashboard that users can access. The input is the analysis results of the causes of food waste, and the output is the visualized data displayed on the dashboard. Specifically, the analysis results are converted into graphs and reports and displayed in a format that is easy for users to access.

[0778] Step 5:

[0779] The server generates an alert for food ingredients approaching their expiration date and notifies the user. The input is the food ingredient data for which the expiration date is approaching, and the output is an alert message displayed on the terminal. Specifically, the server periodically checks the database, generates an alert for food ingredients approaching their expiration date, and notifies the user.

[0780] Step 6:

[0781] The server collects customer visit history data and stores it in a database. The input is the visit history data, and the output is the visit data stored in the database. Specifically, it obtains the visit history data from the POS system and saves it in the database.

[0782] Step 7:

[0783] The server analyzes the visit history data and predicts the next number of customers based on past patterns. The input is the past visit history data, and the output is the predicted number of customers. Specifically, it analyzes visit trends by day of the week and time of day based on data from the past year, and predicts the next number of customers.

[0784] Step 8:

[0785] The server obtains weather forecast information from the weather data API and stores it in a database. The input is the weather forecast information obtained from the weather data API, and the output is the weather forecast data stored in the database. Specifically, the server calls the weather data API, obtains the weather forecast data, and stores it in the database.

[0786] Step 9:

[0787] The server compares past weather data with store visit data and analyzes the correlation. The input is past weather data and store visit data, and the output is the correlation analysis results between weather and store visits. Specifically, it cross-analyzes both sets of data to identify the impact that weather has on the number of store visitors.

[0788] Step 10:

[0789] The server predicts the number of customers based on the weather forecast for the next day. The input is weather forecast data, and the output is the predicted number of customers for the next day. Specifically, the server predicts the number of customers based on the weather forecast data and calculates the appropriate amount of stock to be purchased.

[0790] Step 11:

[0791] The server obtains reservation data from the reservation system and stores it in a database. The input is the reservation data obtained from the reservation system, and the output is the reservation data stored in the database. Specifically, the server accesses the reservation system to obtain data and stores it in the database.

[0792] Step 12:

[0793] The server analyzes the seating rate and reservation cancellation rate based on the reservation data, and generates a purchase adjustment proposal according to the reservation situation. The input is reservation data, and the output is a purchase adjustment proposal. Specifically, it analyzes past reservation history and proposes appropriate purchase amounts based on the cancellation rate and seating rate.

[0794] Step 13:

[0795] The terminal notifies the user of the forecast results and recommended purchase quantities. The input is the recommended purchase data from the server, and the output is a message displayed to the user. Specifically, the terminal notifies the user of the purchase adjustment proposal using a pop-up message or notification function.

[0796] (Application example 1)

[0797] 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."

[0798] In restaurant operations, excessive food waste and lost sales opportunities due to shortages are problems. These problems arise because it is difficult to properly manage inventory and predict customer demand. Also, adjusting purchasing quantities based on fluctuations in weather and customer visit history is difficult, which contributes to waste. Furthermore, inadequate management of expiration dates also leads to food loss.

[0799] 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.

[0800] In this invention, the server includes means for collecting the restaurant's past sales data, purchasing data, and food waste data and storing them in a database, means for preprocessing the data, means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item, means for saving the analysis results in a database and making them accessible to users, means for generating alerts for food ingredients whose expiration dates are approaching, means for displaying the food waste analysis results in graphs and reports on the user's dashboard, means for sending alerts and prediction results via push notifications to the user's mobile device, and means for providing recommended purchase amounts based on the prediction results. This enables the reduction of food waste and efficient inventory management in restaurants.

[0801] "Past sales data of a restaurant" is information relating to the quantity and price of products sold in the past at a restaurant.

[0802] "Purchase data" refers to information about ingredients and other necessities purchased by a restaurant.

[0803] "Food waste data" is information on the amount and type of food that is discarded without being used.

[0804] A "database" is a system for centrally managing and storing collected data.

[0805] "Data preprocessing" is the process of filling in missing data values ​​and correcting outliers, preparing the data in a form that is easy to analyze.

[0806] An "AI model" is an algorithm that uses artificial intelligence to analyze data and make predictions and classifications.

[0807] "Causes of food waste" are the main reasons why food ingredients are discarded unnecessarily.

[0808] "Analysis results" refers to the information and insights obtained as a result of analyzing data.

[0809] An "alert" is a warning message that notifies the user of urgent information.

[0810] A "dashboard" is a tool that visually organizes information and displays it in a way that allows users to intuitively understand it.

[0811] A "mobile terminal" is a mobile device such as a smartphone or tablet.

[0812] "Push notifications" are a method of sending information to a user's device in real time.

[0813] "Recommended purchase quantities" are the appropriate amounts of ingredients to purchase suggested based on forecast data.

[0814] This invention is a system for streamlining restaurant operations and reducing food waste. This system collects sales data, purchasing data, food waste data, etc., and analyzes them using an AI model. It also notifies users of prediction results and alerts, supporting appropriate purchasing and inventory management.

[0815] Data collection and storage

[0816] The server connects to the restaurant's POS system and collects past sales data, purchasing data, and food waste data, storing it in a database. This data is automatically retrieved, organized, and saved after closing time each day.

[0817] Data Preprocessing

[0818] The server uses the Python pandas library to fill in missing values ​​and correct outliers in the collected data, and then formats it for analysis.

[0819] Analysis by AI model

[0820] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item. The AI ​​model uses scikit-learn's Linear Regression model to make highly accurate predictions based on past data.

[0821] Save and notify results

[0822] The analysis results are stored in a database and displayed on a dashboard for user access, and alerts are generated for ingredients approaching their expiration date and sent to users' mobile devices via push notifications.

[0823] User Dashboard

[0824] Users can visually check the results of food waste analysis in the form of graphs and reports through the dashboard, which is implemented using the Shiny package in the R programming language.

[0825] Providing prediction results

[0826] The server calculates sales forecasts and recommended stock quantities based on the predicted number of customers for the next week, and sends these to the user's mobile device via push notification.

[0827] Specific examples

[0828] For example, when a store manager opens the application on their smartphone, it displays next week's predicted sales, purchasing suggestions, and alerts for ingredients that are nearing their expiration date.

[0829] Prompt Sentence Examples

[0830] Examples of prompt sentences include:

[0831] "Please use the store's sales data, purchasing data, food waste data, and weather forecast data from the past month to identify causes of food waste and predict the number of customers visiting the store. Also, please make purchasing amount suggestions based on the results."

[0832] The above is an embodiment of the present invention.

[0833] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0834] Step 1:

[0835] The server connects to the restaurant's POS system and collects past sales data, purchasing data, and food waste data.

[0836] Input: Sales data, purchasing data, and food waste data from the POS system.

[0837] Output: The collected data is stored in a database.

[0838] Specifically, after closing time each day, the server accesses the POS system, automatically retrieves the necessary data via API, and stores it in a database.

[0839] Step 2:

[0840] The server performs data preprocessing by filling in missing values ​​and correcting outliers in the collected data.

[0841] Input: Raw sales data, purchasing data, and food waste data stored in the database.

[0842] Output: Preprocessed data.

[0843] Specifically, missing data is filled in with the previous day's values ​​using Python's pandas library, and outliers are corrected to within a statistically appropriate range.

[0844] Step 3:

[0845] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item.

[0846] Input: Preprocessed sales data, purchasing data, and food waste data.

[0847] Output: Analysis results of causes of food waste.

[0848] Specifically, we use scikit-learn's Linear Regression model to analyze correlations in the data and identify the main causes of food waste and their contribution.

[0849] Step 4:

[0850] The server stores the analysis results in a database and makes them accessible to users through a dashboard.

[0851] Input: Analysis results of causes of food waste.

[0852] Output: Analysis results stored in a database.

[0853] Specifically, the analysis results are stored in a database, and users can view the results by accessing a dashboard via a web interface.

[0854] Step 5:

[0855] The server generates an alert for food ingredients approaching their expiration date and sends a push notification to the user's mobile device.

[0856] Input: Best before information in the database.

[0857] Output: Alert notification.

[0858] Specifically, the database is checked periodically, and if the expiration date is approaching, an alert is sent to the user's email address using an SMTP server.

[0859] Step 6:

[0860] The server calculates sales forecasts and recommended stock quantities based on the predicted number of customers visiting the store next week, and sends these to the user's mobile device via push notification.

[0861] Input: Store visit history data and weather forecast data.

[0862] Output: Sales forecast and recommended purchase quantities.

[0863] Specifically, an AI model makes predictions based on store visit history and weather data, calculates the amount of stock to be purchased based on the results, and notifies the user's smartphone.

[0864] Step 7:

[0865] Users can check food waste analysis results, store visit predictions, purchasing suggestions, and more through the dashboard, and take appropriate action.

[0866] Input: Server-generated analysis results, forecast data, and purchasing recommendations.

[0867] Output: User confirmation and action.

[0868] Specifically, users access the dashboard through a web browser or a dedicated app, view information in the form of graphs and reports, and make adjustments to purchases and menus as needed.

[0869] 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.

[0870] This invention is a system that collects restaurant sales data, purchasing data, and food waste data and uses this data to reduce food waste. Furthermore, this invention achieves more effective operation by combining it with an emotion engine that recognizes user emotions. Below, we will explain in detail how each component works together and functions as an entire system.

[0871] 1. Food waste data collection and analysis

[0872] Data collection

[0873] Server: Works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data, and stores it in a database.

[0874] Example: The server automatically retrieves sales data from the POS system after closing each day and stores it in a database.

[0875] Data Preprocessing

[0876] Server: Complements missing values ​​and corrects outliers in the collected data, and prepares it in a format suitable for analysis.

[0877] Example: The server complements missing data with data from the previous day and corrects any abnormal values ​​to bring them within the normal range.

[0878] Analysis by AI model

[0879] Server: Preprocessed data is input into the AI ​​model and analyzed to identify the causes of food waste for each menu item.

[0880] Example: The AI ​​model uses statistical methods based on data from the past three months to identify the main causes of food waste and their impact.

[0881] Save and notify results

[0882] Server: Stores the analysis results in a database for user access, and generates alerts for ingredients approaching their expiration date.

[0883] Example: The saved analysis results are visualized on a dashboard, and an alert is sent immediately if there is food that has a shelf life of two days.

[0884] 2. Customer Data Predictions

[0885] Collection of store visit history data

[0886] Server: Periodically collects customer visit history and stores it in a database.

[0887] Example: The server retrieves data on customer repeat visits and the number of new customers from the POS system and stores it in a database.

[0888] Analysis of store visit patterns

[0889] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[0890] Example: The server uses visitor data from the past year to analyze visitor trends for specific days of the week and time periods, and predicts the number of customers to visit next week.

[0891] Sales forecast and purchase quantity proposals

[0892] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[0893] Example: The server predicts sales for each menu item based on the predicted number of customers for the next week, and calculates the amount of ingredients needed to purchase to achieve this.

[0894] Proposal Notification

[0895] Terminal: Notifies the user of the forecast results and recommended purchase quantities.

[0896] Example: The terminal displays a pop-up message with suggested purchases for next week (e.g. 10 kg of chicken, 20 kg of vegetables).

[0897] 3. Weather data forecasting

[0898] Obtaining weather data

[0899] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[0900] Example: Every morning, the server calls a weather data API to retrieve the weather forecast data for that day.

[0901] Correlation analysis between weather and customer numbers

[0902] Server: Compares past weather data with store visit data and analyzes correlations.

[0903] Example: The server cross-analyzes weather data and store visit data from the past year to determine the impact of weather on store visits.

[0904] Weather-based customer traffic forecast

[0905] Server: Predict the number of customers based on the weather forecast for the next day.

[0906] Example: Based on the analysis result that "the number of customers decreases by about 20% on rainy days," the server predicts the number of customers if rain is forecast for the next day, taking that impact into account.

[0907] System Notifications

[0908] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[0909] Example: On days when rain is forecast, the terminal will display a pop-up suggesting, "Reduce purchases due to predicted decline in customer numbers."

[0910] 4. Best before date management

[0911] Input of food ingredient data

[0912] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[0913] Example: When new ingredients are purchased, the server registers their expiration date data in the database.

[0914] Best before date monitoring

[0915] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[0916] Example: The server checks the database every morning and generates an alert for ingredients that are due within the next 3 days.

[0917] Alerting and Notifications

[0918] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests recipes to use them in.

[0919] Example: The device notifies the user, "The expiration date of the chicken is approaching in two days. We have some suggestions for new dishes using this chicken."

[0920] 5. Reservation system integration

[0921] Retrieving reservation data

[0922] Server: Obtains the most recent reservation data in real time from the restaurant reservation system and stores it in a database.

[0923] Example: The server checks the reservation system every morning and stores the reservation status for that day in a database.

[0924] Reservation data analysis

[0925] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[0926] Example: The server calculates the cancellation rate of reservations based on historical reservation data from the past few months.

[0927] Adjustment of purchase quantity

[0928] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[0929] Example: The server makes a suggestion such as, "Because the cancellation rate is high on this day, we will reduce the amount of purchases by 10% compared to normal."

[0930] Proposal Notification

[0931] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[0932] Example: The terminal displays the message, "We have a suggested purchase adjustment based on this week's reservation status," and provides detailed recommended quantities.

[0933] 6. Combining Emotion Engines

[0934] Emotion recognition by emotion engine

[0935] Server: Analyzes the user's voice and text input and recognizes emotions using an emotion engine.

[0936] Example: The server analyzes voice comments and feedback in real time as users operate the dashboard, and recognizes emotions using an emotion engine.

[0937] Customized display content based on emotions

[0938] Device: The content displayed on the dashboard is automatically customized based on the user's emotions recognized by the emotion engine.

[0939] Example: If the user is stressed, simplify the display and prioritize important information.

[0940] Changing information provision based on emotions

[0941] Device: Based on the user's emotions recognized by the emotion engine, the method of providing information on reducing food waste and purchasing suggestions is changed.

[0942] Example: If the user is not satisfied with the previous suggestion, switch to a more detailed and illustrated presentation.

[0943] Recording and analyzing emotional data

[0944] Server: The user's emotion data recognized by the emotion engine is stored in a database and used for later analysis.

[0945] Example: The server stores the user's usage history along with emotional data, and periodically analyzes this data to help improve the system.

[0946] The above is the processing flow of a specific embodiment of this system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste. Furthermore, by combining it with an emotion engine, the user experience can be improved and the effectiveness of the system can be further enhanced.

[0947] The processing flow will be explained below.

[0948] 1. Food waste data collection and analysis

[0949] Step 1: Data collection

[0950] Server: Connects to the restaurant's POS system via API, collects past sales data, purchasing data, and food waste data on a daily basis, and stores this data in a database.

[0951] Step 2: Data Preprocessing

[0952] Server: Preprocesses the collected data and performs missing value interpolation and outlier correction. For example, if some sales data is missing, the data from the previous day is used as a reference to complete the data.

[0953] Step 3: Analysis by AI model

[0954] Server: The preprocessed data is input into an AI model equipped with statistical methods, and analysis is performed to identify the causes of food waste for each menu item. The analysis results are then compiled into a report.

[0955] Step 4: Save the results

[0956] Server: The analysis results are stored in a database for later access by users. The stored data includes the causes and impact of food waste for each menu item.

[0957] Step 5: View the dashboard

[0958] Device: The results of food waste analysis are displayed visually in graphs and reports on the user's dedicated dashboard. The interface is optimized to make it intuitive for users.

[0959] Step 6: User Verification

[0960] Users: Access the dashboard to view the main causes of food waste and their associated data, identify problems, and consider solutions.

[0961] 2. Customer Data Predictions

[0962] Step 1: Collect store visit history data

[0963] Server: Periodically collects customer visit history from the restaurant's POS system and stores it in a database.

[0964] Step 2: Analyze store visit patterns

[0965] Server: Analyzes collected store visit history data and identifies patterns of store visits by day of the week, time of day, and season. For example, it extracts trends such as higher customer numbers on weekends compared to weekdays.

[0966] Step 3: Sales forecast

[0967] Server: Based on the analysis of customer visit patterns, it performs calculations to predict the next number of customers and sales. Based on the prediction results, it calculates the recommended stock amount.

[0968] Step 4: Viewing Proposals

[0969] Terminal: The forecast results and recommended purchase quantities are displayed on the interface. For example, the recommended purchase quantities (e.g., 10 kg of chicken and 20 kg of vegetables) based on the predicted number of customers for the next week are displayed.

[0970] Step 5: Confirm instructions

[0971] User: Checks the displayed forecast results and purchase proposals, decides on the actual purchase amount, and places an order with the supplier by pressing the approval button on the screen.

[0972] 3. Weather data forecasting

[0973] Step 1: Getting weather data

[0974] Server: Using the weather data API, the latest weather forecast information is obtained daily and stored in a database.

[0975] Step 2: Correlation analysis between weather and customer traffic

[0976] Server: Correlate historical weather data with store visit data to identify the impact of weather on store visits. For example, confirm that store visits on rainy days are lower than normal.

[0977] Step 3: Weather-based customer traffic forecast

[0978] Server: Based on the weather forecast for the next day, calculates the number of customers to visit. If the weather forecast predicts rain, it takes into account that the number of customers will be lower than usual.

[0979] Step 4: System Notifications

[0980] Terminal: Notifies the user of customer traffic predictions based on weather forecasts and suggests adjustments to purchasing quantities based on this. For example, on days when rain is predicted, a suggestion to reduce purchasing quantities by 20% is displayed.

[0981] Step 5: Check the prediction

[0982] User: Review forecasts and purchasing suggestions based on weather forecasts and make adjustments as needed.

[0983] 4. Best before date management

[0984] Step 1: Input food ingredients data

[0985] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database. Whenever new ingredients are purchased, the expiration date information is registered.

[0986] Step 2: Monitor expiration dates

[0987] Server: Periodically checks the expiration dates of ingredients in the database and identifies ingredients that are approaching their expiration date.

[0988] Step 3: Alert Generation

[0989] Server: Generates an alert message for food ingredients that are approaching their expiration date and notifies the terminal.

[0990] Step 4: Displaying alerts

[0991] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests new recipes using those ingredients. For example, it displays a message like, "Your chicken will expire in two days. How about making a special dish using this chicken?"

[0992] Step 5: Recipe Ideation

[0993] User: Create and serve new menu items based on the suggested recipes. Update the menu display as needed.

[0994] 5. Reservation system integration

[0995] Step 1: Get reservation data

[0996] Server: Obtains reservation data in real time from the restaurant reservation system and stores it in a database.

[0997] Step 2: Analyze your booking data

[0998] Server: Analyzes reservation cancellation rates, seating rates, etc. based on reservation data.

[0999] Step 3: Adjusting inventory by reservation

[1000] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[1001] Step 4: Proposal Notification

[1002] Terminal: Notify the user of a purchase quantity adjustment proposal based on the reservation status. For example, display "There is a purchase adjustment proposal based on this week's reservation status."

[1003] Step 5: Proposal confirmation

[1004] User: Checks the reservation status and places an actual order based on the suggested purchase amount.

[1005] 6. Combining Emotion Engines

[1006] Step 1: Emotion recognition by the emotion engine

[1007] Server: Analyzes the user's voice and text input in real time and recognizes emotions using an emotion engine. For example, if a user inputs a voice comment while operating the dashboard, the voice data is analyzed by the emotion engine.

[1008] Step 2: Customize your display based on emotions

[1009] Device: The dashboard display is automatically customized based on the user's emotions as recognized by the emotion engine. For example, if the user is feeling stressed, the display will be simplified and important information will be prioritized.

[1010] Step 3: Modify your information based on emotions

[1011] Device: Based on the user's emotions recognized by the emotion engine, the way information on food waste reduction and purchasing suggestions is presented is changed. For example, if the user is dissatisfied with the previous suggestion, the explanation is made more detailed and the display is switched to one that makes use of more illustrations.

[1012] Step 4: Record and analyze emotion data

[1013] Server: The user's emotional data recognized by the emotion engine is stored in a database and used for later analysis. The emotional data is used as a reference for periodic system improvements.

[1014] The above is the processing flow of a specific embodiment of this system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste. Furthermore, by combining it with an emotion engine, the user experience can be improved and the effectiveness of the system can be further enhanced.

[1015] Example 2

[1016] 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."

[1017] Appropriate inventory management and food waste reduction are important issues in modern restaurant management. Conventional methods involve manually analyzing sales and purchasing data to generate food waste data, but this method is inaccurate and makes effective food waste reduction and inventory management difficult. Furthermore, there is an insufficient system for integrating and utilizing weather data, restaurant visit forecast data, and reservation data, creating a need for more efficient food ingredient management and customer trend forecasts. Furthermore, there is a lack of information provided that takes user stress and satisfaction into consideration, making it difficult to provide an optimal user experience.

[1018] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting and storing the restaurant's past sales data, purchasing data, and food waste data in a database; means for preprocessing the data; means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item; means for saving the analysis results in a database and making them accessible to the user; means for generating alerts for food ingredients whose expiration dates are approaching; means for displaying the food waste analysis results in graphs and reports on the user's dashboard; means for customizing the display content using an emotion engine that recognizes the user's emotions; and means for recording and analyzing the user's emotion data. This enables efficient food waste reduction, appropriate inventory management, and highly accurate purchasing suggestions based on restaurant visit predictions. Furthermore, optimal information is provided according to the user's emotional state, improving the user experience.

[1019] "Food and beverage establishments" are establishments that serve food and beverages, including restaurants, cafes, and bars.

[1020] "Sales data" refers to information regarding the quantity and value of products sold by a restaurant during a specific period.

[1021] "Purchasing data" refers to information about ingredients, beverages, and other items purchased by a restaurant during a specific period.

[1022] "Food waste data" refers to information on the types and quantities of food ingredients that are discarded unused by restaurants.

[1023] "Database" refers to a system for organizing, storing, and managing collected data.

[1024] "Data preprocessing" refers to the process of performing operations such as filling in missing values ​​and correcting outliers in order to convert data into a format suitable for analysis.

[1025] An "AI model" is a program that uses artificial intelligence to analyze data and make predictions or classifications that are useful for a specific purpose.

[1026] "Causes of food waste" refers to the main factors and reasons why food is wasted.

[1027] "Analysis results" refers to conclusions and findings obtained through data analysis work.

[1028] "Alert" refers to a warning message sent to provide important information or caution.

[1029] A "dashboard" is an interface that visually displays important information, allowing users to understand the situation at a glance.

[1030] An "emotion engine" refers to a system for recognizing and analyzing emotions from a user's voice or text.

[1031] "Customizing the display content" refers to adjusting the display method and content of information according to the user's emotions and needs.

[1032] "Emotional Data" refers to information about a user's emotional state, including that recognized and recorded by the system.

[1033] "Visit history" refers to records of the date, time, and frequency of a customer's visits to a restaurant.

[1034] "Weather Forecast Information" means data regarding future weather conditions in a particular geographic area.

[1035] "Correlation" refers to a statistical association between two or more variables.

[1036] "Reservation data" refers to information regarding seat and service reservations made in advance by customers to restaurants.

[1037] The present invention is a system for reducing food waste and optimizing inventory management in restaurants. This system is built on the interaction between a server, a terminal, and a user, and the invention is implemented as follows.

[1038] Data collection and storage

[1039] The server works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data and store it in a database.

[1040] Example: After closing each day, the server automatically retrieves data from the POS system and stores it in a database.

[1041] Data Preprocessing

[1042] The server performs preprocessing such as filling in missing values ​​in the collected data with data from the previous day and correcting outliers to bring them within the normal range, and then converts the data into a format suitable for analysis.

[1043] Example: The server fills in any missing data with data from the previous day, and corrects any extremely outlying values.

[1044] Analysis by AI model

[1045] The server inputs the preprocessed data into an AI model and performs statistical analysis to identify the causes of food waste in restaurants.

[1046] Example: The server identifies the main causes of food waste based on data from the past three months and assesses their impact.

[1047] Save and notify results

[1048] The server stores the analysis results in a database and generates alerts based on the results for food ingredients approaching their expiration date.

[1049] Example: Food waste analysis results are saved in dashboard format, and an alert message is generated for food ingredients with a shelf life of less than two days.

[1050] User Interface

[1051] The device notifies the user of analysis results and alerts, and displays the food waste analysis results in graphs and reports on the dashboard.

[1052] Example: When users access the dashboard, the causes and impact of food waste for each ingredient are visualized, prompting them to take necessary action.

[1053] Customization with Emotion Engine

[1054] The server analyzes the user's voice and text input and uses an emotion engine to recognize the user's emotions.

[1055] Example: When a user interacts with a dashboard, they can enter feedback and comments, and the system can recognize their emotions from the content.

[1056] The terminal customizes the display content on the dashboard based on the user's emotions recognized by the emotion engine.

[1057] Example: If the user is stressed, simplify the display and prioritize the most important information.

[1058] Storing and analyzing emotional data

[1059] The server stores the recognized emotion data in a database for later analysis.

[1060] Example: Emotional data is stored along with the user's operation history and periodically analyzed to help improve the system.

[1061] Prompt Sentence Examples

[1062] Use the following prompt to instruct the generative AI model to identify the causes of food waste from food waste data:

[1063] "Based on data from the past three months, please identify the main causes of food waste and their impact."

[1064] The above is a specific example of an embodiment of the present invention. This invention enables restaurants to efficiently reduce food waste and achieve appropriate inventory management, thereby improving customer satisfaction.

[1065] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1066] Step 1: Collect and store data

[1067] The server periodically connects to the restaurant's POS system to obtain past sales data, purchasing data, and food waste data.

[1068] Input: Sales data, purchasing data, food waste data collected from POS systems

[1069] Output: Sales data, purchasing data, food waste data stored in a database

[1070] Specific operation: After closing time every day, the server automatically accesses the POS system, extracts the necessary data, and stores it in the database.

[1071] Step 2: Preprocessing the data

[1072] The server completes missing values ​​and corrects outliers in the collected data.

[1073] Input: Sales data, purchasing data, food waste data stored in the database

[1074] Output: Preprocessed data

[1075] Specific operation: The server identifies missing values ​​and fills them with data from the previous day. If an outlier is detected, it corrects it to an appropriate value.

[1076] Step 3: Identifying causes of food waste using an AI model

[1077] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item.

[1078] Input: Preprocessed data

[1079] Output: Report on causes of food waste and their impact

[1080] Specific operation: The server prompts the generative AI model, saying, "Based on data from the past three months, please identify the main causes of food waste and their impact," and analyzes the results.

[1081] Step 4: Save the analysis results and generate alerts

[1082] The server stores the analysis results obtained from the AI ​​model in a database and generates alerts for ingredients that are approaching their expiration date.

[1083] Input: Food waste cause report, food ingredient data

[1084] Output: Saved reports, generated alerts

[1085] Specific operation: The server stores the analysis results in a database in the form of a dashboard and generates an alert for ingredients whose expiration date is within two days.

[1086] Step 5: User interface notification

[1087] The terminal notifies the user of the analysis results and alerts and displays them on a dashboard.

[1088] Input: Analysis results and alerts stored in the database

[1089] Output: Graphs, reports, and popup alerts displayed on the user dashboard

[1090] Specific operation: When a user accesses the dashboard, the device visually displays the causes of food waste and their impact for each ingredient, and notifies them of expiration dates via a pop-up alert.

[1091] Step 6: Emotion Recognition and Customization with the Emotion Engine

[1092] The server analyzes the user's voice and text input using an emotion engine to recognize emotions.

[1093] Input: User voice commands and text feedback

[1094] Output: User emotion data

[1095] Specific operation: The server analyzes the voice comments and feedback provided by the user during operation, and recognizes and records emotions using an emotion engine.

[1096] The device will adjust the content displayed on the dashboard based on the recognized emotion.

[1097] Input: User emotion data

[1098] Output: Customized Dashboard View

[1099] Specific behavior: When the user is feeling stressed, the device simplifies the display and prioritizes displaying important information.

[1100] Step 7: Storing and analyzing sentiment data

[1101] The server stores the user's emotion data recognized by the emotion engine in a database and periodically analyzes it.

[1102] Input: User emotion data

[1103] Output: Sentiment analysis report

[1104] Specific operation: The server stores the user's emotional data along with their operation history in a database, and periodically analyzes the emotional data to improve the system.

[1105] The above are the specific processing steps of the program of this system.

[1106] (Application example 2)

[1107] 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."

[1108] Conventional restaurant inventory management systems often collect and analyze sales and purchasing data separately, making it difficult to reduce food waste and predict appropriate purchasing amounts. Furthermore, proposals did not take into account factors such as weather changes or consumer sentiment, resulting in a lack of concrete countermeasures. The food delivery industry, in particular, requires real-time inventory management and forecasting to respond to fluctuations in orders. A system that solves these problems and enables more efficient inventory management and food waste reduction is needed.

[1109] 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 the restaurant's past sales data, purchasing data, and food waste data and storing them in a database; means for preprocessing the data; means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item; means for saving the analysis results in a database and making them accessible to users; means for generating alerts for food ingredients whose expiration date is approaching; means for displaying the food waste analysis results in graphs and reports on the user's dashboard; means for logging into the user's training platform and viewing and studying educational materials and training videos; means for forecasting food delivery sales and recommending necessary inventory and purchasing; means for importing weather data, analyzing the impact of weather on delivery orders, and notifying the user of the results; and means for recognizing the emotions of delivery personnel and store staff and customizing operation methods and information presentation. This enables comprehensive, real-time inventory management and sales forecasting, further improving the user experience.

[1110] "Sales data" refers to information on the total revenue earned by a restaurant over a certain period of time.

[1111] "Purchasing data" is detailed information about when a restaurant purchases ingredients and products.

[1112] "Food waste data" is information on food ingredients that were discarded because they were not used.

[1113] A "database" is a system for efficiently managing, searching, and manipulating multiple pieces of data.

[1114] "Data preprocessing" is the process of converting collected raw data into a form suitable for analysis.

[1115] An "AI model" is a type of algorithm that uses artificial intelligence to analyze data and make predictions.

[1116] "Food loss" is the waste that occurs when food ingredients are discarded without being used.

[1117] An "alert" is a system that notifies a user of a warning when a specific condition occurs.

[1118] A "dashboard" is a user interface that allows various data to be visually displayed and manipulated.

[1119] "Training Platform" means a system for providing educational materials and training videos.

[1120] "Food delivery" is a service that delivers ordered meals to a designated location.

[1121] "Weather data" is data that includes various information about the weather.

[1122] The "emotion engine" is a function that recognizes and analyzes the user's emotions and adjusts the system's behavior based on the results.

[1123] This invention is a system that collects and analyzes past sales data, purchasing data, and food waste data from restaurants to reduce food waste and achieve efficient inventory management. The invention also aims to improve operability and user experience by incorporating an approach specialized for food delivery services and using an emotion engine that recognizes user emotions.

[1124] The server connects to the POS system to collect various data from the restaurant. Sales data, purchasing data, and food waste data are sent to the server after the end of business each day and stored in a database. The server also performs preprocessing such as filling in missing values ​​and correcting outliers.

[1125] The pre-processed data is then analyzed using a generative AI model. This AI model identifies causes of food waste based on historical data and supports efficient inventory management. It also generates sales forecasts for food delivery services. For example, by combining historical sales data with weather data, it can predict the impact of weather on delivery orders and adjust ingredient purchases accordingly.

[1126] Weather data is obtained from an external weather data API and stored on the server. This data is input into an AI model and used to predict customer numbers and make purchasing recommendations based on the next day's weather forecast. Users can view these predictions on a dashboard and receive specific alerts and purchasing recommendations.

[1127] Furthermore, the server uses an emotion engine to analyze the emotions of delivery personnel and store staff, and customizes the user interface operation method and information presentation. If the user feels stressed about a particular operation, the operation procedure is simplified and important information is prioritized.

[1128] For example, if the emotion engine detects that the user is stressed, it will provide detailed, visual information, or if the user is dissatisfied with the previous purchase suggestion, it will switch to a more detailed explanation and illustration-heavy display.

[1129] Specific prompts that are used include:

[1130] "Please demonstrate an application that uses sales data, purchase data, and waste data from the past three months to forecast sales for the next week and suggest optimal inventory levels. Also, please demonstrate how to take into account the effects of weather and adjust inventory levels on days with bad weather. Finally, please provide a concrete explanation of the forecast based on sales data and how to notify the results."

[1131] This enables comprehensive, real-time inventory management and sales forecasting, further enhancing the user experience.

[1132] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1133] Step 1:

[1134] The server connects to the restaurant's POS system and automatically collects past sales data, purchasing data, and food waste data after each day's business hours. This data is then stored in a database. The inputs are sales data, purchasing data, and waste data obtained from the POS system, and the output is stored in the database.

[1135] Step 2:

[1136] The server fills in missing values ​​and corrects outliers in the collected data to prepare it for analysis. This preprocessing includes, for example, filling in missing data with data from the previous day and correcting outliers to bring them within a normal range. The input is raw data, and the output is preprocessed data.

[1137] Step 3:

[1138] The server inputs the preprocessed data into the AI ​​model to identify the causes of food waste for each menu item. In this process, the AI ​​model performs statistical analysis of the data to identify the main causes of food waste and their impact. The input is the preprocessed data, and the output is the results of identifying the causes of food waste.

[1139] Step 4:

[1140] The server stores the analysis results of the AI ​​model in a database and makes them accessible to users. The analysis results are displayed in the form of graphs and reports on a dashboard. The input is the analysis results of the AI ​​model, and the output is the analysis results converted into an easy-to-read format.

[1141] Step 5:

[1142] The server generates an alert for food items approaching their expiration date. This alert is sent to the user's device as a notification to prompt further action. The input is expiration date data, and the output is an alert notification.

[1143] Step 6:

[1144] Users can check the food loss analysis results on the dashboard and take action as necessary. The user's input is access to the dashboard and the necessary operations, and the output is the displayed analysis results and a presentation of countermeasures.

[1145] Step 7:

[1146] The server obtains weather forecast information from an external weather data API and stores it in a database. The weather data is used to predict the number of customers and delivery orders. The input is the weather forecast information obtained from the weather data API, and the output is the weather data stored in the database.

[1147] Step 8:

[1148] The server predicts the number of delivery orders for the next day based on the weather forecast and calculates the necessary food ingredient stocking amounts. This allows for purchase suggestions that reflect the impact of weather on delivery orders. The inputs are weather data and past order data, and the output is a purchase suggestion.

[1149] Step 9:

[1150] The server uses an emotion engine to recognize the user's emotions and optimize operability. This includes analyzing the user's voice and text input and making adjustments such as simplifying the operation screen if the user is feeling stressed. The input is the user's voice and text data, and the output is an optimized operation screen and the presentation of information.

[1151] Step 10:

[1152] The server sends the notification results to the user, ensuring that important information is provided in a timely manner, such as purchasing suggestions and alert notifications. The inputs include food waste analysis results and suggestions based on weather forecasts, and the output is a notification sent to the user's device.

[1153] 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.

[1154] 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.

[1155] 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.

[1156] [Third embodiment]

[1157] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1158] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1159] 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).

[1160] 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.

[1161] 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.

[1162] 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).

[1163] 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.

[1164] 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.

[1165] 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.

[1166] 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.

[1167] 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.

[1168] 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."

[1169] The present invention is a system for collecting data on restaurant sales, purchasing, and food waste from restaurants and effectively utilizing this data to reduce food waste. An embodiment of the present invention will be described in detail below.

[1170] 1. Food waste data collection and analysis

[1171] Data collection

[1172] Server: Works in conjunction with the restaurant's POS system to collect past sales data, purchasing data, and food waste data, and stores this data in a database.

[1173] Example: After closing time each day, the server automatically retrieves sales data from the restaurant's POS system and stores it in a database.

[1174] Data Preprocessing

[1175] Server: Complements missing values ​​and corrects outliers in the collected data, and prepares it in a format suitable for analysis.

[1176] Example: The server complements missing data with data from the previous day and corrects any abnormal values ​​to bring them within the normal range.

[1177] Analysis by AI model

[1178] Server: Inputs the preprocessed data into the AI ​​model to identify the causes of food waste for each menu item.

[1179] Example: The AI ​​model uses statistical methods based on data from the past three months to identify the main causes of food waste and their impact.

[1180] Save and notify results

[1181] Server: Stores the analysis results in a database for user access, and generates alerts for ingredients approaching their expiration date.

[1182] Example: The saved analysis results are visualized on a dashboard, and an alert is sent immediately if there is food that has a shelf life of two days.

[1183] 2. Customer Data Predictions

[1184] Collection of store visit history data

[1185] Server: Collects customer visit history and stores it in a database.

[1186] Example: The server retrieves data on customer repeat visits and the number of new customers from the POS system and stores it in a database.

[1187] Analysis of store visit patterns

[1188] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[1189] Example: The server uses visitor data from the past year to analyze visitor trends for specific days of the week and time periods, and predicts the number of customers to visit next week.

[1190] Sales forecast and purchase quantity proposals

[1191] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[1192] Example: The server predicts sales for each menu item based on the predicted number of customers for the next week, and calculates the amount of ingredients needed to purchase to achieve this.

[1193] Proposal Notification

[1194] Terminal: Notifies the user of the forecast results and recommended purchase quantities.

[1195] Example: The terminal displays a pop-up message with suggested purchases for next week (e.g. 10 kg of chicken, 20 kg of vegetables).

[1196] 3. Weather data forecasting

[1197] Obtaining weather data

[1198] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[1199] Example: Every morning, the server calls a weather data API to retrieve the weather forecast data for that day.

[1200] Correlation analysis between weather and customer numbers

[1201] Server: Compares past weather data with store visit data and analyzes correlations.

[1202] Example: The server cross-analyzes weather data and store visit data from the past year to determine the impact of weather on store visits.

[1203] Weather-based customer traffic forecast

[1204] Server: Predict the number of customers based on the weather forecast for the next day.

[1205] Example: Based on the analysis result that "the number of customers decreases by about 20% on rainy days," the server predicts the number of customers if rain is forecast for the next day, taking that impact into account.

[1206] System Notifications

[1207] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[1208] Example: On days when rain is forecast, the terminal will display a pop-up suggesting, "Reduce purchases due to predicted decline in customer numbers."

[1209] 4. Best before date management

[1210] Input of food ingredient data

[1211] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[1212] Example: When new ingredients are purchased, the server registers their expiration date data in the database.

[1213] Best before date monitoring

[1214] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[1215] Example: The server checks the database every morning and generates an alert for ingredients that are due within the next 3 days.

[1216] Alerting and Notifications

[1217] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests recipes to use them in.

[1218] Example: The device notifies the user, "The expiration date of the chicken is approaching in two days. We have some suggestions for new dishes using this chicken."

[1219] 5. Reservation system integration

[1220] Retrieving reservation data

[1221] Server: Obtains the most recent reservation data in real time from the restaurant reservation system and stores it in a database.

[1222] Example: The server checks the reservation system every morning and stores the reservation status for that day in a database.

[1223] Reservation data analysis

[1224] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[1225] Example: The server calculates the cancellation rate of reservations based on historical reservation data from the past few months.

[1226] Adjustment of purchase quantity

[1227] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[1228] Example: The server makes a suggestion such as, "Because the cancellation rate is high on this day, we will reduce the amount of purchases by 10% compared to normal."

[1229] Proposal Notification

[1230] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[1231] Example: The terminal displays the message, "We have a suggested purchase adjustment based on this week's reservation status," and provides detailed recommended quantities.

[1232] The above is a specific embodiment of the system, which allows restaurants to appropriately manage inventory and adjust purchasing, reducing food waste and improving cost efficiency.

[1233] The processing flow will be explained below.

[1234] 1. Food waste data collection and analysis

[1235] Step 1: Data collection

[1236] Server: Works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data, and stores this data in a database.

[1237] Step 2: Data Preprocessing

[1238] Server: Checks the collected data for missing or outlier values, and performs imputation or correction as necessary.

[1239] Step 3: Analysis by AI model

[1240] Server: Preprocessed data is input into the AI ​​model and analyzed to identify the causes of food waste for each menu item.

[1241] Step 4: Save the results

[1242] Server: Stores the analysis results in a database and makes them later accessible via the dashboard.

[1243] Step 5: View the dashboard

[1244] Device: The food waste analysis results are displayed in graph and report format on the user's dashboard.

[1245] Step 6: User Verification

[1246] Users: See the top causes of food waste on the dashboard.

[1247] 2. Customer Data Predictions

[1248] Step 1: Collect store visit history data

[1249] Server: Collects customer visit history and stores it in a database.

[1250] Step 2: Analyze store visit patterns

[1251] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[1252] Step 3: Sales forecast

[1253] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[1254] Step 4: Viewing Proposals

[1255] Terminal: Displays forecast results and recommended purchase quantities.

[1256] Step 5: Confirm instructions

[1257] User: Places an order for the required amount based on the displayed proposal.

[1258] 3. Weather data forecasting

[1259] Step 1: Getting weather data

[1260] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[1261] Step 2: Correlation analysis between weather and customer traffic

[1262] Server: Compares past weather data with store visit data and analyzes correlations.

[1263] Step 3: Weather-based customer traffic forecast

[1264] Server: Predict the number of customers based on the weather forecast for the next day.

[1265] Step 4: System Notifications

[1266] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[1267] Step 5: Check the prediction

[1268] User: Review and adjust forecasts and purchasing suggestions based on weather forecasts.

[1269] 4. Best before date management

[1270] Step 1: Input food ingredients data

[1271] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[1272] Step 2: Monitor expiration dates

[1273] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[1274] Step 3: Alert Generation

[1275] Server: Generates alert messages about food items that are approaching their expiration date and sends them to the terminal.

[1276] Step 4: Displaying alerts

[1277] Device: Displays an alert message when ingredients are nearing their expiration date and suggests recipes to use them in.

[1278] Step 5: Recipe Ideation

[1279] User: Create and serve new menu items based on the suggested recipes.

[1280] 5. Reservation system integration

[1281] Step 1: Get reservation data

[1282] Server: Retrieves reservation status data in real time from the restaurant reservation system and stores it in a database.

[1283] Step 2: Analyze your booking data

[1284] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[1285] Step 3: Adjusting inventory by reservation

[1286] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[1287] Step 4: Proposal Notification

[1288] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[1289] Step 5: Proposal confirmation

[1290] User: Check the reservation status and place an order based on the suggested purchase amount.

[1291] The above is the processing flow according to a specific embodiment of the present system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste.

[1292] Example 1

[1293] 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."

[1294] Food waste in restaurants is a major issue, as it not only leads to economic losses but also increases environmental impact. It is also difficult to manage appropriate purchasing amounts due to fluctuations in customer numbers and weather, which can further increase food waste. Furthermore, it is difficult to effectively manage ingredients approaching their expiration date and adjust purchasing appropriately based on reservation status, so a system that can efficiently solve these issues is needed.

[1295] 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.

[1296] In this invention, the server includes means for collecting a restaurant's past sales data, purchasing data, and food waste data and storing them in a database, means for preprocessing the data, means for inputting the preprocessed data into a generative AI model to identify the causes of food waste for each menu item, means for saving the analysis results in a database and making them accessible to users, means for generating alerts for food items approaching their expiration dates, means for displaying the food waste analysis results in graphs and reports on the user's dashboard, means for logging into the user's training platform to view and study educational materials and training videos, means for collecting restaurant visit history data and storing it in a database, means for acquiring weather forecast information and storing it in a database, means for acquiring reservation data from a reservation system and storing it in a database, means for predicting the number of customers and sales based on the acquired data and calculating appropriate purchase amounts, and means for notifying the user of the calculated purchase amounts.This enables restaurants to achieve appropriate inventory management and purchase adjustments, significantly reducing food waste and improving cost efficiency.

[1297] "Sales data" refers to data that records transaction information when products or menu items are sold at a restaurant.

[1298] "Purchase data" is data that records transaction information when a restaurant purchases ingredients or products.

[1299] "Food waste data" refers to data that records information about food ingredients that are discarded without being used by restaurants.

[1300] A "database" is a system for organizing and storing collected data and efficiently retrieving necessary information.

[1301] "Data preprocessing" is the process of preparing data in a format suitable for analysis, such as by filling in missing values ​​and correcting outliers.

[1302] A "generative AI model" is an algorithm that recognizes patterns based on past data and makes predictions and classifications.

[1303] "Causes of food waste" refers to factors that cause food waste and disposal in restaurants.

[1304] "Analysis results" are information that represents findings and conclusions obtained from collected and analyzed data.

[1305] An "alert" is a message that notifies or warns you when a specific condition is met.

[1306] A "dashboard" is an interface that allows users to visualize data.

[1307] A "graph or report format" is a format for visually displaying data, making it easier to understand.

[1308] A "training platform" is an environment or system for users to learn or train.

[1309] "Educational materials" are content or materials for learning specific knowledge or skills.

[1310] A "training video" is a video that provides learning content visually.

[1311] "Visit history data" is recorded information when a customer visits a restaurant.

[1312] "Weather forecast information" is forecast data regarding future weather.

[1313] "Reservation data" is data that records information when a customer reserves a table at a restaurant.

[1314] "Inventory management" is the process of properly maintaining and managing inventory of goods and ingredients.

[1315] "Purchase adjustment" refers to making adjustments to purchase the appropriate amount of ingredients and products based on forecasts and actual results.

[1316] "Improving cost efficiency" refers to reducing costs and utilizing funds efficiently.

[1317] This invention is a system for reducing food waste through the collection and analysis of restaurant sales data, purchasing data, and food waste data. This system operates in cooperation with a server, terminals, and users.

[1318] The server connects to the restaurant's POS system and collects sales data, purchasing data, and food waste data. This data is then stored in a database. For example, after closing each day, the server automatically retrieves sales data from the POS system and stores it in the database. It also extracts and stores purchasing data and food waste data in the same way.

[1319] The server complements missing values ​​and corrects outliers in the collected data. This process improves the reliability of the data and increases the accuracy of analysis. For example, the server complements missing data with data from the previous day and corrects any outliers to bring them within the normal range. This results in a data format suitable for analysis.

[1320] The server then inputs the preprocessed data into a generative AI model, which uses that data to identify the causes of food waste for each menu item. The AI ​​model uses statistical methods based on data from the past few months to identify the main causes of food waste and their impact. For example, it can identify specific causes such as "ingredient B from dish A is frequently wasted."

[1321] The analysis results are stored in a database and displayed on a dashboard that users can access. This dashboard visualizes the data in graphs and reports, and is designed to make it easy for users to understand. For example, it visually displays the main causes of food waste and trends in waste volume.

[1322] In addition, the server generates an alert for food ingredients that are approaching their expiration date and notifies the user. For example, if there is food that has an expiration date of two days, an alert saying "Chicken expiration date is approaching" will be displayed on the terminal. This alert is an important measure to prevent food waste.

[1323] Store visit history data is also collected by the server and stored in a database. This data is analyzed and the next number of customers is predicted based on past patterns. The server uses the past year's store visit data to analyze store visit trends for specific days of the week and time periods, and predicts the number of customers for the following week. For example, based on a pattern of high customer numbers on Friday nights, the server predicts the number of customers for the following Friday.

[1324] Weather forecast information is also obtained by the server and stored in a database. The server calls a weather data API to obtain and store the weather forecast data for that day. This weather data is compared with past store visit data and correlations are analyzed. Based on the analysis results, the server concludes that "the number of customers decreases by approximately 20% on rainy days."

[1325] The server comprehensively analyzes this data and predicts the number of customers based on the weather forecast for the next day. For example, if rain is forecast for the next day, the server predicts that the number of customers will decrease. The server notifies the user of this prediction and a suggested amount of stock to be purchased. The terminal displays a message such as, "The forecast suggests that the number of customers may decrease tomorrow, so we suggest reducing the amount of stock to be purchased."

[1326] Furthermore, the system retrieves reservation data from the reservation system and stores it in a database. Based on this data, it generates a purchase adjustment proposal based on the reservation status and notifies the user. For example, the terminal may display a message saying, "We have a purchase adjustment proposal based on this week's reservation status," along with detailed recommendations for purchase quantities.

[1327] Examples of specific prompts include:

[1328] "Calculate the necessary inventory based on the most recent reservation data."

[1329] "Please identify the main causes of food waste based on sales data and food waste data from the past three months."

[1330] "Based on this week's weather forecast, please predict the number of customers we will have and suggest the amount of stock we should stock."

[1331] This will enable restaurants to properly manage their inventory and adjust their purchasing, significantly reducing food waste and improving cost efficiency.

[1332] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1333] Step 1:

[1334] The server works with the restaurant's POS system to collect sales data, purchasing data, and food waste data. This data is automatically acquired after closing time each day and stored in a database. The input is raw data acquired from the POS system, and the output is raw data stored in the database. Specifically, the server calls the API for the POS system and saves the acquired data in the database.

[1335] Step 2:

[1336] The server complements missing values ​​and corrects outliers in the collected data. This process results in a data format suitable for analysis. The input is raw data stored in the database, and the output is preprocessed data. Specifically, it complements missing values ​​with data from the previous day, and corrects any outliers to within an appropriate range.

[1337] Step 3:

[1338] The server inputs the preprocessed data into the generative AI model to identify the causes of food waste for each menu item. The input is the preprocessed data, and the output is the analysis results of the causes of food waste. Specifically, data from the past few months is input into the generative AI model, which analyzes it using statistical methods to identify the causes of food waste.

[1339] Step 4:

[1340] The server stores the analysis results generated by the AI ​​model in a database and displays them on a dashboard that users can access. The input is the analysis results of the causes of food waste, and the output is the visualized data displayed on the dashboard. Specifically, the analysis results are converted into graphs and reports and displayed in a format that is easy for users to access.

[1341] Step 5:

[1342] The server generates an alert for food ingredients approaching their expiration date and notifies the user. The input is the food ingredient data for which the expiration date is approaching, and the output is an alert message displayed on the terminal. Specifically, the server periodically checks the database, generates an alert for food ingredients approaching their expiration date, and notifies the user.

[1343] Step 6:

[1344] The server collects customer visit history data and stores it in a database. The input is the visit history data, and the output is the visit data stored in the database. Specifically, it obtains the visit history data from the POS system and saves it in the database.

[1345] Step 7:

[1346] The server analyzes the visit history data and predicts the next number of customers based on past patterns. The input is the past visit history data, and the output is the predicted number of customers. Specifically, it analyzes visit trends by day of the week and time of day based on data from the past year, and predicts the next number of customers.

[1347] Step 8:

[1348] The server obtains weather forecast information from the weather data API and stores it in a database. The input is the weather forecast information obtained from the weather data API, and the output is the weather forecast data stored in the database. Specifically, the server calls the weather data API, obtains the weather forecast data, and stores it in the database.

[1349] Step 9:

[1350] The server compares past weather data with store visit data and analyzes the correlation. The input is past weather data and store visit data, and the output is the correlation analysis results between weather and store visits. Specifically, it cross-analyzes both sets of data to identify the impact that weather has on the number of store visitors.

[1351] Step 10:

[1352] The server predicts the number of customers based on the weather forecast for the next day. The input is weather forecast data, and the output is the predicted number of customers for the next day. Specifically, the server predicts the number of customers based on the weather forecast data and calculates the appropriate amount of stock to be purchased.

[1353] Step 11:

[1354] The server obtains reservation data from the reservation system and stores it in a database. The input is the reservation data obtained from the reservation system, and the output is the reservation data stored in the database. Specifically, the server accesses the reservation system to obtain data and stores it in the database.

[1355] Step 12:

[1356] The server analyzes the seating rate and reservation cancellation rate based on the reservation data, and generates a purchase adjustment proposal according to the reservation situation. The input is reservation data, and the output is a purchase adjustment proposal. Specifically, it analyzes past reservation history and proposes appropriate purchase amounts based on the cancellation rate and seating rate.

[1357] Step 13:

[1358] The terminal notifies the user of the forecast results and recommended purchase quantities. The input is the recommended purchase data from the server, and the output is a message displayed to the user. Specifically, the terminal notifies the user of the purchase adjustment proposal using a pop-up message or notification function.

[1359] (Application example 1)

[1360] 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."

[1361] In restaurant operations, excessive food waste and lost sales opportunities due to shortages are problems. These problems arise because it is difficult to properly manage inventory and predict customer demand. Also, adjusting purchasing quantities based on fluctuations in weather and customer visit history is difficult, which contributes to waste. Furthermore, inadequate management of expiration dates also leads to food loss.

[1362] 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.

[1363] In this invention, the server includes means for collecting the restaurant's past sales data, purchasing data, and food waste data and storing them in a database, means for preprocessing the data, means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item, means for saving the analysis results in a database and making them accessible to users, means for generating alerts for food ingredients whose expiration dates are approaching, means for displaying the food waste analysis results in graphs and reports on the user's dashboard, means for sending alerts and prediction results via push notifications to the user's mobile device, and means for providing recommended purchase amounts based on the prediction results. This enables the reduction of food waste and efficient inventory management in restaurants.

[1364] "Past sales data of a restaurant" is information relating to the quantity and price of products sold in the past at a restaurant.

[1365] "Purchase data" refers to information about ingredients and other necessities purchased by a restaurant.

[1366] "Food waste data" is information on the amount and type of food that is discarded without being used.

[1367] A "database" is a system for centrally managing and storing collected data.

[1368] "Data preprocessing" is the process of filling in missing data values ​​and correcting outliers, preparing the data in a form that is easy to analyze.

[1369] An "AI model" is an algorithm that uses artificial intelligence to analyze data and make predictions and classifications.

[1370] "Causes of food waste" are the main reasons why food ingredients are discarded unnecessarily.

[1371] "Analysis results" refers to the information and insights obtained as a result of analyzing data.

[1372] An "alert" is a warning message that notifies the user of urgent information.

[1373] A "dashboard" is a tool that visually organizes information and displays it in a way that allows users to intuitively understand it.

[1374] A "mobile terminal" is a mobile device such as a smartphone or tablet.

[1375] "Push notifications" are a method of sending information to a user's device in real time.

[1376] "Recommended purchase quantities" are the appropriate amounts of ingredients to purchase suggested based on forecast data.

[1377] This invention is a system for streamlining restaurant operations and reducing food waste. This system collects sales data, purchasing data, food waste data, etc., and analyzes them using an AI model. It also notifies users of prediction results and alerts, supporting appropriate purchasing and inventory management.

[1378] Data collection and storage

[1379] The server connects to the restaurant's POS system and collects past sales data, purchasing data, and food waste data, storing it in a database. This data is automatically retrieved, organized, and saved after closing time each day.

[1380] Data Preprocessing

[1381] The server uses the Python pandas library to fill in missing values ​​and correct outliers in the collected data, and then formats it for analysis.

[1382] Analysis by AI model

[1383] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item. The AI ​​model uses scikit-learn's Linear Regression model to make highly accurate predictions based on past data.

[1384] Save and notify results

[1385] The analysis results are stored in a database and displayed on a dashboard for user access, and alerts are generated for ingredients approaching their expiration date and sent to users' mobile devices via push notifications.

[1386] User Dashboard

[1387] Users can visually check the results of food waste analysis in the form of graphs and reports through the dashboard, which is implemented using the Shiny package in the R programming language.

[1388] Providing prediction results

[1389] The server calculates sales forecasts and recommended stock quantities based on the predicted number of customers for the next week, and sends these to the user's mobile device via push notification.

[1390] Specific examples

[1391] For example, when a store manager opens the application on their smartphone, it displays next week's predicted sales, purchasing suggestions, and alerts for ingredients that are nearing their expiration date.

[1392] Prompt Sentence Examples

[1393] Examples of prompt sentences include:

[1394] "Please use the store's sales data, purchasing data, food waste data, and weather forecast data from the past month to identify causes of food waste and predict the number of customers visiting the store. Also, please make purchasing amount suggestions based on the results."

[1395] The above is an embodiment of the present invention.

[1396] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1397] Step 1:

[1398] The server connects to the restaurant's POS system and collects past sales data, purchasing data, and food waste data.

[1399] Input: Sales data, purchasing data, and food waste data from the POS system.

[1400] Output: The collected data is stored in a database.

[1401] Specifically, after closing time each day, the server accesses the POS system, automatically retrieves the necessary data via API, and stores it in a database.

[1402] Step 2:

[1403] The server performs data preprocessing by filling in missing values ​​and correcting outliers in the collected data.

[1404] Input: Raw sales data, purchasing data, and food waste data stored in the database.

[1405] Output: Preprocessed data.

[1406] Specifically, missing data is filled in with the previous day's values ​​using Python's pandas library, and outliers are corrected to within a statistically appropriate range.

[1407] Step 3:

[1408] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item.

[1409] Input: Preprocessed sales data, purchasing data, and food waste data.

[1410] Output: Analysis results of causes of food waste.

[1411] Specifically, we use scikit-learn's Linear Regression model to analyze correlations in the data and identify the main causes of food waste and their contribution.

[1412] Step 4:

[1413] The server stores the analysis results in a database and makes them accessible to users through a dashboard.

[1414] Input: Analysis results of causes of food waste.

[1415] Output: Analysis results stored in a database.

[1416] Specifically, the analysis results are stored in a database, and users can view the results by accessing a dashboard via a web interface.

[1417] Step 5:

[1418] The server generates an alert for food ingredients approaching their expiration date and sends a push notification to the user's mobile device.

[1419] Input: Best before information in the database.

[1420] Output: Alert notification.

[1421] Specifically, the database is checked periodically, and if the expiration date is approaching, an alert is sent to the user's email address using an SMTP server.

[1422] Step 6:

[1423] The server calculates sales forecasts and recommended stock quantities based on the predicted number of customers visiting the store next week, and sends these to the user's mobile device via push notification.

[1424] Input: Store visit history data and weather forecast data.

[1425] Output: Sales forecast and recommended purchase quantities.

[1426] Specifically, an AI model makes predictions based on store visit history and weather data, calculates the amount of stock to be purchased based on the results, and notifies the user's smartphone.

[1427] Step 7:

[1428] Users can check food waste analysis results, store visit predictions, purchasing suggestions, and more through the dashboard, and take appropriate action.

[1429] Input: Server-generated analysis results, forecast data, and purchasing recommendations.

[1430] Output: User confirmation and action.

[1431] Specifically, users access the dashboard through a web browser or a dedicated app, view information in the form of graphs and reports, and make adjustments to purchases and menus as needed.

[1432] 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.

[1433] This invention is a system that collects restaurant sales data, purchasing data, and food waste data and uses this data to reduce food waste. Furthermore, this invention achieves more effective operation by combining it with an emotion engine that recognizes user emotions. Below, we will explain in detail how each component works together and functions as an entire system.

[1434] 1. Food waste data collection and analysis

[1435] Data collection

[1436] Server: Works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data, and stores it in a database.

[1437] Example: The server automatically retrieves sales data from the POS system after closing each day and stores it in a database.

[1438] Data Preprocessing

[1439] Server: Complements missing values ​​and corrects outliers in the collected data, and prepares it in a format suitable for analysis.

[1440] Example: The server complements missing data with data from the previous day and corrects any abnormal values ​​to bring them within the normal range.

[1441] Analysis by AI model

[1442] Server: Preprocessed data is input into the AI ​​model and analyzed to identify the causes of food waste for each menu item.

[1443] Example: The AI ​​model uses statistical methods based on data from the past three months to identify the main causes of food waste and their impact.

[1444] Save and notify results

[1445] Server: Stores the analysis results in a database for user access, and generates alerts for ingredients approaching their expiration date.

[1446] Example: The saved analysis results are visualized on a dashboard, and an alert is sent immediately if there is food that has a shelf life of two days.

[1447] 2. Customer Data Predictions

[1448] Collection of store visit history data

[1449] Server: Periodically collects customer visit history and stores it in a database.

[1450] Example: The server retrieves data on customer repeat visits and the number of new customers from the POS system and stores it in a database.

[1451] Analysis of store visit patterns

[1452] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[1453] Example: The server uses visitor data from the past year to analyze visitor trends for specific days of the week and time periods, and predicts the number of customers to visit next week.

[1454] Sales forecast and purchase quantity proposals

[1455] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[1456] Example: The server predicts sales for each menu item based on the predicted number of customers for the next week, and calculates the amount of ingredients needed to purchase to achieve this.

[1457] Proposal Notification

[1458] Terminal: Notifies the user of the forecast results and recommended purchase quantities.

[1459] Example: The terminal displays a pop-up message with suggested purchases for next week (e.g. 10 kg of chicken, 20 kg of vegetables).

[1460] 3. Weather data forecasting

[1461] Obtaining weather data

[1462] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[1463] Example: Every morning, the server calls a weather data API to retrieve the weather forecast data for that day.

[1464] Correlation analysis between weather and customer numbers

[1465] Server: Compares past weather data with store visit data and analyzes correlations.

[1466] Example: The server cross-analyzes weather data and store visit data from the past year to determine the impact of weather on store visits.

[1467] Weather-based customer traffic forecast

[1468] Server: Predict the number of customers based on the weather forecast for the next day.

[1469] Example: Based on the analysis result that "the number of customers decreases by about 20% on rainy days," the server predicts the number of customers if rain is forecast for the next day, taking that impact into account.

[1470] System Notifications

[1471] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[1472] Example: On days when rain is forecast, the terminal will display a pop-up suggesting, "Reduce purchases due to predicted decline in customer numbers."

[1473] 4. Best before date management

[1474] Input of food ingredient data

[1475] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[1476] Example: When new ingredients are purchased, the server registers their expiration date data in the database.

[1477] Best before date monitoring

[1478] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[1479] Example: The server checks the database every morning and generates an alert for ingredients that are due within the next 3 days.

[1480] Alerting and Notifications

[1481] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests recipes to use them in.

[1482] Example: The device notifies the user, "The expiration date of the chicken is approaching in two days. We have some suggestions for new dishes using this chicken."

[1483] 5. Reservation system integration

[1484] Retrieving reservation data

[1485] Server: Obtains the most recent reservation data in real time from the restaurant reservation system and stores it in a database.

[1486] Example: The server checks the reservation system every morning and stores the reservation status for that day in a database.

[1487] Reservation data analysis

[1488] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[1489] Example: The server calculates the cancellation rate of reservations based on historical reservation data from the past few months.

[1490] Adjustment of purchase quantity

[1491] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[1492] Example: The server makes a suggestion such as, "Because the cancellation rate is high on this day, we will reduce the amount of purchases by 10% compared to normal."

[1493] Proposal Notification

[1494] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[1495] Example: The terminal displays the message, "We have a suggested purchase adjustment based on this week's reservation status," and provides detailed recommended quantities.

[1496] 6. Combining Emotion Engines

[1497] Emotion recognition by emotion engine

[1498] Server: Analyzes the user's voice and text input and recognizes emotions using an emotion engine.

[1499] Example: The server analyzes voice comments and feedback in real time as users operate the dashboard, and recognizes emotions using an emotion engine.

[1500] Customized display content based on emotions

[1501] Device: The content displayed on the dashboard is automatically customized based on the user's emotions recognized by the emotion engine.

[1502] Example: If the user is stressed, simplify the display and prioritize important information.

[1503] Changing information provision based on emotions

[1504] Device: Based on the user's emotions recognized by the emotion engine, the method of providing information on reducing food waste and purchasing suggestions is changed.

[1505] Example: If the user is not satisfied with the previous suggestion, switch to a more detailed and illustrated presentation.

[1506] Recording and analyzing emotional data

[1507] Server: The user's emotion data recognized by the emotion engine is stored in a database and used for later analysis.

[1508] Example: The server stores the user's usage history along with emotional data, and periodically analyzes this data to help improve the system.

[1509] The above is the processing flow of a specific embodiment of this system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste. Furthermore, by combining it with an emotion engine, the user experience can be improved and the effectiveness of the system can be further enhanced.

[1510] The processing flow will be explained below.

[1511] 1. Food waste data collection and analysis

[1512] Step 1: Data collection

[1513] Server: Connects to the restaurant's POS system via API, collects past sales data, purchasing data, and food waste data on a daily basis, and stores this data in a database.

[1514] Step 2: Data Preprocessing

[1515] Server: Preprocesses the collected data and performs missing value interpolation and outlier correction. For example, if some sales data is missing, the data from the previous day is used as a reference to complete the data.

[1516] Step 3: Analysis by AI model

[1517] Server: The preprocessed data is input into an AI model equipped with statistical methods, and analysis is performed to identify the causes of food waste for each menu item. The analysis results are then compiled into a report.

[1518] Step 4: Save the results

[1519] Server: The analysis results are stored in a database for later access by users. The stored data includes the causes and impact of food waste for each menu item.

[1520] Step 5: View the dashboard

[1521] Device: The results of food waste analysis are displayed visually in graphs and reports on the user's dedicated dashboard. The interface is optimized to make it intuitive for users.

[1522] Step 6: User Verification

[1523] Users: Access the dashboard to view the main causes of food waste and their associated data, identify problems, and consider solutions.

[1524] 2. Customer Data Predictions

[1525] Step 1: Collect store visit history data

[1526] Server: Periodically collects customer visit history from the restaurant's POS system and stores it in a database.

[1527] Step 2: Analyze store visit patterns

[1528] Server: Analyzes collected store visit history data and identifies patterns of store visits by day of the week, time of day, and season. For example, it extracts trends such as higher customer numbers on weekends compared to weekdays.

[1529] Step 3: Sales forecast

[1530] Server: Based on the analysis of customer visit patterns, it performs calculations to predict the next number of customers and sales. Based on the prediction results, it calculates the recommended stock amount.

[1531] Step 4: Viewing Proposals

[1532] Terminal: The forecast results and recommended purchase quantities are displayed on the interface. For example, the recommended purchase quantities (e.g., 10 kg of chicken and 20 kg of vegetables) based on the predicted number of customers for the next week are displayed.

[1533] Step 5: Confirm instructions

[1534] User: Checks the displayed forecast results and purchase proposals, decides on the actual purchase amount, and places an order with the supplier by pressing the approval button on the screen.

[1535] 3. Weather data forecasting

[1536] Step 1: Getting weather data

[1537] Server: Using the weather data API, the latest weather forecast information is obtained daily and stored in a database.

[1538] Step 2: Correlation analysis between weather and customer traffic

[1539] Server: Correlate historical weather data with store visit data to identify the impact of weather on store visits. For example, confirm that store visits on rainy days are lower than normal.

[1540] Step 3: Weather-based customer traffic forecast

[1541] Server: Based on the weather forecast for the next day, calculates the number of customers to visit. If the weather forecast predicts rain, it takes into account that the number of customers will be lower than usual.

[1542] Step 4: System Notifications

[1543] Terminal: Notifies the user of customer traffic predictions based on weather forecasts and suggests adjustments to purchasing quantities based on this. For example, on days when rain is predicted, a suggestion to reduce purchasing quantities by 20% is displayed.

[1544] Step 5: Check the prediction

[1545] User: Review forecasts and purchasing suggestions based on weather forecasts and make adjustments as needed.

[1546] 4. Best before date management

[1547] Step 1: Input food ingredients data

[1548] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database. Whenever new ingredients are purchased, the expiration date information is registered.

[1549] Step 2: Monitor expiration dates

[1550] Server: Periodically checks the expiration dates of ingredients in the database and identifies ingredients that are approaching their expiration date.

[1551] Step 3: Alert Generation

[1552] Server: Generates an alert message for food ingredients that are approaching their expiration date and notifies the terminal.

[1553] Step 4: Displaying alerts

[1554] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests new recipes using those ingredients. For example, it displays a message like, "Your chicken will expire in two days. How about making a special dish using this chicken?"

[1555] Step 5: Recipe Ideation

[1556] User: Create and serve new menu items based on the suggested recipes. Update the menu display as needed.

[1557] 5. Reservation system integration

[1558] Step 1: Get reservation data

[1559] Server: Obtains reservation data in real time from the restaurant reservation system and stores it in a database.

[1560] Step 2: Analyze your booking data

[1561] Server: Analyzes reservation cancellation rates, seating rates, etc. based on reservation data.

[1562] Step 3: Adjusting inventory by reservation

[1563] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[1564] Step 4: Proposal Notification

[1565] Terminal: Notify the user of a purchase quantity adjustment proposal based on the reservation status. For example, display "There is a purchase adjustment proposal based on this week's reservation status."

[1566] Step 5: Proposal confirmation

[1567] User: Checks the reservation status and places an actual order based on the suggested purchase amount.

[1568] 6. Combining Emotion Engines

[1569] Step 1: Emotion recognition by the emotion engine

[1570] Server: Analyzes the user's voice and text input in real time and recognizes emotions using an emotion engine. For example, if a user inputs a voice comment while operating the dashboard, the voice data is analyzed by the emotion engine.

[1571] Step 2: Customize your display based on emotions

[1572] Device: The dashboard display is automatically customized based on the user's emotions as recognized by the emotion engine. For example, if the user is feeling stressed, the display will be simplified and important information will be prioritized.

[1573] Step 3: Modify your information based on emotions

[1574] Device: Based on the user's emotions recognized by the emotion engine, the way information on food waste reduction and purchasing suggestions is presented is changed. For example, if the user is dissatisfied with the previous suggestion, the explanation is made more detailed and the display is switched to one that makes use of more illustrations.

[1575] Step 4: Record and analyze emotion data

[1576] Server: The user's emotional data recognized by the emotion engine is stored in a database and used for later analysis. The emotional data is used as a reference for periodic system improvements.

[1577] The above is the processing flow of a specific embodiment of this system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste. Furthermore, by combining it with an emotion engine, the user experience can be improved and the effectiveness of the system can be further enhanced.

[1578] Example 2

[1579] 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."

[1580] Appropriate inventory management and food waste reduction are important issues in modern restaurant management. Conventional methods involve manually analyzing sales and purchasing data to generate food waste data, but this method is inaccurate and makes effective food waste reduction and inventory management difficult. Furthermore, there is an insufficient system for integrating and utilizing weather data, restaurant visit forecast data, and reservation data, creating a need for more efficient food ingredient management and customer trend forecasts. Furthermore, there is a lack of information provided that takes user stress and satisfaction into consideration, making it difficult to provide an optimal user experience.

[1581] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting and storing the restaurant's past sales data, purchasing data, and food waste data in a database; means for preprocessing the data; means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item; means for saving the analysis results in a database and making them accessible to the user; means for generating alerts for food ingredients whose expiration dates are approaching; means for displaying the food waste analysis results in graphs and reports on the user's dashboard; means for customizing the display content using an emotion engine that recognizes the user's emotions; and means for recording and analyzing the user's emotion data. This enables efficient food waste reduction, appropriate inventory management, and highly accurate purchasing suggestions based on restaurant visit predictions. Furthermore, optimal information is provided according to the user's emotional state, improving the user experience.

[1582] "Food and beverage establishments" are establishments that serve food and beverages, including restaurants, cafes, and bars.

[1583] "Sales data" refers to information regarding the quantity and value of products sold by a restaurant during a specific period.

[1584] "Purchasing data" refers to information about ingredients, beverages, and other items purchased by a restaurant during a specific period.

[1585] "Food waste data" refers to information on the types and quantities of food ingredients that are discarded unused by restaurants.

[1586] "Database" refers to a system for organizing, storing, and managing collected data.

[1587] "Data preprocessing" refers to the process of performing operations such as filling in missing values ​​and correcting outliers in order to convert data into a format suitable for analysis.

[1588] An "AI model" is a program that uses artificial intelligence to analyze data and make predictions or classifications that are useful for a specific purpose.

[1589] "Causes of food waste" refers to the main factors and reasons why food is wasted.

[1590] "Analysis results" refers to conclusions and findings obtained through data analysis work.

[1591] "Alert" refers to a warning message sent to provide important information or caution.

[1592] A "dashboard" is an interface that visually displays important information, allowing users to understand the situation at a glance.

[1593] An "emotion engine" refers to a system for recognizing and analyzing emotions from a user's voice or text.

[1594] "Customizing the display content" refers to adjusting the display method and content of information according to the user's emotions and needs.

[1595] "Emotional Data" refers to information about a user's emotional state, including that recognized and recorded by the system.

[1596] "Visit history" refers to records of the date, time, and frequency of a customer's visits to a restaurant.

[1597] "Weather Forecast Information" means data regarding future weather conditions in a particular geographic area.

[1598] "Correlation" refers to a statistical association between two or more variables.

[1599] "Reservation data" refers to information regarding seat and service reservations made in advance by customers to restaurants.

[1600] The present invention is a system for reducing food waste and optimizing inventory management in restaurants. This system is built on the interaction between a server, a terminal, and a user, and the invention is implemented as follows.

[1601] Data collection and storage

[1602] The server works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data and store it in a database.

[1603] Example: After closing each day, the server automatically retrieves data from the POS system and stores it in a database.

[1604] Data Preprocessing

[1605] The server performs preprocessing such as filling in missing values ​​in the collected data with data from the previous day and correcting outliers to bring them within the normal range, and then converts the data into a format suitable for analysis.

[1606] Example: The server fills in any missing data with data from the previous day, and corrects any extremely outlying values.

[1607] Analysis by AI model

[1608] The server inputs the preprocessed data into an AI model and performs statistical analysis to identify the causes of food waste in restaurants.

[1609] Example: The server identifies the main causes of food waste based on data from the past three months and assesses their impact.

[1610] Save and notify results

[1611] The server stores the analysis results in a database and generates alerts based on the results for food ingredients approaching their expiration date.

[1612] Example: Food waste analysis results are saved in dashboard format, and an alert message is generated for food ingredients with a shelf life of less than two days.

[1613] User Interface

[1614] The device notifies the user of analysis results and alerts, and displays the food waste analysis results in graphs and reports on the dashboard.

[1615] Example: When users access the dashboard, the causes and impact of food waste for each ingredient are visualized, prompting them to take necessary action.

[1616] Customization with Emotion Engine

[1617] The server analyzes the user's voice and text input and uses an emotion engine to recognize the user's emotions.

[1618] Example: When a user interacts with a dashboard, they can enter feedback and comments, and the system can recognize their emotions from the content.

[1619] The terminal customizes the display content on the dashboard based on the user's emotions recognized by the emotion engine.

[1620] Example: If the user is stressed, simplify the display and prioritize the most important information.

[1621] Storing and analyzing emotional data

[1622] The server stores the recognized emotion data in a database for later analysis.

[1623] Example: Emotional data is stored along with the user's operation history and periodically analyzed to help improve the system.

[1624] Prompt Sentence Examples

[1625] Use the following prompt to instruct the generative AI model to identify the causes of food waste from food waste data:

[1626] "Based on data from the past three months, please identify the main causes of food waste and their impact."

[1627] The above is a specific example of an embodiment of the present invention. This invention enables restaurants to efficiently reduce food waste and achieve appropriate inventory management, thereby improving customer satisfaction.

[1628] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1629] Step 1: Collect and store data

[1630] The server periodically connects to the restaurant's POS system to obtain past sales data, purchasing data, and food waste data.

[1631] Input: Sales data, purchasing data, food waste data collected from POS systems

[1632] Output: Sales data, purchasing data, food waste data stored in a database

[1633] Specific operation: After closing time every day, the server automatically accesses the POS system, extracts the necessary data, and stores it in the database.

[1634] Step 2: Preprocessing the data

[1635] The server completes missing values ​​and corrects outliers in the collected data.

[1636] Input: Sales data, purchasing data, food waste data stored in the database

[1637] Output: Preprocessed data

[1638] Specific operation: The server identifies missing values ​​and fills them with data from the previous day. If an outlier is detected, it corrects it to an appropriate value.

[1639] Step 3: Identifying causes of food waste using an AI model

[1640] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item.

[1641] Input: Preprocessed data

[1642] Output: Report on causes of food waste and their impact

[1643] Specific operation: The server prompts the generative AI model, saying, "Based on data from the past three months, please identify the main causes of food waste and their impact," and analyzes the results.

[1644] Step 4: Save the analysis results and generate alerts

[1645] The server stores the analysis results obtained from the AI ​​model in a database and generates alerts for ingredients that are approaching their expiration date.

[1646] Input: Food waste cause report, food ingredient data

[1647] Output: Saved reports, generated alerts

[1648] Specific operation: The server stores the analysis results in a database in the form of a dashboard and generates an alert for ingredients whose expiration date is within two days.

[1649] Step 5: User interface notification

[1650] The terminal notifies the user of the analysis results and alerts and displays them on a dashboard.

[1651] Input: Analysis results and alerts stored in the database

[1652] Output: Graphs, reports, and popup alerts displayed on the user dashboard

[1653] Specific operation: When a user accesses the dashboard, the device visually displays the causes of food waste and their impact for each ingredient, and notifies them of expiration dates via a pop-up alert.

[1654] Step 6: Emotion Recognition and Customization with the Emotion Engine

[1655] The server analyzes the user's voice and text input using an emotion engine to recognize emotions.

[1656] Input: User voice commands and text feedback

[1657] Output: User emotion data

[1658] Specific operation: The server analyzes the voice comments and feedback provided by the user during operation, and recognizes and records emotions using an emotion engine.

[1659] The device will adjust the content displayed on the dashboard based on the recognized emotion.

[1660] Input: User emotion data

[1661] Output: Customized Dashboard View

[1662] Specific behavior: When the user is feeling stressed, the device simplifies the display and prioritizes displaying important information.

[1663] Step 7: Storing and analyzing sentiment data

[1664] The server stores the user's emotion data recognized by the emotion engine in a database and periodically analyzes it.

[1665] Input: User emotion data

[1666] Output: Sentiment analysis report

[1667] Specific operation: The server stores the user's emotional data along with their operation history in a database, and periodically analyzes the emotional data to improve the system.

[1668] The above are the specific processing steps of the program of this system.

[1669] (Application example 2)

[1670] 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."

[1671] Conventional restaurant inventory management systems often collect and analyze sales and purchasing data separately, making it difficult to reduce food waste and predict appropriate purchasing amounts. Furthermore, proposals did not take into account factors such as weather changes or consumer sentiment, resulting in a lack of concrete countermeasures. The food delivery industry, in particular, requires real-time inventory management and forecasting to respond to fluctuations in orders. A system that solves these problems and enables more efficient inventory management and food waste reduction is needed.

[1672] 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 the restaurant's past sales data, purchasing data, and food waste data and storing them in a database; means for preprocessing the data; means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item; means for saving the analysis results in a database and making them accessible to users; means for generating alerts for food ingredients whose expiration date is approaching; means for displaying the food waste analysis results in graphs and reports on the user's dashboard; means for logging into the user's training platform and viewing and studying educational materials and training videos; means for forecasting food delivery sales and recommending necessary inventory and purchasing; means for importing weather data, analyzing the impact of weather on delivery orders, and notifying the user of the results; and means for recognizing the emotions of delivery personnel and store staff and customizing operation methods and information presentation. This enables comprehensive, real-time inventory management and sales forecasting, further improving the user experience.

[1673] "Sales data" refers to information on the total revenue earned by a restaurant over a certain period of time.

[1674] "Purchasing data" is detailed information about when a restaurant purchases ingredients and products.

[1675] "Food waste data" is information on food ingredients that were discarded because they were not used.

[1676] A "database" is a system for efficiently managing, searching, and manipulating multiple pieces of data.

[1677] "Data preprocessing" is the process of converting collected raw data into a form suitable for analysis.

[1678] An "AI model" is a type of algorithm that uses artificial intelligence to analyze data and make predictions.

[1679] "Food loss" is the waste that occurs when food ingredients are discarded without being used.

[1680] An "alert" is a system that notifies a user of a warning when a specific condition occurs.

[1681] A "dashboard" is a user interface that allows various data to be visually displayed and manipulated.

[1682] "Training Platform" means a system for providing educational materials and training videos.

[1683] "Food delivery" is a service that delivers ordered meals to a designated location.

[1684] "Weather data" is data that includes various information about the weather.

[1685] The "emotion engine" is a function that recognizes and analyzes the user's emotions and adjusts the system's behavior based on the results.

[1686] This invention is a system that collects and analyzes past sales data, purchasing data, and food waste data from restaurants to reduce food waste and achieve efficient inventory management. The invention also aims to improve operability and user experience by incorporating an approach specialized for food delivery services and using an emotion engine that recognizes user emotions.

[1687] The server connects to the POS system to collect various data from the restaurant. Sales data, purchasing data, and food waste data are sent to the server after the end of business each day and stored in a database. The server also performs preprocessing such as filling in missing values ​​and correcting outliers.

[1688] The pre-processed data is then analyzed using a generative AI model. This AI model identifies causes of food waste based on historical data and supports efficient inventory management. It also generates sales forecasts for food delivery services. For example, by combining historical sales data with weather data, it can predict the impact of weather on delivery orders and adjust ingredient purchases accordingly.

[1689] Weather data is obtained from an external weather data API and stored on the server. This data is input into an AI model and used to predict customer numbers and make purchasing recommendations based on the next day's weather forecast. Users can view these predictions on a dashboard and receive specific alerts and purchasing recommendations.

[1690] Furthermore, the server uses an emotion engine to analyze the emotions of delivery personnel and store staff, and customizes the user interface operation method and information presentation. If the user feels stressed about a particular operation, the operation procedure is simplified and important information is prioritized.

[1691] For example, if the emotion engine detects that the user is stressed, it will provide detailed, visual information, or if the user is dissatisfied with the previous purchase suggestion, it will switch to a more detailed explanation and illustration-heavy display.

[1692] Specific prompts that are used include:

[1693] "Please demonstrate an application that uses sales data, purchase data, and waste data from the past three months to forecast sales for the next week and suggest optimal inventory levels. Also, please demonstrate how to take into account the effects of weather and adjust inventory levels on days with bad weather. Finally, please provide a concrete explanation of the forecast based on sales data and how to notify the results."

[1694] This enables comprehensive, real-time inventory management and sales forecasting, further enhancing the user experience.

[1695] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1696] Step 1:

[1697] The server connects to the restaurant's POS system and automatically collects past sales data, purchasing data, and food waste data after each day's business hours. This data is then stored in a database. The inputs are sales data, purchasing data, and waste data obtained from the POS system, and the output is stored in the database.

[1698] Step 2:

[1699] The server fills in missing values ​​and corrects outliers in the collected data to prepare it for analysis. This preprocessing includes, for example, filling in missing data with data from the previous day and correcting outliers to bring them within a normal range. The input is raw data, and the output is preprocessed data.

[1700] Step 3:

[1701] The server inputs the preprocessed data into the AI ​​model to identify the causes of food waste for each menu item. In this process, the AI ​​model performs statistical analysis of the data to identify the main causes of food waste and their impact. The input is the preprocessed data, and the output is the results of identifying the causes of food waste.

[1702] Step 4:

[1703] The server stores the analysis results of the AI ​​model in a database and makes them accessible to users. The analysis results are displayed in the form of graphs and reports on a dashboard. The input is the analysis results of the AI ​​model, and the output is the analysis results converted into an easy-to-read format.

[1704] Step 5:

[1705] The server generates an alert for food items approaching their expiration date. This alert is sent to the user's device as a notification to prompt further action. The input is expiration date data, and the output is an alert notification.

[1706] Step 6:

[1707] Users can check the food loss analysis results on the dashboard and take action as necessary. The user's input is access to the dashboard and the necessary operations, and the output is the displayed analysis results and a presentation of countermeasures.

[1708] Step 7:

[1709] The server obtains weather forecast information from an external weather data API and stores it in a database. The weather data is used to predict the number of customers and delivery orders. The input is the weather forecast information obtained from the weather data API, and the output is the weather data stored in the database.

[1710] Step 8:

[1711] The server predicts the number of delivery orders for the next day based on the weather forecast and calculates the necessary food ingredient stocking amounts. This allows for purchase suggestions that reflect the impact of weather on delivery orders. The inputs are weather data and past order data, and the output is a purchase suggestion.

[1712] Step 9:

[1713] The server uses an emotion engine to recognize the user's emotions and optimize operability. This includes analyzing the user's voice and text input and making adjustments such as simplifying the operation screen if the user is feeling stressed. The input is the user's voice and text data, and the output is an optimized operation screen and the presentation of information.

[1714] Step 10:

[1715] The server sends the notification results to the user, ensuring that important information is provided in a timely manner, such as purchasing suggestions and alert notifications. The inputs include food waste analysis results and suggestions based on weather forecasts, and the output is a notification sent to the user's device.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] [Fourth embodiment]

[1720] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1721] 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.

[1722] 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).

[1723] 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.

[1724] 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.

[1725] 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).

[1726] 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.

[1727] 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.

[1728] 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.

[1729] 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.

[1730] 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.

[1731] 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.

[1732] 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."

[1733] The present invention is a system for collecting data on restaurant sales, purchasing, and food waste from restaurants and effectively utilizing this data to reduce food waste. An embodiment of the present invention will be described in detail below.

[1734] 1. Food waste data collection and analysis

[1735] Data collection

[1736] Server: Works in conjunction with the restaurant's POS system to collect past sales data, purchasing data, and food waste data, and stores this data in a database.

[1737] Example: After closing time each day, the server automatically retrieves sales data from the restaurant's POS system and stores it in a database.

[1738] Data Preprocessing

[1739] Server: Complements missing values ​​and corrects outliers in the collected data, and prepares it in a format suitable for analysis.

[1740] Example: The server complements missing data with data from the previous day and corrects any abnormal values ​​to bring them within the normal range.

[1741] Analysis by AI model

[1742] Server: Inputs the preprocessed data into the AI ​​model to identify the causes of food waste for each menu item.

[1743] Example: The AI ​​model uses statistical methods based on data from the past three months to identify the main causes of food waste and their impact.

[1744] Save and notify results

[1745] Server: Stores the analysis results in a database for user access, and generates alerts for ingredients approaching their expiration date.

[1746] Example: The saved analysis results are visualized on a dashboard, and an alert is sent immediately if there is food that has a shelf life of two days.

[1747] 2. Customer Data Predictions

[1748] Collection of store visit history data

[1749] Server: Collects customer visit history and stores it in a database.

[1750] Example: The server retrieves data on customer repeat visits and the number of new customers from the POS system and stores it in a database.

[1751] Analysis of store visit patterns

[1752] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[1753] Example: The server uses visitor data from the past year to analyze visitor trends for specific days of the week and time periods, and predicts the number of customers to visit next week.

[1754] Sales forecast and purchase quantity proposals

[1755] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[1756] Example: The server predicts sales for each menu item based on the predicted number of customers for the next week, and calculates the amount of ingredients needed to purchase to achieve this.

[1757] Proposal Notification

[1758] Terminal: Notifies the user of the forecast results and recommended purchase quantities.

[1759] Example: The terminal displays a pop-up message with suggested purchases for next week (e.g. 10 kg of chicken, 20 kg of vegetables).

[1760] 3. Weather data forecasting

[1761] Obtaining weather data

[1762] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[1763] Example: Every morning, the server calls a weather data API to retrieve the weather forecast data for that day.

[1764] Correlation analysis between weather and customer numbers

[1765] Server: Compares past weather data with store visit data and analyzes correlations.

[1766] Example: The server cross-analyzes weather data and store visit data from the past year to determine the impact of weather on store visits.

[1767] Weather-based customer traffic forecast

[1768] Server: Predict the number of customers based on the weather forecast for the next day.

[1769] Example: Based on the analysis result that "the number of customers decreases by about 20% on rainy days," the server predicts the number of customers if rain is forecast for the next day, taking that impact into account.

[1770] System Notifications

[1771] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[1772] Example: On days when rain is forecast, the terminal will display a pop-up suggesting, "Reduce purchases due to predicted decline in customer numbers."

[1773] 4. Best before date management

[1774] Input of food ingredient data

[1775] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[1776] Example: When new ingredients are purchased, the server registers their expiration date data in the database.

[1777] Best before date monitoring

[1778] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[1779] Example: The server checks the database every morning and generates an alert for ingredients that are due within the next 3 days.

[1780] Alerting and Notifications

[1781] Device: Displays an alert message for ingredients that are nearing their expiration date and suggests recipes to use them in.

[1782] Example: The device notifies the user, "The expiration date of the chicken is approaching in two days. We have some suggestions for new dishes using this chicken."

[1783] 5. Reservation system integration

[1784] Retrieving reservation data

[1785] Server: Obtains the most recent reservation data in real time from the restaurant reservation system and stores it in a database.

[1786] Example: The server checks the reservation system every morning and stores the reservation status for that day in a database.

[1787] Reservation data analysis

[1788] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[1789] Example: The server calculates the cancellation rate of reservations based on historical reservation data from the past few months.

[1790] Adjustment of purchase quantity

[1791] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[1792] Example: The server makes a suggestion such as, "Because the cancellation rate is high on this day, we will reduce the amount of purchases by 10% compared to normal."

[1793] Proposal Notification

[1794] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[1795] Example: The terminal displays the message, "We have a suggested purchase adjustment based on this week's reservation status," and provides detailed recommended quantities.

[1796] The above is a specific embodiment of the system, which allows restaurants to appropriately manage inventory and adjust purchasing, reducing food waste and improving cost efficiency.

[1797] The processing flow will be explained below.

[1798] 1. Food waste data collection and analysis

[1799] Step 1: Data collection

[1800] Server: Works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data, and stores this data in a database.

[1801] Step 2: Data Preprocessing

[1802] Server: Checks the collected data for missing or outlier values, and performs imputation or correction as necessary.

[1803] Step 3: Analysis by AI model

[1804] Server: Preprocessed data is input into the AI ​​model and analyzed to identify the causes of food waste for each menu item.

[1805] Step 4: Save the results

[1806] Server: Stores the analysis results in a database and makes them later accessible via the dashboard.

[1807] Step 5: View the dashboard

[1808] Device: The food waste analysis results are displayed in graph and report format on the user's dashboard.

[1809] Step 6: User Verification

[1810] Users: See the top causes of food waste on the dashboard.

[1811] 2. Customer Data Predictions

[1812] Step 1: Collect store visit history data

[1813] Server: Collects customer visit history and stores it in a database.

[1814] Step 2: Analyze store visit patterns

[1815] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[1816] Step 3: Sales forecast

[1817] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[1818] Step 4: Viewing Proposals

[1819] Terminal: Displays forecast results and recommended purchase quantities.

[1820] Step 5: Confirm instructions

[1821] User: Places an order for the required amount based on the displayed proposal.

[1822] 3. Weather data forecasting

[1823] Step 1: Getting weather data

[1824] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[1825] Step 2: Correlation analysis between weather and customer traffic

[1826] Server: Compares past weather data with store visit data and analyzes correlations.

[1827] Step 3: Weather-based customer traffic forecast

[1828] Server: Predict the number of customers based on the weather forecast for the next day.

[1829] Step 4: System Notifications

[1830] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[1831] Step 5: Check the prediction

[1832] User: Review and adjust forecasts and purchasing suggestions based on weather forecasts.

[1833] 4. Best before date management

[1834] Step 1: Input food ingredients data

[1835] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[1836] Step 2: Monitor expiration dates

[1837] Server: Periodically checks the expiration dates of ingredients in the database and creates alerts when the expiration date approaches.

[1838] Step 3: Alert Generation

[1839] Server: Generates alert messages about food items that are approaching their expiration date and sends them to the terminal.

[1840] Step 4: Displaying alerts

[1841] Device: Displays an alert message when ingredients are nearing their expiration date and suggests recipes to use them in.

[1842] Step 5: Recipe Ideation

[1843] User: Create and serve new menu items based on the suggested recipes.

[1844] 5. Reservation system integration

[1845] Step 1: Get reservation data

[1846] Server: Retrieves reservation status data in real time from the restaurant reservation system and stores it in a database.

[1847] Step 2: Analyze your booking data

[1848] Server: Analyze seating rates, reservation cancellation rates, etc. based on reservation data.

[1849] Step 3: Adjusting inventory by reservation

[1850] Server: Based on the analysis results, generate proposals for adjusting purchase quantities in response to reservations and cancellations.

[1851] Step 4: Proposal Notification

[1852] Terminal: Notifies the user of suggested adjustments to purchase quantities based on reservation status.

[1853] Step 5: Proposal confirmation

[1854] User: Check the reservation status and place an order based on the suggested purchase amount.

[1855] The above is the processing flow according to a specific embodiment of the present system. This flow allows restaurants to properly manage their inventory and significantly reduce food waste.

[1856] Example 1

[1857] 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."

[1858] Food waste in restaurants is a major issue, as it not only leads to economic losses but also increases environmental impact. It is also difficult to manage appropriate purchasing amounts due to fluctuations in customer numbers and weather, which can further increase food waste. Furthermore, it is difficult to effectively manage ingredients approaching their expiration date and adjust purchasing appropriately based on reservation status, so a system that can efficiently solve these issues is needed.

[1859] 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.

[1860] In this invention, the server includes means for collecting a restaurant's past sales data, purchasing data, and food waste data and storing them in a database, means for preprocessing the data, means for inputting the preprocessed data into a generative AI model to identify the causes of food waste for each menu item, means for saving the analysis results in a database and making them accessible to users, means for generating alerts for food items approaching their expiration dates, means for displaying the food waste analysis results in graphs and reports on the user's dashboard, means for logging into the user's training platform to view and study educational materials and training videos, means for collecting restaurant visit history data and storing it in a database, means for acquiring weather forecast information and storing it in a database, means for acquiring reservation data from a reservation system and storing it in a database, means for predicting the number of customers and sales based on the acquired data and calculating appropriate purchase amounts, and means for notifying the user of the calculated purchase amounts.This enables restaurants to achieve appropriate inventory management and purchase adjustments, significantly reducing food waste and improving cost efficiency.

[1861] "Sales data" refers to data that records transaction information when products or menu items are sold at a restaurant.

[1862] "Purchase data" is data that records transaction information when a restaurant purchases ingredients or products.

[1863] "Food waste data" refers to data that records information about food ingredients that are discarded without being used by restaurants.

[1864] A "database" is a system for organizing and storing collected data and efficiently retrieving necessary information.

[1865] "Data preprocessing" is the process of preparing data in a format suitable for analysis, such as by filling in missing values ​​and correcting outliers.

[1866] A "generative AI model" is an algorithm that recognizes patterns based on past data and makes predictions and classifications.

[1867] "Causes of food waste" refers to factors that cause food waste and disposal in restaurants.

[1868] "Analysis results" are information that represents findings and conclusions obtained from collected and analyzed data.

[1869] An "alert" is a message that notifies or warns you when a specific condition is met.

[1870] A "dashboard" is an interface that allows users to visualize data.

[1871] A "graph or report format" is a format for visually displaying data, making it easier to understand.

[1872] A "training platform" is an environment or system for users to learn or train.

[1873] "Educational materials" are content or materials for learning specific knowledge or skills.

[1874] A "training video" is a video that provides learning content visually.

[1875] "Visit history data" is recorded information when a customer visits a restaurant.

[1876] "Weather forecast information" is forecast data regarding future weather.

[1877] "Reservation data" is data that records information when a customer reserves a table at a restaurant.

[1878] "Inventory management" is the process of properly maintaining and managing inventory of goods and ingredients.

[1879] "Purchase adjustment" refers to making adjustments to purchase the appropriate amount of ingredients and products based on forecasts and actual results.

[1880] "Improving cost efficiency" refers to reducing costs and utilizing funds efficiently.

[1881] This invention is a system for reducing food waste through the collection and analysis of restaurant sales data, purchasing data, and food waste data. This system operates in cooperation with a server, terminals, and users.

[1882] The server connects to the restaurant's POS system and collects sales data, purchasing data, and food waste data. This data is then stored in a database. For example, after closing each day, the server automatically retrieves sales data from the POS system and stores it in the database. It also extracts and stores purchasing data and food waste data in the same way.

[1883] The server complements missing values ​​and corrects outliers in the collected data. This process improves the reliability of the data and increases the accuracy of analysis. For example, the server complements missing data with data from the previous day and corrects any outliers to bring them within the normal range. This results in a data format suitable for analysis.

[1884] The server then inputs the preprocessed data into a generative AI model, which uses that data to identify the causes of food waste for each menu item. The AI ​​model uses statistical methods based on data from the past few months to identify the main causes of food waste and their impact. For example, it can identify specific causes such as "ingredient B from dish A is frequently wasted."

[1885] The analysis results are stored in a database and displayed on a dashboard that users can access. This dashboard visualizes the data in graphs and reports, and is designed to make it easy for users to understand. For example, it visually displays the main causes of food waste and trends in waste volume.

[1886] In addition, the server generates an alert for food ingredients that are approaching their expiration date and notifies the user. For example, if there is food that has an expiration date of two days, an alert saying "Chicken expiration date is approaching" will be displayed on the terminal. This alert is an important measure to prevent food waste.

[1887] Store visit history data is also collected by the server and stored in a database. This data is analyzed and the next number of customers is predicted based on past patterns. The server uses the past year's store visit data to analyze store visit trends for specific days of the week and time periods, and predicts the number of customers for the following week. For example, based on a pattern of high customer numbers on Friday nights, the server predicts the number of customers for the following Friday.

[1888] Weather forecast information is also obtained by the server and stored in a database. The server calls a weather data API to obtain and store the weather forecast data for that day. This weather data is compared with past store visit data and correlations are analyzed. Based on the analysis results, the server concludes that "the number of customers decreases by approximately 20% on rainy days."

[1889] The server comprehensively analyzes this data and predicts the number of customers based on the weather forecast for the next day. For example, if rain is forecast for the next day, the server predicts that the number of customers will decrease. The server notifies the user of this prediction and a suggested amount of stock to be purchased. The terminal displays a message such as, "The forecast suggests that the number of customers may decrease tomorrow, so we suggest reducing the amount of stock to be purchased."

[1890] Furthermore, the system retrieves reservation data from the reservation system and stores it in a database. Based on this data, it generates a purchase adjustment proposal based on the reservation status and notifies the user. For example, the terminal may display a message saying, "We have a purchase adjustment proposal based on this week's reservation status," along with detailed recommendations for purchase quantities.

[1891] Examples of specific prompts include:

[1892] "Calculate the necessary inventory based on the most recent reservation data."

[1893] "Please identify the main causes of food waste based on sales data and food waste data from the past three months."

[1894] "Based on this week's weather forecast, please predict the number of customers we will have and suggest the amount of stock we should stock."

[1895] This will enable restaurants to properly manage their inventory and adjust their purchasing, significantly reducing food waste and improving cost efficiency.

[1896] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1897] Step 1:

[1898] The server works with the restaurant's POS system to collect sales data, purchasing data, and food waste data. This data is automatically acquired after closing time each day and stored in a database. The input is raw data acquired from the POS system, and the output is raw data stored in the database. Specifically, the server calls the API for the POS system and saves the acquired data in the database.

[1899] Step 2:

[1900] The server complements missing values ​​and corrects outliers in the collected data. This process results in a data format suitable for analysis. The input is raw data stored in the database, and the output is preprocessed data. Specifically, it complements missing values ​​with data from the previous day, and corrects any outliers to within an appropriate range.

[1901] Step 3:

[1902] The server inputs the preprocessed data into the generative AI model to identify the causes of food waste for each menu item. The input is the preprocessed data, and the output is the analysis results of the causes of food waste. Specifically, data from the past few months is input into the generative AI model, which analyzes it using statistical methods to identify the causes of food waste.

[1903] Step 4:

[1904] The server stores the analysis results generated by the AI ​​model in a database and displays them on a dashboard that users can access. The input is the analysis results of the causes of food waste, and the output is the visualized data displayed on the dashboard. Specifically, the analysis results are converted into graphs and reports and displayed in a format that is easy for users to access.

[1905] Step 5:

[1906] The server generates an alert for food ingredients approaching their expiration date and notifies the user. The input is the food ingredient data for which the expiration date is approaching, and the output is an alert message displayed on the terminal. Specifically, the server periodically checks the database, generates an alert for food ingredients approaching their expiration date, and notifies the user.

[1907] Step 6:

[1908] The server collects customer visit history data and stores it in a database. The input is the visit history data, and the output is the visit data stored in the database. Specifically, it obtains the visit history data from the POS system and saves it in the database.

[1909] Step 7:

[1910] The server analyzes the visit history data and predicts the next number of customers based on past patterns. The input is the past visit history data, and the output is the predicted number of customers. Specifically, it analyzes visit trends by day of the week and time of day based on data from the past year, and predicts the next number of customers.

[1911] Step 8:

[1912] The server obtains weather forecast information from the weather data API and stores it in a database. The input is the weather forecast information obtained from the weather data API, and the output is the weather forecast data stored in the database. Specifically, the server calls the weather data API, obtains the weather forecast data, and stores it in the database.

[1913] Step 9:

[1914] The server compares past weather data with store visit data and analyzes the correlation. The input is past weather data and store visit data, and the output is the correlation analysis results between weather and store visits. Specifically, it cross-analyzes both sets of data to identify the impact that weather has on the number of store visitors.

[1915] Step 10:

[1916] The server predicts the number of customers based on the weather forecast for the next day. The input is weather forecast data, and the output is the predicted number of customers for the next day. Specifically, the server predicts the number of customers based on the weather forecast data and calculates the appropriate amount of stock to be purchased.

[1917] Step 11:

[1918] The server obtains reservation data from the reservation system and stores it in a database. The input is the reservation data obtained from the reservation system, and the output is the reservation data stored in the database. Specifically, the server accesses the reservation system to obtain data and stores it in the database.

[1919] Step 12:

[1920] The server analyzes the seating rate and reservation cancellation rate based on the reservation data, and generates a purchase adjustment proposal according to the reservation situation. The input is reservation data, and the output is a purchase adjustment proposal. Specifically, it analyzes past reservation history and proposes appropriate purchase amounts based on the cancellation rate and seating rate.

[1921] Step 13:

[1922] The terminal notifies the user of the forecast results and recommended purchase quantities. The input is the recommended purchase data from the server, and the output is a message displayed to the user. Specifically, the terminal notifies the user of the purchase adjustment proposal using a pop-up message or notification function.

[1923] (Application example 1)

[1924] 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."

[1925] In restaurant operations, excessive food waste and lost sales opportunities due to shortages are problems. These problems arise because it is difficult to properly manage inventory and predict customer demand. Also, adjusting purchasing quantities based on fluctuations in weather and customer visit history is difficult, which contributes to waste. Furthermore, inadequate management of expiration dates also leads to food loss.

[1926] 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.

[1927] In this invention, the server includes means for collecting the restaurant's past sales data, purchasing data, and food waste data and storing them in a database, means for preprocessing the data, means for inputting the preprocessed data into an AI model to identify the causes of food waste for each menu item, means for saving the analysis results in a database and making them accessible to users, means for generating alerts for food ingredients whose expiration dates are approaching, means for displaying the food waste analysis results in graphs and reports on the user's dashboard, means for sending alerts and prediction results via push notifications to the user's mobile device, and means for providing recommended purchase amounts based on the prediction results. This enables the reduction of food waste and efficient inventory management in restaurants.

[1928] "Past sales data of a restaurant" is information relating to the quantity and price of products sold in the past at a restaurant.

[1929] "Purchase data" refers to information about ingredients and other necessities purchased by a restaurant.

[1930] "Food waste data" is information on the amount and type of food that is discarded without being used.

[1931] A "database" is a system for centrally managing and storing collected data.

[1932] "Data preprocessing" is the process of filling in missing data values ​​and correcting outliers, preparing the data in a form that is easy to analyze.

[1933] An "AI model" is an algorithm that uses artificial intelligence to analyze data and make predictions and classifications.

[1934] "Causes of food waste" are the main reasons why food ingredients are discarded unnecessarily.

[1935] "Analysis results" refers to the information and insights obtained as a result of analyzing data.

[1936] An "alert" is a warning message that notifies the user of urgent information.

[1937] A "dashboard" is a tool that visually organizes information and displays it in a way that allows users to intuitively understand it.

[1938] A "mobile terminal" is a mobile device such as a smartphone or tablet.

[1939] "Push notifications" are a method of sending information to a user's device in real time.

[1940] "Recommended purchase quantities" are the appropriate amounts of ingredients to purchase suggested based on forecast data.

[1941] This invention is a system for streamlining restaurant operations and reducing food waste. This system collects sales data, purchasing data, food waste data, etc., and analyzes them using an AI model. It also notifies users of prediction results and alerts, supporting appropriate purchasing and inventory management.

[1942] Data collection and storage

[1943] The server connects to the restaurant's POS system and collects past sales data, purchasing data, and food waste data, storing it in a database. This data is automatically retrieved, organized, and saved after closing time each day.

[1944] Data Preprocessing

[1945] The server uses the Python pandas library to fill in missing values ​​and correct outliers in the collected data, and then formats it for analysis.

[1946] Analysis by AI model

[1947] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item. The AI ​​model uses scikit-learn's Linear Regression model to make highly accurate predictions based on past data.

[1948] Save and notify results

[1949] The analysis results are stored in a database and displayed on a dashboard for user access, and alerts are generated for ingredients approaching their expiration date and sent to users' mobile devices via push notifications.

[1950] User Dashboard

[1951] Users can visually check the results of food waste analysis in the form of graphs and reports through the dashboard, which is implemented using the Shiny package in the R programming language.

[1952] Providing prediction results

[1953] The server calculates sales forecasts and recommended stock quantities based on the predicted number of customers for the next week, and sends these to the user's mobile device via push notification.

[1954] Specific examples

[1955] For example, when a store manager opens the application on their smartphone, it displays next week's predicted sales, purchasing suggestions, and alerts for ingredients that are nearing their expiration date.

[1956] Prompt Sentence Examples

[1957] Examples of prompt sentences include:

[1958] "Please use the store's sales data, purchasing data, food waste data, and weather forecast data from the past month to identify causes of food waste and predict the number of customers visiting the store. Also, please make purchasing amount suggestions based on the results."

[1959] The above is an embodiment of the present invention.

[1960] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1961] Step 1:

[1962] The server connects to the restaurant's POS system and collects past sales data, purchasing data, and food waste data.

[1963] Input: Sales data, purchasing data, and food waste data from the POS system.

[1964] Output: The collected data is stored in a database.

[1965] Specifically, after closing time each day, the server accesses the POS system, automatically retrieves the necessary data via API, and stores it in a database.

[1966] Step 2:

[1967] The server performs data preprocessing by filling in missing values ​​and correcting outliers in the collected data.

[1968] Input: Raw sales data, purchasing data, and food waste data stored in the database.

[1969] Output: Preprocessed data.

[1970] Specifically, missing data is filled in with the previous day's values ​​using Python's pandas library, and outliers are corrected to within a statistically appropriate range.

[1971] Step 3:

[1972] The server inputs the preprocessed data into an AI model to identify the causes of food waste for each menu item.

[1973] Input: Preprocessed sales data, purchasing data, and food waste data.

[1974] Output: Analysis results of causes of food waste.

[1975] Specifically, we use scikit-learn's Linear Regression model to analyze correlations in the data and identify the main causes of food waste and their contribution.

[1976] Step 4:

[1977] The server stores the analysis results in a database and makes them accessible to users through a dashboard.

[1978] Input: Analysis results of causes of food waste.

[1979] Output: Analysis results stored in a database.

[1980] Specifically, the analysis results are stored in a database, and users can view the results by accessing a dashboard via a web interface.

[1981] Step 5:

[1982] The server generates an alert for food ingredients approaching their expiration date and sends a push notification to the user's mobile device.

[1983] Input: Best before information in the database.

[1984] Output: Alert notification.

[1985] Specifically, the database is checked periodically, and if the expiration date is approaching, an alert is sent to the user's email address using an SMTP server.

[1986] Step 6:

[1987] The server calculates sales forecasts and recommended stock quantities based on the predicted number of customers visiting the store next week, and sends these to the user's mobile device via push notification.

[1988] Input: Store visit history data and weather forecast data.

[1989] Output: Sales forecast and recommended purchase quantities.

[1990] Specifically, an AI model makes predictions based on store visit history and weather data, calculates the amount of stock to be purchased based on the results, and notifies the user's smartphone.

[1991] Step 7:

[1992] Users can check food waste analysis results, store visit predictions, purchasing suggestions, and more through the dashboard, and take appropriate action.

[1993] Input: Server-generated analysis results, forecast data, and purchasing recommendations.

[1994] Output: User confirmation and action.

[1995] Specifically, users access the dashboard through a web browser or a dedicated app, view information in the form of graphs and reports, and make adjustments to purchases and menus as needed.

[1996] 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.

[1997] This invention is a system that collects restaurant sales data, purchasing data, and food waste data and uses this data to reduce food waste. Furthermore, this invention achieves more effective operation by combining it with an emotion engine that recognizes user emotions. Below, we will explain in detail how each component works together and functions as an entire system.

[1998] 1. Food waste data collection and analysis

[1999] Data collection

[2000] Server: Works in conjunction with the restaurant's POS system to periodically collect past sales data, purchasing data, and food waste data, and stores it in a database.

[2001] Example: The server automatically retrieves sales data from the POS system after closing each day and stores it in a database.

[2002] Data Preprocessing

[2003] Server: Complements missing values ​​and corrects outliers in the collected data, and prepares it in a format suitable for analysis.

[2004] Example: The server complements missing data with data from the previous day and corrects any abnormal values ​​to bring them within the normal range.

[2005] Analysis by AI model

[2006] Server: Preprocessed data is input into the AI ​​model and analyzed to identify the causes of food waste for each menu item.

[2007] Example: The AI ​​model uses statistical methods based on data from the past three months to identify the main causes of food waste and their impact.

[2008] Save and notify results

[2009] Server: Stores the analysis results in a database for user access, and generates alerts for ingredients approaching their expiration date.

[2010] Example: The saved analysis results are visualized on a dashboard, and an alert is sent immediately if there is food that has a shelf life of two days.

[2011] 2. Customer Data Predictions

[2012] Collection of store visit history data

[2013] Server: Periodically collects customer visit history and stores it in a database.

[2014] Example: The server retrieves data on customer repeat visits and the number of new customers from the POS system and stores it in a database.

[2015] Analysis of store visit patterns

[2016] Server: Analyzes customer visit history and predicts the next number of customers based on past patterns.

[2017] Example: The server uses visitor data from the past year to analyze visitor trends for specific days of the week and time periods, and predicts the number of customers to visit next week.

[2018] Sales forecast and purchase quantity proposals

[2019] Server: Based on the store visit forecast, make sales forecasts and calculate recommended purchase quantities.

[2020] Example: The server predicts sales for each menu item based on the predicted number of customers for the next week, and calculates the amount of ingredients needed to purchase to achieve this.

[2021] Proposal Notification

[2022] Terminal: Notifies the user of the forecast results and recommended purchase quantities.

[2023] Example: The terminal displays a pop-up message with suggested purchases for next week (e.g. 10 kg of chicken, 20 kg of vegetables).

[2024] 3. Weather data forecasting

[2025] Obtaining weather data

[2026] Server: Obtains weather forecast information from the weather data API and stores it in a database.

[2027] Example: Every morning, the server calls a weather data API to retrieve the weather forecast data for that day.

[2028] Correlation analysis between weather and customer numbers

[2029] Server: Compares past weather data with store visit data and analyzes correlations.

[2030] Example: The server cross-analyzes weather data and store visit data from the past year to determine the impact of weather on store visits.

[2031] Weather-based customer traffic forecast

[2032] Server: Predict the number of customers based on the weather forecast for the next day.

[2033] Example: Based on the analysis result that "the number of customers decreases by about 20% on rainy days," the server predicts the number of customers if rain is forecast for the next day, taking that impact into account.

[2034] System Notifications

[2035] Terminal: Notifies the user of customer numbers predicted based on weather forecasts and suggested purchase quantities.

[2036] Example: On days when rain is forecast, the terminal will display a pop-up suggesting, "Reduce purchases due to predicted decline in customer numbers."

[2037] 4. Best before date management

[2038] Input of food ingredient data

[2039] Server: Inputs purchasing information and manages the expiration dates of each ingredient in a database.

[2040] ...

Claims

1. A means for collecting and storing past sales data, purchasing data, and food waste data of restaurants in a database; a means for pre-processing the data; A method to input preprocessed data into an AI model and identify the causes of food waste for each menu item, a means for storing the results of the analysis in a database and making them accessible to users; A means of generating alerts for food items approaching their expiration date; A means to display the food loss analysis results in graphs and reports on the user's dashboard, A system that includes a means for users to log in to the training platform and view and study educational materials and training videos.

2. A means for collecting and storing store visit history in a database; A method for analyzing store visit history and predicting the next number of customers based on past patterns; A means for forecasting sales and calculating recommended purchase amounts based on the store visit forecast; The system of claim 1 further comprising means for displaying the forecast results and the recommended purchase amounts.

3. A means of obtaining weather forecast information from the weather data API and storing it in a database; A means of comparing past weather data with store visit data and analyzing correlations; A method for predicting the number of customers based on the weather forecast for the next day, The system according to claim 1 , further comprising means for notifying the user of a forecast of customer numbers and a suggested amount of stock based on a weather forecast.

Images